diff --git "a/generated_query.json" "b/generated_query.json" new file mode 100644--- /dev/null +++ "b/generated_query.json" @@ -0,0 +1,50520 @@ +[ + { + "seed_identities_with_labels": [ + { + "name": "eric phillips", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua waller", + "label": "negative", + "script": "latin" + }, + { + "name": "christina price", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica kelly", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole rush", + "label": "negative", + "script": "latin" + }, + { + "name": "terry rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley tanner", + "label": "negative", + "script": "latin" + }, + { + "name": "stephen gallagher", + "label": "negative", + "script": "latin" + }, + { + "name": "karl smith", + "label": "negative", + "script": "latin" + }, + { + "name": "lance murphy", + "label": "negative", + "script": "latin" + }, + { + "name": "clive hamilton", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua clarke", + "label": "negative", + "script": "latin" + }, + { + "name": "heather nixon", + "label": "negative", + "script": "latin" + }, + { + "name": "sabrina miranda", + "label": "negative", + "script": "latin" + }, + { + "name": "jorge berry", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title prefix (Mr., Dr., etc.), and Insert a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_leading_title", + "insert_random_letter" + ], + "rule_descriptions": { + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)", + "insert_random_letter": "Insert a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "nathan willis", + "label": "negative", + "script": "latin" + }, + { + "name": "donald lee", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy warren", + "label": "negative", + "script": "latin" + }, + { + "name": "aimee burgess", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda parker", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica gibson", + "label": "negative", + "script": "latin" + }, + { + "name": "david pollard", + "label": "negative", + "script": "latin" + }, + { + "name": "corey cooke", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher jensen", + "label": "negative", + "script": "latin" + }, + { + "name": "bradley scott", + "label": "negative", + "script": "latin" + }, + { + "name": "richard castro", + "label": "negative", + "script": "latin" + }, + { + "name": "rodney sims", + "label": "negative", + "script": "latin" + }, + { + "name": "carl sandoval", + "label": "negative", + "script": "latin" + }, + { + "name": "sandra ramos", + "label": "negative", + "script": "latin" + }, + { + "name": "elizabeth brewer", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Delete a random letter, Replace double letters with a single letter, and Replace random consonants with different consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "delete_random_letter", + "replace_double_letters_with_single_letter", + "replace_random_consonant_with_random_consonant" + ], + "rule_descriptions": { + "delete_random_letter": "Delete a random letter", + "replace_double_letters_with_single_letter": "Replace double letters with a single letter", + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "colleen lindsey", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle talbot", + "label": "negative", + "script": "latin" + }, + { + "name": "amy williams", + "label": "negative", + "script": "latin" + }, + { + "name": "nathaniel jones", + "label": "negative", + "script": "latin" + }, + { + "name": "james sheppard", + "label": "negative", + "script": "latin" + }, + { + "name": "ralph best", + "label": "negative", + "script": "latin" + }, + { + "name": "richard miller", + "label": "negative", + "script": "latin" + }, + { + "name": "kaitlyn ward", + "label": "negative", + "script": "latin" + }, + { + "name": "steven neal", + "label": "negative", + "script": "latin" + }, + { + "name": "shannon pearson", + "label": "negative", + "script": "latin" + }, + { + "name": "holly phillips", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer silva", + "label": "negative", + "script": "latin" + }, + { + "name": "donna schmidt", + "label": "negative", + "script": "latin" + }, + { + "name": "holly fox", + "label": "negative", + "script": "latin" + }, + { + "name": "jonathan russell", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace random consonants with different consonants, and Swap adjacent syllables.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_consonant_with_random_consonant", + "swap_adjacent_syllables" + ], + "rule_descriptions": { + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants", + "swap_adjacent_syllables": "Swap adjacent syllables" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "kerri edwards", + "label": "negative", + "script": "latin" + }, + { + "name": "caitlin read", + "label": "negative", + "script": "latin" + }, + { + "name": "teresa george", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa barrett", + "label": "negative", + "script": "latin" + }, + { + "name": "grace jones", + "label": "negative", + "script": "latin" + }, + { + "name": "maria barrera", + "label": "negative", + "script": "latin" + }, + { + "name": "aaron mitchell", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph kelly", + "label": "negative", + "script": "latin" + }, + { + "name": "kenneth davis", + "label": "negative", + "script": "latin" + }, + { + "name": "annette douglas", + "label": "negative", + "script": "latin" + }, + { + "name": "aaron gay", + "label": "negative", + "script": "latin" + }, + { + "name": "christine miranda", + "label": "negative", + "script": "latin" + }, + { + "name": "james thomas", + "label": "negative", + "script": "latin" + }, + { + "name": "stacy diaz", + "label": "negative", + "script": "latin" + }, + { + "name": "alexandra gonzalez", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap adjacent consonants, and Replace random vowels with different vowels.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_consonants", + "replace_random_vowel_with_random_vowel" + ], + "rule_descriptions": { + "swap_adjacent_consonants": "Swap adjacent consonants", + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "morgan keith", + "label": "negative", + "script": "latin" + }, + { + "name": "shawn hughes", + "label": "negative", + "script": "latin" + }, + { + "name": "brian gilbert", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle davis", + "label": "negative", + "script": "latin" + }, + { + "name": "veronica evans", + "label": "negative", + "script": "latin" + }, + { + "name": "katherine morrison", + "label": "negative", + "script": "latin" + }, + { + "name": "roger adams", + "label": "negative", + "script": "latin" + }, + { + "name": "kristen jones", + "label": "negative", + "script": "latin" + }, + { + "name": "amy harrison", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew shaw", + "label": "negative", + "script": "latin" + }, + { + "name": "alexis lee", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua young", + "label": "negative", + "script": "latin" + }, + { + "name": "helen stephenson", + "label": "negative", + "script": "latin" + }, + { + "name": "angela smith", + "label": "negative", + "script": "latin" + }, + { + "name": "craig kennedy", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace spaces with special characters, Remove all spaces, and Replace random consonants with different consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_spaces_with_random_special_characters", + "remove_all_spaces", + "replace_random_consonant_with_random_consonant" + ], + "rule_descriptions": { + "replace_spaces_with_random_special_characters": "Replace spaces with special characters", + "remove_all_spaces": "Remove all spaces", + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "sheila evans", + "label": "negative", + "script": "latin" + }, + { + "name": "neil buckley", + "label": "negative", + "script": "latin" + }, + { + "name": "leslie scott", + "label": "negative", + "script": "latin" + }, + { + "name": "gareth mills", + "label": "negative", + "script": "latin" + }, + { + "name": "julie ellis", + "label": "negative", + "script": "latin" + }, + { + "name": "kenneth fischer", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony walker", + "label": "negative", + "script": "latin" + }, + { + "name": "roy harrison", + "label": "negative", + "script": "latin" + }, + { + "name": "james hall", + "label": "negative", + "script": "latin" + }, + { + "name": "kristen phillips", + "label": "negative", + "script": "latin" + }, + { + "name": "brian brennan", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley hayes", + "label": "negative", + "script": "latin" + }, + { + "name": "abdul jenkins", + "label": "negative", + "script": "latin" + }, + { + "name": "valerie green", + "label": "negative", + "script": "latin" + }, + { + "name": "michael gomez", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title prefix (Mr., Dr., etc.), and Replace random vowels with different vowels.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_leading_title", + "replace_random_vowel_with_random_vowel" + ], + "rule_descriptions": { + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)", + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "anita gibson", + "label": "negative", + "script": "latin" + }, + { + "name": "bethany hill", + "label": "negative", + "script": "latin" + }, + { + "name": "francis sanchez", + "label": "negative", + "script": "latin" + }, + { + "name": "eric larson", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa owen", + "label": "negative", + "script": "latin" + }, + { + "name": "diane jennings", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa turner", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole cooper", + "label": "negative", + "script": "latin" + }, + { + "name": "alyssa foster", + "label": "negative", + "script": "latin" + }, + { + "name": "david mitchell", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua murray", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer mason", + "label": "negative", + "script": "latin" + }, + { + "name": "kyle rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "nancy davies", + "label": "negative", + "script": "latin" + }, + { + "name": "michael cunningham", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Convert name to initials.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_initials" + ], + "rule_descriptions": { + "shorten_name_to_initials": "Convert name to initials" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "george williams", + "label": "negative", + "script": "latin" + }, + { + "name": "luis benjamin", + "label": "negative", + "script": "latin" + }, + { + "name": "tammy mercado", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa chandler", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa montgomery", + "label": "negative", + "script": "latin" + }, + { + "name": "julie robinson", + "label": "negative", + "script": "latin" + }, + { + "name": "holly ritter", + "label": "negative", + "script": "latin" + }, + { + "name": "emma hobbs", + "label": "negative", + "script": "latin" + }, + { + "name": "hilary hensley", + "label": "negative", + "script": "latin" + }, + { + "name": "katy bennett", + "label": "negative", + "script": "latin" + }, + { + "name": "russell merritt", + "label": "negative", + "script": "latin" + }, + { + "name": "jenna rios", + "label": "negative", + "script": "latin" + }, + { + "name": "megan bibi", + "label": "negative", + "script": "latin" + }, + { + "name": "jacob williams", + "label": "negative", + "script": "latin" + }, + { + "name": "valerie williams", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title suffix (Jr., PhD, etc.), and Delete a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_trailing_title", + "delete_random_letter" + ], + "rule_descriptions": { + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)", + "delete_random_letter": "Delete a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "ian stewart", + "label": "negative", + "script": "latin" + }, + { + "name": "mitchell robinson", + "label": "negative", + "script": "latin" + }, + { + "name": "taylor parrish", + "label": "negative", + "script": "latin" + }, + { + "name": "krista ward", + "label": "negative", + "script": "latin" + }, + { + "name": "toni barr", + "label": "negative", + "script": "latin" + }, + { + "name": "jonathan white", + "label": "negative", + "script": "latin" + }, + { + "name": "jasmin pruitt", + "label": "negative", + "script": "latin" + }, + { + "name": "emily coles", + "label": "negative", + "script": "latin" + }, + { + "name": "diana walker", + "label": "negative", + "script": "latin" + }, + { + "name": "cameron sanchez", + "label": "negative", + "script": "latin" + }, + { + "name": "francis thompson", + "label": "negative", + "script": "latin" + }, + { + "name": "albert white", + "label": "negative", + "script": "latin" + }, + { + "name": "rhonda grant", + "label": "negative", + "script": "latin" + }, + { + "name": "andrew elliott", + "label": "negative", + "script": "latin" + }, + { + "name": "shawn mcneil", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Reorder name parts, and Add a title prefix (Mr., Dr., etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "name_parts_permutations", + "add_random_leading_title" + ], + "rule_descriptions": { + "name_parts_permutations": "Reorder name parts", + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "kerry parker", + "label": "negative", + "script": "latin" + }, + { + "name": "veronica king", + "label": "negative", + "script": "latin" + }, + { + "name": "gabriel andrade", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole sandoval", + "label": "negative", + "script": "latin" + }, + { + "name": "albert williams", + "label": "negative", + "script": "latin" + }, + { + "name": "carrie smith", + "label": "negative", + "script": "latin" + }, + { + "name": "diane hansen", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa jones", + "label": "negative", + "script": "latin" + }, + { + "name": "ricky benjamin", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffrey harris", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie allen", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher spencer", + "label": "negative", + "script": "latin" + }, + { + "name": "margaret gomez", + "label": "negative", + "script": "latin" + }, + { + "name": "michael kelly", + "label": "negative", + "script": "latin" + }, + { + "name": "naomi hill", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title prefix (Mr., Dr., etc.), and Delete a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_leading_title", + "delete_random_letter" + ], + "rule_descriptions": { + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)", + "delete_random_letter": "Delete a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "julie roberts", + "label": "negative", + "script": "latin" + }, + { + "name": "william cole", + "label": "negative", + "script": "latin" + }, + { + "name": "miranda mann", + "label": "negative", + "script": "latin" + }, + { + "name": "rodney rose", + "label": "negative", + "script": "latin" + }, + { + "name": "carolyn franco", + "label": "negative", + "script": "latin" + }, + { + "name": "stephen wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "kara costa", + "label": "negative", + "script": "latin" + }, + { + "name": "diana king", + "label": "negative", + "script": "latin" + }, + { + "name": "brian mcgee", + "label": "negative", + "script": "latin" + }, + { + "name": "jimmy lambert", + "label": "negative", + "script": "latin" + }, + { + "name": "jay watson", + "label": "negative", + "script": "latin" + }, + { + "name": "crystal skinner", + "label": "negative", + "script": "latin" + }, + { + "name": "adrian robertson", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher weaver", + "label": "negative", + "script": "latin" + }, + { + "name": "tonya wright", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Use first name initial with last name.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "initial_only_first_name" + ], + "rule_descriptions": { + "initial_only_first_name": "Use first name initial with last name" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "allison johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "kyle rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "erin potter", + "label": "negative", + "script": "latin" + }, + { + "name": "jason newton", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie lewis", + "label": "negative", + "script": "latin" + }, + { + "name": "lauren rivera", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle higgins", + "label": "negative", + "script": "latin" + }, + { + "name": "jake fischer", + "label": "negative", + "script": "latin" + }, + { + "name": "dustin ramirez", + "label": "negative", + "script": "latin" + }, + { + "name": "jenna preston", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua thomas", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica garcia", + "label": "negative", + "script": "latin" + }, + { + "name": "james dean", + "label": "negative", + "script": "latin" + }, + { + "name": "john fraser", + "label": "negative", + "script": "latin" + }, + { + "name": "brian mcpherson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Duplicate a random letter, Replace double letters with a single letter, and Add a title prefix (Mr., Dr., etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "duplicate_random_letter_as_double_letter", + "replace_double_letters_with_single_letter", + "add_random_leading_title" + ], + "rule_descriptions": { + "duplicate_random_letter_as_double_letter": "Duplicate a random letter", + "replace_double_letters_with_single_letter": "Replace double letters with a single letter", + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "douglas martin", + "label": "negative", + "script": "latin" + }, + { + "name": "carl lopez", + "label": "negative", + "script": "latin" + }, + { + "name": "sue griffiths", + "label": "negative", + "script": "latin" + }, + { + "name": "declan jones", + "label": "negative", + "script": "latin" + }, + { + "name": "alexander johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "adam moss", + "label": "negative", + "script": "latin" + }, + { + "name": "kim lopez", + "label": "negative", + "script": "latin" + }, + { + "name": "marcus evans", + "label": "negative", + "script": "latin" + }, + { + "name": "michael dunn", + "label": "negative", + "script": "latin" + }, + { + "name": "greg anderson", + "label": "negative", + "script": "latin" + }, + { + "name": "gabriel wright", + "label": "negative", + "script": "latin" + }, + { + "name": "guy harris", + "label": "negative", + "script": "latin" + }, + { + "name": "shannon allen", + "label": "negative", + "script": "latin" + }, + { + "name": "molly o'brien", + "label": "negative", + "script": "latin" + }, + { + "name": "charles rodriguez", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Duplicate a random letter, and Swap adjacent consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "duplicate_random_letter_as_double_letter", + "swap_adjacent_consonants" + ], + "rule_descriptions": { + "duplicate_random_letter_as_double_letter": "Duplicate a random letter", + "swap_adjacent_consonants": "Swap adjacent consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "elizabeth henderson", + "label": "negative", + "script": "latin" + }, + { + "name": "lorraine valdez", + "label": "negative", + "script": "latin" + }, + { + "name": "andrew williams", + "label": "negative", + "script": "latin" + }, + { + "name": "marcus holden", + "label": "negative", + "script": "latin" + }, + { + "name": "hannah turner", + "label": "negative", + "script": "latin" + }, + { + "name": "geoffrey rollins", + "label": "negative", + "script": "latin" + }, + { + "name": "marc wise", + "label": "negative", + "script": "latin" + }, + { + "name": "brittany wright", + "label": "negative", + "script": "latin" + }, + { + "name": "emma wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "brian boyle", + "label": "negative", + "script": "latin" + }, + { + "name": "kathleen smith", + "label": "negative", + "script": "latin" + }, + { + "name": "brenda arnold", + "label": "negative", + "script": "latin" + }, + { + "name": "carol wiggins", + "label": "negative", + "script": "latin" + }, + { + "name": "calvin anderson", + "label": "negative", + "script": "latin" + }, + { + "name": "hilary harding", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Duplicate a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "duplicate_random_letter_as_double_letter" + ], + "rule_descriptions": { + "duplicate_random_letter_as_double_letter": "Duplicate a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "james collins", + "label": "negative", + "script": "latin" + }, + { + "name": "john garcia", + "label": "negative", + "script": "latin" + }, + { + "name": "molly phillips", + "label": "negative", + "script": "latin" + }, + { + "name": "john mann", + "label": "negative", + "script": "latin" + }, + { + "name": "harry stewart", + "label": "negative", + "script": "latin" + }, + { + "name": "heather gonzalez", + "label": "negative", + "script": "latin" + }, + { + "name": "emily mitchell", + "label": "negative", + "script": "latin" + }, + { + "name": "eileen holt", + "label": "negative", + "script": "latin" + }, + { + "name": "samantha martinez", + "label": "negative", + "script": "latin" + }, + { + "name": "arthur johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "brooke wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "brittany walker", + "label": "negative", + "script": "latin" + }, + { + "name": "harriet roberts", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley cox", + "label": "negative", + "script": "latin" + }, + { + "name": "christine thompson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Duplicate a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "duplicate_random_letter_as_double_letter" + ], + "rule_descriptions": { + "duplicate_random_letter_as_double_letter": "Duplicate a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "james cooper", + "label": "negative", + "script": "latin" + }, + { + "name": "dawn rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "laura ryan", + "label": "negative", + "script": "latin" + }, + { + "name": "carl daniel", + "label": "negative", + "script": "latin" + }, + { + "name": "angela smith", + "label": "negative", + "script": "latin" + }, + { + "name": "barbara watson", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher phillips", + "label": "negative", + "script": "latin" + }, + { + "name": "sara atkinson", + "label": "negative", + "script": "latin" + }, + { + "name": "andrea james", + "label": "negative", + "script": "latin" + }, + { + "name": "lynda griffin", + "label": "negative", + "script": "latin" + }, + { + "name": "diana phillips", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas bell", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa davis", + "label": "negative", + "script": "latin" + }, + { + "name": "teresa clark", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua brooks", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Add a title suffix (Jr., PhD, etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_trailing_title" + ], + "rule_descriptions": { + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "angela mitchell", + "label": "negative", + "script": "latin" + }, + { + "name": "patrick knight", + "label": "negative", + "script": "latin" + }, + { + "name": "beverly fernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa nichols", + "label": "negative", + "script": "latin" + }, + { + "name": "crystal barker", + "label": "negative", + "script": "latin" + }, + { + "name": "joyce stanley", + "label": "negative", + "script": "latin" + }, + { + "name": "wanda davis", + "label": "negative", + "script": "latin" + }, + { + "name": "colin david", + "label": "negative", + "script": "latin" + }, + { + "name": "brendan roberts", + "label": "negative", + "script": "latin" + }, + { + "name": "nathan watson", + "label": "negative", + "script": "latin" + }, + { + "name": "valerie garcia", + "label": "negative", + "script": "latin" + }, + { + "name": "sheila dodd", + "label": "negative", + "script": "latin" + }, + { + "name": "juan walker", + "label": "negative", + "script": "latin" + }, + { + "name": "katie castro", + "label": "negative", + "script": "latin" + }, + { + "name": "mark scott", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Delete a random letter, and Reorder name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "delete_random_letter", + "name_parts_permutations" + ], + "rule_descriptions": { + "delete_random_letter": "Delete a random letter", + "name_parts_permutations": "Reorder name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "james bell", + "label": "negative", + "script": "latin" + }, + { + "name": "mason wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "michael gardner", + "label": "negative", + "script": "latin" + }, + { + "name": "william hood", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew sosa", + "label": "negative", + "script": "latin" + }, + { + "name": "brandon robinson", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "elizabeth martin", + "label": "negative", + "script": "latin" + }, + { + "name": "rose lopez", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel obrien", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony lopez", + "label": "negative", + "script": "latin" + }, + { + "name": "toby schmidt", + "label": "negative", + "script": "latin" + }, + { + "name": "george taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "janice davidson", + "label": "negative", + "script": "latin" + }, + { + "name": "gene ray", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Insert a random letter, Remove a random consonant, and Replace random vowels with different vowels.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "insert_random_letter", + "remove_random_consonant", + "replace_random_vowel_with_random_vowel" + ], + "rule_descriptions": { + "insert_random_letter": "Insert a random letter", + "remove_random_consonant": "Remove a random consonant", + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "damian jordan", + "label": "negative", + "script": "latin" + }, + { + "name": "shelley evans", + "label": "negative", + "script": "latin" + }, + { + "name": "jenna hunt", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew perez", + "label": "negative", + "script": "latin" + }, + { + "name": "francis meadows", + "label": "negative", + "script": "latin" + }, + { + "name": "candice perez", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin white", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie sparks", + "label": "negative", + "script": "latin" + }, + { + "name": "phillip kelly", + "label": "negative", + "script": "latin" + }, + { + "name": "monique miller", + "label": "negative", + "script": "latin" + }, + { + "name": "teresa thompson", + "label": "negative", + "script": "latin" + }, + { + "name": "mandy baker", + "label": "negative", + "script": "latin" + }, + { + "name": "nathaniel jones", + "label": "negative", + "script": "latin" + }, + { + "name": "robert mckee", + "label": "negative", + "script": "latin" + }, + { + "name": "edward hamilton", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap random adjacent letters, Replace random vowels with different vowels, and Convert name to initials.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_random_letter", + "replace_random_vowel_with_random_vowel", + "shorten_name_to_initials" + ], + "rule_descriptions": { + "swap_random_letter": "Swap random adjacent letters", + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels", + "shorten_name_to_initials": "Convert name to initials" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "sara carter", + "label": "negative", + "script": "latin" + }, + { + "name": "lynne jones", + "label": "negative", + "script": "latin" + }, + { + "name": "candace johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "phillip hobbs", + "label": "negative", + "script": "latin" + }, + { + "name": "scott allen", + "label": "negative", + "script": "latin" + }, + { + "name": "christine duarte", + "label": "negative", + "script": "latin" + }, + { + "name": "erika cline", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle davis", + "label": "negative", + "script": "latin" + }, + { + "name": "marcia smith", + "label": "negative", + "script": "latin" + }, + { + "name": "catherine mays", + "label": "negative", + "script": "latin" + }, + { + "name": "robert walker", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica haynes", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas fuller", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah cox", + "label": "negative", + "script": "latin" + }, + { + "name": "marissa tran", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove a random consonant, and Convert name to initials.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_consonant", + "shorten_name_to_initials" + ], + "rule_descriptions": { + "remove_random_consonant": "Remove a random consonant", + "shorten_name_to_initials": "Convert name to initials" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "michelle hansen", + "label": "negative", + "script": "latin" + }, + { + "name": "andrew evans", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica barton", + "label": "negative", + "script": "latin" + }, + { + "name": "kenneth benton", + "label": "negative", + "script": "latin" + }, + { + "name": "ronald stevens", + "label": "negative", + "script": "latin" + }, + { + "name": "james roberts", + "label": "negative", + "script": "latin" + }, + { + "name": "erika ward", + "label": "negative", + "script": "latin" + }, + { + "name": "shane peterson", + "label": "negative", + "script": "latin" + }, + { + "name": "vickie mitchell", + "label": "negative", + "script": "latin" + }, + { + "name": "scott parkin", + "label": "negative", + "script": "latin" + }, + { + "name": "brandon wright", + "label": "negative", + "script": "latin" + }, + { + "name": "mercedes figueroa", + "label": "negative", + "script": "latin" + }, + { + "name": "richard sanders", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie cook", + "label": "negative", + "script": "latin" + }, + { + "name": "ryan stevens", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Reorder name parts, and Add a title prefix (Mr., Dr., etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "name_parts_permutations", + "add_random_leading_title" + ], + "rule_descriptions": { + "name_parts_permutations": "Reorder name parts", + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "timothy sandoval", + "label": "negative", + "script": "latin" + }, + { + "name": "wendy bird", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew mitchell", + "label": "negative", + "script": "latin" + }, + { + "name": "martyn diaz", + "label": "negative", + "script": "latin" + }, + { + "name": "judith wilkins", + "label": "negative", + "script": "latin" + }, + { + "name": "jeremiah mayo", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher kim", + "label": "negative", + "script": "latin" + }, + { + "name": "kayla lowe", + "label": "negative", + "script": "latin" + }, + { + "name": "leah jackson", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua gillespie", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas baker", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph morales", + "label": "negative", + "script": "latin" + }, + { + "name": "lindsey fisher", + "label": "negative", + "script": "latin" + }, + { + "name": "gary chen", + "label": "negative", + "script": "latin" + }, + { + "name": "michael west", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap random adjacent letters, and Replace random consonants with different consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_random_letter", + "replace_random_consonant_with_random_consonant" + ], + "rule_descriptions": { + "swap_random_letter": "Swap random adjacent letters", + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "steve morris", + "label": "negative", + "script": "latin" + }, + { + "name": "hannah holland", + "label": "negative", + "script": "latin" + }, + { + "name": "david brown", + "label": "negative", + "script": "latin" + }, + { + "name": "amber woods", + "label": "negative", + "script": "latin" + }, + { + "name": "courtney owen", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher coles", + "label": "negative", + "script": "latin" + }, + { + "name": "bernard ibarra", + "label": "negative", + "script": "latin" + }, + { + "name": "clifford potts", + "label": "negative", + "script": "latin" + }, + { + "name": "jonathan robinson", + "label": "negative", + "script": "latin" + }, + { + "name": "kayla deleon", + "label": "negative", + "script": "latin" + }, + { + "name": "derek sanchez", + "label": "negative", + "script": "latin" + }, + { + "name": "monica johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "nichole shepherd", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer hernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "caroline anderson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Replace double letters with a single letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_double_letters_with_single_letter" + ], + "rule_descriptions": { + "replace_double_letters_with_single_letter": "Replace double letters with a single letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "sara espinoza", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica little", + "label": "negative", + "script": "latin" + }, + { + "name": "hollie lester", + "label": "negative", + "script": "latin" + }, + { + "name": "david palmer", + "label": "negative", + "script": "latin" + }, + { + "name": "rebecca gardiner", + "label": "negative", + "script": "latin" + }, + { + "name": "cristina bowen", + "label": "negative", + "script": "latin" + }, + { + "name": "catherine cummings", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph cruz", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew jenkins", + "label": "negative", + "script": "latin" + }, + { + "name": "dustin robinson", + "label": "negative", + "script": "latin" + }, + { + "name": "courtney mendoza", + "label": "negative", + "script": "latin" + }, + { + "name": "tina hernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa adams", + "label": "negative", + "script": "latin" + }, + { + "name": "yolanda petersen", + "label": "negative", + "script": "latin" + }, + { + "name": "richard jones", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace double letters with a single letter, Add a title prefix (Mr., Dr., etc.), and Swap random adjacent letters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_double_letters_with_single_letter", + "add_random_leading_title", + "swap_random_letter" + ], + "rule_descriptions": { + "replace_double_letters_with_single_letter": "Replace double letters with a single letter", + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)", + "swap_random_letter": "Swap random adjacent letters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "jacqueline schaefer", + "label": "negative", + "script": "latin" + }, + { + "name": "cameron bartlett", + "label": "negative", + "script": "latin" + }, + { + "name": "hannah leblanc", + "label": "negative", + "script": "latin" + }, + { + "name": "brandon bell", + "label": "negative", + "script": "latin" + }, + { + "name": "jonathan calderon", + "label": "negative", + "script": "latin" + }, + { + "name": "shelly berry", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher walker", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda gallagher", + "label": "negative", + "script": "latin" + }, + { + "name": "charles moses", + "label": "negative", + "script": "latin" + }, + { + "name": "blake ryan", + "label": "negative", + "script": "latin" + }, + { + "name": "robert foster", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa kelly", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew morris", + "label": "negative", + "script": "latin" + }, + { + "name": "joanna miller", + "label": "negative", + "script": "latin" + }, + { + "name": "dominique webb", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Insert a random letter, and Swap random adjacent letters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "insert_random_letter", + "swap_random_letter" + ], + "rule_descriptions": { + "insert_random_letter": "Insert a random letter", + "swap_random_letter": "Swap random adjacent letters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "jessica massey", + "label": "negative", + "script": "latin" + }, + { + "name": "elizabeth pierce", + "label": "negative", + "script": "latin" + }, + { + "name": "lance king", + "label": "negative", + "script": "latin" + }, + { + "name": "neil rios", + "label": "negative", + "script": "latin" + }, + { + "name": "vincent johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer coleman", + "label": "negative", + "script": "latin" + }, + { + "name": "megan glover", + "label": "negative", + "script": "latin" + }, + { + "name": "sara graham", + "label": "negative", + "script": "latin" + }, + { + "name": "margaret clark", + "label": "negative", + "script": "latin" + }, + { + "name": "leslie gonzales", + "label": "negative", + "script": "latin" + }, + { + "name": "desiree bryant", + "label": "negative", + "script": "latin" + }, + { + "name": "ryan huff", + "label": "negative", + "script": "latin" + }, + { + "name": "michael sanders", + "label": "negative", + "script": "latin" + }, + { + "name": "david taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "pamela weeks", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap adjacent consonants, and Duplicate a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_consonants", + "duplicate_random_letter_as_double_letter" + ], + "rule_descriptions": { + "swap_adjacent_consonants": "Swap adjacent consonants", + "duplicate_random_letter_as_double_letter": "Duplicate a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "lisa berger", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda moss", + "label": "negative", + "script": "latin" + }, + { + "name": "mitchell blackwell", + "label": "negative", + "script": "latin" + }, + { + "name": "fiona adams", + "label": "negative", + "script": "latin" + }, + { + "name": "james mercado", + "label": "negative", + "script": "latin" + }, + { + "name": "todd waller", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer richard", + "label": "negative", + "script": "latin" + }, + { + "name": "alan collins", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa marshall", + "label": "negative", + "script": "latin" + }, + { + "name": "margaret johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "victor brooks", + "label": "negative", + "script": "latin" + }, + { + "name": "vanessa lopez", + "label": "negative", + "script": "latin" + }, + { + "name": "lucas gordon", + "label": "negative", + "script": "latin" + }, + { + "name": "andrea weber", + "label": "negative", + "script": "latin" + }, + { + "name": "robin white", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Abbreviate name parts, Add a title suffix (Jr., PhD, etc.), and Reorder name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_abbreviations", + "add_random_trailing_title", + "name_parts_permutations" + ], + "rule_descriptions": { + "shorten_name_to_abbreviations": "Abbreviate name parts", + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)", + "name_parts_permutations": "Reorder name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "victor hunter", + "label": "negative", + "script": "latin" + }, + { + "name": "dorothy lewis", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie burton", + "label": "negative", + "script": "latin" + }, + { + "name": "tammy smith", + "label": "negative", + "script": "latin" + }, + { + "name": "harry simpson", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer jenkins", + "label": "negative", + "script": "latin" + }, + { + "name": "courtney moore", + "label": "negative", + "script": "latin" + }, + { + "name": "callum reynolds", + "label": "negative", + "script": "latin" + }, + { + "name": "richard reed", + "label": "negative", + "script": "latin" + }, + { + "name": "brandon andrade", + "label": "negative", + "script": "latin" + }, + { + "name": "blake young", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer kennedy", + "label": "negative", + "script": "latin" + }, + { + "name": "melinda barron", + "label": "negative", + "script": "latin" + }, + { + "name": "roger gomez", + "label": "negative", + "script": "latin" + }, + { + "name": "robert huynh", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Remove all spaces.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_all_spaces" + ], + "rule_descriptions": { + "remove_all_spaces": "Remove all spaces" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "christopher jones", + "label": "negative", + "script": "latin" + }, + { + "name": "ruth ross", + "label": "negative", + "script": "latin" + }, + { + "name": "beth guzman", + "label": "negative", + "script": "latin" + }, + { + "name": "robert martinez", + "label": "negative", + "script": "latin" + }, + { + "name": "michael ross", + "label": "negative", + "script": "latin" + }, + { + "name": "erin christian", + "label": "negative", + "script": "latin" + }, + { + "name": "jack manning", + "label": "negative", + "script": "latin" + }, + { + "name": "james jackson", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas harrison", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "erin watts", + "label": "negative", + "script": "latin" + }, + { + "name": "catherine kelly", + "label": "negative", + "script": "latin" + }, + { + "name": "april griffiths", + "label": "negative", + "script": "latin" + }, + { + "name": "jason campos", + "label": "negative", + "script": "latin" + }, + { + "name": "karen dawson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Swap adjacent consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_consonants" + ], + "rule_descriptions": { + "swap_adjacent_consonants": "Swap adjacent consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "joseph hussain", + "label": "negative", + "script": "latin" + }, + { + "name": "harriet horn", + "label": "negative", + "script": "latin" + }, + { + "name": "emma brown", + "label": "negative", + "script": "latin" + }, + { + "name": "joe maldonado", + "label": "negative", + "script": "latin" + }, + { + "name": "amelia young", + "label": "negative", + "script": "latin" + }, + { + "name": "marissa gonzalez", + "label": "negative", + "script": "latin" + }, + { + "name": "valerie king", + "label": "negative", + "script": "latin" + }, + { + "name": "martyn todd", + "label": "negative", + "script": "latin" + }, + { + "name": "michael blanchard", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie potts", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin wagner", + "label": "negative", + "script": "latin" + }, + { + "name": "yesenia cole", + "label": "negative", + "script": "latin" + }, + { + "name": "ben miller", + "label": "negative", + "script": "latin" + }, + { + "name": "william thomas", + "label": "negative", + "script": "latin" + }, + { + "name": "clifford baker", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Reorder name parts, and Swap adjacent consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "name_parts_permutations", + "swap_adjacent_consonants" + ], + "rule_descriptions": { + "name_parts_permutations": "Reorder name parts", + "swap_adjacent_consonants": "Swap adjacent consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "daniel evans", + "label": "negative", + "script": "latin" + }, + { + "name": "tyler craig", + "label": "negative", + "script": "latin" + }, + { + "name": "lindsey martin", + "label": "negative", + "script": "latin" + }, + { + "name": "louise white", + "label": "negative", + "script": "latin" + }, + { + "name": "ricky jackson", + "label": "negative", + "script": "latin" + }, + { + "name": "robert frost", + "label": "negative", + "script": "latin" + }, + { + "name": "pamela nguyen", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie monroe", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas patel", + "label": "negative", + "script": "latin" + }, + { + "name": "charles mccullough", + "label": "negative", + "script": "latin" + }, + { + "name": "victoria fletcher", + "label": "negative", + "script": "latin" + }, + { + "name": "marion mcpherson", + "label": "negative", + "script": "latin" + }, + { + "name": "dorothy marshall", + "label": "negative", + "script": "latin" + }, + { + "name": "michael wright", + "label": "negative", + "script": "latin" + }, + { + "name": "robert hale", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Swap random adjacent letters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_random_letter" + ], + "rule_descriptions": { + "swap_random_letter": "Swap random adjacent letters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "jacqueline santiago", + "label": "negative", + "script": "latin" + }, + { + "name": "andrea o'neill", + "label": "negative", + "script": "latin" + }, + { + "name": "kelly elliott", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew richardson", + "label": "negative", + "script": "latin" + }, + { + "name": "scott dixon", + "label": "negative", + "script": "latin" + }, + { + "name": "jermaine williams", + "label": "negative", + "script": "latin" + }, + { + "name": "duane harper", + "label": "negative", + "script": "latin" + }, + { + "name": "gary lindsey", + "label": "negative", + "script": "latin" + }, + { + "name": "steven abbott", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph key", + "label": "negative", + "script": "latin" + }, + { + "name": "patricia gill", + "label": "negative", + "script": "latin" + }, + { + "name": "ross mcmillan", + "label": "negative", + "script": "latin" + }, + { + "name": "francisco chapman", + "label": "negative", + "script": "latin" + }, + { + "name": "angela cruz", + "label": "negative", + "script": "latin" + }, + { + "name": "anna white", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title suffix (Jr., PhD, etc.), and Remove all spaces.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_trailing_title", + "remove_all_spaces" + ], + "rule_descriptions": { + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)", + "remove_all_spaces": "Remove all spaces" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "glenn mitchell", + "label": "negative", + "script": "latin" + }, + { + "name": "marco adams", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer burke", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa nash", + "label": "negative", + "script": "latin" + }, + { + "name": "melanie johnston", + "label": "negative", + "script": "latin" + }, + { + "name": "cheryl smith", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin green", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony hendricks", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy murray", + "label": "negative", + "script": "latin" + }, + { + "name": "travis jacobs", + "label": "negative", + "script": "latin" + }, + { + "name": "norma carr", + "label": "negative", + "script": "latin" + }, + { + "name": "justin french", + "label": "negative", + "script": "latin" + }, + { + "name": "patricia bradford", + "label": "negative", + "script": "latin" + }, + { + "name": "mohamed woods", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas brown", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove all spaces, Replace spaces with special characters, and Replace random vowels with different vowels.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_all_spaces", + "replace_spaces_with_random_special_characters", + "replace_random_vowel_with_random_vowel" + ], + "rule_descriptions": { + "remove_all_spaces": "Remove all spaces", + "replace_spaces_with_random_special_characters": "Replace spaces with special characters", + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "mark martin", + "label": "negative", + "script": "latin" + }, + { + "name": "maria brown", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica phillips", + "label": "negative", + "script": "latin" + }, + { + "name": "marian harper", + "label": "negative", + "script": "latin" + }, + { + "name": "lesley walker", + "label": "negative", + "script": "latin" + }, + { + "name": "kyle bush", + "label": "negative", + "script": "latin" + }, + { + "name": "marcus sims", + "label": "negative", + "script": "latin" + }, + { + "name": "amy shields", + "label": "negative", + "script": "latin" + }, + { + "name": "amy jackson", + "label": "negative", + "script": "latin" + }, + { + "name": "john barnes", + "label": "negative", + "script": "latin" + }, + { + "name": "gary carlson", + "label": "negative", + "script": "latin" + }, + { + "name": "sara perez", + "label": "negative", + "script": "latin" + }, + { + "name": "shaun graham", + "label": "negative", + "script": "latin" + }, + { + "name": "jason glass", + "label": "negative", + "script": "latin" + }, + { + "name": "brian morris", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap random adjacent letters, Swap adjacent consonants, and Duplicate a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_random_letter", + "swap_adjacent_consonants", + "duplicate_random_letter_as_double_letter" + ], + "rule_descriptions": { + "swap_random_letter": "Swap random adjacent letters", + "swap_adjacent_consonants": "Swap adjacent consonants", + "duplicate_random_letter_as_double_letter": "Duplicate a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "robin mueller", + "label": "negative", + "script": "latin" + }, + { + "name": "leslie tyler", + "label": "negative", + "script": "latin" + }, + { + "name": "steven leach", + "label": "negative", + "script": "latin" + }, + { + "name": "glen rowe", + "label": "negative", + "script": "latin" + }, + { + "name": "elizabeth mejia", + "label": "negative", + "script": "latin" + }, + { + "name": "jacob moran", + "label": "negative", + "script": "latin" + }, + { + "name": "tabitha smith", + "label": "negative", + "script": "latin" + }, + { + "name": "emily smith", + "label": "negative", + "script": "latin" + }, + { + "name": "brian fernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "olivia williams", + "label": "negative", + "script": "latin" + }, + { + "name": "tracy miller", + "label": "negative", + "script": "latin" + }, + { + "name": "anna rivers", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah mcmillan", + "label": "negative", + "script": "latin" + }, + { + "name": "linda kelly", + "label": "negative", + "script": "latin" + }, + { + "name": "deborah martin", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace spaces with special characters, and Insert a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_spaces_with_random_special_characters", + "insert_random_letter" + ], + "rule_descriptions": { + "replace_spaces_with_random_special_characters": "Replace spaces with special characters", + "insert_random_letter": "Insert a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "karl payne", + "label": "negative", + "script": "latin" + }, + { + "name": "carl hicks", + "label": "negative", + "script": "latin" + }, + { + "name": "alex fisher", + "label": "negative", + "script": "latin" + }, + { + "name": "donald duncan", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle reid", + "label": "negative", + "script": "latin" + }, + { + "name": "kari miller", + "label": "negative", + "script": "latin" + }, + { + "name": "carolyn hines", + "label": "negative", + "script": "latin" + }, + { + "name": "graeme carter", + "label": "negative", + "script": "latin" + }, + { + "name": "zachary tran", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin carter", + "label": "negative", + "script": "latin" + }, + { + "name": "mohammed rowley", + "label": "negative", + "script": "latin" + }, + { + "name": "gregory robson", + "label": "negative", + "script": "latin" + }, + { + "name": "jodi price", + "label": "negative", + "script": "latin" + }, + { + "name": "austin palmer", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica brown", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Duplicate a random letter, and Remove a random consonant.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "duplicate_random_letter_as_double_letter", + "remove_random_consonant" + ], + "rule_descriptions": { + "duplicate_random_letter_as_double_letter": "Duplicate a random letter", + "remove_random_consonant": "Remove a random consonant" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "angela smith", + "label": "negative", + "script": "latin" + }, + { + "name": "dustin patel", + "label": "negative", + "script": "latin" + }, + { + "name": "ronald dawson", + "label": "negative", + "script": "latin" + }, + { + "name": "carol green", + "label": "negative", + "script": "latin" + }, + { + "name": "michael martin", + "label": "negative", + "script": "latin" + }, + { + "name": "jacqueline lee", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa robinson", + "label": "negative", + "script": "latin" + }, + { + "name": "randy booth", + "label": "negative", + "script": "latin" + }, + { + "name": "gregory peterson", + "label": "negative", + "script": "latin" + }, + { + "name": "rebecca weiss", + "label": "negative", + "script": "latin" + }, + { + "name": "stacey rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "erin rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "amber browne", + "label": "negative", + "script": "latin" + }, + { + "name": "kristina turner", + "label": "negative", + "script": "latin" + }, + { + "name": "brian thompson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap adjacent consonants, and Duplicate a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_consonants", + "duplicate_random_letter_as_double_letter" + ], + "rule_descriptions": { + "swap_adjacent_consonants": "Swap adjacent consonants", + "duplicate_random_letter_as_double_letter": "Duplicate a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "robin knight", + "label": "negative", + "script": "latin" + }, + { + "name": "jasmine miller", + "label": "negative", + "script": "latin" + }, + { + "name": "gemma ramirez", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel vance", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua roberts", + "label": "negative", + "script": "latin" + }, + { + "name": "jill ross", + "label": "negative", + "script": "latin" + }, + { + "name": "danielle harris", + "label": "negative", + "script": "latin" + }, + { + "name": "john estes", + "label": "negative", + "script": "latin" + }, + { + "name": "gina byrne", + "label": "negative", + "script": "latin" + }, + { + "name": "douglas crane", + "label": "negative", + "script": "latin" + }, + { + "name": "gerald chadwick", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua brown", + "label": "negative", + "script": "latin" + }, + { + "name": "michael king", + "label": "negative", + "script": "latin" + }, + { + "name": "lauren jones", + "label": "negative", + "script": "latin" + }, + { + "name": "maria williams", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Replace random vowels with different vowels.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_vowel_with_random_vowel" + ], + "rule_descriptions": { + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "jennifer hunter", + "label": "negative", + "script": "latin" + }, + { + "name": "todd wright", + "label": "negative", + "script": "latin" + }, + { + "name": "danny alvarado", + "label": "negative", + "script": "latin" + }, + { + "name": "cheryl roberts", + "label": "negative", + "script": "latin" + }, + { + "name": "sandra waters", + "label": "negative", + "script": "latin" + }, + { + "name": "michael rhodes", + "label": "negative", + "script": "latin" + }, + { + "name": "sandra mason", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy valenzuela", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer miller", + "label": "negative", + "script": "latin" + }, + { + "name": "douglas moore", + "label": "negative", + "script": "latin" + }, + { + "name": "dennis lee", + "label": "negative", + "script": "latin" + }, + { + "name": "erica daniels", + "label": "negative", + "script": "latin" + }, + { + "name": "david roberts", + "label": "negative", + "script": "latin" + }, + { + "name": "kathryn gordon", + "label": "negative", + "script": "latin" + }, + { + "name": "james stewart", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Use first name initial with last name, Delete a random letter, and Replace random vowels with different vowels.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "initial_only_first_name", + "delete_random_letter", + "replace_random_vowel_with_random_vowel" + ], + "rule_descriptions": { + "initial_only_first_name": "Use first name initial with last name", + "delete_random_letter": "Delete a random letter", + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "christopher ingram", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer pearson", + "label": "negative", + "script": "latin" + }, + { + "name": "joanne kelly", + "label": "negative", + "script": "latin" + }, + { + "name": "charlene clarke", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda williamson", + "label": "negative", + "script": "latin" + }, + { + "name": "jade arnold", + "label": "negative", + "script": "latin" + }, + { + "name": "danielle cooper", + "label": "negative", + "script": "latin" + }, + { + "name": "tasha hall", + "label": "negative", + "script": "latin" + }, + { + "name": "kayleigh mckenzie", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda nash", + "label": "negative", + "script": "latin" + }, + { + "name": "joel jordan", + "label": "negative", + "script": "latin" + }, + { + "name": "jason herrera", + "label": "negative", + "script": "latin" + }, + { + "name": "kimberly johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "paul nguyen", + "label": "negative", + "script": "latin" + }, + { + "name": "monica black", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Duplicate a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "duplicate_random_letter_as_double_letter" + ], + "rule_descriptions": { + "duplicate_random_letter_as_double_letter": "Duplicate a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "benjamin reed", + "label": "negative", + "script": "latin" + }, + { + "name": "kimberly carpenter", + "label": "negative", + "script": "latin" + }, + { + "name": "yvonne may", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas walker", + "label": "negative", + "script": "latin" + }, + { + "name": "brian lyons", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah bryant", + "label": "negative", + "script": "latin" + }, + { + "name": "rhys singh", + "label": "negative", + "script": "latin" + }, + { + "name": "angela mitchell", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda murray", + "label": "negative", + "script": "latin" + }, + { + "name": "nathaniel martin", + "label": "negative", + "script": "latin" + }, + { + "name": "jacob morgan", + "label": "negative", + "script": "latin" + }, + { + "name": "kelli cooper", + "label": "negative", + "script": "latin" + }, + { + "name": "sheila tucker", + "label": "negative", + "script": "latin" + }, + { + "name": "natalie allen", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy brown", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Convert name to initials.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_initials" + ], + "rule_descriptions": { + "shorten_name_to_initials": "Convert name to initials" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "nicole cook", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "carl clarke", + "label": "negative", + "script": "latin" + }, + { + "name": "kyle forbes", + "label": "negative", + "script": "latin" + }, + { + "name": "john cortez", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah rogers", + "label": "negative", + "script": "latin" + }, + { + "name": "justin hayes", + "label": "negative", + "script": "latin" + }, + { + "name": "deborah henry", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua torres", + "label": "negative", + "script": "latin" + }, + { + "name": "yolanda kerr", + "label": "negative", + "script": "latin" + }, + { + "name": "diana pope", + "label": "negative", + "script": "latin" + }, + { + "name": "morgan martinez", + "label": "negative", + "script": "latin" + }, + { + "name": "douglas wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "jason johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "roberta moore", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title suffix (Jr., PhD, etc.), and Swap adjacent consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_trailing_title", + "swap_adjacent_consonants" + ], + "rule_descriptions": { + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)", + "swap_adjacent_consonants": "Swap adjacent consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "jessica williams", + "label": "negative", + "script": "latin" + }, + { + "name": "shirley miller", + "label": "negative", + "script": "latin" + }, + { + "name": "victoria wall", + "label": "negative", + "script": "latin" + }, + { + "name": "angela clarke", + "label": "negative", + "script": "latin" + }, + { + "name": "elizabeth anderson", + "label": "negative", + "script": "latin" + }, + { + "name": "doris bennett", + "label": "negative", + "script": "latin" + }, + { + "name": "tracy jackson", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "margaret shepherd", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua davis", + "label": "negative", + "script": "latin" + }, + { + "name": "bryan wheeler", + "label": "negative", + "script": "latin" + }, + { + "name": "benjamin lee", + "label": "negative", + "script": "latin" + }, + { + "name": "dominique grant", + "label": "negative", + "script": "latin" + }, + { + "name": "bruce weeks", + "label": "negative", + "script": "latin" + }, + { + "name": "debra richardson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title suffix (Jr., PhD, etc.), Insert a random letter, and Swap random adjacent letters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_trailing_title", + "insert_random_letter", + "swap_random_letter" + ], + "rule_descriptions": { + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)", + "insert_random_letter": "Insert a random letter", + "swap_random_letter": "Swap random adjacent letters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "victoria ruiz", + "label": "negative", + "script": "latin" + }, + { + "name": "carole torres", + "label": "negative", + "script": "latin" + }, + { + "name": "lauren arnold", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua martinez", + "label": "negative", + "script": "latin" + }, + { + "name": "neil hoover", + "label": "negative", + "script": "latin" + }, + { + "name": "john mckee", + "label": "negative", + "script": "latin" + }, + { + "name": "carlos valencia", + "label": "negative", + "script": "latin" + }, + { + "name": "michael patterson", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda anderson", + "label": "negative", + "script": "latin" + }, + { + "name": "hailey williams", + "label": "negative", + "script": "latin" + }, + { + "name": "nancy green", + "label": "negative", + "script": "latin" + }, + { + "name": "emma yates", + "label": "negative", + "script": "latin" + }, + { + "name": "alexandra shaffer", + "label": "negative", + "script": "latin" + }, + { + "name": "james lee", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda brown", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Insert a random letter, Delete a random letter, and Remove all spaces.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "insert_random_letter", + "delete_random_letter", + "remove_all_spaces" + ], + "rule_descriptions": { + "insert_random_letter": "Insert a random letter", + "delete_random_letter": "Delete a random letter", + "remove_all_spaces": "Remove all spaces" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "andrea rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "keith moreno", + "label": "negative", + "script": "latin" + }, + { + "name": "vanessa anderson", + "label": "negative", + "script": "latin" + }, + { + "name": "vicki rivera", + "label": "negative", + "script": "latin" + }, + { + "name": "troy raymond", + "label": "negative", + "script": "latin" + }, + { + "name": "adam young", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa acosta", + "label": "negative", + "script": "latin" + }, + { + "name": "heather brown", + "label": "negative", + "script": "latin" + }, + { + "name": "jason mendoza", + "label": "negative", + "script": "latin" + }, + { + "name": "rebekah torres", + "label": "negative", + "script": "latin" + }, + { + "name": "curtis shea", + "label": "negative", + "script": "latin" + }, + { + "name": "kim hudson", + "label": "negative", + "script": "latin" + }, + { + "name": "samantha castillo", + "label": "negative", + "script": "latin" + }, + { + "name": "tammy brooks", + "label": "negative", + "script": "latin" + }, + { + "name": "amy macdonald", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title suffix (Jr., PhD, etc.), Use first name initial with last name, and Remove a random vowel.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_trailing_title", + "initial_only_first_name", + "remove_random_vowel" + ], + "rule_descriptions": { + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)", + "initial_only_first_name": "Use first name initial with last name", + "remove_random_vowel": "Remove a random vowel" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "joshua watson", + "label": "negative", + "script": "latin" + }, + { + "name": "crystal lewis", + "label": "negative", + "script": "latin" + }, + { + "name": "walter butler", + "label": "negative", + "script": "latin" + }, + { + "name": "maureen sullivan", + "label": "negative", + "script": "latin" + }, + { + "name": "brenda crawford", + "label": "negative", + "script": "latin" + }, + { + "name": "marvin clay", + "label": "negative", + "script": "latin" + }, + { + "name": "howard holmes", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle lamb", + "label": "negative", + "script": "latin" + }, + { + "name": "brandon tucker", + "label": "negative", + "script": "latin" + }, + { + "name": "steven wade", + "label": "negative", + "script": "latin" + }, + { + "name": "gregory wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "mark dodd", + "label": "negative", + "script": "latin" + }, + { + "name": "hannah dunn", + "label": "negative", + "script": "latin" + }, + { + "name": "veronica allan", + "label": "negative", + "script": "latin" + }, + { + "name": "julie jones", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Duplicate a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "duplicate_random_letter_as_double_letter" + ], + "rule_descriptions": { + "duplicate_random_letter_as_double_letter": "Duplicate a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "bradley pitts", + "label": "negative", + "script": "latin" + }, + { + "name": "tyler cooke", + "label": "negative", + "script": "latin" + }, + { + "name": "bethan cooper", + "label": "negative", + "script": "latin" + }, + { + "name": "glen rogers", + "label": "negative", + "script": "latin" + }, + { + "name": "david ward", + "label": "negative", + "script": "latin" + }, + { + "name": "alan crawford", + "label": "negative", + "script": "latin" + }, + { + "name": "javier mcdaniel", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony austin", + "label": "negative", + "script": "latin" + }, + { + "name": "rebecca curtis", + "label": "negative", + "script": "latin" + }, + { + "name": "erik lewis", + "label": "negative", + "script": "latin" + }, + { + "name": "tammy hill", + "label": "negative", + "script": "latin" + }, + { + "name": "cody ramos", + "label": "negative", + "script": "latin" + }, + { + "name": "russell levy", + "label": "negative", + "script": "latin" + }, + { + "name": "miguel crawford", + "label": "negative", + "script": "latin" + }, + { + "name": "eric blake", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove a random consonant, Reorder name parts, and Insert a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_consonant", + "name_parts_permutations", + "insert_random_letter" + ], + "rule_descriptions": { + "remove_random_consonant": "Remove a random consonant", + "name_parts_permutations": "Reorder name parts", + "insert_random_letter": "Insert a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "cory salinas", + "label": "negative", + "script": "latin" + }, + { + "name": "william dodson", + "label": "negative", + "script": "latin" + }, + { + "name": "parker brewer", + "label": "negative", + "script": "latin" + }, + { + "name": "juan love", + "label": "negative", + "script": "latin" + }, + { + "name": "angela collins", + "label": "negative", + "script": "latin" + }, + { + "name": "deborah henderson", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa rice", + "label": "negative", + "script": "latin" + }, + { + "name": "margaret livingston", + "label": "negative", + "script": "latin" + }, + { + "name": "danny coffey", + "label": "negative", + "script": "latin" + }, + { + "name": "jackson walker", + "label": "negative", + "script": "latin" + }, + { + "name": "ann mullins", + "label": "negative", + "script": "latin" + }, + { + "name": "teresa hill", + "label": "negative", + "script": "latin" + }, + { + "name": "katie brown", + "label": "negative", + "script": "latin" + }, + { + "name": "maria williams", + "label": "negative", + "script": "latin" + }, + { + "name": "autumn cooper", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace spaces with special characters, and Reorder name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_spaces_with_random_special_characters", + "name_parts_permutations" + ], + "rule_descriptions": { + "replace_spaces_with_random_special_characters": "Replace spaces with special characters", + "name_parts_permutations": "Reorder name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "benjamin todd", + "label": "negative", + "script": "latin" + }, + { + "name": "stuart hamilton", + "label": "negative", + "script": "latin" + }, + { + "name": "megan ellis", + "label": "negative", + "script": "latin" + }, + { + "name": "gloria gordon", + "label": "negative", + "script": "latin" + }, + { + "name": "lauren salas", + "label": "negative", + "script": "latin" + }, + { + "name": "troy hyde", + "label": "negative", + "script": "latin" + }, + { + "name": "derek gregory", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda frazier", + "label": "negative", + "script": "latin" + }, + { + "name": "natasha mora", + "label": "negative", + "script": "latin" + }, + { + "name": "leon clarke", + "label": "negative", + "script": "latin" + }, + { + "name": "justin rivera", + "label": "negative", + "script": "latin" + }, + { + "name": "willie potter", + "label": "negative", + "script": "latin" + }, + { + "name": "oliver mendoza", + "label": "negative", + "script": "latin" + }, + { + "name": "katie barrett", + "label": "negative", + "script": "latin" + }, + { + "name": "maria gomez", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Reorder name parts, Swap random adjacent letters, and Insert a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "name_parts_permutations", + "swap_random_letter", + "insert_random_letter" + ], + "rule_descriptions": { + "name_parts_permutations": "Reorder name parts", + "swap_random_letter": "Swap random adjacent letters", + "insert_random_letter": "Insert a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "brett begum", + "label": "negative", + "script": "latin" + }, + { + "name": "cynthia anderson", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher little", + "label": "negative", + "script": "latin" + }, + { + "name": "alyssa rivera", + "label": "negative", + "script": "latin" + }, + { + "name": "mary fernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "dawn conley", + "label": "negative", + "script": "latin" + }, + { + "name": "john riley", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah gutierrez", + "label": "negative", + "script": "latin" + }, + { + "name": "gary steele", + "label": "negative", + "script": "latin" + }, + { + "name": "stacey jenkins", + "label": "negative", + "script": "latin" + }, + { + "name": "candice hamilton", + "label": "negative", + "script": "latin" + }, + { + "name": "brett white", + "label": "negative", + "script": "latin" + }, + { + "name": "russell gonzales", + "label": "negative", + "script": "latin" + }, + { + "name": "heather dunn", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony michael", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Duplicate a random letter, Reorder name parts, and Replace random consonants with different consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "duplicate_random_letter_as_double_letter", + "name_parts_permutations", + "replace_random_consonant_with_random_consonant" + ], + "rule_descriptions": { + "duplicate_random_letter_as_double_letter": "Duplicate a random letter", + "name_parts_permutations": "Reorder name parts", + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "amy tran", + "label": "negative", + "script": "latin" + }, + { + "name": "carmen hebert", + "label": "negative", + "script": "latin" + }, + { + "name": "kimberley sanford", + "label": "negative", + "script": "latin" + }, + { + "name": "brandon palmer", + "label": "negative", + "script": "latin" + }, + { + "name": "tanya ray", + "label": "negative", + "script": "latin" + }, + { + "name": "sara hutchinson", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua baker", + "label": "negative", + "script": "latin" + }, + { + "name": "elijah stewart", + "label": "negative", + "script": "latin" + }, + { + "name": "maria powell", + "label": "negative", + "script": "latin" + }, + { + "name": "leslie walters", + "label": "negative", + "script": "latin" + }, + { + "name": "ronald estrada", + "label": "negative", + "script": "latin" + }, + { + "name": "krista harris", + "label": "negative", + "script": "latin" + }, + { + "name": "john johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa smith", + "label": "negative", + "script": "latin" + }, + { + "name": "robert douglas", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Swap random adjacent letters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_random_letter" + ], + "rule_descriptions": { + "swap_random_letter": "Swap random adjacent letters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "karen butler", + "label": "negative", + "script": "latin" + }, + { + "name": "philip smith", + "label": "negative", + "script": "latin" + }, + { + "name": "isaac flynn", + "label": "negative", + "script": "latin" + }, + { + "name": "elizabeth turner", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley brown", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole pierce", + "label": "negative", + "script": "latin" + }, + { + "name": "donald edwards", + "label": "negative", + "script": "latin" + }, + { + "name": "nicholas brown", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher sanchez", + "label": "negative", + "script": "latin" + }, + { + "name": "beverley baker", + "label": "negative", + "script": "latin" + }, + { + "name": "marilyn murphy", + "label": "negative", + "script": "latin" + }, + { + "name": "michael davis", + "label": "negative", + "script": "latin" + }, + { + "name": "helen evans", + "label": "negative", + "script": "latin" + }, + { + "name": "vincent olson", + "label": "negative", + "script": "latin" + }, + { + "name": "natasha green", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove a random vowel, Remove all spaces, and Replace random vowels with different vowels.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_vowel", + "remove_all_spaces", + "replace_random_vowel_with_random_vowel" + ], + "rule_descriptions": { + "remove_random_vowel": "Remove a random vowel", + "remove_all_spaces": "Remove all spaces", + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "lauren crosby", + "label": "negative", + "script": "latin" + }, + { + "name": "john peters", + "label": "negative", + "script": "latin" + }, + { + "name": "anita perez", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah jacobs", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph guerrero", + "label": "negative", + "script": "latin" + }, + { + "name": "kelly alvarez", + "label": "negative", + "script": "latin" + }, + { + "name": "jacob gutierrez", + "label": "negative", + "script": "latin" + }, + { + "name": "robert carr", + "label": "negative", + "script": "latin" + }, + { + "name": "summer carter", + "label": "negative", + "script": "latin" + }, + { + "name": "donna cunningham", + "label": "negative", + "script": "latin" + }, + { + "name": "patrick hyde", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher vargas", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew jenkins", + "label": "negative", + "script": "latin" + }, + { + "name": "paige newman", + "label": "negative", + "script": "latin" + }, + { + "name": "alexandra hanson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace spaces with special characters, and Swap adjacent syllables.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_spaces_with_random_special_characters", + "swap_adjacent_syllables" + ], + "rule_descriptions": { + "replace_spaces_with_random_special_characters": "Replace spaces with special characters", + "swap_adjacent_syllables": "Swap adjacent syllables" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "terry kay", + "label": "negative", + "script": "latin" + }, + { + "name": "kyle morris", + "label": "negative", + "script": "latin" + }, + { + "name": "deborah lewis", + "label": "negative", + "script": "latin" + }, + { + "name": "regina austin", + "label": "negative", + "script": "latin" + }, + { + "name": "bradley clements", + "label": "negative", + "script": "latin" + }, + { + "name": "sandra campbell", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy prince", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa brown", + "label": "negative", + "script": "latin" + }, + { + "name": "kerry king", + "label": "negative", + "script": "latin" + }, + { + "name": "elizabeth hill", + "label": "negative", + "script": "latin" + }, + { + "name": "neil thompson", + "label": "negative", + "script": "latin" + }, + { + "name": "emily stewart", + "label": "negative", + "script": "latin" + }, + { + "name": "tiffany curry", + "label": "negative", + "script": "latin" + }, + { + "name": "joyce baker", + "label": "negative", + "script": "latin" + }, + { + "name": "robert ross", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace random consonants with different consonants, and Remove all spaces.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_consonant_with_random_consonant", + "remove_all_spaces" + ], + "rule_descriptions": { + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants", + "remove_all_spaces": "Remove all spaces" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "scott clayton", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy clarke", + "label": "negative", + "script": "latin" + }, + { + "name": "donald dyer", + "label": "negative", + "script": "latin" + }, + { + "name": "brittany oconnell", + "label": "negative", + "script": "latin" + }, + { + "name": "gareth abbott", + "label": "negative", + "script": "latin" + }, + { + "name": "margaret young", + "label": "negative", + "script": "latin" + }, + { + "name": "george shaffer", + "label": "negative", + "script": "latin" + }, + { + "name": "janice mitchell", + "label": "negative", + "script": "latin" + }, + { + "name": "conor smith", + "label": "negative", + "script": "latin" + }, + { + "name": "tanya davies", + "label": "negative", + "script": "latin" + }, + { + "name": "mathew ramirez", + "label": "negative", + "script": "latin" + }, + { + "name": "leslie taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew david", + "label": "negative", + "script": "latin" + }, + { + "name": "manuel brown", + "label": "negative", + "script": "latin" + }, + { + "name": "natasha hudson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace random consonants with different consonants, Add a title suffix (Jr., PhD, etc.), and Reorder name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_consonant_with_random_consonant", + "add_random_trailing_title", + "name_parts_permutations" + ], + "rule_descriptions": { + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants", + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)", + "name_parts_permutations": "Reorder name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "nicole oneal", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa larson", + "label": "negative", + "script": "latin" + }, + { + "name": "julia marshall", + "label": "negative", + "script": "latin" + }, + { + "name": "susan may", + "label": "negative", + "script": "latin" + }, + { + "name": "isaac perez", + "label": "negative", + "script": "latin" + }, + { + "name": "roy waller", + "label": "negative", + "script": "latin" + }, + { + "name": "adam maxwell", + "label": "negative", + "script": "latin" + }, + { + "name": "dana haley", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel thompson", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa russell", + "label": "negative", + "script": "latin" + }, + { + "name": "tony farley", + "label": "negative", + "script": "latin" + }, + { + "name": "kathryn phillips", + "label": "negative", + "script": "latin" + }, + { + "name": "dawn pham", + "label": "negative", + "script": "latin" + }, + { + "name": "jamie chen", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew stephens", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Use first name initial with last name, and Remove a random vowel.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "initial_only_first_name", + "remove_random_vowel" + ], + "rule_descriptions": { + "initial_only_first_name": "Use first name initial with last name", + "remove_random_vowel": "Remove a random vowel" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "roger stanley", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher olson", + "label": "negative", + "script": "latin" + }, + { + "name": "david taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "alexander hamilton", + "label": "negative", + "script": "latin" + }, + { + "name": "gregory schmitt", + "label": "negative", + "script": "latin" + }, + { + "name": "alan wade", + "label": "negative", + "script": "latin" + }, + { + "name": "joyce heath", + "label": "negative", + "script": "latin" + }, + { + "name": "mary wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "hayley lopez", + "label": "negative", + "script": "latin" + }, + { + "name": "shane hughes", + "label": "negative", + "script": "latin" + }, + { + "name": "christian white", + "label": "negative", + "script": "latin" + }, + { + "name": "bruce baldwin", + "label": "negative", + "script": "latin" + }, + { + "name": "christian cline", + "label": "negative", + "script": "latin" + }, + { + "name": "james lopez", + "label": "negative", + "script": "latin" + }, + { + "name": "lydia carr", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap random adjacent letters, and Reorder name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_random_letter", + "name_parts_permutations" + ], + "rule_descriptions": { + "swap_random_letter": "Swap random adjacent letters", + "name_parts_permutations": "Reorder name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "charles johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "scott glenn", + "label": "negative", + "script": "latin" + }, + { + "name": "michael holloway", + "label": "negative", + "script": "latin" + }, + { + "name": "alyssa gonzalez", + "label": "negative", + "script": "latin" + }, + { + "name": "carlos donnelly", + "label": "negative", + "script": "latin" + }, + { + "name": "justin franco", + "label": "negative", + "script": "latin" + }, + { + "name": "megan castillo", + "label": "negative", + "script": "latin" + }, + { + "name": "brianna bond", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle daugherty", + "label": "negative", + "script": "latin" + }, + { + "name": "michael ortega", + "label": "negative", + "script": "latin" + }, + { + "name": "katrina evans", + "label": "negative", + "script": "latin" + }, + { + "name": "denis mitchell", + "label": "negative", + "script": "latin" + }, + { + "name": "alicia woods", + "label": "negative", + "script": "latin" + }, + { + "name": "mary gregory", + "label": "negative", + "script": "latin" + }, + { + "name": "irene ortiz", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace random consonants with different consonants, and Remove a random consonant.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_consonant_with_random_consonant", + "remove_random_consonant" + ], + "rule_descriptions": { + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants", + "remove_random_consonant": "Remove a random consonant" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "christopher brown", + "label": "negative", + "script": "latin" + }, + { + "name": "graeme cameron", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda avila", + "label": "negative", + "script": "latin" + }, + { + "name": "emily woods", + "label": "negative", + "script": "latin" + }, + { + "name": "barry mcpherson", + "label": "negative", + "script": "latin" + }, + { + "name": "paul cuevas", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley jordan", + "label": "negative", + "script": "latin" + }, + { + "name": "alexander webster", + "label": "negative", + "script": "latin" + }, + { + "name": "marie jones", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole moss", + "label": "negative", + "script": "latin" + }, + { + "name": "katie beasley", + "label": "negative", + "script": "latin" + }, + { + "name": "aaron gregory", + "label": "negative", + "script": "latin" + }, + { + "name": "haley drake", + "label": "negative", + "script": "latin" + }, + { + "name": "gregory kerr", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin craig", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove a random consonant, Insert a random letter, and Swap random adjacent letters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_consonant", + "insert_random_letter", + "swap_random_letter" + ], + "rule_descriptions": { + "remove_random_consonant": "Remove a random consonant", + "insert_random_letter": "Insert a random letter", + "swap_random_letter": "Swap random adjacent letters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "lisa moore", + "label": "negative", + "script": "latin" + }, + { + "name": "sharon carroll", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy wu", + "label": "negative", + "script": "latin" + }, + { + "name": "damian delacruz", + "label": "negative", + "script": "latin" + }, + { + "name": "stacey rhodes", + "label": "negative", + "script": "latin" + }, + { + "name": "douglas mellor", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher fox", + "label": "negative", + "script": "latin" + }, + { + "name": "michael page", + "label": "negative", + "script": "latin" + }, + { + "name": "denise durham", + "label": "negative", + "script": "latin" + }, + { + "name": "hannah cain", + "label": "negative", + "script": "latin" + }, + { + "name": "josh talbot", + "label": "negative", + "script": "latin" + }, + { + "name": "brandon holloway", + "label": "negative", + "script": "latin" + }, + { + "name": "nancy martinez", + "label": "negative", + "script": "latin" + }, + { + "name": "emma avila", + "label": "negative", + "script": "latin" + }, + { + "name": "trevor roth", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace spaces with special characters, and Add a title prefix (Mr., Dr., etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_spaces_with_random_special_characters", + "add_random_leading_title" + ], + "rule_descriptions": { + "replace_spaces_with_random_special_characters": "Replace spaces with special characters", + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "charles johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "hazel elliott", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda bowman", + "label": "negative", + "script": "latin" + }, + { + "name": "denise herrera", + "label": "negative", + "script": "latin" + }, + { + "name": "ryan hall", + "label": "negative", + "script": "latin" + }, + { + "name": "kimberly rose", + "label": "negative", + "script": "latin" + }, + { + "name": "angela matthews", + "label": "negative", + "script": "latin" + }, + { + "name": "guy moran", + "label": "negative", + "script": "latin" + }, + { + "name": "heather lane", + "label": "negative", + "script": "latin" + }, + { + "name": "julia castro", + "label": "negative", + "script": "latin" + }, + { + "name": "brendan gomez", + "label": "negative", + "script": "latin" + }, + { + "name": "barry carr", + "label": "negative", + "script": "latin" + }, + { + "name": "carrie hayes", + "label": "negative", + "script": "latin" + }, + { + "name": "derek clements", + "label": "negative", + "script": "latin" + }, + { + "name": "jordan boone", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Reorder name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "name_parts_permutations" + ], + "rule_descriptions": { + "name_parts_permutations": "Reorder name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "elizabeth andrews", + "label": "negative", + "script": "latin" + }, + { + "name": "andrew smith", + "label": "negative", + "script": "latin" + }, + { + "name": "william duran", + "label": "negative", + "script": "latin" + }, + { + "name": "jorge wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "barbara phillips", + "label": "negative", + "script": "latin" + }, + { + "name": "lynda spencer", + "label": "negative", + "script": "latin" + }, + { + "name": "danielle burrows", + "label": "negative", + "script": "latin" + }, + { + "name": "jose cochran", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah davis", + "label": "negative", + "script": "latin" + }, + { + "name": "fred walsh", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole hill", + "label": "negative", + "script": "latin" + }, + { + "name": "john wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "allison stevenson", + "label": "negative", + "script": "latin" + }, + { + "name": "john williams", + "label": "negative", + "script": "latin" + }, + { + "name": "jasmin stephens", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove a random consonant, and Reorder name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_consonant", + "name_parts_permutations" + ], + "rule_descriptions": { + "remove_random_consonant": "Remove a random consonant", + "name_parts_permutations": "Reorder name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "joel gonzales", + "label": "negative", + "script": "latin" + }, + { + "name": "ryan yates", + "label": "negative", + "script": "latin" + }, + { + "name": "jasmine fisher", + "label": "negative", + "script": "latin" + }, + { + "name": "erik clark", + "label": "negative", + "script": "latin" + }, + { + "name": "chloe allen", + "label": "negative", + "script": "latin" + }, + { + "name": "jason williams", + "label": "negative", + "script": "latin" + }, + { + "name": "jean gonzalez", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony freeman", + "label": "negative", + "script": "latin" + }, + { + "name": "crystal rojas", + "label": "negative", + "script": "latin" + }, + { + "name": "david thomas", + "label": "negative", + "script": "latin" + }, + { + "name": "kyle adkins", + "label": "negative", + "script": "latin" + }, + { + "name": "david taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "shannon mcgee", + "label": "negative", + "script": "latin" + }, + { + "name": "veronica gill", + "label": "negative", + "script": "latin" + }, + { + "name": "mary casey", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace random vowels with different vowels, and Convert name to initials.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_vowel_with_random_vowel", + "shorten_name_to_initials" + ], + "rule_descriptions": { + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels", + "shorten_name_to_initials": "Convert name to initials" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "kirsten walls", + "label": "negative", + "script": "latin" + }, + { + "name": "samantha harris", + "label": "negative", + "script": "latin" + }, + { + "name": "kathleen miller", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "raymond mcdaniel", + "label": "negative", + "script": "latin" + }, + { + "name": "amy andrews", + "label": "negative", + "script": "latin" + }, + { + "name": "taylor gallagher", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew lewis", + "label": "negative", + "script": "latin" + }, + { + "name": "rebecca lopez", + "label": "negative", + "script": "latin" + }, + { + "name": "steven nelson", + "label": "negative", + "script": "latin" + }, + { + "name": "herbert jones", + "label": "negative", + "script": "latin" + }, + { + "name": "michael hess", + "label": "negative", + "script": "latin" + }, + { + "name": "ricky jackson", + "label": "negative", + "script": "latin" + }, + { + "name": "karla huff", + "label": "negative", + "script": "latin" + }, + { + "name": "john anderson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Reorder name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "name_parts_permutations" + ], + "rule_descriptions": { + "name_parts_permutations": "Reorder name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "chris hope", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony stanley", + "label": "negative", + "script": "latin" + }, + { + "name": "ann lane", + "label": "negative", + "script": "latin" + }, + { + "name": "sian cooper", + "label": "negative", + "script": "latin" + }, + { + "name": "june gonzalez", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas martin", + "label": "negative", + "script": "latin" + }, + { + "name": "susan clark", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel scott", + "label": "negative", + "script": "latin" + }, + { + "name": "megan frazier", + "label": "negative", + "script": "latin" + }, + { + "name": "ricky brown", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher farrell", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel mercer", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel mason", + "label": "negative", + "script": "latin" + }, + { + "name": "brent stewart", + "label": "negative", + "script": "latin" + }, + { + "name": "robert stout", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap adjacent consonants, and Swap random adjacent letters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_consonants", + "swap_random_letter" + ], + "rule_descriptions": { + "swap_adjacent_consonants": "Swap adjacent consonants", + "swap_random_letter": "Swap random adjacent letters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "jeffery haynes", + "label": "negative", + "script": "latin" + }, + { + "name": "terence kay", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel rogers", + "label": "negative", + "script": "latin" + }, + { + "name": "william mills", + "label": "negative", + "script": "latin" + }, + { + "name": "ryan houghton", + "label": "negative", + "script": "latin" + }, + { + "name": "philip willis", + "label": "negative", + "script": "latin" + }, + { + "name": "kristina ortiz", + "label": "negative", + "script": "latin" + }, + { + "name": "josh arnold", + "label": "negative", + "script": "latin" + }, + { + "name": "luis young", + "label": "negative", + "script": "latin" + }, + { + "name": "julian harding", + "label": "negative", + "script": "latin" + }, + { + "name": "rhonda campos", + "label": "negative", + "script": "latin" + }, + { + "name": "leah lopez", + "label": "negative", + "script": "latin" + }, + { + "name": "michael goodman", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa watson", + "label": "negative", + "script": "latin" + }, + { + "name": "cynthia martinez", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Add a title suffix (Jr., PhD, etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_trailing_title" + ], + "rule_descriptions": { + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "kristen davidson", + "label": "negative", + "script": "latin" + }, + { + "name": "debra chavez", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda evans", + "label": "negative", + "script": "latin" + }, + { + "name": "brian alvarez", + "label": "negative", + "script": "latin" + }, + { + "name": "maurice carlson", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa reed", + "label": "negative", + "script": "latin" + }, + { + "name": "sophie gardiner", + "label": "negative", + "script": "latin" + }, + { + "name": "benjamin silva", + "label": "negative", + "script": "latin" + }, + { + "name": "damien lyons", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah key", + "label": "negative", + "script": "latin" + }, + { + "name": "danielle rose", + "label": "negative", + "script": "latin" + }, + { + "name": "samantha evans", + "label": "negative", + "script": "latin" + }, + { + "name": "mark bowman", + "label": "negative", + "script": "latin" + }, + { + "name": "michael smith", + "label": "negative", + "script": "latin" + }, + { + "name": "leslie mann", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace spaces with special characters, and Swap random adjacent letters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_spaces_with_random_special_characters", + "swap_random_letter" + ], + "rule_descriptions": { + "replace_spaces_with_random_special_characters": "Replace spaces with special characters", + "swap_random_letter": "Swap random adjacent letters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "brooke owen", + "label": "negative", + "script": "latin" + }, + { + "name": "paul evans", + "label": "negative", + "script": "latin" + }, + { + "name": "jacob lee", + "label": "negative", + "script": "latin" + }, + { + "name": "austin waters", + "label": "negative", + "script": "latin" + }, + { + "name": "jenna perez", + "label": "negative", + "script": "latin" + }, + { + "name": "michael brewer", + "label": "negative", + "script": "latin" + }, + { + "name": "deborah vincent", + "label": "negative", + "script": "latin" + }, + { + "name": "steven hull", + "label": "negative", + "script": "latin" + }, + { + "name": "dana green", + "label": "negative", + "script": "latin" + }, + { + "name": "david shea", + "label": "negative", + "script": "latin" + }, + { + "name": "valerie bell", + "label": "negative", + "script": "latin" + }, + { + "name": "darius simpson", + "label": "negative", + "script": "latin" + }, + { + "name": "michael gonzales", + "label": "negative", + "script": "latin" + }, + { + "name": "robin clarke", + "label": "negative", + "script": "latin" + }, + { + "name": "olivia young", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Duplicate a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "duplicate_random_letter_as_double_letter" + ], + "rule_descriptions": { + "duplicate_random_letter_as_double_letter": "Duplicate a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "philip morgan", + "label": "negative", + "script": "latin" + }, + { + "name": "amy brown", + "label": "negative", + "script": "latin" + }, + { + "name": "tara price", + "label": "negative", + "script": "latin" + }, + { + "name": "craig dixon", + "label": "negative", + "script": "latin" + }, + { + "name": "david barnett", + "label": "negative", + "script": "latin" + }, + { + "name": "john brown", + "label": "negative", + "script": "latin" + }, + { + "name": "leslie griffith", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua porter", + "label": "negative", + "script": "latin" + }, + { + "name": "kelly martinez", + "label": "negative", + "script": "latin" + }, + { + "name": "nathan baker", + "label": "negative", + "script": "latin" + }, + { + "name": "rhys carey", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph arnold", + "label": "negative", + "script": "latin" + }, + { + "name": "laura bates", + "label": "negative", + "script": "latin" + }, + { + "name": "michele fisher", + "label": "negative", + "script": "latin" + }, + { + "name": "henry huerta", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Replace random consonants with different consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_consonant_with_random_consonant" + ], + "rule_descriptions": { + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "david chandler", + "label": "negative", + "script": "latin" + }, + { + "name": "janice garcia", + "label": "negative", + "script": "latin" + }, + { + "name": "wendy thompson", + "label": "negative", + "script": "latin" + }, + { + "name": "robert smith", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher freeman", + "label": "negative", + "script": "latin" + }, + { + "name": "gary mueller", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda baker", + "label": "negative", + "script": "latin" + }, + { + "name": "barbara hubbard", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley collier", + "label": "negative", + "script": "latin" + }, + { + "name": "bradley wells", + "label": "negative", + "script": "latin" + }, + { + "name": "samuel jones", + "label": "negative", + "script": "latin" + }, + { + "name": "tracy king", + "label": "negative", + "script": "latin" + }, + { + "name": "samantha sykes", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua eaton", + "label": "negative", + "script": "latin" + }, + { + "name": "mary stephenson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap adjacent syllables, Insert a random letter, and Use first name initial with last name.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_syllables", + "insert_random_letter", + "initial_only_first_name" + ], + "rule_descriptions": { + "swap_adjacent_syllables": "Swap adjacent syllables", + "insert_random_letter": "Insert a random letter", + "initial_only_first_name": "Use first name initial with last name" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "bradley harris", + "label": "negative", + "script": "latin" + }, + { + "name": "jay lopez", + "label": "negative", + "script": "latin" + }, + { + "name": "sara thomas", + "label": "negative", + "script": "latin" + }, + { + "name": "craig scott", + "label": "negative", + "script": "latin" + }, + { + "name": "charles potter", + "label": "negative", + "script": "latin" + }, + { + "name": "shawn vance", + "label": "negative", + "script": "latin" + }, + { + "name": "louis walker", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah marshall", + "label": "negative", + "script": "latin" + }, + { + "name": "sandra page", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher henry", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda walker", + "label": "negative", + "script": "latin" + }, + { + "name": "kenneth walsh", + "label": "negative", + "script": "latin" + }, + { + "name": "mariah klein", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffrey fry", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy klein", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap random adjacent letters, Remove a random consonant, and Replace double letters with a single letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_random_letter", + "remove_random_consonant", + "replace_double_letters_with_single_letter" + ], + "rule_descriptions": { + "swap_random_letter": "Swap random adjacent letters", + "remove_random_consonant": "Remove a random consonant", + "replace_double_letters_with_single_letter": "Replace double letters with a single letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "adam nunez", + "label": "negative", + "script": "latin" + }, + { + "name": "maxwell richardson", + "label": "negative", + "script": "latin" + }, + { + "name": "lawrence willis", + "label": "negative", + "script": "latin" + }, + { + "name": "adam myers", + "label": "negative", + "script": "latin" + }, + { + "name": "christian phillips", + "label": "negative", + "script": "latin" + }, + { + "name": "nathan beck", + "label": "negative", + "script": "latin" + }, + { + "name": "brian kim", + "label": "negative", + "script": "latin" + }, + { + "name": "stacey rosales", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffrey rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "luis simpson", + "label": "negative", + "script": "latin" + }, + { + "name": "hannah burke", + "label": "negative", + "script": "latin" + }, + { + "name": "jacqueline turner", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole willis", + "label": "negative", + "script": "latin" + }, + { + "name": "william cantu", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas cobb", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Swap adjacent syllables.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_syllables" + ], + "rule_descriptions": { + "swap_adjacent_syllables": "Swap adjacent syllables" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "stephanie gonzalez", + "label": "negative", + "script": "latin" + }, + { + "name": "angela foster", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer cooke", + "label": "negative", + "script": "latin" + }, + { + "name": "david garrett", + "label": "negative", + "script": "latin" + }, + { + "name": "gregory hughes", + "label": "negative", + "script": "latin" + }, + { + "name": "janice baker", + "label": "negative", + "script": "latin" + }, + { + "name": "iain riley", + "label": "negative", + "script": "latin" + }, + { + "name": "keith barker", + "label": "negative", + "script": "latin" + }, + { + "name": "kyle sanchez", + "label": "negative", + "script": "latin" + }, + { + "name": "zoe hayes", + "label": "negative", + "script": "latin" + }, + { + "name": "catherine collins", + "label": "negative", + "script": "latin" + }, + { + "name": "valerie smith", + "label": "negative", + "script": "latin" + }, + { + "name": "sara sanchez", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa wagner", + "label": "negative", + "script": "latin" + }, + { + "name": "logan dixon", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Convert name to initials, Replace spaces with special characters, and Delete a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_initials", + "replace_spaces_with_random_special_characters", + "delete_random_letter" + ], + "rule_descriptions": { + "shorten_name_to_initials": "Convert name to initials", + "replace_spaces_with_random_special_characters": "Replace spaces with special characters", + "delete_random_letter": "Delete a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "kimberly phelps", + "label": "negative", + "script": "latin" + }, + { + "name": "jean scott", + "label": "negative", + "script": "latin" + }, + { + "name": "angela bartlett", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel ferguson", + "label": "negative", + "script": "latin" + }, + { + "name": "james wu", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa graham", + "label": "negative", + "script": "latin" + }, + { + "name": "brandon boyd", + "label": "negative", + "script": "latin" + }, + { + "name": "annette jennings", + "label": "negative", + "script": "latin" + }, + { + "name": "angel brooks", + "label": "negative", + "script": "latin" + }, + { + "name": "brianna stone", + "label": "negative", + "script": "latin" + }, + { + "name": "marc long", + "label": "negative", + "script": "latin" + }, + { + "name": "carolyn dunlap", + "label": "negative", + "script": "latin" + }, + { + "name": "george myers", + "label": "negative", + "script": "latin" + }, + { + "name": "derek miles", + "label": "negative", + "script": "latin" + }, + { + "name": "dennis wall", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title prefix (Mr., Dr., etc.), Remove all spaces, and Remove a random vowel.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_leading_title", + "remove_all_spaces", + "remove_random_vowel" + ], + "rule_descriptions": { + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)", + "remove_all_spaces": "Remove all spaces", + "remove_random_vowel": "Remove a random vowel" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "amanda williams", + "label": "negative", + "script": "latin" + }, + { + "name": "anna molina", + "label": "negative", + "script": "latin" + }, + { + "name": "taylor ray", + "label": "negative", + "script": "latin" + }, + { + "name": "richard terry", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah west", + "label": "negative", + "script": "latin" + }, + { + "name": "brandon mendez", + "label": "negative", + "script": "latin" + }, + { + "name": "craig lopez", + "label": "negative", + "script": "latin" + }, + { + "name": "ricardo daniel", + "label": "negative", + "script": "latin" + }, + { + "name": "carlos williams", + "label": "negative", + "script": "latin" + }, + { + "name": "brenda brown", + "label": "negative", + "script": "latin" + }, + { + "name": "joan arias", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony berry", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle potter", + "label": "negative", + "script": "latin" + }, + { + "name": "sara patel", + "label": "negative", + "script": "latin" + }, + { + "name": "sally henderson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace random vowels with different vowels, Remove a random consonant, and Add a title prefix (Mr., Dr., etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_vowel_with_random_vowel", + "remove_random_consonant", + "add_random_leading_title" + ], + "rule_descriptions": { + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels", + "remove_random_consonant": "Remove a random consonant", + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "victor alexander", + "label": "negative", + "script": "latin" + }, + { + "name": "lauren powell", + "label": "negative", + "script": "latin" + }, + { + "name": "john phillips", + "label": "negative", + "script": "latin" + }, + { + "name": "terence guzman", + "label": "negative", + "script": "latin" + }, + { + "name": "madison mata", + "label": "negative", + "script": "latin" + }, + { + "name": "elizabeth cooper", + "label": "negative", + "script": "latin" + }, + { + "name": "carolyn miller", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa gray", + "label": "negative", + "script": "latin" + }, + { + "name": "christina robinson", + "label": "negative", + "script": "latin" + }, + { + "name": "mary burke", + "label": "negative", + "script": "latin" + }, + { + "name": "martyn hudson", + "label": "negative", + "script": "latin" + }, + { + "name": "kyle hines", + "label": "negative", + "script": "latin" + }, + { + "name": "benjamin thompson", + "label": "negative", + "script": "latin" + }, + { + "name": "brianna cooper", + "label": "negative", + "script": "latin" + }, + { + "name": "taylor acosta", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Duplicate a random letter, and Add a title suffix (Jr., PhD, etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "duplicate_random_letter_as_double_letter", + "add_random_trailing_title" + ], + "rule_descriptions": { + "duplicate_random_letter_as_double_letter": "Duplicate a random letter", + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "joshua martin", + "label": "negative", + "script": "latin" + }, + { + "name": "kenneth davis", + "label": "negative", + "script": "latin" + }, + { + "name": "andrew york", + "label": "negative", + "script": "latin" + }, + { + "name": "david medina", + "label": "negative", + "script": "latin" + }, + { + "name": "james harris", + "label": "negative", + "script": "latin" + }, + { + "name": "gregory pham", + "label": "negative", + "script": "latin" + }, + { + "name": "paul smith", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle newman", + "label": "negative", + "script": "latin" + }, + { + "name": "nathan wright", + "label": "negative", + "script": "latin" + }, + { + "name": "brenda gregory", + "label": "negative", + "script": "latin" + }, + { + "name": "laura hughes", + "label": "negative", + "script": "latin" + }, + { + "name": "tonya powell", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas goodwin", + "label": "negative", + "script": "latin" + }, + { + "name": "ian franklin", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie mccormick", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Remove a random consonant.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_consonant" + ], + "rule_descriptions": { + "remove_random_consonant": "Remove a random consonant" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "corey allen", + "label": "negative", + "script": "latin" + }, + { + "name": "mitchell hernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "michael alexander", + "label": "negative", + "script": "latin" + }, + { + "name": "kelly white", + "label": "negative", + "script": "latin" + }, + { + "name": "jacob mistry", + "label": "negative", + "script": "latin" + }, + { + "name": "kirsty williams", + "label": "negative", + "script": "latin" + }, + { + "name": "ann pena", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffrey ramirez", + "label": "negative", + "script": "latin" + }, + { + "name": "marc murray", + "label": "negative", + "script": "latin" + }, + { + "name": "victoria barnes", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica white", + "label": "negative", + "script": "latin" + }, + { + "name": "james williams", + "label": "negative", + "script": "latin" + }, + { + "name": "cody brown", + "label": "negative", + "script": "latin" + }, + { + "name": "hayley garcia", + "label": "negative", + "script": "latin" + }, + { + "name": "deborah edwards", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap random adjacent letters, Add a title suffix (Jr., PhD, etc.), and Replace random consonants with different consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_random_letter", + "add_random_trailing_title", + "replace_random_consonant_with_random_consonant" + ], + "rule_descriptions": { + "swap_random_letter": "Swap random adjacent letters", + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)", + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "catherine morris", + "label": "negative", + "script": "latin" + }, + { + "name": "devin clark", + "label": "negative", + "script": "latin" + }, + { + "name": "aaron daugherty", + "label": "negative", + "script": "latin" + }, + { + "name": "margaret holt", + "label": "negative", + "script": "latin" + }, + { + "name": "deanna gomez", + "label": "negative", + "script": "latin" + }, + { + "name": "john mejia", + "label": "negative", + "script": "latin" + }, + { + "name": "debbie delacruz", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa murphy", + "label": "negative", + "script": "latin" + }, + { + "name": "james george", + "label": "negative", + "script": "latin" + }, + { + "name": "tracy carpenter", + "label": "negative", + "script": "latin" + }, + { + "name": "raymond jackson", + "label": "negative", + "script": "latin" + }, + { + "name": "naomi lloyd", + "label": "negative", + "script": "latin" + }, + { + "name": "hilary rivera", + "label": "negative", + "script": "latin" + }, + { + "name": "linda martinez", + "label": "negative", + "script": "latin" + }, + { + "name": "brian hansen", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Use first name initial with last name.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "initial_only_first_name" + ], + "rule_descriptions": { + "initial_only_first_name": "Use first name initial with last name" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "stewart johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "tabitha ali", + "label": "negative", + "script": "latin" + }, + { + "name": "christine gregory", + "label": "negative", + "script": "latin" + }, + { + "name": "catherine trujillo", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffery thomas", + "label": "negative", + "script": "latin" + }, + { + "name": "kara robinson", + "label": "negative", + "script": "latin" + }, + { + "name": "corey pham", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin guzman", + "label": "negative", + "script": "latin" + }, + { + "name": "kate morgan", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy scott", + "label": "negative", + "script": "latin" + }, + { + "name": "kayleigh clay", + "label": "negative", + "script": "latin" + }, + { + "name": "katy norris", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer mcconnell", + "label": "negative", + "script": "latin" + }, + { + "name": "annette morgan", + "label": "negative", + "script": "latin" + }, + { + "name": "nicholas silva", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Abbreviate name parts, Reorder name parts, and Replace double letters with a single letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_abbreviations", + "name_parts_permutations", + "replace_double_letters_with_single_letter" + ], + "rule_descriptions": { + "shorten_name_to_abbreviations": "Abbreviate name parts", + "name_parts_permutations": "Reorder name parts", + "replace_double_letters_with_single_letter": "Replace double letters with a single letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "lindsay hernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "eleanor johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "jordan levy", + "label": "negative", + "script": "latin" + }, + { + "name": "ryan hargreaves", + "label": "negative", + "script": "latin" + }, + { + "name": "kate moore", + "label": "negative", + "script": "latin" + }, + { + "name": "charlotte murray", + "label": "negative", + "script": "latin" + }, + { + "name": "katelyn thomas", + "label": "negative", + "script": "latin" + }, + { + "name": "shane orozco", + "label": "negative", + "script": "latin" + }, + { + "name": "donna gallagher", + "label": "negative", + "script": "latin" + }, + { + "name": "amber nelson", + "label": "negative", + "script": "latin" + }, + { + "name": "samuel cox", + "label": "negative", + "script": "latin" + }, + { + "name": "frederick day", + "label": "negative", + "script": "latin" + }, + { + "name": "terri bell", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas jenkins", + "label": "negative", + "script": "latin" + }, + { + "name": "david vazquez", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title prefix (Mr., Dr., etc.), Replace random consonants with different consonants, and Remove a random vowel.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_leading_title", + "replace_random_consonant_with_random_consonant", + "remove_random_vowel" + ], + "rule_descriptions": { + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)", + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants", + "remove_random_vowel": "Remove a random vowel" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "jessica ponce", + "label": "negative", + "script": "latin" + }, + { + "name": "robert nelson", + "label": "negative", + "script": "latin" + }, + { + "name": "phillip barnes", + "label": "negative", + "script": "latin" + }, + { + "name": "kimberly ingram", + "label": "negative", + "script": "latin" + }, + { + "name": "donna alexander", + "label": "negative", + "script": "latin" + }, + { + "name": "kylie davison", + "label": "negative", + "script": "latin" + }, + { + "name": "katie herman", + "label": "negative", + "script": "latin" + }, + { + "name": "laura stewart", + "label": "negative", + "script": "latin" + }, + { + "name": "mary marshall", + "label": "negative", + "script": "latin" + }, + { + "name": "danielle becker", + "label": "negative", + "script": "latin" + }, + { + "name": "abigail holland", + "label": "negative", + "script": "latin" + }, + { + "name": "seth thomas", + "label": "negative", + "script": "latin" + }, + { + "name": "robert wright", + "label": "negative", + "script": "latin" + }, + { + "name": "marian mccann", + "label": "negative", + "script": "latin" + }, + { + "name": "rebecca kelly", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Insert a random letter, and Swap random adjacent letters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "insert_random_letter", + "swap_random_letter" + ], + "rule_descriptions": { + "insert_random_letter": "Insert a random letter", + "swap_random_letter": "Swap random adjacent letters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "dorothy watson", + "label": "negative", + "script": "latin" + }, + { + "name": "brenda marshall", + "label": "negative", + "script": "latin" + }, + { + "name": "valerie gonzalez", + "label": "negative", + "script": "latin" + }, + { + "name": "suzanne henderson", + "label": "negative", + "script": "latin" + }, + { + "name": "roger roy", + "label": "negative", + "script": "latin" + }, + { + "name": "eric martinez", + "label": "negative", + "script": "latin" + }, + { + "name": "erika cameron", + "label": "negative", + "script": "latin" + }, + { + "name": "angela trevino", + "label": "negative", + "script": "latin" + }, + { + "name": "guy elliott", + "label": "negative", + "script": "latin" + }, + { + "name": "deborah solis", + "label": "negative", + "script": "latin" + }, + { + "name": "john baird", + "label": "negative", + "script": "latin" + }, + { + "name": "benjamin harris", + "label": "negative", + "script": "latin" + }, + { + "name": "duncan nguyen", + "label": "negative", + "script": "latin" + }, + { + "name": "michael sutton", + "label": "negative", + "script": "latin" + }, + { + "name": "madison davis", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title suffix (Jr., PhD, etc.), Remove a random consonant, and Remove a random vowel.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_trailing_title", + "remove_random_consonant", + "remove_random_vowel" + ], + "rule_descriptions": { + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)", + "remove_random_consonant": "Remove a random consonant", + "remove_random_vowel": "Remove a random vowel" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "kerry crawford", + "label": "negative", + "script": "latin" + }, + { + "name": "kathleen olson", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica reyes", + "label": "negative", + "script": "latin" + }, + { + "name": "elizabeth montoya", + "label": "negative", + "script": "latin" + }, + { + "name": "norma robertson", + "label": "negative", + "script": "latin" + }, + { + "name": "stacy bryant", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin robinson", + "label": "negative", + "script": "latin" + }, + { + "name": "jerry nash", + "label": "negative", + "script": "latin" + }, + { + "name": "eric frost", + "label": "negative", + "script": "latin" + }, + { + "name": "stanley snyder", + "label": "negative", + "script": "latin" + }, + { + "name": "ryan wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "randall rhodes", + "label": "negative", + "script": "latin" + }, + { + "name": "nancy thompson", + "label": "negative", + "script": "latin" + }, + { + "name": "john rowe", + "label": "negative", + "script": "latin" + }, + { + "name": "michael pugh", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Remove a random consonant.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_consonant" + ], + "rule_descriptions": { + "remove_random_consonant": "Remove a random consonant" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "paula yang", + "label": "negative", + "script": "latin" + }, + { + "name": "maureen smith", + "label": "negative", + "script": "latin" + }, + { + "name": "kristen gay", + "label": "negative", + "script": "latin" + }, + { + "name": "brett smith", + "label": "negative", + "script": "latin" + }, + { + "name": "sylvia mcclain", + "label": "negative", + "script": "latin" + }, + { + "name": "sean gray", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher liu", + "label": "negative", + "script": "latin" + }, + { + "name": "helen martinez", + "label": "negative", + "script": "latin" + }, + { + "name": "marc baker", + "label": "negative", + "script": "latin" + }, + { + "name": "scott potter", + "label": "negative", + "script": "latin" + }, + { + "name": "martin shannon", + "label": "negative", + "script": "latin" + }, + { + "name": "cody hughes", + "label": "negative", + "script": "latin" + }, + { + "name": "jeremiah hernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "ricky brown", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua doyle", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Duplicate a random letter, Reorder name parts, and Swap adjacent consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "duplicate_random_letter_as_double_letter", + "name_parts_permutations", + "swap_adjacent_consonants" + ], + "rule_descriptions": { + "duplicate_random_letter_as_double_letter": "Duplicate a random letter", + "name_parts_permutations": "Reorder name parts", + "swap_adjacent_consonants": "Swap adjacent consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "marissa mays", + "label": "negative", + "script": "latin" + }, + { + "name": "georgia woodward", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin ortiz", + "label": "negative", + "script": "latin" + }, + { + "name": "alex johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "candice evans", + "label": "negative", + "script": "latin" + }, + { + "name": "david aguirre", + "label": "negative", + "script": "latin" + }, + { + "name": "maurice blanchard", + "label": "negative", + "script": "latin" + }, + { + "name": "douglas lewis", + "label": "negative", + "script": "latin" + }, + { + "name": "cody williams", + "label": "negative", + "script": "latin" + }, + { + "name": "john gordon", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda morton", + "label": "negative", + "script": "latin" + }, + { + "name": "angela richards", + "label": "negative", + "script": "latin" + }, + { + "name": "kerry hill", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher patel", + "label": "negative", + "script": "latin" + }, + { + "name": "lucas hood", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Duplicate a random letter, and Reorder name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "duplicate_random_letter_as_double_letter", + "name_parts_permutations" + ], + "rule_descriptions": { + "duplicate_random_letter_as_double_letter": "Duplicate a random letter", + "name_parts_permutations": "Reorder name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "kathleen yang", + "label": "negative", + "script": "latin" + }, + { + "name": "geoffrey warren", + "label": "negative", + "script": "latin" + }, + { + "name": "michele patel", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie nelson", + "label": "negative", + "script": "latin" + }, + { + "name": "david yates", + "label": "negative", + "script": "latin" + }, + { + "name": "kenneth reeves", + "label": "negative", + "script": "latin" + }, + { + "name": "william jenkins", + "label": "negative", + "script": "latin" + }, + { + "name": "kimberly curtis", + "label": "negative", + "script": "latin" + }, + { + "name": "jimmy holland", + "label": "negative", + "script": "latin" + }, + { + "name": "ross schultz", + "label": "negative", + "script": "latin" + }, + { + "name": "stephen james", + "label": "negative", + "script": "latin" + }, + { + "name": "tina lewis", + "label": "negative", + "script": "latin" + }, + { + "name": "tyler barajas", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony hayden", + "label": "negative", + "script": "latin" + }, + { + "name": "donna wilkins", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap adjacent syllables, and Remove all spaces.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_syllables", + "remove_all_spaces" + ], + "rule_descriptions": { + "swap_adjacent_syllables": "Swap adjacent syllables", + "remove_all_spaces": "Remove all spaces" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "melissa pena", + "label": "negative", + "script": "latin" + }, + { + "name": "ellie black", + "label": "negative", + "script": "latin" + }, + { + "name": "patrick morton", + "label": "negative", + "script": "latin" + }, + { + "name": "maurice conner", + "label": "negative", + "script": "latin" + }, + { + "name": "donald myers", + "label": "negative", + "script": "latin" + }, + { + "name": "rebecca shelton", + "label": "negative", + "script": "latin" + }, + { + "name": "william brandt", + "label": "negative", + "script": "latin" + }, + { + "name": "chelsea king", + "label": "negative", + "script": "latin" + }, + { + "name": "jean williams", + "label": "negative", + "script": "latin" + }, + { + "name": "nancy clark", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa jackson", + "label": "negative", + "script": "latin" + }, + { + "name": "kenneth baker", + "label": "negative", + "script": "latin" + }, + { + "name": "whitney obrien", + "label": "negative", + "script": "latin" + }, + { + "name": "andrew freeman", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher miller", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove a random consonant, Remove all spaces, and Replace random vowels with different vowels.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_consonant", + "remove_all_spaces", + "replace_random_vowel_with_random_vowel" + ], + "rule_descriptions": { + "remove_random_consonant": "Remove a random consonant", + "remove_all_spaces": "Remove all spaces", + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "marie smith", + "label": "negative", + "script": "latin" + }, + { + "name": "tina mills", + "label": "negative", + "script": "latin" + }, + { + "name": "margaret fitzgerald", + "label": "negative", + "script": "latin" + }, + { + "name": "jared johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher roy", + "label": "negative", + "script": "latin" + }, + { + "name": "nigel turner", + "label": "negative", + "script": "latin" + }, + { + "name": "edward winters", + "label": "negative", + "script": "latin" + }, + { + "name": "jacob wells", + "label": "negative", + "script": "latin" + }, + { + "name": "pamela barnett", + "label": "negative", + "script": "latin" + }, + { + "name": "amber vargas", + "label": "negative", + "script": "latin" + }, + { + "name": "jose martin", + "label": "negative", + "script": "latin" + }, + { + "name": "debbie schroeder", + "label": "negative", + "script": "latin" + }, + { + "name": "emily butler", + "label": "negative", + "script": "latin" + }, + { + "name": "ellie horn", + "label": "negative", + "script": "latin" + }, + { + "name": "carmen duncan", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Swap adjacent syllables.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_syllables" + ], + "rule_descriptions": { + "swap_adjacent_syllables": "Swap adjacent syllables" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "alicia riggs", + "label": "negative", + "script": "latin" + }, + { + "name": "kendra brooks", + "label": "negative", + "script": "latin" + }, + { + "name": "jimmy villarreal", + "label": "negative", + "script": "latin" + }, + { + "name": "abigail wolfe", + "label": "negative", + "script": "latin" + }, + { + "name": "donald frey", + "label": "negative", + "script": "latin" + }, + { + "name": "steven walters", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie ruiz", + "label": "negative", + "script": "latin" + }, + { + "name": "zachary mason", + "label": "negative", + "script": "latin" + }, + { + "name": "travis taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "michael dawson", + "label": "negative", + "script": "latin" + }, + { + "name": "dawn king", + "label": "negative", + "script": "latin" + }, + { + "name": "shannon james", + "label": "negative", + "script": "latin" + }, + { + "name": "molly banks", + "label": "negative", + "script": "latin" + }, + { + "name": "todd freeman", + "label": "negative", + "script": "latin" + }, + { + "name": "heather jones", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace random vowels with different vowels, Swap adjacent consonants, and Insert a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_vowel_with_random_vowel", + "swap_adjacent_consonants", + "insert_random_letter" + ], + "rule_descriptions": { + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels", + "swap_adjacent_consonants": "Swap adjacent consonants", + "insert_random_letter": "Insert a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "tammy blake", + "label": "negative", + "script": "latin" + }, + { + "name": "terrance lopez", + "label": "negative", + "script": "latin" + }, + { + "name": "ricky cowan", + "label": "negative", + "script": "latin" + }, + { + "name": "brooke jenkins", + "label": "negative", + "script": "latin" + }, + { + "name": "monica cherry", + "label": "negative", + "script": "latin" + }, + { + "name": "marcia newton", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua carpenter", + "label": "negative", + "script": "latin" + }, + { + "name": "adriana best", + "label": "negative", + "script": "latin" + }, + { + "name": "trevor everett", + "label": "negative", + "script": "latin" + }, + { + "name": "robert ferguson", + "label": "negative", + "script": "latin" + }, + { + "name": "hilary mills", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph marsh", + "label": "negative", + "script": "latin" + }, + { + "name": "kathleen haley", + "label": "negative", + "script": "latin" + }, + { + "name": "mallory villa", + "label": "negative", + "script": "latin" + }, + { + "name": "antony gibson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Insert a random letter, and Swap random adjacent letters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "insert_random_letter", + "swap_random_letter" + ], + "rule_descriptions": { + "insert_random_letter": "Insert a random letter", + "swap_random_letter": "Swap random adjacent letters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "earl walker", + "label": "negative", + "script": "latin" + }, + { + "name": "jason gallegos", + "label": "negative", + "script": "latin" + }, + { + "name": "francesca alvarado", + "label": "negative", + "script": "latin" + }, + { + "name": "gabrielle vaughan", + "label": "negative", + "script": "latin" + }, + { + "name": "trevor bailey", + "label": "negative", + "script": "latin" + }, + { + "name": "tommy wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "jenna jones", + "label": "negative", + "script": "latin" + }, + { + "name": "bryan alexander", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph berg", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffrey harris", + "label": "negative", + "script": "latin" + }, + { + "name": "elizabeth james", + "label": "negative", + "script": "latin" + }, + { + "name": "austin taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle roberts", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa garcia", + "label": "negative", + "script": "latin" + }, + { + "name": "kathy alvarez", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Abbreviate name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_abbreviations" + ], + "rule_descriptions": { + "shorten_name_to_abbreviations": "Abbreviate name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "stephanie wolf", + "label": "negative", + "script": "latin" + }, + { + "name": "brooke cox", + "label": "negative", + "script": "latin" + }, + { + "name": "frank bautista", + "label": "negative", + "script": "latin" + }, + { + "name": "suzanne li", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel ball", + "label": "negative", + "script": "latin" + }, + { + "name": "david clark", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer morgan", + "label": "negative", + "script": "latin" + }, + { + "name": "sean fox", + "label": "negative", + "script": "latin" + }, + { + "name": "james landry", + "label": "negative", + "script": "latin" + }, + { + "name": "zachary gaines", + "label": "negative", + "script": "latin" + }, + { + "name": "anita wood", + "label": "negative", + "script": "latin" + }, + { + "name": "kenneth tran", + "label": "negative", + "script": "latin" + }, + { + "name": "shawn thomas", + "label": "negative", + "script": "latin" + }, + { + "name": "robert anderson", + "label": "negative", + "script": "latin" + }, + { + "name": "larry smith", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Insert a random letter, Swap random adjacent letters, and Swap adjacent syllables.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "insert_random_letter", + "swap_random_letter", + "swap_adjacent_syllables" + ], + "rule_descriptions": { + "insert_random_letter": "Insert a random letter", + "swap_random_letter": "Swap random adjacent letters", + "swap_adjacent_syllables": "Swap adjacent syllables" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "natasha ortiz", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah ramirez", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda rogers", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie henry", + "label": "negative", + "script": "latin" + }, + { + "name": "bradley lang", + "label": "negative", + "script": "latin" + }, + { + "name": "bradley rivas", + "label": "negative", + "script": "latin" + }, + { + "name": "megan mann", + "label": "negative", + "script": "latin" + }, + { + "name": "taylor perez", + "label": "negative", + "script": "latin" + }, + { + "name": "justin davis", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "tina daniels", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda mclean", + "label": "negative", + "script": "latin" + }, + { + "name": "robert horton", + "label": "negative", + "script": "latin" + }, + { + "name": "stacey mejia", + "label": "negative", + "script": "latin" + }, + { + "name": "wendy henderson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Add a title suffix (Jr., PhD, etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_trailing_title" + ], + "rule_descriptions": { + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "tyler ray", + "label": "negative", + "script": "latin" + }, + { + "name": "nancy chan", + "label": "negative", + "script": "latin" + }, + { + "name": "andrea anderson", + "label": "negative", + "script": "latin" + }, + { + "name": "william hill", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin wallace", + "label": "negative", + "script": "latin" + }, + { + "name": "jenny stewart", + "label": "negative", + "script": "latin" + }, + { + "name": "frank moore", + "label": "negative", + "script": "latin" + }, + { + "name": "abdul brown", + "label": "negative", + "script": "latin" + }, + { + "name": "russell martinez", + "label": "negative", + "script": "latin" + }, + { + "name": "javier brookes", + "label": "negative", + "script": "latin" + }, + { + "name": "dominique koch", + "label": "negative", + "script": "latin" + }, + { + "name": "josephine scott", + "label": "negative", + "script": "latin" + }, + { + "name": "jacqueline murphy", + "label": "negative", + "script": "latin" + }, + { + "name": "shelley ball", + "label": "negative", + "script": "latin" + }, + { + "name": "kyle freeman", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Replace spaces with special characters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_spaces_with_random_special_characters" + ], + "rule_descriptions": { + "replace_spaces_with_random_special_characters": "Replace spaces with special characters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "barbara wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "brian jones", + "label": "negative", + "script": "latin" + }, + { + "name": "christina cook", + "label": "negative", + "script": "latin" + }, + { + "name": "richard wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "sara hart", + "label": "negative", + "script": "latin" + }, + { + "name": "katie pope", + "label": "negative", + "script": "latin" + }, + { + "name": "james kent", + "label": "negative", + "script": "latin" + }, + { + "name": "tina yang", + "label": "negative", + "script": "latin" + }, + { + "name": "mark moody", + "label": "negative", + "script": "latin" + }, + { + "name": "alice williams", + "label": "negative", + "script": "latin" + }, + { + "name": "john smith", + "label": "negative", + "script": "latin" + }, + { + "name": "emily williams", + "label": "negative", + "script": "latin" + }, + { + "name": "jonathan mitchell", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley fox", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa bowman", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Convert name to initials, Replace spaces with special characters, and Replace double letters with a single letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_initials", + "replace_spaces_with_random_special_characters", + "replace_double_letters_with_single_letter" + ], + "rule_descriptions": { + "shorten_name_to_initials": "Convert name to initials", + "replace_spaces_with_random_special_characters": "Replace spaces with special characters", + "replace_double_letters_with_single_letter": "Replace double letters with a single letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "michael rowe", + "label": "negative", + "script": "latin" + }, + { + "name": "michael williams", + "label": "negative", + "script": "latin" + }, + { + "name": "cody miller", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle thomas", + "label": "negative", + "script": "latin" + }, + { + "name": "walter dodd", + "label": "negative", + "script": "latin" + }, + { + "name": "rodney dawson", + "label": "negative", + "script": "latin" + }, + { + "name": "richard meadows", + "label": "negative", + "script": "latin" + }, + { + "name": "richard adams", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel watkins", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer carr", + "label": "negative", + "script": "latin" + }, + { + "name": "david harrell", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley thompson", + "label": "negative", + "script": "latin" + }, + { + "name": "amber sanders", + "label": "negative", + "script": "latin" + }, + { + "name": "tom bowman", + "label": "negative", + "script": "latin" + }, + { + "name": "robert george", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Remove a random consonant.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_consonant" + ], + "rule_descriptions": { + "remove_random_consonant": "Remove a random consonant" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "travis bradley", + "label": "negative", + "script": "latin" + }, + { + "name": "william harrison", + "label": "negative", + "script": "latin" + }, + { + "name": "stuart brown", + "label": "negative", + "script": "latin" + }, + { + "name": "chelsea sexton", + "label": "negative", + "script": "latin" + }, + { + "name": "elizabeth reed", + "label": "negative", + "script": "latin" + }, + { + "name": "shawn goddard", + "label": "negative", + "script": "latin" + }, + { + "name": "graeme palmer", + "label": "negative", + "script": "latin" + }, + { + "name": "tina marsh", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa hill", + "label": "negative", + "script": "latin" + }, + { + "name": "eric pena", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "mitchell mills", + "label": "negative", + "script": "latin" + }, + { + "name": "carolyn medina", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa jackson", + "label": "negative", + "script": "latin" + }, + { + "name": "carolyn mata", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title prefix (Mr., Dr., etc.), and Swap random adjacent letters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_leading_title", + "swap_random_letter" + ], + "rule_descriptions": { + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)", + "swap_random_letter": "Swap random adjacent letters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "phillip stafford", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica thompson", + "label": "negative", + "script": "latin" + }, + { + "name": "kendra clarke", + "label": "negative", + "script": "latin" + }, + { + "name": "jason edwards", + "label": "negative", + "script": "latin" + }, + { + "name": "kyle walker", + "label": "negative", + "script": "latin" + }, + { + "name": "damien evans", + "label": "negative", + "script": "latin" + }, + { + "name": "kristina franco", + "label": "negative", + "script": "latin" + }, + { + "name": "david greene", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph shaw", + "label": "negative", + "script": "latin" + }, + { + "name": "tara campbell", + "label": "negative", + "script": "latin" + }, + { + "name": "brenda jones", + "label": "negative", + "script": "latin" + }, + { + "name": "brandy henderson", + "label": "negative", + "script": "latin" + }, + { + "name": "joanna friedman", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie hughes", + "label": "negative", + "script": "latin" + }, + { + "name": "kate lynch", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Swap adjacent syllables.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_syllables" + ], + "rule_descriptions": { + "swap_adjacent_syllables": "Swap adjacent syllables" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "tracy vang", + "label": "negative", + "script": "latin" + }, + { + "name": "gillian greene", + "label": "negative", + "script": "latin" + }, + { + "name": "luis heath", + "label": "negative", + "script": "latin" + }, + { + "name": "michele miller", + "label": "negative", + "script": "latin" + }, + { + "name": "david smith", + "label": "negative", + "script": "latin" + }, + { + "name": "samuel rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "nicholas york", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "ronald baker", + "label": "negative", + "script": "latin" + }, + { + "name": "danielle case", + "label": "negative", + "script": "latin" + }, + { + "name": "kara chapman", + "label": "negative", + "script": "latin" + }, + { + "name": "william hill", + "label": "negative", + "script": "latin" + }, + { + "name": "lucas erickson", + "label": "negative", + "script": "latin" + }, + { + "name": "todd fletcher", + "label": "negative", + "script": "latin" + }, + { + "name": "katrina jones", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Reorder name parts, and Swap adjacent syllables.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "name_parts_permutations", + "swap_adjacent_syllables" + ], + "rule_descriptions": { + "name_parts_permutations": "Reorder name parts", + "swap_adjacent_syllables": "Swap adjacent syllables" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "mark jones", + "label": "negative", + "script": "latin" + }, + { + "name": "linda law", + "label": "negative", + "script": "latin" + }, + { + "name": "patrick wright", + "label": "negative", + "script": "latin" + }, + { + "name": "karen lewis", + "label": "negative", + "script": "latin" + }, + { + "name": "elaine andrews", + "label": "negative", + "script": "latin" + }, + { + "name": "scott davis", + "label": "negative", + "script": "latin" + }, + { + "name": "graeme lambert", + "label": "negative", + "script": "latin" + }, + { + "name": "jacob mullins", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel silva", + "label": "negative", + "script": "latin" + }, + { + "name": "shannon reed", + "label": "negative", + "script": "latin" + }, + { + "name": "autumn williams", + "label": "negative", + "script": "latin" + }, + { + "name": "emily knapp", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew rhodes", + "label": "negative", + "script": "latin" + }, + { + "name": "jon johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "martin lamb", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Convert name to initials, Remove a random vowel, and Add a title suffix (Jr., PhD, etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_initials", + "remove_random_vowel", + "add_random_trailing_title" + ], + "rule_descriptions": { + "shorten_name_to_initials": "Convert name to initials", + "remove_random_vowel": "Remove a random vowel", + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "nicole whitehead", + "label": "negative", + "script": "latin" + }, + { + "name": "melinda henderson", + "label": "negative", + "script": "latin" + }, + { + "name": "christina jenkins", + "label": "negative", + "script": "latin" + }, + { + "name": "tiffany smith", + "label": "negative", + "script": "latin" + }, + { + "name": "joanne andrade", + "label": "negative", + "script": "latin" + }, + { + "name": "richard hutchinson", + "label": "negative", + "script": "latin" + }, + { + "name": "deborah shepherd", + "label": "negative", + "script": "latin" + }, + { + "name": "stacy wilkinson", + "label": "negative", + "script": "latin" + }, + { + "name": "tyler doyle", + "label": "negative", + "script": "latin" + }, + { + "name": "karl george", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer fisher", + "label": "negative", + "script": "latin" + }, + { + "name": "laura sanchez", + "label": "negative", + "script": "latin" + }, + { + "name": "wanda obrien", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica vasquez", + "label": "negative", + "script": "latin" + }, + { + "name": "brett carpenter", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Add a title prefix (Mr., Dr., etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_leading_title" + ], + "rule_descriptions": { + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "sheila leonard", + "label": "negative", + "script": "latin" + }, + { + "name": "mary johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "lindsey garcia", + "label": "negative", + "script": "latin" + }, + { + "name": "douglas waters", + "label": "negative", + "script": "latin" + }, + { + "name": "katy rogers", + "label": "negative", + "script": "latin" + }, + { + "name": "david brooks", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua miller", + "label": "negative", + "script": "latin" + }, + { + "name": "jacob wiggins", + "label": "negative", + "script": "latin" + }, + { + "name": "jason hernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "gillian johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "damian west", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica lynch", + "label": "negative", + "script": "latin" + }, + { + "name": "tyler estrada", + "label": "negative", + "script": "latin" + }, + { + "name": "donald roberts", + "label": "negative", + "script": "latin" + }, + { + "name": "blake le", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Remove all spaces.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_all_spaces" + ], + "rule_descriptions": { + "remove_all_spaces": "Remove all spaces" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "timothy foster", + "label": "negative", + "script": "latin" + }, + { + "name": "brian rhodes", + "label": "negative", + "script": "latin" + }, + { + "name": "dorothy robertson", + "label": "negative", + "script": "latin" + }, + { + "name": "david adams", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah lee", + "label": "negative", + "script": "latin" + }, + { + "name": "dawn thomas", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony castillo", + "label": "negative", + "script": "latin" + }, + { + "name": "amy bell", + "label": "negative", + "script": "latin" + }, + { + "name": "tiffany hanson", + "label": "negative", + "script": "latin" + }, + { + "name": "olivia jones", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony adams", + "label": "negative", + "script": "latin" + }, + { + "name": "dawn white", + "label": "negative", + "script": "latin" + }, + { + "name": "angela zuniga", + "label": "negative", + "script": "latin" + }, + { + "name": "jackie martin", + "label": "negative", + "script": "latin" + }, + { + "name": "mathew davis", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap random adjacent letters, and Abbreviate name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_random_letter", + "shorten_name_to_abbreviations" + ], + "rule_descriptions": { + "swap_random_letter": "Swap random adjacent letters", + "shorten_name_to_abbreviations": "Abbreviate name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "wanda hodges", + "label": "negative", + "script": "latin" + }, + { + "name": "shawn villegas", + "label": "negative", + "script": "latin" + }, + { + "name": "deborah clarke", + "label": "negative", + "script": "latin" + }, + { + "name": "mariah smith", + "label": "negative", + "script": "latin" + }, + { + "name": "karl knight", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah harris", + "label": "negative", + "script": "latin" + }, + { + "name": "dwayne taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "sonya quinn", + "label": "negative", + "script": "latin" + }, + { + "name": "barbara gonzales", + "label": "negative", + "script": "latin" + }, + { + "name": "cody smith", + "label": "negative", + "script": "latin" + }, + { + "name": "james davila", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffrey owens", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa nicholls", + "label": "negative", + "script": "latin" + }, + { + "name": "megan porter", + "label": "negative", + "script": "latin" + }, + { + "name": "stacey nash", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Use first name initial with last name.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "initial_only_first_name" + ], + "rule_descriptions": { + "initial_only_first_name": "Use first name initial with last name" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "tony chambers", + "label": "negative", + "script": "latin" + }, + { + "name": "diane wright", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffery davis", + "label": "negative", + "script": "latin" + }, + { + "name": "diana olson", + "label": "negative", + "script": "latin" + }, + { + "name": "randy patel", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica garcia", + "label": "negative", + "script": "latin" + }, + { + "name": "terry duncan", + "label": "negative", + "script": "latin" + }, + { + "name": "deanna wood", + "label": "negative", + "script": "latin" + }, + { + "name": "danielle huerta", + "label": "negative", + "script": "latin" + }, + { + "name": "alicia lee", + "label": "negative", + "script": "latin" + }, + { + "name": "bruce lopez", + "label": "negative", + "script": "latin" + }, + { + "name": "michael bates", + "label": "negative", + "script": "latin" + }, + { + "name": "taylor combs", + "label": "negative", + "script": "latin" + }, + { + "name": "bianca davis", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffrey perry", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Reorder name parts, and Replace random consonants with different consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "name_parts_permutations", + "replace_random_consonant_with_random_consonant" + ], + "rule_descriptions": { + "name_parts_permutations": "Reorder name parts", + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "john zimmerman", + "label": "negative", + "script": "latin" + }, + { + "name": "michael reed", + "label": "negative", + "script": "latin" + }, + { + "name": "deborah curtis", + "label": "negative", + "script": "latin" + }, + { + "name": "kristi ramirez", + "label": "negative", + "script": "latin" + }, + { + "name": "ruth murphy", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy smith", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy tomlinson", + "label": "negative", + "script": "latin" + }, + { + "name": "henry ibarra", + "label": "negative", + "script": "latin" + }, + { + "name": "josephine jones", + "label": "negative", + "script": "latin" + }, + { + "name": "harry wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "gregory mayo", + "label": "negative", + "script": "latin" + }, + { + "name": "kelsey johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "billy hill", + "label": "negative", + "script": "latin" + }, + { + "name": "patrick nielsen", + "label": "negative", + "script": "latin" + }, + { + "name": "megan floyd", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap adjacent syllables, and Insert a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_syllables", + "insert_random_letter" + ], + "rule_descriptions": { + "swap_adjacent_syllables": "Swap adjacent syllables", + "insert_random_letter": "Insert a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "adam porter", + "label": "negative", + "script": "latin" + }, + { + "name": "jesse andrade", + "label": "negative", + "script": "latin" + }, + { + "name": "kari mullen", + "label": "negative", + "script": "latin" + }, + { + "name": "nathaniel carey", + "label": "negative", + "script": "latin" + }, + { + "name": "shannon stokes", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah fuller", + "label": "negative", + "script": "latin" + }, + { + "name": "adam murphy", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher smith", + "label": "negative", + "script": "latin" + }, + { + "name": "phillip jackson", + "label": "negative", + "script": "latin" + }, + { + "name": "jon miller", + "label": "negative", + "script": "latin" + }, + { + "name": "erika edwards", + "label": "negative", + "script": "latin" + }, + { + "name": "nathan ramirez", + "label": "negative", + "script": "latin" + }, + { + "name": "yvette chase", + "label": "negative", + "script": "latin" + }, + { + "name": "becky chandler", + "label": "negative", + "script": "latin" + }, + { + "name": "linda johnson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Use first name initial with last name, and Replace random consonants with different consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "initial_only_first_name", + "replace_random_consonant_with_random_consonant" + ], + "rule_descriptions": { + "initial_only_first_name": "Use first name initial with last name", + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "justin walsh", + "label": "negative", + "script": "latin" + }, + { + "name": "crystal garner", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle dobson", + "label": "negative", + "script": "latin" + }, + { + "name": "john gallagher", + "label": "negative", + "script": "latin" + }, + { + "name": "haley small", + "label": "negative", + "script": "latin" + }, + { + "name": "jamie long", + "label": "negative", + "script": "latin" + }, + { + "name": "frank wallace", + "label": "negative", + "script": "latin" + }, + { + "name": "john fitzpatrick", + "label": "negative", + "script": "latin" + }, + { + "name": "ronnie espinoza", + "label": "negative", + "script": "latin" + }, + { + "name": "liam robinson", + "label": "negative", + "script": "latin" + }, + { + "name": "harriet stevens", + "label": "negative", + "script": "latin" + }, + { + "name": "donna nguyen", + "label": "negative", + "script": "latin" + }, + { + "name": "joe hall", + "label": "negative", + "script": "latin" + }, + { + "name": "robert wiggins", + "label": "negative", + "script": "latin" + }, + { + "name": "elizabeth whitaker", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace spaces with special characters, and Insert a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_spaces_with_random_special_characters", + "insert_random_letter" + ], + "rule_descriptions": { + "replace_spaces_with_random_special_characters": "Replace spaces with special characters", + "insert_random_letter": "Insert a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "todd watson", + "label": "negative", + "script": "latin" + }, + { + "name": "kathryn smith", + "label": "negative", + "script": "latin" + }, + { + "name": "hazel garcia", + "label": "negative", + "script": "latin" + }, + { + "name": "mariah campbell", + "label": "negative", + "script": "latin" + }, + { + "name": "tracy hamilton", + "label": "negative", + "script": "latin" + }, + { + "name": "cody kennedy", + "label": "negative", + "script": "latin" + }, + { + "name": "christina roberts", + "label": "negative", + "script": "latin" + }, + { + "name": "ruth brown", + "label": "negative", + "script": "latin" + }, + { + "name": "christian blackburn", + "label": "negative", + "script": "latin" + }, + { + "name": "michael rivas", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa fernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "steven donnelly", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa campbell", + "label": "negative", + "script": "latin" + }, + { + "name": "laura graham", + "label": "negative", + "script": "latin" + }, + { + "name": "travis wells", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Abbreviate name parts, and Delete a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_abbreviations", + "delete_random_letter" + ], + "rule_descriptions": { + "shorten_name_to_abbreviations": "Abbreviate name parts", + "delete_random_letter": "Delete a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "yvonne stewart", + "label": "negative", + "script": "latin" + }, + { + "name": "brandon peterson", + "label": "negative", + "script": "latin" + }, + { + "name": "david foster", + "label": "negative", + "script": "latin" + }, + { + "name": "cathy phillips", + "label": "negative", + "script": "latin" + }, + { + "name": "dale montgomery", + "label": "negative", + "script": "latin" + }, + { + "name": "vanessa brown", + "label": "negative", + "script": "latin" + }, + { + "name": "terence ross", + "label": "negative", + "script": "latin" + }, + { + "name": "andres hahn", + "label": "negative", + "script": "latin" + }, + { + "name": "tiffany lopez", + "label": "negative", + "script": "latin" + }, + { + "name": "marilyn mccarthy", + "label": "negative", + "script": "latin" + }, + { + "name": "andrew reed", + "label": "negative", + "script": "latin" + }, + { + "name": "andrew jones", + "label": "negative", + "script": "latin" + }, + { + "name": "charlene carpenter", + "label": "negative", + "script": "latin" + }, + { + "name": "breanna campbell", + "label": "negative", + "script": "latin" + }, + { + "name": "seth davies", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Delete a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "delete_random_letter" + ], + "rule_descriptions": { + "delete_random_letter": "Delete a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "anthony thornton", + "label": "negative", + "script": "latin" + }, + { + "name": "richard byrd", + "label": "negative", + "script": "latin" + }, + { + "name": "clive roberts", + "label": "negative", + "script": "latin" + }, + { + "name": "carla wells", + "label": "negative", + "script": "latin" + }, + { + "name": "austin jimenez", + "label": "negative", + "script": "latin" + }, + { + "name": "owen holmes", + "label": "negative", + "script": "latin" + }, + { + "name": "pamela carroll", + "label": "negative", + "script": "latin" + }, + { + "name": "tasha shah", + "label": "negative", + "script": "latin" + }, + { + "name": "donna walker", + "label": "negative", + "script": "latin" + }, + { + "name": "shannon rojas", + "label": "negative", + "script": "latin" + }, + { + "name": "kathleen robinson", + "label": "negative", + "script": "latin" + }, + { + "name": "martin mccall", + "label": "negative", + "script": "latin" + }, + { + "name": "charles frank", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer kemp", + "label": "negative", + "script": "latin" + }, + { + "name": "amy rose", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace double letters with a single letter, Delete a random letter, and Reorder name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_double_letters_with_single_letter", + "delete_random_letter", + "name_parts_permutations" + ], + "rule_descriptions": { + "replace_double_letters_with_single_letter": "Replace double letters with a single letter", + "delete_random_letter": "Delete a random letter", + "name_parts_permutations": "Reorder name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "jason jimenez", + "label": "negative", + "script": "latin" + }, + { + "name": "kelly taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "desiree smith", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley salazar", + "label": "negative", + "script": "latin" + }, + { + "name": "alexander morse", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah crane", + "label": "negative", + "script": "latin" + }, + { + "name": "brittany james", + "label": "negative", + "script": "latin" + }, + { + "name": "aaron sullivan", + "label": "negative", + "script": "latin" + }, + { + "name": "brandy potter", + "label": "negative", + "script": "latin" + }, + { + "name": "robert miller", + "label": "negative", + "script": "latin" + }, + { + "name": "michele cross", + "label": "negative", + "script": "latin" + }, + { + "name": "beverly harvey", + "label": "negative", + "script": "latin" + }, + { + "name": "felicia khan", + "label": "negative", + "script": "latin" + }, + { + "name": "yvonne mills", + "label": "negative", + "script": "latin" + }, + { + "name": "arthur bird", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove a random vowel, Use first name initial with last name, and Remove all spaces.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_vowel", + "initial_only_first_name", + "remove_all_spaces" + ], + "rule_descriptions": { + "remove_random_vowel": "Remove a random vowel", + "initial_only_first_name": "Use first name initial with last name", + "remove_all_spaces": "Remove all spaces" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "emily simpson", + "label": "negative", + "script": "latin" + }, + { + "name": "anne hall", + "label": "negative", + "script": "latin" + }, + { + "name": "shaun byrd", + "label": "negative", + "script": "latin" + }, + { + "name": "sara case", + "label": "negative", + "script": "latin" + }, + { + "name": "austin holmes", + "label": "negative", + "script": "latin" + }, + { + "name": "bradley davis", + "label": "negative", + "script": "latin" + }, + { + "name": "paula price", + "label": "negative", + "script": "latin" + }, + { + "name": "kerry miller", + "label": "negative", + "script": "latin" + }, + { + "name": "pamela smith", + "label": "negative", + "script": "latin" + }, + { + "name": "amy miller", + "label": "negative", + "script": "latin" + }, + { + "name": "maria martinez", + "label": "negative", + "script": "latin" + }, + { + "name": "alison howe", + "label": "negative", + "script": "latin" + }, + { + "name": "nathan bell", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica hunter", + "label": "negative", + "script": "latin" + }, + { + "name": "carlos johnson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Insert a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "insert_random_letter" + ], + "rule_descriptions": { + "insert_random_letter": "Insert a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "christopher costa", + "label": "negative", + "script": "latin" + }, + { + "name": "adam rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "jon carroll", + "label": "negative", + "script": "latin" + }, + { + "name": "laura chavez", + "label": "negative", + "script": "latin" + }, + { + "name": "paula browne", + "label": "negative", + "script": "latin" + }, + { + "name": "billy payne", + "label": "negative", + "script": "latin" + }, + { + "name": "jesse jones", + "label": "negative", + "script": "latin" + }, + { + "name": "leonard obrien", + "label": "negative", + "script": "latin" + }, + { + "name": "dana graham", + "label": "negative", + "script": "latin" + }, + { + "name": "aimee lawson", + "label": "negative", + "script": "latin" + }, + { + "name": "graeme michael", + "label": "negative", + "script": "latin" + }, + { + "name": "carrie green", + "label": "negative", + "script": "latin" + }, + { + "name": "dawn barker", + "label": "negative", + "script": "latin" + }, + { + "name": "susan weber", + "label": "negative", + "script": "latin" + }, + { + "name": "ronald quinn", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Convert name to initials, and Duplicate a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_initials", + "duplicate_random_letter_as_double_letter" + ], + "rule_descriptions": { + "shorten_name_to_initials": "Convert name to initials", + "duplicate_random_letter_as_double_letter": "Duplicate a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "trevor lopez", + "label": "negative", + "script": "latin" + }, + { + "name": "ryan carlson", + "label": "negative", + "script": "latin" + }, + { + "name": "shannon thompson", + "label": "negative", + "script": "latin" + }, + { + "name": "steven barnes", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua parker", + "label": "negative", + "script": "latin" + }, + { + "name": "sharon morse", + "label": "negative", + "script": "latin" + }, + { + "name": "diana smith", + "label": "negative", + "script": "latin" + }, + { + "name": "james bishop", + "label": "negative", + "script": "latin" + }, + { + "name": "damien taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy arnold", + "label": "negative", + "script": "latin" + }, + { + "name": "douglas brown", + "label": "negative", + "script": "latin" + }, + { + "name": "nicholas scott", + "label": "negative", + "script": "latin" + }, + { + "name": "kelsey rogers", + "label": "negative", + "script": "latin" + }, + { + "name": "veronica williams", + "label": "negative", + "script": "latin" + }, + { + "name": "ryan edwards", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace spaces with special characters, Abbreviate name parts, and Swap adjacent syllables.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_spaces_with_random_special_characters", + "shorten_name_to_abbreviations", + "swap_adjacent_syllables" + ], + "rule_descriptions": { + "replace_spaces_with_random_special_characters": "Replace spaces with special characters", + "shorten_name_to_abbreviations": "Abbreviate name parts", + "swap_adjacent_syllables": "Swap adjacent syllables" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "daniel adams", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin williams", + "label": "negative", + "script": "latin" + }, + { + "name": "emily mathews", + "label": "negative", + "script": "latin" + }, + { + "name": "beth cole", + "label": "negative", + "script": "latin" + }, + { + "name": "james hall", + "label": "negative", + "script": "latin" + }, + { + "name": "tamara stein", + "label": "negative", + "script": "latin" + }, + { + "name": "william espinoza", + "label": "negative", + "script": "latin" + }, + { + "name": "sonya collins", + "label": "negative", + "script": "latin" + }, + { + "name": "tina burgess", + "label": "negative", + "script": "latin" + }, + { + "name": "summer williams", + "label": "negative", + "script": "latin" + }, + { + "name": "heather harrison", + "label": "negative", + "script": "latin" + }, + { + "name": "cindy brown", + "label": "negative", + "script": "latin" + }, + { + "name": "tonya cohen", + "label": "negative", + "script": "latin" + }, + { + "name": "aaron cohen", + "label": "negative", + "script": "latin" + }, + { + "name": "katherine robinson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove all spaces, Add a title prefix (Mr., Dr., etc.), and Swap adjacent consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_all_spaces", + "add_random_leading_title", + "swap_adjacent_consonants" + ], + "rule_descriptions": { + "remove_all_spaces": "Remove all spaces", + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)", + "swap_adjacent_consonants": "Swap adjacent consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "elizabeth garza", + "label": "negative", + "script": "latin" + }, + { + "name": "denise johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "elizabeth rivas", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph stevens", + "label": "negative", + "script": "latin" + }, + { + "name": "eric dominguez", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel brock", + "label": "negative", + "script": "latin" + }, + { + "name": "kristin smith", + "label": "negative", + "script": "latin" + }, + { + "name": "jeremy greenwood", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa jones", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole scott", + "label": "negative", + "script": "latin" + }, + { + "name": "john lane", + "label": "negative", + "script": "latin" + }, + { + "name": "marilyn chapman", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa white", + "label": "negative", + "script": "latin" + }, + { + "name": "jason berger", + "label": "negative", + "script": "latin" + }, + { + "name": "damian gamble", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap random adjacent letters, Duplicate a random letter, and Abbreviate name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_random_letter", + "duplicate_random_letter_as_double_letter", + "shorten_name_to_abbreviations" + ], + "rule_descriptions": { + "swap_random_letter": "Swap random adjacent letters", + "duplicate_random_letter_as_double_letter": "Duplicate a random letter", + "shorten_name_to_abbreviations": "Abbreviate name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "sonya patrick", + "label": "negative", + "script": "latin" + }, + { + "name": "sherry shepherd", + "label": "negative", + "script": "latin" + }, + { + "name": "crystal stephenson", + "label": "negative", + "script": "latin" + }, + { + "name": "william simpson", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin walton", + "label": "negative", + "script": "latin" + }, + { + "name": "tom harper", + "label": "negative", + "script": "latin" + }, + { + "name": "bonnie wright", + "label": "negative", + "script": "latin" + }, + { + "name": "diana barber", + "label": "negative", + "script": "latin" + }, + { + "name": "angela lewis", + "label": "negative", + "script": "latin" + }, + { + "name": "natalie heath", + "label": "negative", + "script": "latin" + }, + { + "name": "jonathan jackson", + "label": "negative", + "script": "latin" + }, + { + "name": "sherri owens", + "label": "negative", + "script": "latin" + }, + { + "name": "eric rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "kimberly holland", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph wright", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Abbreviate name parts, and Replace spaces with special characters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_abbreviations", + "replace_spaces_with_random_special_characters" + ], + "rule_descriptions": { + "shorten_name_to_abbreviations": "Abbreviate name parts", + "replace_spaces_with_random_special_characters": "Replace spaces with special characters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "ryan donovan", + "label": "negative", + "script": "latin" + }, + { + "name": "julia shaw", + "label": "negative", + "script": "latin" + }, + { + "name": "william russell", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy jones", + "label": "negative", + "script": "latin" + }, + { + "name": "david day", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffrey peters", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas lee", + "label": "negative", + "script": "latin" + }, + { + "name": "sheri butler", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa hall", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew roberts", + "label": "negative", + "script": "latin" + }, + { + "name": "sabrina allen", + "label": "negative", + "script": "latin" + }, + { + "name": "jacob marshall", + "label": "negative", + "script": "latin" + }, + { + "name": "susan thomas", + "label": "negative", + "script": "latin" + }, + { + "name": "shawn griffin", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin briggs", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap adjacent consonants, and Insert a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_consonants", + "insert_random_letter" + ], + "rule_descriptions": { + "swap_adjacent_consonants": "Swap adjacent consonants", + "insert_random_letter": "Insert a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "theresa orr", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer wagner", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah whitehead", + "label": "negative", + "script": "latin" + }, + { + "name": "seth cooper", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole nicholls", + "label": "negative", + "script": "latin" + }, + { + "name": "carrie moore", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel massey", + "label": "negative", + "script": "latin" + }, + { + "name": "martyn jenkins", + "label": "negative", + "script": "latin" + }, + { + "name": "kelli hernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "chad williams", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony kirby", + "label": "negative", + "script": "latin" + }, + { + "name": "graeme douglas", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel richmond", + "label": "negative", + "script": "latin" + }, + { + "name": "mercedes smith", + "label": "negative", + "script": "latin" + }, + { + "name": "louis wilson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Insert a random letter, Delete a random letter, and Abbreviate name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "insert_random_letter", + "delete_random_letter", + "shorten_name_to_abbreviations" + ], + "rule_descriptions": { + "insert_random_letter": "Insert a random letter", + "delete_random_letter": "Delete a random letter", + "shorten_name_to_abbreviations": "Abbreviate name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "julia ramirez", + "label": "negative", + "script": "latin" + }, + { + "name": "kimberly taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "bradley mitchell", + "label": "negative", + "script": "latin" + }, + { + "name": "damien west", + "label": "negative", + "script": "latin" + }, + { + "name": "brittany blackwell", + "label": "negative", + "script": "latin" + }, + { + "name": "sylvia wood", + "label": "negative", + "script": "latin" + }, + { + "name": "robin schneider", + "label": "negative", + "script": "latin" + }, + { + "name": "william mendoza", + "label": "negative", + "script": "latin" + }, + { + "name": "billy evans", + "label": "negative", + "script": "latin" + }, + { + "name": "molly burgess", + "label": "negative", + "script": "latin" + }, + { + "name": "jason simpson", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher russo", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica pearson", + "label": "negative", + "script": "latin" + }, + { + "name": "susan mitchell", + "label": "negative", + "script": "latin" + }, + { + "name": "helen smith", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Remove a random vowel.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_vowel" + ], + "rule_descriptions": { + "remove_random_vowel": "Remove a random vowel" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "elizabeth durham", + "label": "negative", + "script": "latin" + }, + { + "name": "william hamilton", + "label": "negative", + "script": "latin" + }, + { + "name": "jason long", + "label": "negative", + "script": "latin" + }, + { + "name": "trevor fisher", + "label": "negative", + "script": "latin" + }, + { + "name": "cheryl lewis", + "label": "negative", + "script": "latin" + }, + { + "name": "oliver martin", + "label": "negative", + "script": "latin" + }, + { + "name": "edward hall", + "label": "negative", + "script": "latin" + }, + { + "name": "lydia reynolds", + "label": "negative", + "script": "latin" + }, + { + "name": "ryan simpson", + "label": "negative", + "script": "latin" + }, + { + "name": "martin george", + "label": "negative", + "script": "latin" + }, + { + "name": "conor cox", + "label": "negative", + "script": "latin" + }, + { + "name": "shannon scott", + "label": "negative", + "script": "latin" + }, + { + "name": "ronald montgomery", + "label": "negative", + "script": "latin" + }, + { + "name": "ann lang", + "label": "negative", + "script": "latin" + }, + { + "name": "corey thomas", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Convert name to initials, Use first name initial with last name, and Replace random vowels with different vowels.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_initials", + "initial_only_first_name", + "replace_random_vowel_with_random_vowel" + ], + "rule_descriptions": { + "shorten_name_to_initials": "Convert name to initials", + "initial_only_first_name": "Use first name initial with last name", + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "tara patel", + "label": "negative", + "script": "latin" + }, + { + "name": "leslie munoz", + "label": "negative", + "script": "latin" + }, + { + "name": "james jacobson", + "label": "negative", + "script": "latin" + }, + { + "name": "rebecca kent", + "label": "negative", + "script": "latin" + }, + { + "name": "ryan jones", + "label": "negative", + "script": "latin" + }, + { + "name": "kristopher williams", + "label": "negative", + "script": "latin" + }, + { + "name": "michael morrison", + "label": "negative", + "script": "latin" + }, + { + "name": "anne griffin", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle bass", + "label": "negative", + "script": "latin" + }, + { + "name": "hannah owen", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph warren", + "label": "negative", + "script": "latin" + }, + { + "name": "angela strong", + "label": "negative", + "script": "latin" + }, + { + "name": "wayne nelson", + "label": "negative", + "script": "latin" + }, + { + "name": "diana smith", + "label": "negative", + "script": "latin" + }, + { + "name": "patrick walker", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap random adjacent letters, Use first name initial with last name, and Replace spaces with special characters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_random_letter", + "initial_only_first_name", + "replace_spaces_with_random_special_characters" + ], + "rule_descriptions": { + "swap_random_letter": "Swap random adjacent letters", + "initial_only_first_name": "Use first name initial with last name", + "replace_spaces_with_random_special_characters": "Replace spaces with special characters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "denise joseph", + "label": "negative", + "script": "latin" + }, + { + "name": "justin williams", + "label": "negative", + "script": "latin" + }, + { + "name": "ryan mahoney", + "label": "negative", + "script": "latin" + }, + { + "name": "bill palmer", + "label": "negative", + "script": "latin" + }, + { + "name": "tasha rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "jeremy bowen", + "label": "negative", + "script": "latin" + }, + { + "name": "pedro adams", + "label": "negative", + "script": "latin" + }, + { + "name": "briana blair", + "label": "negative", + "script": "latin" + }, + { + "name": "amy johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "abbie sullivan", + "label": "negative", + "script": "latin" + }, + { + "name": "april davies", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda perkins", + "label": "negative", + "script": "latin" + }, + { + "name": "deborah wright", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer king", + "label": "negative", + "script": "latin" + }, + { + "name": "joel hodgson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Abbreviate name parts, Add a title prefix (Mr., Dr., etc.), and Swap adjacent consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_abbreviations", + "add_random_leading_title", + "swap_adjacent_consonants" + ], + "rule_descriptions": { + "shorten_name_to_abbreviations": "Abbreviate name parts", + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)", + "swap_adjacent_consonants": "Swap adjacent consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "jessica gomez", + "label": "negative", + "script": "latin" + }, + { + "name": "karen dunn", + "label": "negative", + "script": "latin" + }, + { + "name": "nicholas sanders", + "label": "negative", + "script": "latin" + }, + { + "name": "kirsty hunt", + "label": "negative", + "script": "latin" + }, + { + "name": "joanne austin", + "label": "negative", + "script": "latin" + }, + { + "name": "henry taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "donald graham", + "label": "negative", + "script": "latin" + }, + { + "name": "brandon kim", + "label": "negative", + "script": "latin" + }, + { + "name": "hilary wilkinson", + "label": "negative", + "script": "latin" + }, + { + "name": "patrick hart", + "label": "negative", + "script": "latin" + }, + { + "name": "benjamin baxter", + "label": "negative", + "script": "latin" + }, + { + "name": "mary brown", + "label": "negative", + "script": "latin" + }, + { + "name": "jordan lee", + "label": "negative", + "script": "latin" + }, + { + "name": "kimberly shaw", + "label": "negative", + "script": "latin" + }, + { + "name": "john cox", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace random consonants with different consonants, Abbreviate name parts, and Swap adjacent syllables.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_consonant_with_random_consonant", + "shorten_name_to_abbreviations", + "swap_adjacent_syllables" + ], + "rule_descriptions": { + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants", + "shorten_name_to_abbreviations": "Abbreviate name parts", + "swap_adjacent_syllables": "Swap adjacent syllables" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "leah stephens", + "label": "negative", + "script": "latin" + }, + { + "name": "robert hansen", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel edwards", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy hoffman", + "label": "negative", + "script": "latin" + }, + { + "name": "phillip miles", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua heath", + "label": "negative", + "script": "latin" + }, + { + "name": "donald morgan", + "label": "negative", + "script": "latin" + }, + { + "name": "cheyenne allen", + "label": "negative", + "script": "latin" + }, + { + "name": "lydia barry", + "label": "negative", + "script": "latin" + }, + { + "name": "rachel sykes", + "label": "negative", + "script": "latin" + }, + { + "name": "amelia richmond", + "label": "negative", + "script": "latin" + }, + { + "name": "mary gonzalez", + "label": "negative", + "script": "latin" + }, + { + "name": "bruce leon", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy smart", + "label": "negative", + "script": "latin" + }, + { + "name": "brian walls", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title suffix (Jr., PhD, etc.), and Swap adjacent consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_trailing_title", + "swap_adjacent_consonants" + ], + "rule_descriptions": { + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)", + "swap_adjacent_consonants": "Swap adjacent consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "gail lynn", + "label": "negative", + "script": "latin" + }, + { + "name": "michele carrillo", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher palmer", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph ruiz", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah leblanc", + "label": "negative", + "script": "latin" + }, + { + "name": "travis edwards", + "label": "negative", + "script": "latin" + }, + { + "name": "sian turner", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica watson", + "label": "negative", + "script": "latin" + }, + { + "name": "lynda larsen", + "label": "negative", + "script": "latin" + }, + { + "name": "anna parry", + "label": "negative", + "script": "latin" + }, + { + "name": "zachary williams", + "label": "negative", + "script": "latin" + }, + { + "name": "norma wade", + "label": "negative", + "script": "latin" + }, + { + "name": "guy morris", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie pope", + "label": "negative", + "script": "latin" + }, + { + "name": "steven king", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Insert a random letter, and Swap adjacent syllables.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "insert_random_letter", + "swap_adjacent_syllables" + ], + "rule_descriptions": { + "insert_random_letter": "Insert a random letter", + "swap_adjacent_syllables": "Swap adjacent syllables" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "martin patel", + "label": "negative", + "script": "latin" + }, + { + "name": "kelsey bentley", + "label": "negative", + "script": "latin" + }, + { + "name": "marc harrison", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle parsons", + "label": "negative", + "script": "latin" + }, + { + "name": "aaron bartlett", + "label": "negative", + "script": "latin" + }, + { + "name": "vanessa horton", + "label": "negative", + "script": "latin" + }, + { + "name": "john skinner", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher barton", + "label": "negative", + "script": "latin" + }, + { + "name": "deborah watson", + "label": "negative", + "script": "latin" + }, + { + "name": "catherine mclaughlin", + "label": "negative", + "script": "latin" + }, + { + "name": "misty woods", + "label": "negative", + "script": "latin" + }, + { + "name": "samantha johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "lori pena", + "label": "negative", + "script": "latin" + }, + { + "name": "richard byrd", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle hamilton", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove a random vowel, Add a title prefix (Mr., Dr., etc.), and Remove a random consonant.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_vowel", + "add_random_leading_title", + "remove_random_consonant" + ], + "rule_descriptions": { + "remove_random_vowel": "Remove a random vowel", + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)", + "remove_random_consonant": "Remove a random consonant" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "mathew marsh", + "label": "negative", + "script": "latin" + }, + { + "name": "monique anderson", + "label": "negative", + "script": "latin" + }, + { + "name": "brian johnston", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua wong", + "label": "negative", + "script": "latin" + }, + { + "name": "barbara arroyo", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel parker", + "label": "negative", + "script": "latin" + }, + { + "name": "ryan clarke", + "label": "negative", + "script": "latin" + }, + { + "name": "dawn lawrence", + "label": "negative", + "script": "latin" + }, + { + "name": "clive flynn", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "christian weiss", + "label": "negative", + "script": "latin" + }, + { + "name": "latasha hayes", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph perez", + "label": "negative", + "script": "latin" + }, + { + "name": "jenna morris", + "label": "negative", + "script": "latin" + }, + { + "name": "victoria harris", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Use first name initial with last name, and Replace random vowels with different vowels.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "initial_only_first_name", + "replace_random_vowel_with_random_vowel" + ], + "rule_descriptions": { + "initial_only_first_name": "Use first name initial with last name", + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "scott johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew chambers", + "label": "negative", + "script": "latin" + }, + { + "name": "christy forbes", + "label": "negative", + "script": "latin" + }, + { + "name": "nicola carter", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole smith", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa porter", + "label": "negative", + "script": "latin" + }, + { + "name": "david richardson", + "label": "negative", + "script": "latin" + }, + { + "name": "andrew graham", + "label": "negative", + "script": "latin" + }, + { + "name": "benjamin craig", + "label": "negative", + "script": "latin" + }, + { + "name": "danny wright", + "label": "negative", + "script": "latin" + }, + { + "name": "rachael brown", + "label": "negative", + "script": "latin" + }, + { + "name": "kristina martinez", + "label": "negative", + "script": "latin" + }, + { + "name": "chelsea wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "mary young", + "label": "negative", + "script": "latin" + }, + { + "name": "lydia barajas", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace random vowels with different vowels, and Replace random consonants with different consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_vowel_with_random_vowel", + "replace_random_consonant_with_random_consonant" + ], + "rule_descriptions": { + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels", + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "douglas taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "linda miller", + "label": "negative", + "script": "latin" + }, + { + "name": "albert hardy", + "label": "negative", + "script": "latin" + }, + { + "name": "teresa howard", + "label": "negative", + "script": "latin" + }, + { + "name": "todd wolfe", + "label": "negative", + "script": "latin" + }, + { + "name": "edward dennis", + "label": "negative", + "script": "latin" + }, + { + "name": "mohammad brown", + "label": "negative", + "script": "latin" + }, + { + "name": "frank watson", + "label": "negative", + "script": "latin" + }, + { + "name": "james benjamin", + "label": "negative", + "script": "latin" + }, + { + "name": "angela bailey", + "label": "negative", + "script": "latin" + }, + { + "name": "brittany pacheco", + "label": "negative", + "script": "latin" + }, + { + "name": "savannah little", + "label": "negative", + "script": "latin" + }, + { + "name": "emma bailey", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle rivera", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle lindsey", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Swap adjacent syllables.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_syllables" + ], + "rule_descriptions": { + "swap_adjacent_syllables": "Swap adjacent syllables" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "katherine perez", + "label": "negative", + "script": "latin" + }, + { + "name": "rachael taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "tracy cox", + "label": "negative", + "script": "latin" + }, + { + "name": "dennis jones", + "label": "negative", + "script": "latin" + }, + { + "name": "nicola kim", + "label": "negative", + "script": "latin" + }, + { + "name": "katie navarro", + "label": "negative", + "script": "latin" + }, + { + "name": "billy valencia", + "label": "negative", + "script": "latin" + }, + { + "name": "carol woods", + "label": "negative", + "script": "latin" + }, + { + "name": "david bentley", + "label": "negative", + "script": "latin" + }, + { + "name": "beth patel", + "label": "negative", + "script": "latin" + }, + { + "name": "robin yang", + "label": "negative", + "script": "latin" + }, + { + "name": "wesley lopez", + "label": "negative", + "script": "latin" + }, + { + "name": "charlotte smith", + "label": "negative", + "script": "latin" + }, + { + "name": "paul collins", + "label": "negative", + "script": "latin" + }, + { + "name": "connor simmons", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Use first name initial with last name, and Delete a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "initial_only_first_name", + "delete_random_letter" + ], + "rule_descriptions": { + "initial_only_first_name": "Use first name initial with last name", + "delete_random_letter": "Delete a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "tracy richardson", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy knight", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley watson", + "label": "negative", + "script": "latin" + }, + { + "name": "daisy jenkins", + "label": "negative", + "script": "latin" + }, + { + "name": "ronald baker", + "label": "negative", + "script": "latin" + }, + { + "name": "james west", + "label": "negative", + "script": "latin" + }, + { + "name": "carl turner", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda jones", + "label": "negative", + "script": "latin" + }, + { + "name": "tyler martinez", + "label": "negative", + "script": "latin" + }, + { + "name": "duncan davis", + "label": "negative", + "script": "latin" + }, + { + "name": "lauren murphy", + "label": "negative", + "script": "latin" + }, + { + "name": "wendy blair", + "label": "negative", + "script": "latin" + }, + { + "name": "brandy sullivan", + "label": "negative", + "script": "latin" + }, + { + "name": "brandy hicks", + "label": "negative", + "script": "latin" + }, + { + "name": "james dixon", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title suffix (Jr., PhD, etc.), Swap adjacent syllables, and Remove all spaces.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_trailing_title", + "swap_adjacent_syllables", + "remove_all_spaces" + ], + "rule_descriptions": { + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)", + "swap_adjacent_syllables": "Swap adjacent syllables", + "remove_all_spaces": "Remove all spaces" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "tami martin", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole ayala", + "label": "negative", + "script": "latin" + }, + { + "name": "lauren wise", + "label": "negative", + "script": "latin" + }, + { + "name": "stacy lambert", + "label": "negative", + "script": "latin" + }, + { + "name": "emily banks", + "label": "negative", + "script": "latin" + }, + { + "name": "kenneth hooper", + "label": "negative", + "script": "latin" + }, + { + "name": "wayne powers", + "label": "negative", + "script": "latin" + }, + { + "name": "sally dean", + "label": "negative", + "script": "latin" + }, + { + "name": "donald law", + "label": "negative", + "script": "latin" + }, + { + "name": "tiffany powell", + "label": "negative", + "script": "latin" + }, + { + "name": "patrick martinez", + "label": "negative", + "script": "latin" + }, + { + "name": "savannah cooper", + "label": "negative", + "script": "latin" + }, + { + "name": "brian myers", + "label": "negative", + "script": "latin" + }, + { + "name": "trevor herman", + "label": "negative", + "script": "latin" + }, + { + "name": "shannon vasquez", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Use first name initial with last name, Replace random vowels with different vowels, and Swap adjacent consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "initial_only_first_name", + "replace_random_vowel_with_random_vowel", + "swap_adjacent_consonants" + ], + "rule_descriptions": { + "initial_only_first_name": "Use first name initial with last name", + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels", + "swap_adjacent_consonants": "Swap adjacent consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "ricky perez", + "label": "negative", + "script": "latin" + }, + { + "name": "julie mcintyre", + "label": "negative", + "script": "latin" + }, + { + "name": "shirley smith", + "label": "negative", + "script": "latin" + }, + { + "name": "shannon garcia", + "label": "negative", + "script": "latin" + }, + { + "name": "michael rangel", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony cordova", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley matthews", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah harris", + "label": "negative", + "script": "latin" + }, + { + "name": "grant green", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas baxter", + "label": "negative", + "script": "latin" + }, + { + "name": "gregory smith", + "label": "negative", + "script": "latin" + }, + { + "name": "david schmidt", + "label": "negative", + "script": "latin" + }, + { + "name": "william chambers", + "label": "negative", + "script": "latin" + }, + { + "name": "lynda lowe", + "label": "negative", + "script": "latin" + }, + { + "name": "wendy parker", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Reorder name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "name_parts_permutations" + ], + "rule_descriptions": { + "name_parts_permutations": "Reorder name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "katie nash", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin shepard", + "label": "negative", + "script": "latin" + }, + { + "name": "james miller", + "label": "negative", + "script": "latin" + }, + { + "name": "nicholas cooper", + "label": "negative", + "script": "latin" + }, + { + "name": "tony lynch", + "label": "negative", + "script": "latin" + }, + { + "name": "carlos nguyen", + "label": "negative", + "script": "latin" + }, + { + "name": "jillian gilbert", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas davies", + "label": "negative", + "script": "latin" + }, + { + "name": "garrett gomez", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony jones", + "label": "negative", + "script": "latin" + }, + { + "name": "dennis black", + "label": "negative", + "script": "latin" + }, + { + "name": "maurice hampton", + "label": "negative", + "script": "latin" + }, + { + "name": "charles cardenas", + "label": "negative", + "script": "latin" + }, + { + "name": "diana schmidt", + "label": "negative", + "script": "latin" + }, + { + "name": "teresa roberts", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Add a title prefix (Mr., Dr., etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_leading_title" + ], + "rule_descriptions": { + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "kevin walsh", + "label": "negative", + "script": "latin" + }, + { + "name": "adam wade", + "label": "negative", + "script": "latin" + }, + { + "name": "brooke clark", + "label": "negative", + "script": "latin" + }, + { + "name": "sandra kemp", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole shaw", + "label": "negative", + "script": "latin" + }, + { + "name": "sylvia washington", + "label": "negative", + "script": "latin" + }, + { + "name": "ryan wood", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffrey jacobs", + "label": "negative", + "script": "latin" + }, + { + "name": "rachel bishop", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica andrews", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica garrison", + "label": "negative", + "script": "latin" + }, + { + "name": "david smith", + "label": "negative", + "script": "latin" + }, + { + "name": "mark turner", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony ruiz", + "label": "negative", + "script": "latin" + }, + { + "name": "danny fitzgerald", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Abbreviate name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_abbreviations" + ], + "rule_descriptions": { + "shorten_name_to_abbreviations": "Abbreviate name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "karen hart", + "label": "negative", + "script": "latin" + }, + { + "name": "john alvarez", + "label": "negative", + "script": "latin" + }, + { + "name": "shane wilcox", + "label": "negative", + "script": "latin" + }, + { + "name": "phyllis berry", + "label": "negative", + "script": "latin" + }, + { + "name": "stacey hall", + "label": "negative", + "script": "latin" + }, + { + "name": "charles hardy", + "label": "negative", + "script": "latin" + }, + { + "name": "donna fry", + "label": "negative", + "script": "latin" + }, + { + "name": "emily orr", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel rogers", + "label": "negative", + "script": "latin" + }, + { + "name": "andrea ayers", + "label": "negative", + "script": "latin" + }, + { + "name": "andrew lees", + "label": "negative", + "script": "latin" + }, + { + "name": "anne hatfield", + "label": "negative", + "script": "latin" + }, + { + "name": "cynthia duffy", + "label": "negative", + "script": "latin" + }, + { + "name": "wayne cooper", + "label": "negative", + "script": "latin" + }, + { + "name": "jade harris", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Swap adjacent consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_consonants" + ], + "rule_descriptions": { + "swap_adjacent_consonants": "Swap adjacent consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "christopher cameron", + "label": "negative", + "script": "latin" + }, + { + "name": "charlotte coleman", + "label": "negative", + "script": "latin" + }, + { + "name": "lydia adams", + "label": "negative", + "script": "latin" + }, + { + "name": "robert brown", + "label": "negative", + "script": "latin" + }, + { + "name": "gary martinez", + "label": "negative", + "script": "latin" + }, + { + "name": "mark bowen", + "label": "negative", + "script": "latin" + }, + { + "name": "scott simmons", + "label": "negative", + "script": "latin" + }, + { + "name": "bethan estrada", + "label": "negative", + "script": "latin" + }, + { + "name": "lawrence lawrence", + "label": "negative", + "script": "latin" + }, + { + "name": "clarence hutchinson", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua foster", + "label": "negative", + "script": "latin" + }, + { + "name": "omar long", + "label": "negative", + "script": "latin" + }, + { + "name": "vincent wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "paul marshall", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah jones", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace random vowels with different vowels, and Remove a random vowel.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_vowel_with_random_vowel", + "remove_random_vowel" + ], + "rule_descriptions": { + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels", + "remove_random_vowel": "Remove a random vowel" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "peter dean", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah mccarthy", + "label": "negative", + "script": "latin" + }, + { + "name": "frances singh", + "label": "negative", + "script": "latin" + }, + { + "name": "james farrell", + "label": "negative", + "script": "latin" + }, + { + "name": "sheila williams", + "label": "negative", + "script": "latin" + }, + { + "name": "richard horton", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie white", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica gibson", + "label": "negative", + "script": "latin" + }, + { + "name": "karla clark", + "label": "negative", + "script": "latin" + }, + { + "name": "gina miller", + "label": "negative", + "script": "latin" + }, + { + "name": "curtis poole", + "label": "negative", + "script": "latin" + }, + { + "name": "brittney morris", + "label": "negative", + "script": "latin" + }, + { + "name": "michael fox", + "label": "negative", + "script": "latin" + }, + { + "name": "harriet kelley", + "label": "negative", + "script": "latin" + }, + { + "name": "kelly logan", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Remove all spaces.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_all_spaces" + ], + "rule_descriptions": { + "remove_all_spaces": "Remove all spaces" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "jennifer mitchell", + "label": "negative", + "script": "latin" + }, + { + "name": "kenneth watson", + "label": "negative", + "script": "latin" + }, + { + "name": "lynne bailey", + "label": "negative", + "script": "latin" + }, + { + "name": "antonio jones", + "label": "negative", + "script": "latin" + }, + { + "name": "tina vance", + "label": "negative", + "script": "latin" + }, + { + "name": "cynthia rose", + "label": "negative", + "script": "latin" + }, + { + "name": "aaron perry", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua patterson", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher duncan", + "label": "negative", + "script": "latin" + }, + { + "name": "john charles", + "label": "negative", + "script": "latin" + }, + { + "name": "anne williams", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie hammond", + "label": "negative", + "script": "latin" + }, + { + "name": "sally andrews", + "label": "negative", + "script": "latin" + }, + { + "name": "mohammad davis", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony jackson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Use first name initial with last name, and Insert a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "initial_only_first_name", + "insert_random_letter" + ], + "rule_descriptions": { + "initial_only_first_name": "Use first name initial with last name", + "insert_random_letter": "Insert a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "amy mcdonald", + "label": "negative", + "script": "latin" + }, + { + "name": "harold atkins", + "label": "negative", + "script": "latin" + }, + { + "name": "peter bolton", + "label": "negative", + "script": "latin" + }, + { + "name": "miguel jones", + "label": "negative", + "script": "latin" + }, + { + "name": "erin tapia", + "label": "negative", + "script": "latin" + }, + { + "name": "wesley kline", + "label": "negative", + "script": "latin" + }, + { + "name": "brandon williams", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica williams", + "label": "negative", + "script": "latin" + }, + { + "name": "lynda khan", + "label": "negative", + "script": "latin" + }, + { + "name": "tonya gardner", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa reyes", + "label": "negative", + "script": "latin" + }, + { + "name": "kieran crawford", + "label": "negative", + "script": "latin" + }, + { + "name": "hayley clark", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy bond", + "label": "negative", + "script": "latin" + }, + { + "name": "william white", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Replace random vowels with different vowels.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_vowel_with_random_vowel" + ], + "rule_descriptions": { + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "patricia martinez", + "label": "negative", + "script": "latin" + }, + { + "name": "brenda stone", + "label": "negative", + "script": "latin" + }, + { + "name": "kyle booker", + "label": "negative", + "script": "latin" + }, + { + "name": "sandra thorpe", + "label": "negative", + "script": "latin" + }, + { + "name": "phillip lamb", + "label": "negative", + "script": "latin" + }, + { + "name": "anne maldonado", + "label": "negative", + "script": "latin" + }, + { + "name": "ronald fletcher", + "label": "negative", + "script": "latin" + }, + { + "name": "lucas cox", + "label": "negative", + "script": "latin" + }, + { + "name": "jacqueline johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica begum", + "label": "negative", + "script": "latin" + }, + { + "name": "melanie thompson", + "label": "negative", + "script": "latin" + }, + { + "name": "stephen henry", + "label": "negative", + "script": "latin" + }, + { + "name": "katy young", + "label": "negative", + "script": "latin" + }, + { + "name": "elizabeth thompson", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel anthony", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap random adjacent letters, and Duplicate a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_random_letter", + "duplicate_random_letter_as_double_letter" + ], + "rule_descriptions": { + "swap_random_letter": "Swap random adjacent letters", + "duplicate_random_letter_as_double_letter": "Duplicate a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "deanna keith", + "label": "negative", + "script": "latin" + }, + { + "name": "rachel bell", + "label": "negative", + "script": "latin" + }, + { + "name": "frank matthews", + "label": "negative", + "script": "latin" + }, + { + "name": "beth cunningham", + "label": "negative", + "script": "latin" + }, + { + "name": "adam barry", + "label": "negative", + "script": "latin" + }, + { + "name": "andrea russo", + "label": "negative", + "script": "latin" + }, + { + "name": "katie price", + "label": "negative", + "script": "latin" + }, + { + "name": "elijah rivera", + "label": "negative", + "script": "latin" + }, + { + "name": "james fields", + "label": "negative", + "script": "latin" + }, + { + "name": "geraldine ward", + "label": "negative", + "script": "latin" + }, + { + "name": "susan ferguson", + "label": "negative", + "script": "latin" + }, + { + "name": "michele wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "marcus kim", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer hall", + "label": "negative", + "script": "latin" + }, + { + "name": "kimberly hudson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace double letters with a single letter, and Delete a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_double_letters_with_single_letter", + "delete_random_letter" + ], + "rule_descriptions": { + "replace_double_letters_with_single_letter": "Replace double letters with a single letter", + "delete_random_letter": "Delete a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "albert adams", + "label": "negative", + "script": "latin" + }, + { + "name": "johnny church", + "label": "negative", + "script": "latin" + }, + { + "name": "michael atkins", + "label": "negative", + "script": "latin" + }, + { + "name": "john alexander", + "label": "negative", + "script": "latin" + }, + { + "name": "carol wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "marilyn woods", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda walker", + "label": "negative", + "script": "latin" + }, + { + "name": "shannon brown", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle bennett", + "label": "negative", + "script": "latin" + }, + { + "name": "jill kelly", + "label": "negative", + "script": "latin" + }, + { + "name": "jerry lewis", + "label": "negative", + "script": "latin" + }, + { + "name": "kathryn price", + "label": "negative", + "script": "latin" + }, + { + "name": "earl dickerson", + "label": "negative", + "script": "latin" + }, + { + "name": "lindsay williams", + "label": "negative", + "script": "latin" + }, + { + "name": "vanessa thompson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap adjacent syllables, Delete a random letter, and Use first name initial with last name.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_syllables", + "delete_random_letter", + "initial_only_first_name" + ], + "rule_descriptions": { + "swap_adjacent_syllables": "Swap adjacent syllables", + "delete_random_letter": "Delete a random letter", + "initial_only_first_name": "Use first name initial with last name" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "amanda henderson", + "label": "negative", + "script": "latin" + }, + { + "name": "amy wise", + "label": "negative", + "script": "latin" + }, + { + "name": "willie foster", + "label": "negative", + "script": "latin" + }, + { + "name": "julie salazar", + "label": "negative", + "script": "latin" + }, + { + "name": "jose smith", + "label": "negative", + "script": "latin" + }, + { + "name": "amber smith", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole sullivan", + "label": "negative", + "script": "latin" + }, + { + "name": "raymond scott", + "label": "negative", + "script": "latin" + }, + { + "name": "john becker", + "label": "negative", + "script": "latin" + }, + { + "name": "lori smith", + "label": "negative", + "script": "latin" + }, + { + "name": "laura wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "andrea taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "william short", + "label": "negative", + "script": "latin" + }, + { + "name": "james mckee", + "label": "negative", + "script": "latin" + }, + { + "name": "terry petty", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Use first name initial with last name, Add a title suffix (Jr., PhD, etc.), and Remove a random vowel.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "initial_only_first_name", + "add_random_trailing_title", + "remove_random_vowel" + ], + "rule_descriptions": { + "initial_only_first_name": "Use first name initial with last name", + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)", + "remove_random_vowel": "Remove a random vowel" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "erica ramirez", + "label": "negative", + "script": "latin" + }, + { + "name": "colin ayers", + "label": "negative", + "script": "latin" + }, + { + "name": "charlene smith", + "label": "negative", + "script": "latin" + }, + { + "name": "christina morrison", + "label": "negative", + "script": "latin" + }, + { + "name": "pamela gonzalez", + "label": "negative", + "script": "latin" + }, + { + "name": "mitchell rivera", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley mitchell", + "label": "negative", + "script": "latin" + }, + { + "name": "phillip frey", + "label": "negative", + "script": "latin" + }, + { + "name": "marco lucas", + "label": "negative", + "script": "latin" + }, + { + "name": "barbara pace", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle howe", + "label": "negative", + "script": "latin" + }, + { + "name": "donna watkins", + "label": "negative", + "script": "latin" + }, + { + "name": "tiffany kent", + "label": "negative", + "script": "latin" + }, + { + "name": "richard johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "caleb moore", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Remove a random consonant.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_consonant" + ], + "rule_descriptions": { + "remove_random_consonant": "Remove a random consonant" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "bryce ortiz", + "label": "negative", + "script": "latin" + }, + { + "name": "joel chandler", + "label": "negative", + "script": "latin" + }, + { + "name": "elizabeth martin", + "label": "negative", + "script": "latin" + }, + { + "name": "hayley brown", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa kirby", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle hill", + "label": "negative", + "script": "latin" + }, + { + "name": "maxwell carter", + "label": "negative", + "script": "latin" + }, + { + "name": "frances hill", + "label": "negative", + "script": "latin" + }, + { + "name": "lynn carey", + "label": "negative", + "script": "latin" + }, + { + "name": "glen hudson", + "label": "negative", + "script": "latin" + }, + { + "name": "gail meyer", + "label": "negative", + "script": "latin" + }, + { + "name": "megan schmitt", + "label": "negative", + "script": "latin" + }, + { + "name": "antonio hamilton", + "label": "negative", + "script": "latin" + }, + { + "name": "kyle wood", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph lowe", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Delete a random letter, Add a title suffix (Jr., PhD, etc.), and Swap adjacent syllables.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "delete_random_letter", + "add_random_trailing_title", + "swap_adjacent_syllables" + ], + "rule_descriptions": { + "delete_random_letter": "Delete a random letter", + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)", + "swap_adjacent_syllables": "Swap adjacent syllables" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "victor mathis", + "label": "negative", + "script": "latin" + }, + { + "name": "erin smith", + "label": "negative", + "script": "latin" + }, + { + "name": "julia ferguson", + "label": "negative", + "script": "latin" + }, + { + "name": "veronica gutierrez", + "label": "negative", + "script": "latin" + }, + { + "name": "john shelton", + "label": "negative", + "script": "latin" + }, + { + "name": "hilary brown", + "label": "negative", + "script": "latin" + }, + { + "name": "patricia phillips", + "label": "negative", + "script": "latin" + }, + { + "name": "sophie king", + "label": "negative", + "script": "latin" + }, + { + "name": "sandra guerrero", + "label": "negative", + "script": "latin" + }, + { + "name": "lewis wang", + "label": "negative", + "script": "latin" + }, + { + "name": "nicholas williams", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew atkinson", + "label": "negative", + "script": "latin" + }, + { + "name": "ann hughes", + "label": "negative", + "script": "latin" + }, + { + "name": "jason calderon", + "label": "negative", + "script": "latin" + }, + { + "name": "michael harris", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Insert a random letter, and Use first name initial with last name.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "insert_random_letter", + "initial_only_first_name" + ], + "rule_descriptions": { + "insert_random_letter": "Insert a random letter", + "initial_only_first_name": "Use first name initial with last name" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "sheri berry", + "label": "negative", + "script": "latin" + }, + { + "name": "gary walker", + "label": "negative", + "script": "latin" + }, + { + "name": "jonathan hill", + "label": "negative", + "script": "latin" + }, + { + "name": "laura hawkins", + "label": "negative", + "script": "latin" + }, + { + "name": "karen byrd", + "label": "negative", + "script": "latin" + }, + { + "name": "angela hill", + "label": "negative", + "script": "latin" + }, + { + "name": "charles anderson", + "label": "negative", + "script": "latin" + }, + { + "name": "theresa mcmahon", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffrey armstrong", + "label": "negative", + "script": "latin" + }, + { + "name": "katherine thomas", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle williams", + "label": "negative", + "script": "latin" + }, + { + "name": "jared chase", + "label": "negative", + "script": "latin" + }, + { + "name": "joan brown", + "label": "negative", + "script": "latin" + }, + { + "name": "jane collins", + "label": "negative", + "script": "latin" + }, + { + "name": "debra smith", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove all spaces, Use first name initial with last name, and Swap adjacent syllables.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_all_spaces", + "initial_only_first_name", + "swap_adjacent_syllables" + ], + "rule_descriptions": { + "remove_all_spaces": "Remove all spaces", + "initial_only_first_name": "Use first name initial with last name", + "swap_adjacent_syllables": "Swap adjacent syllables" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "jonathan arnold", + "label": "negative", + "script": "latin" + }, + { + "name": "penny hudson", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah rogers", + "label": "negative", + "script": "latin" + }, + { + "name": "victor johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "alex rogers", + "label": "negative", + "script": "latin" + }, + { + "name": "charles booker", + "label": "negative", + "script": "latin" + }, + { + "name": "jerry allen", + "label": "negative", + "script": "latin" + }, + { + "name": "holly sanchez", + "label": "negative", + "script": "latin" + }, + { + "name": "ian welch", + "label": "negative", + "script": "latin" + }, + { + "name": "lee shepherd", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua lawrence", + "label": "negative", + "script": "latin" + }, + { + "name": "fiona rogers", + "label": "negative", + "script": "latin" + }, + { + "name": "vickie booth", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel joseph", + "label": "negative", + "script": "latin" + }, + { + "name": "adrian walker", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Reorder name parts, Swap adjacent consonants, and Replace spaces with special characters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "name_parts_permutations", + "swap_adjacent_consonants", + "replace_spaces_with_random_special_characters" + ], + "rule_descriptions": { + "name_parts_permutations": "Reorder name parts", + "swap_adjacent_consonants": "Swap adjacent consonants", + "replace_spaces_with_random_special_characters": "Replace spaces with special characters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "annette smith", + "label": "negative", + "script": "latin" + }, + { + "name": "billy norris", + "label": "negative", + "script": "latin" + }, + { + "name": "kyle nicholson", + "label": "negative", + "script": "latin" + }, + { + "name": "nancy williams", + "label": "negative", + "script": "latin" + }, + { + "name": "stanley edwards", + "label": "negative", + "script": "latin" + }, + { + "name": "michael walton", + "label": "negative", + "script": "latin" + }, + { + "name": "sara martin", + "label": "negative", + "script": "latin" + }, + { + "name": "cheryl baker", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew burgess", + "label": "negative", + "script": "latin" + }, + { + "name": "kathleen lewis", + "label": "negative", + "script": "latin" + }, + { + "name": "robert dennis", + "label": "negative", + "script": "latin" + }, + { + "name": "joel moran", + "label": "negative", + "script": "latin" + }, + { + "name": "tyler york", + "label": "negative", + "script": "latin" + }, + { + "name": "megan johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "alan garcia", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Reorder name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "name_parts_permutations" + ], + "rule_descriptions": { + "name_parts_permutations": "Reorder name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "john miller", + "label": "negative", + "script": "latin" + }, + { + "name": "courtney johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin rogers", + "label": "negative", + "script": "latin" + }, + { + "name": "sharon henson", + "label": "negative", + "script": "latin" + }, + { + "name": "megan barber", + "label": "negative", + "script": "latin" + }, + { + "name": "michael lee", + "label": "negative", + "script": "latin" + }, + { + "name": "dylan read", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda o'brien", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua wood", + "label": "negative", + "script": "latin" + }, + { + "name": "steve nolan", + "label": "negative", + "script": "latin" + }, + { + "name": "jeremy jones", + "label": "negative", + "script": "latin" + }, + { + "name": "brianna garcia", + "label": "negative", + "script": "latin" + }, + { + "name": "chad king", + "label": "negative", + "script": "latin" + }, + { + "name": "julie campbell", + "label": "negative", + "script": "latin" + }, + { + "name": "brian murray", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap adjacent syllables, and Remove a random consonant.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_syllables", + "remove_random_consonant" + ], + "rule_descriptions": { + "swap_adjacent_syllables": "Swap adjacent syllables", + "remove_random_consonant": "Remove a random consonant" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "craig middleton", + "label": "negative", + "script": "latin" + }, + { + "name": "joyce franklin", + "label": "negative", + "script": "latin" + }, + { + "name": "kathryn hamilton", + "label": "negative", + "script": "latin" + }, + { + "name": "courtney wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "rickey garcia", + "label": "negative", + "script": "latin" + }, + { + "name": "jason brooks", + "label": "negative", + "script": "latin" + }, + { + "name": "marcus salazar", + "label": "negative", + "script": "latin" + }, + { + "name": "david turner", + "label": "negative", + "script": "latin" + }, + { + "name": "gregory taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "stephen cross", + "label": "negative", + "script": "latin" + }, + { + "name": "charles white", + "label": "negative", + "script": "latin" + }, + { + "name": "michael patel", + "label": "negative", + "script": "latin" + }, + { + "name": "dawn walker", + "label": "negative", + "script": "latin" + }, + { + "name": "douglas romero", + "label": "negative", + "script": "latin" + }, + { + "name": "natasha mclaughlin", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove a random vowel, Delete a random letter, and Replace spaces with special characters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_vowel", + "delete_random_letter", + "replace_spaces_with_random_special_characters" + ], + "rule_descriptions": { + "remove_random_vowel": "Remove a random vowel", + "delete_random_letter": "Delete a random letter", + "replace_spaces_with_random_special_characters": "Replace spaces with special characters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "david morales", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy oneill", + "label": "negative", + "script": "latin" + }, + { + "name": "charles frank", + "label": "negative", + "script": "latin" + }, + { + "name": "michael james", + "label": "negative", + "script": "latin" + }, + { + "name": "rachel butler", + "label": "negative", + "script": "latin" + }, + { + "name": "lori saunders", + "label": "negative", + "script": "latin" + }, + { + "name": "bethany cunningham", + "label": "negative", + "script": "latin" + }, + { + "name": "megan barry", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher castaneda", + "label": "negative", + "script": "latin" + }, + { + "name": "james barnes", + "label": "negative", + "script": "latin" + }, + { + "name": "deborah wells", + "label": "negative", + "script": "latin" + }, + { + "name": "caroline rowland", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer price", + "label": "negative", + "script": "latin" + }, + { + "name": "jonathan berry", + "label": "negative", + "script": "latin" + }, + { + "name": "robert phillips", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Add a title prefix (Mr., Dr., etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_leading_title" + ], + "rule_descriptions": { + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "janet lowe", + "label": "negative", + "script": "latin" + }, + { + "name": "krista dunn", + "label": "negative", + "script": "latin" + }, + { + "name": "jorge matthews", + "label": "negative", + "script": "latin" + }, + { + "name": "kathleen smith", + "label": "negative", + "script": "latin" + }, + { + "name": "mercedes williams", + "label": "negative", + "script": "latin" + }, + { + "name": "steven poole", + "label": "negative", + "script": "latin" + }, + { + "name": "laura burke", + "label": "negative", + "script": "latin" + }, + { + "name": "john shaw", + "label": "negative", + "script": "latin" + }, + { + "name": "marvin raymond", + "label": "negative", + "script": "latin" + }, + { + "name": "samuel cross", + "label": "negative", + "script": "latin" + }, + { + "name": "nicholas carpenter", + "label": "negative", + "script": "latin" + }, + { + "name": "brooke connolly", + "label": "negative", + "script": "latin" + }, + { + "name": "sean mcmillan", + "label": "negative", + "script": "latin" + }, + { + "name": "juan wright", + "label": "negative", + "script": "latin" + }, + { + "name": "lee simpson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Add a title suffix (Jr., PhD, etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_trailing_title" + ], + "rule_descriptions": { + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "rebecca o'neill", + "label": "negative", + "script": "latin" + }, + { + "name": "tony shah", + "label": "negative", + "script": "latin" + }, + { + "name": "paige jones", + "label": "negative", + "script": "latin" + }, + { + "name": "christy burgess", + "label": "negative", + "script": "latin" + }, + { + "name": "susan shepherd", + "label": "negative", + "script": "latin" + }, + { + "name": "michael lewis", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "valerie koch", + "label": "negative", + "script": "latin" + }, + { + "name": "tracy castillo", + "label": "negative", + "script": "latin" + }, + { + "name": "angela jones", + "label": "negative", + "script": "latin" + }, + { + "name": "amber carter", + "label": "negative", + "script": "latin" + }, + { + "name": "john brown", + "label": "negative", + "script": "latin" + }, + { + "name": "amelia hernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "malcolm mcdonald", + "label": "negative", + "script": "latin" + }, + { + "name": "caleb montes", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Replace random consonants with different consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_consonant_with_random_consonant" + ], + "rule_descriptions": { + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "kyle johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "marilyn butler", + "label": "negative", + "script": "latin" + }, + { + "name": "brandon price", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley jones", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy glass", + "label": "negative", + "script": "latin" + }, + { + "name": "jonathan velez", + "label": "negative", + "script": "latin" + }, + { + "name": "jonathan johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "michael crane", + "label": "negative", + "script": "latin" + }, + { + "name": "grant thompson", + "label": "negative", + "script": "latin" + }, + { + "name": "debra norris", + "label": "negative", + "script": "latin" + }, + { + "name": "derrick cox", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica french", + "label": "negative", + "script": "latin" + }, + { + "name": "lauren mcintyre", + "label": "negative", + "script": "latin" + }, + { + "name": "gerald graham", + "label": "negative", + "script": "latin" + }, + { + "name": "angel diaz", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Remove a random consonant.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_consonant" + ], + "rule_descriptions": { + "remove_random_consonant": "Remove a random consonant" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "michael harris", + "label": "negative", + "script": "latin" + }, + { + "name": "patty luna", + "label": "negative", + "script": "latin" + }, + { + "name": "harriet lane", + "label": "negative", + "script": "latin" + }, + { + "name": "alexander collier", + "label": "negative", + "script": "latin" + }, + { + "name": "alexis burke", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa berry", + "label": "negative", + "script": "latin" + }, + { + "name": "nathan palmer", + "label": "negative", + "script": "latin" + }, + { + "name": "rachel holland", + "label": "negative", + "script": "latin" + }, + { + "name": "kerri miller", + "label": "negative", + "script": "latin" + }, + { + "name": "sandy smith", + "label": "negative", + "script": "latin" + }, + { + "name": "dan young", + "label": "negative", + "script": "latin" + }, + { + "name": "christina cameron", + "label": "negative", + "script": "latin" + }, + { + "name": "david chang", + "label": "negative", + "script": "latin" + }, + { + "name": "michael klein", + "label": "negative", + "script": "latin" + }, + { + "name": "sophie daly", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace spaces with special characters, Swap adjacent consonants, and Delete a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_spaces_with_random_special_characters", + "swap_adjacent_consonants", + "delete_random_letter" + ], + "rule_descriptions": { + "replace_spaces_with_random_special_characters": "Replace spaces with special characters", + "swap_adjacent_consonants": "Swap adjacent consonants", + "delete_random_letter": "Delete a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "george mitchell", + "label": "negative", + "script": "latin" + }, + { + "name": "lindsey smith", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin jones", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah schmidt", + "label": "negative", + "script": "latin" + }, + { + "name": "steven green", + "label": "negative", + "script": "latin" + }, + { + "name": "rodney jones", + "label": "negative", + "script": "latin" + }, + { + "name": "david jones", + "label": "negative", + "script": "latin" + }, + { + "name": "nicholas miller", + "label": "negative", + "script": "latin" + }, + { + "name": "martin carter", + "label": "negative", + "script": "latin" + }, + { + "name": "kristine thomas", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole mejia", + "label": "negative", + "script": "latin" + }, + { + "name": "damian sanchez", + "label": "negative", + "script": "latin" + }, + { + "name": "tracy rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "paul williams", + "label": "negative", + "script": "latin" + }, + { + "name": "jacqueline barrett", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap adjacent syllables, Duplicate a random letter, and Replace spaces with special characters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_syllables", + "duplicate_random_letter_as_double_letter", + "replace_spaces_with_random_special_characters" + ], + "rule_descriptions": { + "swap_adjacent_syllables": "Swap adjacent syllables", + "duplicate_random_letter_as_double_letter": "Duplicate a random letter", + "replace_spaces_with_random_special_characters": "Replace spaces with special characters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "marc rogers", + "label": "negative", + "script": "latin" + }, + { + "name": "janet miranda", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley villa", + "label": "negative", + "script": "latin" + }, + { + "name": "david lawrence", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer weber", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher gonzalez", + "label": "negative", + "script": "latin" + }, + { + "name": "ruth gregory", + "label": "negative", + "script": "latin" + }, + { + "name": "barbara trevino", + "label": "negative", + "script": "latin" + }, + { + "name": "claudia garcia", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa nielsen", + "label": "negative", + "script": "latin" + }, + { + "name": "eric taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "kate johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "frank marquez", + "label": "negative", + "script": "latin" + }, + { + "name": "kelly johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole martin", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace double letters with a single letter, Abbreviate name parts, and Replace random vowels with different vowels.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_double_letters_with_single_letter", + "shorten_name_to_abbreviations", + "replace_random_vowel_with_random_vowel" + ], + "rule_descriptions": { + "replace_double_letters_with_single_letter": "Replace double letters with a single letter", + "shorten_name_to_abbreviations": "Abbreviate name parts", + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "hannah rivera", + "label": "negative", + "script": "latin" + }, + { + "name": "shannon ross", + "label": "negative", + "script": "latin" + }, + { + "name": "brett velasquez", + "label": "negative", + "script": "latin" + }, + { + "name": "ashleigh buckley", + "label": "negative", + "script": "latin" + }, + { + "name": "conor yang", + "label": "negative", + "script": "latin" + }, + { + "name": "adam johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "mark reyes", + "label": "negative", + "script": "latin" + }, + { + "name": "kayla wagner", + "label": "negative", + "script": "latin" + }, + { + "name": "kathleen benton", + "label": "negative", + "script": "latin" + }, + { + "name": "kari gallagher", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer williams", + "label": "negative", + "script": "latin" + }, + { + "name": "teresa russo", + "label": "negative", + "script": "latin" + }, + { + "name": "brenda scott", + "label": "negative", + "script": "latin" + }, + { + "name": "spencer jones", + "label": "negative", + "script": "latin" + }, + { + "name": "seth jones", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title prefix (Mr., Dr., etc.), and Swap adjacent syllables.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_leading_title", + "swap_adjacent_syllables" + ], + "rule_descriptions": { + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)", + "swap_adjacent_syllables": "Swap adjacent syllables" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "alison hale", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua baxter", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas smith", + "label": "negative", + "script": "latin" + }, + { + "name": "tamara brown", + "label": "negative", + "script": "latin" + }, + { + "name": "susan sullivan", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole krause", + "label": "negative", + "script": "latin" + }, + { + "name": "valerie munoz", + "label": "negative", + "script": "latin" + }, + { + "name": "laurie carey", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole cannon", + "label": "negative", + "script": "latin" + }, + { + "name": "clifford klein", + "label": "negative", + "script": "latin" + }, + { + "name": "marie daniel", + "label": "negative", + "script": "latin" + }, + { + "name": "joyce scott", + "label": "negative", + "script": "latin" + }, + { + "name": "frederick underwood", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer ware", + "label": "negative", + "script": "latin" + }, + { + "name": "margaret hooper", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Remove all spaces.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_all_spaces" + ], + "rule_descriptions": { + "remove_all_spaces": "Remove all spaces" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "joseph smith", + "label": "negative", + "script": "latin" + }, + { + "name": "david williams", + "label": "negative", + "script": "latin" + }, + { + "name": "wyatt evans", + "label": "negative", + "script": "latin" + }, + { + "name": "kristen ballard", + "label": "negative", + "script": "latin" + }, + { + "name": "antonio garcia", + "label": "negative", + "script": "latin" + }, + { + "name": "david love", + "label": "negative", + "script": "latin" + }, + { + "name": "garry stevenson", + "label": "negative", + "script": "latin" + }, + { + "name": "robert gutierrez", + "label": "negative", + "script": "latin" + }, + { + "name": "samuel barrett", + "label": "negative", + "script": "latin" + }, + { + "name": "kristin reyes", + "label": "negative", + "script": "latin" + }, + { + "name": "lance miller", + "label": "negative", + "script": "latin" + }, + { + "name": "marvin ahmed", + "label": "negative", + "script": "latin" + }, + { + "name": "dennis kaur", + "label": "negative", + "script": "latin" + }, + { + "name": "philip kelley", + "label": "negative", + "script": "latin" + }, + { + "name": "tiffany morgan", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace double letters with a single letter, and Remove a random vowel.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_double_letters_with_single_letter", + "remove_random_vowel" + ], + "rule_descriptions": { + "replace_double_letters_with_single_letter": "Replace double letters with a single letter", + "remove_random_vowel": "Remove a random vowel" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "noah dalton", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer valentine", + "label": "negative", + "script": "latin" + }, + { + "name": "mark wilkinson", + "label": "negative", + "script": "latin" + }, + { + "name": "patrick cordova", + "label": "negative", + "script": "latin" + }, + { + "name": "patrick harmon", + "label": "negative", + "script": "latin" + }, + { + "name": "david white", + "label": "negative", + "script": "latin" + }, + { + "name": "rebecca west", + "label": "negative", + "script": "latin" + }, + { + "name": "michael hill", + "label": "negative", + "script": "latin" + }, + { + "name": "damien atkins", + "label": "negative", + "script": "latin" + }, + { + "name": "deborah kemp", + "label": "negative", + "script": "latin" + }, + { + "name": "madeline munoz", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda rogers", + "label": "negative", + "script": "latin" + }, + { + "name": "rita obrien", + "label": "negative", + "script": "latin" + }, + { + "name": "samantha lopez", + "label": "negative", + "script": "latin" + }, + { + "name": "alicia goodwin", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Remove a random vowel.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_vowel" + ], + "rule_descriptions": { + "remove_random_vowel": "Remove a random vowel" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "daniel irwin", + "label": "negative", + "script": "latin" + }, + { + "name": "garrett mayo", + "label": "negative", + "script": "latin" + }, + { + "name": "michael tomlinson", + "label": "negative", + "script": "latin" + }, + { + "name": "robert thomas", + "label": "negative", + "script": "latin" + }, + { + "name": "tamara green", + "label": "negative", + "script": "latin" + }, + { + "name": "victoria richmond", + "label": "negative", + "script": "latin" + }, + { + "name": "karen field", + "label": "negative", + "script": "latin" + }, + { + "name": "sean hamilton", + "label": "negative", + "script": "latin" + }, + { + "name": "natalie may", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa lamb", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin powell", + "label": "negative", + "script": "latin" + }, + { + "name": "theresa robinson", + "label": "negative", + "script": "latin" + }, + { + "name": "tammy moore", + "label": "negative", + "script": "latin" + }, + { + "name": "jeff gonzalez", + "label": "negative", + "script": "latin" + }, + { + "name": "jason craig", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace random vowels with different vowels, Use first name initial with last name, and Remove a random consonant.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_vowel_with_random_vowel", + "initial_only_first_name", + "remove_random_consonant" + ], + "rule_descriptions": { + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels", + "initial_only_first_name": "Use first name initial with last name", + "remove_random_consonant": "Remove a random consonant" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "adam johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "lawrence pugh", + "label": "negative", + "script": "latin" + }, + { + "name": "corey reynolds", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa skinner", + "label": "negative", + "script": "latin" + }, + { + "name": "tony diaz", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah jenkins", + "label": "negative", + "script": "latin" + }, + { + "name": "dawn davis", + "label": "negative", + "script": "latin" + }, + { + "name": "xavier potts", + "label": "negative", + "script": "latin" + }, + { + "name": "taylor riley", + "label": "negative", + "script": "latin" + }, + { + "name": "robin gardner", + "label": "negative", + "script": "latin" + }, + { + "name": "francis lopez", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffrey miller", + "label": "negative", + "script": "latin" + }, + { + "name": "wendy henderson", + "label": "negative", + "script": "latin" + }, + { + "name": "brian burns", + "label": "negative", + "script": "latin" + }, + { + "name": "elliot brown", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Replace random vowels with different vowels.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_vowel_with_random_vowel" + ], + "rule_descriptions": { + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "sarah aguilar", + "label": "negative", + "script": "latin" + }, + { + "name": "carly white", + "label": "negative", + "script": "latin" + }, + { + "name": "chad graham", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher davis", + "label": "negative", + "script": "latin" + }, + { + "name": "charles hunter", + "label": "negative", + "script": "latin" + }, + { + "name": "patrick gonzalez", + "label": "negative", + "script": "latin" + }, + { + "name": "donald rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "jason chen", + "label": "negative", + "script": "latin" + }, + { + "name": "terri kaur", + "label": "negative", + "script": "latin" + }, + { + "name": "kelly espinoza", + "label": "negative", + "script": "latin" + }, + { + "name": "james hanson", + "label": "negative", + "script": "latin" + }, + { + "name": "ross andrews", + "label": "negative", + "script": "latin" + }, + { + "name": "mitchell howell", + "label": "negative", + "script": "latin" + }, + { + "name": "eileen zimmerman", + "label": "negative", + "script": "latin" + }, + { + "name": "ernest hurst", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Insert a random letter, Add a title prefix (Mr., Dr., etc.), and Remove a random vowel.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "insert_random_letter", + "add_random_leading_title", + "remove_random_vowel" + ], + "rule_descriptions": { + "insert_random_letter": "Insert a random letter", + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)", + "remove_random_vowel": "Remove a random vowel" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "carol harvey", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa james", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew chandler", + "label": "negative", + "script": "latin" + }, + { + "name": "julia chambers", + "label": "negative", + "script": "latin" + }, + { + "name": "misty alexander", + "label": "negative", + "script": "latin" + }, + { + "name": "teresa davis", + "label": "negative", + "script": "latin" + }, + { + "name": "yvette savage", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle gay", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda hardy", + "label": "negative", + "script": "latin" + }, + { + "name": "margaret osborne", + "label": "negative", + "script": "latin" + }, + { + "name": "brian morales", + "label": "negative", + "script": "latin" + }, + { + "name": "danielle burton", + "label": "negative", + "script": "latin" + }, + { + "name": "chelsea jones", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley graham", + "label": "negative", + "script": "latin" + }, + { + "name": "marie burton", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Duplicate a random letter, and Remove a random consonant.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "duplicate_random_letter_as_double_letter", + "remove_random_consonant" + ], + "rule_descriptions": { + "duplicate_random_letter_as_double_letter": "Duplicate a random letter", + "remove_random_consonant": "Remove a random consonant" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "david evans", + "label": "negative", + "script": "latin" + }, + { + "name": "patricia berry", + "label": "negative", + "script": "latin" + }, + { + "name": "robert knight", + "label": "negative", + "script": "latin" + }, + { + "name": "laura hall", + "label": "negative", + "script": "latin" + }, + { + "name": "amy garner", + "label": "negative", + "script": "latin" + }, + { + "name": "martin meyer", + "label": "negative", + "script": "latin" + }, + { + "name": "manuel frye", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony odom", + "label": "negative", + "script": "latin" + }, + { + "name": "donna hill", + "label": "negative", + "script": "latin" + }, + { + "name": "laurie parks", + "label": "negative", + "script": "latin" + }, + { + "name": "jill rivera", + "label": "negative", + "script": "latin" + }, + { + "name": "brianna west", + "label": "negative", + "script": "latin" + }, + { + "name": "chelsea adams", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew murray", + "label": "negative", + "script": "latin" + }, + { + "name": "andrea wilson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Use first name initial with last name, and Delete a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "initial_only_first_name", + "delete_random_letter" + ], + "rule_descriptions": { + "initial_only_first_name": "Use first name initial with last name", + "delete_random_letter": "Delete a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "john valenzuela", + "label": "negative", + "script": "latin" + }, + { + "name": "karen smith", + "label": "negative", + "script": "latin" + }, + { + "name": "shannon woods", + "label": "negative", + "script": "latin" + }, + { + "name": "jason macdonald", + "label": "negative", + "script": "latin" + }, + { + "name": "pamela english", + "label": "negative", + "script": "latin" + }, + { + "name": "amy brown", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua bird", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew keller", + "label": "negative", + "script": "latin" + }, + { + "name": "grant jenkins", + "label": "negative", + "script": "latin" + }, + { + "name": "william reid", + "label": "negative", + "script": "latin" + }, + { + "name": "michael rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "george harris", + "label": "negative", + "script": "latin" + }, + { + "name": "jordan molina", + "label": "negative", + "script": "latin" + }, + { + "name": "mandy sanders", + "label": "negative", + "script": "latin" + }, + { + "name": "felicia aguilar", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace spaces with special characters, Abbreviate name parts, and Replace random consonants with different consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_spaces_with_random_special_characters", + "shorten_name_to_abbreviations", + "replace_random_consonant_with_random_consonant" + ], + "rule_descriptions": { + "replace_spaces_with_random_special_characters": "Replace spaces with special characters", + "shorten_name_to_abbreviations": "Abbreviate name parts", + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "stephen cooper", + "label": "negative", + "script": "latin" + }, + { + "name": "david sandoval", + "label": "negative", + "script": "latin" + }, + { + "name": "ethan chavez", + "label": "negative", + "script": "latin" + }, + { + "name": "robert riley", + "label": "negative", + "script": "latin" + }, + { + "name": "kelli davison", + "label": "negative", + "script": "latin" + }, + { + "name": "kerry carter", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel medina", + "label": "negative", + "script": "latin" + }, + { + "name": "tracy austin", + "label": "negative", + "script": "latin" + }, + { + "name": "katherine vaughan", + "label": "negative", + "script": "latin" + }, + { + "name": "carlos kelly", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel williams", + "label": "negative", + "script": "latin" + }, + { + "name": "donald perez", + "label": "negative", + "script": "latin" + }, + { + "name": "sharon lawrence", + "label": "negative", + "script": "latin" + }, + { + "name": "katie evans", + "label": "negative", + "script": "latin" + }, + { + "name": "molly howell", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace random consonants with different consonants, and Add a title suffix (Jr., PhD, etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_consonant_with_random_consonant", + "add_random_trailing_title" + ], + "rule_descriptions": { + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants", + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "barry kelly", + "label": "negative", + "script": "latin" + }, + { + "name": "benjamin powers", + "label": "negative", + "script": "latin" + }, + { + "name": "michael white", + "label": "negative", + "script": "latin" + }, + { + "name": "renee harrison", + "label": "negative", + "script": "latin" + }, + { + "name": "melinda cantu", + "label": "negative", + "script": "latin" + }, + { + "name": "kyle barber", + "label": "negative", + "script": "latin" + }, + { + "name": "jamie stewart", + "label": "negative", + "script": "latin" + }, + { + "name": "maria robinson", + "label": "negative", + "script": "latin" + }, + { + "name": "amber bradley", + "label": "negative", + "script": "latin" + }, + { + "name": "michael joyce", + "label": "negative", + "script": "latin" + }, + { + "name": "jared randall", + "label": "negative", + "script": "latin" + }, + { + "name": "jamie rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "edgar barton", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "raymond lewis", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Convert name to initials, Swap adjacent syllables, and Add a title prefix (Mr., Dr., etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_initials", + "swap_adjacent_syllables", + "add_random_leading_title" + ], + "rule_descriptions": { + "shorten_name_to_initials": "Convert name to initials", + "swap_adjacent_syllables": "Swap adjacent syllables", + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "seth alvarez", + "label": "negative", + "script": "latin" + }, + { + "name": "kyle bell", + "label": "negative", + "script": "latin" + }, + { + "name": "crystal stone", + "label": "negative", + "script": "latin" + }, + { + "name": "annette howard", + "label": "negative", + "script": "latin" + }, + { + "name": "vanessa davison", + "label": "negative", + "script": "latin" + }, + { + "name": "laura reed", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole farmer", + "label": "negative", + "script": "latin" + }, + { + "name": "susan logan", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffrey hodge", + "label": "negative", + "script": "latin" + }, + { + "name": "kelly wilkins", + "label": "negative", + "script": "latin" + }, + { + "name": "morgan murphy", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "robert jones", + "label": "negative", + "script": "latin" + }, + { + "name": "jonathon green", + "label": "negative", + "script": "latin" + }, + { + "name": "megan garcia", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Remove a random vowel.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_vowel" + ], + "rule_descriptions": { + "remove_random_vowel": "Remove a random vowel" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "clifford hall", + "label": "negative", + "script": "latin" + }, + { + "name": "wanda brennan", + "label": "negative", + "script": "latin" + }, + { + "name": "robert smith", + "label": "negative", + "script": "latin" + }, + { + "name": "dawn mosley", + "label": "negative", + "script": "latin" + }, + { + "name": "catherine perry", + "label": "negative", + "script": "latin" + }, + { + "name": "leah nixon", + "label": "negative", + "script": "latin" + }, + { + "name": "angela jones", + "label": "negative", + "script": "latin" + }, + { + "name": "erica black", + "label": "negative", + "script": "latin" + }, + { + "name": "bethany olsen", + "label": "negative", + "script": "latin" + }, + { + "name": "jason weiss", + "label": "negative", + "script": "latin" + }, + { + "name": "brandon finley", + "label": "negative", + "script": "latin" + }, + { + "name": "john lopez", + "label": "negative", + "script": "latin" + }, + { + "name": "kara haney", + "label": "negative", + "script": "latin" + }, + { + "name": "david webb", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony harding", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Use first name initial with last name.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "initial_only_first_name" + ], + "rule_descriptions": { + "initial_only_first_name": "Use first name initial with last name" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "catherine williams", + "label": "negative", + "script": "latin" + }, + { + "name": "steven marks", + "label": "negative", + "script": "latin" + }, + { + "name": "michael lewis", + "label": "negative", + "script": "latin" + }, + { + "name": "rebecca meyer", + "label": "negative", + "script": "latin" + }, + { + "name": "caitlin munoz", + "label": "negative", + "script": "latin" + }, + { + "name": "john wolf", + "label": "negative", + "script": "latin" + }, + { + "name": "rachael mitchell", + "label": "negative", + "script": "latin" + }, + { + "name": "desiree daniels", + "label": "negative", + "script": "latin" + }, + { + "name": "luke diaz", + "label": "negative", + "script": "latin" + }, + { + "name": "carlos george", + "label": "negative", + "script": "latin" + }, + { + "name": "peter cooper", + "label": "negative", + "script": "latin" + }, + { + "name": "rebecca campbell", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "michael kennedy", + "label": "negative", + "script": "latin" + }, + { + "name": "carlos carrillo", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap adjacent syllables, and Duplicate a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_syllables", + "duplicate_random_letter_as_double_letter" + ], + "rule_descriptions": { + "swap_adjacent_syllables": "Swap adjacent syllables", + "duplicate_random_letter_as_double_letter": "Duplicate a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "richard rose", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel lawrence", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph stewart", + "label": "negative", + "script": "latin" + }, + { + "name": "lindsey walker", + "label": "negative", + "script": "latin" + }, + { + "name": "james bird", + "label": "negative", + "script": "latin" + }, + { + "name": "james harrison", + "label": "negative", + "script": "latin" + }, + { + "name": "chelsea glover", + "label": "negative", + "script": "latin" + }, + { + "name": "damon chavez", + "label": "negative", + "script": "latin" + }, + { + "name": "anna hernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "clare mason", + "label": "negative", + "script": "latin" + }, + { + "name": "jon martin", + "label": "negative", + "script": "latin" + }, + { + "name": "donna cook", + "label": "negative", + "script": "latin" + }, + { + "name": "craig davis", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew roth", + "label": "negative", + "script": "latin" + }, + { + "name": "reece snyder", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Replace double letters with a single letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_double_letters_with_single_letter" + ], + "rule_descriptions": { + "replace_double_letters_with_single_letter": "Replace double letters with a single letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "anne hodges", + "label": "negative", + "script": "latin" + }, + { + "name": "ryan thornton", + "label": "negative", + "script": "latin" + }, + { + "name": "shannon smith", + "label": "negative", + "script": "latin" + }, + { + "name": "jasmine king", + "label": "negative", + "script": "latin" + }, + { + "name": "cassandra wilkins", + "label": "negative", + "script": "latin" + }, + { + "name": "sandra davis", + "label": "negative", + "script": "latin" + }, + { + "name": "rhys curtis", + "label": "negative", + "script": "latin" + }, + { + "name": "annette barnett", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer vaughn", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa novak", + "label": "negative", + "script": "latin" + }, + { + "name": "brandon savage", + "label": "negative", + "script": "latin" + }, + { + "name": "holly moon", + "label": "negative", + "script": "latin" + }, + { + "name": "tyler miller", + "label": "negative", + "script": "latin" + }, + { + "name": "kimberley french", + "label": "negative", + "script": "latin" + }, + { + "name": "billy willis", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Reorder name parts, Swap adjacent consonants, and Remove a random vowel.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "name_parts_permutations", + "swap_adjacent_consonants", + "remove_random_vowel" + ], + "rule_descriptions": { + "name_parts_permutations": "Reorder name parts", + "swap_adjacent_consonants": "Swap adjacent consonants", + "remove_random_vowel": "Remove a random vowel" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "haley glover", + "label": "negative", + "script": "latin" + }, + { + "name": "jayne swanson", + "label": "negative", + "script": "latin" + }, + { + "name": "william berry", + "label": "negative", + "script": "latin" + }, + { + "name": "sara miller", + "label": "negative", + "script": "latin" + }, + { + "name": "kathy henson", + "label": "negative", + "script": "latin" + }, + { + "name": "nigel solis", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher harvey", + "label": "negative", + "script": "latin" + }, + { + "name": "rachel gibson", + "label": "negative", + "script": "latin" + }, + { + "name": "bobby brown", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa murphy", + "label": "negative", + "script": "latin" + }, + { + "name": "david herrera", + "label": "negative", + "script": "latin" + }, + { + "name": "martin oneal", + "label": "negative", + "script": "latin" + }, + { + "name": "richard harris", + "label": "negative", + "script": "latin" + }, + { + "name": "miranda walker", + "label": "negative", + "script": "latin" + }, + { + "name": "gerald lane", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace double letters with a single letter, and Add a title suffix (Jr., PhD, etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_double_letters_with_single_letter", + "add_random_trailing_title" + ], + "rule_descriptions": { + "replace_double_letters_with_single_letter": "Replace double letters with a single letter", + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "nicholas blake", + "label": "negative", + "script": "latin" + }, + { + "name": "amy anderson", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole jimenez", + "label": "negative", + "script": "latin" + }, + { + "name": "tammy stokes", + "label": "negative", + "script": "latin" + }, + { + "name": "mary ward", + "label": "negative", + "script": "latin" + }, + { + "name": "jacob adams", + "label": "negative", + "script": "latin" + }, + { + "name": "tom rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "sierra wheeler", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel hall", + "label": "negative", + "script": "latin" + }, + { + "name": "donna doyle", + "label": "negative", + "script": "latin" + }, + { + "name": "gerard webb", + "label": "negative", + "script": "latin" + }, + { + "name": "jo smith", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel williams", + "label": "negative", + "script": "latin" + }, + { + "name": "scott morrow", + "label": "negative", + "script": "latin" + }, + { + "name": "miguel everett", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Insert a random letter, and Remove all spaces.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "insert_random_letter", + "remove_all_spaces" + ], + "rule_descriptions": { + "insert_random_letter": "Insert a random letter", + "remove_all_spaces": "Remove all spaces" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "dominic brown", + "label": "negative", + "script": "latin" + }, + { + "name": "amy strickland", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher bryant", + "label": "negative", + "script": "latin" + }, + { + "name": "david kelly", + "label": "negative", + "script": "latin" + }, + { + "name": "joe hansen", + "label": "negative", + "script": "latin" + }, + { + "name": "zachary hanson", + "label": "negative", + "script": "latin" + }, + { + "name": "shaun cooper", + "label": "negative", + "script": "latin" + }, + { + "name": "david jones", + "label": "negative", + "script": "latin" + }, + { + "name": "kathleen gonzales", + "label": "negative", + "script": "latin" + }, + { + "name": "alyssa rogers", + "label": "negative", + "script": "latin" + }, + { + "name": "kimberly robbins", + "label": "negative", + "script": "latin" + }, + { + "name": "steven gross", + "label": "negative", + "script": "latin" + }, + { + "name": "ellen ross", + "label": "negative", + "script": "latin" + }, + { + "name": "irene long", + "label": "negative", + "script": "latin" + }, + { + "name": "charles davis", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove a random consonant, Convert name to initials, and Use first name initial with last name.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_consonant", + "shorten_name_to_initials", + "initial_only_first_name" + ], + "rule_descriptions": { + "remove_random_consonant": "Remove a random consonant", + "shorten_name_to_initials": "Convert name to initials", + "initial_only_first_name": "Use first name initial with last name" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "william lawrence", + "label": "negative", + "script": "latin" + }, + { + "name": "miranda metcalfe", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah ferrell", + "label": "negative", + "script": "latin" + }, + { + "name": "pamela bright", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher gibbs", + "label": "negative", + "script": "latin" + }, + { + "name": "marion hess", + "label": "negative", + "script": "latin" + }, + { + "name": "carly french", + "label": "negative", + "script": "latin" + }, + { + "name": "roy moore", + "label": "negative", + "script": "latin" + }, + { + "name": "alec scott", + "label": "negative", + "script": "latin" + }, + { + "name": "michael pearce", + "label": "negative", + "script": "latin" + }, + { + "name": "michael chambers", + "label": "negative", + "script": "latin" + }, + { + "name": "beverly reynolds", + "label": "negative", + "script": "latin" + }, + { + "name": "patrick young", + "label": "negative", + "script": "latin" + }, + { + "name": "nicholas young", + "label": "negative", + "script": "latin" + }, + { + "name": "barbara williams", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title suffix (Jr., PhD, etc.), and Swap random adjacent letters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_trailing_title", + "swap_random_letter" + ], + "rule_descriptions": { + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)", + "swap_random_letter": "Swap random adjacent letters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "caitlin martinez", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin west", + "label": "negative", + "script": "latin" + }, + { + "name": "ronald ortiz", + "label": "negative", + "script": "latin" + }, + { + "name": "donald cox", + "label": "negative", + "script": "latin" + }, + { + "name": "cassandra lawson", + "label": "negative", + "script": "latin" + }, + { + "name": "angela miles", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah myers", + "label": "negative", + "script": "latin" + }, + { + "name": "jorge walters", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa byrne", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa mclean", + "label": "negative", + "script": "latin" + }, + { + "name": "joy gross", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher coleman", + "label": "negative", + "script": "latin" + }, + { + "name": "donna farrell", + "label": "negative", + "script": "latin" + }, + { + "name": "james rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "emily patterson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap random adjacent letters, and Add a title suffix (Jr., PhD, etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_random_letter", + "add_random_trailing_title" + ], + "rule_descriptions": { + "swap_random_letter": "Swap random adjacent letters", + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "mikayla hawkins", + "label": "negative", + "script": "latin" + }, + { + "name": "derrick friedman", + "label": "negative", + "script": "latin" + }, + { + "name": "georgina russell", + "label": "negative", + "script": "latin" + }, + { + "name": "vincent cook", + "label": "negative", + "script": "latin" + }, + { + "name": "rebecca stokes", + "label": "negative", + "script": "latin" + }, + { + "name": "laura wright", + "label": "negative", + "script": "latin" + }, + { + "name": "kayla curtis", + "label": "negative", + "script": "latin" + }, + { + "name": "linda barron", + "label": "negative", + "script": "latin" + }, + { + "name": "elliott johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "pamela todd", + "label": "negative", + "script": "latin" + }, + { + "name": "terry smith", + "label": "negative", + "script": "latin" + }, + { + "name": "andrew walker", + "label": "negative", + "script": "latin" + }, + { + "name": "richard wood", + "label": "negative", + "script": "latin" + }, + { + "name": "robin baker", + "label": "negative", + "script": "latin" + }, + { + "name": "kelly shaw", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove a random consonant, Add a title prefix (Mr., Dr., etc.), and Insert a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_consonant", + "add_random_leading_title", + "insert_random_letter" + ], + "rule_descriptions": { + "remove_random_consonant": "Remove a random consonant", + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)", + "insert_random_letter": "Insert a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "matthew carroll", + "label": "negative", + "script": "latin" + }, + { + "name": "gemma robinson", + "label": "negative", + "script": "latin" + }, + { + "name": "rebecca long", + "label": "negative", + "script": "latin" + }, + { + "name": "marcus torres", + "label": "negative", + "script": "latin" + }, + { + "name": "megan pittman", + "label": "negative", + "script": "latin" + }, + { + "name": "crystal ward", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffery robertson", + "label": "negative", + "script": "latin" + }, + { + "name": "gerald knight", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "erin shaw", + "label": "negative", + "script": "latin" + }, + { + "name": "michael dennis", + "label": "negative", + "script": "latin" + }, + { + "name": "heather wagner", + "label": "negative", + "script": "latin" + }, + { + "name": "natalie reilly", + "label": "negative", + "script": "latin" + }, + { + "name": "kayleigh dickinson", + "label": "negative", + "script": "latin" + }, + { + "name": "amy kelly", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Duplicate a random letter, Reorder name parts, and Swap adjacent consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "duplicate_random_letter_as_double_letter", + "name_parts_permutations", + "swap_adjacent_consonants" + ], + "rule_descriptions": { + "duplicate_random_letter_as_double_letter": "Duplicate a random letter", + "name_parts_permutations": "Reorder name parts", + "swap_adjacent_consonants": "Swap adjacent consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "stephen wood", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer barker", + "label": "negative", + "script": "latin" + }, + { + "name": "rhonda johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel chavez", + "label": "negative", + "script": "latin" + }, + { + "name": "michael barrett", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa stevens", + "label": "negative", + "script": "latin" + }, + { + "name": "abigail lambert", + "label": "negative", + "script": "latin" + }, + { + "name": "cody hernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "jake jefferson", + "label": "negative", + "script": "latin" + }, + { + "name": "shawn clay", + "label": "negative", + "script": "latin" + }, + { + "name": "vincent nichols", + "label": "negative", + "script": "latin" + }, + { + "name": "kirsty diaz", + "label": "negative", + "script": "latin" + }, + { + "name": "lindsey may", + "label": "negative", + "script": "latin" + }, + { + "name": "jenny greene", + "label": "negative", + "script": "latin" + }, + { + "name": "heather bush", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Replace random vowels with different vowels.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_vowel_with_random_vowel" + ], + "rule_descriptions": { + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "charles gilbert", + "label": "negative", + "script": "latin" + }, + { + "name": "michael brown", + "label": "negative", + "script": "latin" + }, + { + "name": "michael hart", + "label": "negative", + "script": "latin" + }, + { + "name": "michael gill", + "label": "negative", + "script": "latin" + }, + { + "name": "adrienne adams", + "label": "negative", + "script": "latin" + }, + { + "name": "patricia smith", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley robinson", + "label": "negative", + "script": "latin" + }, + { + "name": "jason burgess", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa cook", + "label": "negative", + "script": "latin" + }, + { + "name": "abigail mills", + "label": "negative", + "script": "latin" + }, + { + "name": "debra richardson", + "label": "negative", + "script": "latin" + }, + { + "name": "rebecca holland", + "label": "negative", + "script": "latin" + }, + { + "name": "marcus bibi", + "label": "negative", + "script": "latin" + }, + { + "name": "heather thompson", + "label": "negative", + "script": "latin" + }, + { + "name": "steven smith", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Delete a random letter, and Swap random adjacent letters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "delete_random_letter", + "swap_random_letter" + ], + "rule_descriptions": { + "delete_random_letter": "Delete a random letter", + "swap_random_letter": "Swap random adjacent letters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "glenn thompson", + "label": "negative", + "script": "latin" + }, + { + "name": "michael black", + "label": "negative", + "script": "latin" + }, + { + "name": "natalie wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "victoria chandler", + "label": "negative", + "script": "latin" + }, + { + "name": "kenneth combs", + "label": "negative", + "script": "latin" + }, + { + "name": "dawn hall", + "label": "negative", + "script": "latin" + }, + { + "name": "courtney burgess", + "label": "negative", + "script": "latin" + }, + { + "name": "gerard lee", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda clark", + "label": "negative", + "script": "latin" + }, + { + "name": "julie marquez", + "label": "negative", + "script": "latin" + }, + { + "name": "janet moore", + "label": "negative", + "script": "latin" + }, + { + "name": "laura townsend", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "max smith", + "label": "negative", + "script": "latin" + }, + { + "name": "diana gray", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Swap random adjacent letters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_random_letter" + ], + "rule_descriptions": { + "swap_random_letter": "Swap random adjacent letters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "joseph phillips", + "label": "negative", + "script": "latin" + }, + { + "name": "katherine brown", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel kerr", + "label": "negative", + "script": "latin" + }, + { + "name": "alan henderson", + "label": "negative", + "script": "latin" + }, + { + "name": "louis walton", + "label": "negative", + "script": "latin" + }, + { + "name": "steven fox", + "label": "negative", + "script": "latin" + }, + { + "name": "adam sosa", + "label": "negative", + "script": "latin" + }, + { + "name": "kimberly cook", + "label": "negative", + "script": "latin" + }, + { + "name": "caitlin willis", + "label": "negative", + "script": "latin" + }, + { + "name": "christina brewer", + "label": "negative", + "script": "latin" + }, + { + "name": "emily cole", + "label": "negative", + "script": "latin" + }, + { + "name": "stacey moran", + "label": "negative", + "script": "latin" + }, + { + "name": "marie ford", + "label": "negative", + "script": "latin" + }, + { + "name": "denise edwards", + "label": "negative", + "script": "latin" + }, + { + "name": "kathleen hart", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Abbreviate name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_abbreviations" + ], + "rule_descriptions": { + "shorten_name_to_abbreviations": "Abbreviate name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "patrick bates", + "label": "negative", + "script": "latin" + }, + { + "name": "joyce cruz", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah hubbard", + "label": "negative", + "script": "latin" + }, + { + "name": "brittany calderon", + "label": "negative", + "script": "latin" + }, + { + "name": "heather ramirez", + "label": "negative", + "script": "latin" + }, + { + "name": "norma gonzalez", + "label": "negative", + "script": "latin" + }, + { + "name": "hayley cobb", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy bennett", + "label": "negative", + "script": "latin" + }, + { + "name": "kimberly sampson", + "label": "negative", + "script": "latin" + }, + { + "name": "sean rowley", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua dalton", + "label": "negative", + "script": "latin" + }, + { + "name": "michael cooke", + "label": "negative", + "script": "latin" + }, + { + "name": "maria field", + "label": "negative", + "script": "latin" + }, + { + "name": "natasha martin", + "label": "negative", + "script": "latin" + }, + { + "name": "austin tran", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Remove all spaces.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_all_spaces" + ], + "rule_descriptions": { + "remove_all_spaces": "Remove all spaces" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "gabriel mckee", + "label": "negative", + "script": "latin" + }, + { + "name": "laura johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "tony randall", + "label": "negative", + "script": "latin" + }, + { + "name": "gregory doyle", + "label": "negative", + "script": "latin" + }, + { + "name": "laura fritz", + "label": "negative", + "script": "latin" + }, + { + "name": "kyle garrett", + "label": "negative", + "script": "latin" + }, + { + "name": "marcus johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "bryan clark", + "label": "negative", + "script": "latin" + }, + { + "name": "alyssa morgan", + "label": "negative", + "script": "latin" + }, + { + "name": "juan walker", + "label": "negative", + "script": "latin" + }, + { + "name": "shaun marks", + "label": "negative", + "script": "latin" + }, + { + "name": "rodney johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "miranda mcdaniel", + "label": "negative", + "script": "latin" + }, + { + "name": "joe turner", + "label": "negative", + "script": "latin" + }, + { + "name": "shannon taylor", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace spaces with special characters, and Replace double letters with a single letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_spaces_with_random_special_characters", + "replace_double_letters_with_single_letter" + ], + "rule_descriptions": { + "replace_spaces_with_random_special_characters": "Replace spaces with special characters", + "replace_double_letters_with_single_letter": "Replace double letters with a single letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "carol davies", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew ashley", + "label": "negative", + "script": "latin" + }, + { + "name": "michele martinez", + "label": "negative", + "script": "latin" + }, + { + "name": "andrew vance", + "label": "negative", + "script": "latin" + }, + { + "name": "connie wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "alex johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah arias", + "label": "negative", + "script": "latin" + }, + { + "name": "dale ramirez", + "label": "negative", + "script": "latin" + }, + { + "name": "alison schmidt", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer luna", + "label": "negative", + "script": "latin" + }, + { + "name": "rebecca jacobs", + "label": "negative", + "script": "latin" + }, + { + "name": "darren martin", + "label": "negative", + "script": "latin" + }, + { + "name": "victor stevens", + "label": "negative", + "script": "latin" + }, + { + "name": "richard ramirez", + "label": "negative", + "script": "latin" + }, + { + "name": "erin pickering", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Add a title prefix (Mr., Dr., etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_leading_title" + ], + "rule_descriptions": { + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "joyce martinez", + "label": "negative", + "script": "latin" + }, + { + "name": "david murphy", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah martin", + "label": "negative", + "script": "latin" + }, + { + "name": "frank travis", + "label": "negative", + "script": "latin" + }, + { + "name": "shawn smith", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah barr", + "label": "negative", + "script": "latin" + }, + { + "name": "benjamin robinson", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony marshall", + "label": "negative", + "script": "latin" + }, + { + "name": "karen miller", + "label": "negative", + "script": "latin" + }, + { + "name": "christine hall", + "label": "negative", + "script": "latin" + }, + { + "name": "steven medina", + "label": "negative", + "script": "latin" + }, + { + "name": "jake ramsey", + "label": "negative", + "script": "latin" + }, + { + "name": "allen moore", + "label": "negative", + "script": "latin" + }, + { + "name": "chad rowe", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony jackson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Use first name initial with last name.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "initial_only_first_name" + ], + "rule_descriptions": { + "initial_only_first_name": "Use first name initial with last name" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "helen schwartz", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffrey davis", + "label": "negative", + "script": "latin" + }, + { + "name": "damien smith", + "label": "negative", + "script": "latin" + }, + { + "name": "erika watson", + "label": "negative", + "script": "latin" + }, + { + "name": "katrina rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "joyce baxter", + "label": "negative", + "script": "latin" + }, + { + "name": "robert walker", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah butler", + "label": "negative", + "script": "latin" + }, + { + "name": "bethany barlow", + "label": "negative", + "script": "latin" + }, + { + "name": "robert reeves", + "label": "negative", + "script": "latin" + }, + { + "name": "charlene palmer", + "label": "negative", + "script": "latin" + }, + { + "name": "rhys robinson", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew thompson", + "label": "negative", + "script": "latin" + }, + { + "name": "kathy dickerson", + "label": "negative", + "script": "latin" + }, + { + "name": "abbie benson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove all spaces, Duplicate a random letter, and Swap random adjacent letters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_all_spaces", + "duplicate_random_letter_as_double_letter", + "swap_random_letter" + ], + "rule_descriptions": { + "remove_all_spaces": "Remove all spaces", + "duplicate_random_letter_as_double_letter": "Duplicate a random letter", + "swap_random_letter": "Swap random adjacent letters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "ryan johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "cody bond", + "label": "negative", + "script": "latin" + }, + { + "name": "julie walsh", + "label": "negative", + "script": "latin" + }, + { + "name": "lauren barnett", + "label": "negative", + "script": "latin" + }, + { + "name": "brad young", + "label": "negative", + "script": "latin" + }, + { + "name": "justin walton", + "label": "negative", + "script": "latin" + }, + { + "name": "rachel lewis", + "label": "negative", + "script": "latin" + }, + { + "name": "lindsey williams", + "label": "negative", + "script": "latin" + }, + { + "name": "graeme ward", + "label": "negative", + "script": "latin" + }, + { + "name": "sara johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "william wallis", + "label": "negative", + "script": "latin" + }, + { + "name": "jesus taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "julie sinclair", + "label": "negative", + "script": "latin" + }, + { + "name": "kenneth stevenson", + "label": "negative", + "script": "latin" + }, + { + "name": "allan miller", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Use first name initial with last name, and Remove all spaces.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "initial_only_first_name", + "remove_all_spaces" + ], + "rule_descriptions": { + "initial_only_first_name": "Use first name initial with last name", + "remove_all_spaces": "Remove all spaces" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "alison khan", + "label": "negative", + "script": "latin" + }, + { + "name": "ronald peterson", + "label": "negative", + "script": "latin" + }, + { + "name": "brandon hooper", + "label": "negative", + "script": "latin" + }, + { + "name": "christine odonnell", + "label": "negative", + "script": "latin" + }, + { + "name": "ian wright", + "label": "negative", + "script": "latin" + }, + { + "name": "janet shepard", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas powell", + "label": "negative", + "script": "latin" + }, + { + "name": "spencer hampton", + "label": "negative", + "script": "latin" + }, + { + "name": "richard moss", + "label": "negative", + "script": "latin" + }, + { + "name": "duncan cervantes", + "label": "negative", + "script": "latin" + }, + { + "name": "leah martinez", + "label": "negative", + "script": "latin" + }, + { + "name": "margaret williams", + "label": "negative", + "script": "latin" + }, + { + "name": "scott bird", + "label": "negative", + "script": "latin" + }, + { + "name": "evelyn cantrell", + "label": "negative", + "script": "latin" + }, + { + "name": "brian mccarthy", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Remove a random consonant.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_consonant" + ], + "rule_descriptions": { + "remove_random_consonant": "Remove a random consonant" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "jeffrey jones", + "label": "negative", + "script": "latin" + }, + { + "name": "nicholas shannon", + "label": "negative", + "script": "latin" + }, + { + "name": "mitchell lane", + "label": "negative", + "script": "latin" + }, + { + "name": "zachary smith", + "label": "negative", + "script": "latin" + }, + { + "name": "scott pena", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa douglas", + "label": "negative", + "script": "latin" + }, + { + "name": "melanie phillips", + "label": "negative", + "script": "latin" + }, + { + "name": "rebecca berry", + "label": "negative", + "script": "latin" + }, + { + "name": "carlos herrera", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel price", + "label": "negative", + "script": "latin" + }, + { + "name": "tina gray", + "label": "negative", + "script": "latin" + }, + { + "name": "raymond compton", + "label": "negative", + "script": "latin" + }, + { + "name": "rodney gentry", + "label": "negative", + "script": "latin" + }, + { + "name": "jacqueline meyers", + "label": "negative", + "script": "latin" + }, + { + "name": "erin pope", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Remove a random consonant.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_consonant" + ], + "rule_descriptions": { + "remove_random_consonant": "Remove a random consonant" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "shelley hodge", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole sherman", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica perez", + "label": "negative", + "script": "latin" + }, + { + "name": "ellie mckinney", + "label": "negative", + "script": "latin" + }, + { + "name": "kirsty wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "jamie hayes", + "label": "negative", + "script": "latin" + }, + { + "name": "steve pearson", + "label": "negative", + "script": "latin" + }, + { + "name": "mckenzie lucas", + "label": "negative", + "script": "latin" + }, + { + "name": "jacob white", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony blevins", + "label": "negative", + "script": "latin" + }, + { + "name": "kimberly lee", + "label": "negative", + "script": "latin" + }, + { + "name": "olivia smith", + "label": "negative", + "script": "latin" + }, + { + "name": "connie barton", + "label": "negative", + "script": "latin" + }, + { + "name": "geraldine clark", + "label": "negative", + "script": "latin" + }, + { + "name": "jerry hobbs", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Replace random vowels with different vowels.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_vowel_with_random_vowel" + ], + "rule_descriptions": { + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "monique wu", + "label": "negative", + "script": "latin" + }, + { + "name": "kayla jones", + "label": "negative", + "script": "latin" + }, + { + "name": "devon howarth", + "label": "negative", + "script": "latin" + }, + { + "name": "michael harris", + "label": "negative", + "script": "latin" + }, + { + "name": "pamela stone", + "label": "negative", + "script": "latin" + }, + { + "name": "abbie wright", + "label": "negative", + "script": "latin" + }, + { + "name": "dylan rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "jamie fields", + "label": "negative", + "script": "latin" + }, + { + "name": "courtney andrews", + "label": "negative", + "script": "latin" + }, + { + "name": "tanya ortiz", + "label": "negative", + "script": "latin" + }, + { + "name": "terry scott", + "label": "negative", + "script": "latin" + }, + { + "name": "crystal vincent", + "label": "negative", + "script": "latin" + }, + { + "name": "frederick kaur", + "label": "negative", + "script": "latin" + }, + { + "name": "cindy williams", + "label": "negative", + "script": "latin" + }, + { + "name": "steven wood", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Delete a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "delete_random_letter" + ], + "rule_descriptions": { + "delete_random_letter": "Delete a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "charles forbes", + "label": "negative", + "script": "latin" + }, + { + "name": "brenda smith", + "label": "negative", + "script": "latin" + }, + { + "name": "gerard kirk", + "label": "negative", + "script": "latin" + }, + { + "name": "susan washington", + "label": "negative", + "script": "latin" + }, + { + "name": "robert serrano", + "label": "negative", + "script": "latin" + }, + { + "name": "angela burch", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer moore", + "label": "negative", + "script": "latin" + }, + { + "name": "bryan gibson", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew field", + "label": "negative", + "script": "latin" + }, + { + "name": "robert holmes", + "label": "negative", + "script": "latin" + }, + { + "name": "emily lynn", + "label": "negative", + "script": "latin" + }, + { + "name": "ruth brown", + "label": "negative", + "script": "latin" + }, + { + "name": "tyler warren", + "label": "negative", + "script": "latin" + }, + { + "name": "denis diaz", + "label": "negative", + "script": "latin" + }, + { + "name": "sean mccarthy", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace spaces with special characters, and Swap random adjacent letters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_spaces_with_random_special_characters", + "swap_random_letter" + ], + "rule_descriptions": { + "replace_spaces_with_random_special_characters": "Replace spaces with special characters", + "swap_random_letter": "Swap random adjacent letters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "daniel dixon", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel diaz", + "label": "negative", + "script": "latin" + }, + { + "name": "grace hall", + "label": "negative", + "script": "latin" + }, + { + "name": "dean henson", + "label": "negative", + "script": "latin" + }, + { + "name": "charlene mcdonald", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher cooper", + "label": "negative", + "script": "latin" + }, + { + "name": "kathleen lane", + "label": "negative", + "script": "latin" + }, + { + "name": "john barry", + "label": "negative", + "script": "latin" + }, + { + "name": "edward bradley", + "label": "negative", + "script": "latin" + }, + { + "name": "samantha rogers", + "label": "negative", + "script": "latin" + }, + { + "name": "lindsey page", + "label": "negative", + "script": "latin" + }, + { + "name": "bradley gonzalez", + "label": "negative", + "script": "latin" + }, + { + "name": "jane holt", + "label": "negative", + "script": "latin" + }, + { + "name": "deanna smith", + "label": "negative", + "script": "latin" + }, + { + "name": "amber sanford", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Swap adjacent consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_consonants" + ], + "rule_descriptions": { + "swap_adjacent_consonants": "Swap adjacent consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "jessica lee", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda cruz", + "label": "negative", + "script": "latin" + }, + { + "name": "david ross", + "label": "negative", + "script": "latin" + }, + { + "name": "paul howard", + "label": "negative", + "script": "latin" + }, + { + "name": "james scott", + "label": "negative", + "script": "latin" + }, + { + "name": "brandon kim", + "label": "negative", + "script": "latin" + }, + { + "name": "marc fernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "jody austin", + "label": "negative", + "script": "latin" + }, + { + "name": "luke thomas", + "label": "negative", + "script": "latin" + }, + { + "name": "barbara lawson", + "label": "negative", + "script": "latin" + }, + { + "name": "mary cabrera", + "label": "negative", + "script": "latin" + }, + { + "name": "darrell taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "aaron frederick", + "label": "negative", + "script": "latin" + }, + { + "name": "sandra case", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph schroeder", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace random vowels with different vowels, Duplicate a random letter, and Swap adjacent syllables.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_vowel_with_random_vowel", + "duplicate_random_letter_as_double_letter", + "swap_adjacent_syllables" + ], + "rule_descriptions": { + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels", + "duplicate_random_letter_as_double_letter": "Duplicate a random letter", + "swap_adjacent_syllables": "Swap adjacent syllables" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "jay gibbs", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "morgan freeman", + "label": "negative", + "script": "latin" + }, + { + "name": "aaron williams", + "label": "negative", + "script": "latin" + }, + { + "name": "sylvia li", + "label": "negative", + "script": "latin" + }, + { + "name": "todd bailey", + "label": "negative", + "script": "latin" + }, + { + "name": "victoria hughes", + "label": "negative", + "script": "latin" + }, + { + "name": "brandon drake", + "label": "negative", + "script": "latin" + }, + { + "name": "victor anderson", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica baker", + "label": "negative", + "script": "latin" + }, + { + "name": "sally williams", + "label": "negative", + "script": "latin" + }, + { + "name": "ryan davis", + "label": "negative", + "script": "latin" + }, + { + "name": "michael parker", + "label": "negative", + "script": "latin" + }, + { + "name": "heather lewis", + "label": "negative", + "script": "latin" + }, + { + "name": "david moss", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Convert name to initials.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_initials" + ], + "rule_descriptions": { + "shorten_name_to_initials": "Convert name to initials" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "gordon bullock", + "label": "negative", + "script": "latin" + }, + { + "name": "angela smith", + "label": "negative", + "script": "latin" + }, + { + "name": "cynthia dixon", + "label": "negative", + "script": "latin" + }, + { + "name": "steven abbott", + "label": "negative", + "script": "latin" + }, + { + "name": "annette barnett", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffrey daniels", + "label": "negative", + "script": "latin" + }, + { + "name": "aaron fox", + "label": "negative", + "script": "latin" + }, + { + "name": "amber proctor", + "label": "negative", + "script": "latin" + }, + { + "name": "travis young", + "label": "negative", + "script": "latin" + }, + { + "name": "valerie brown", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa williams", + "label": "negative", + "script": "latin" + }, + { + "name": "hannah greene", + "label": "negative", + "script": "latin" + }, + { + "name": "jason jenkins", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher gonzales", + "label": "negative", + "script": "latin" + }, + { + "name": "jeremy morrison", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Swap adjacent consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_consonants" + ], + "rule_descriptions": { + "swap_adjacent_consonants": "Swap adjacent consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "rita sandoval", + "label": "negative", + "script": "latin" + }, + { + "name": "mary watkins", + "label": "negative", + "script": "latin" + }, + { + "name": "alan holden", + "label": "negative", + "script": "latin" + }, + { + "name": "iain ball", + "label": "negative", + "script": "latin" + }, + { + "name": "alison mata", + "label": "negative", + "script": "latin" + }, + { + "name": "philip horn", + "label": "negative", + "script": "latin" + }, + { + "name": "kenneth riley", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda simpson", + "label": "negative", + "script": "latin" + }, + { + "name": "jonathan benson", + "label": "negative", + "script": "latin" + }, + { + "name": "tammy brown", + "label": "negative", + "script": "latin" + }, + { + "name": "geoffrey dunn", + "label": "negative", + "script": "latin" + }, + { + "name": "monica martin", + "label": "negative", + "script": "latin" + }, + { + "name": "michael hicks", + "label": "negative", + "script": "latin" + }, + { + "name": "denise lopez", + "label": "negative", + "script": "latin" + }, + { + "name": "kristin young", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title prefix (Mr., Dr., etc.), and Remove all spaces.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_leading_title", + "remove_all_spaces" + ], + "rule_descriptions": { + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)", + "remove_all_spaces": "Remove all spaces" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "kelly dyer", + "label": "negative", + "script": "latin" + }, + { + "name": "alison pickering", + "label": "negative", + "script": "latin" + }, + { + "name": "elizabeth fox", + "label": "negative", + "script": "latin" + }, + { + "name": "shannon brock", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph patel", + "label": "negative", + "script": "latin" + }, + { + "name": "james wheeler", + "label": "negative", + "script": "latin" + }, + { + "name": "michael spencer", + "label": "negative", + "script": "latin" + }, + { + "name": "willie bowman", + "label": "negative", + "script": "latin" + }, + { + "name": "sally fox", + "label": "negative", + "script": "latin" + }, + { + "name": "antony bryant", + "label": "negative", + "script": "latin" + }, + { + "name": "louis holland", + "label": "negative", + "script": "latin" + }, + { + "name": "april murphy", + "label": "negative", + "script": "latin" + }, + { + "name": "patricia winters", + "label": "negative", + "script": "latin" + }, + { + "name": "danielle navarro", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Use first name initial with last name, and Replace random vowels with different vowels.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "initial_only_first_name", + "replace_random_vowel_with_random_vowel" + ], + "rule_descriptions": { + "initial_only_first_name": "Use first name initial with last name", + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "lawrence burns", + "label": "negative", + "script": "latin" + }, + { + "name": "kenneth bennett", + "label": "negative", + "script": "latin" + }, + { + "name": "cindy casey", + "label": "negative", + "script": "latin" + }, + { + "name": "patricia brooks", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica fisher", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher lopez", + "label": "negative", + "script": "latin" + }, + { + "name": "pamela nelson", + "label": "negative", + "script": "latin" + }, + { + "name": "brian ahmed", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy nicholson", + "label": "negative", + "script": "latin" + }, + { + "name": "dennis henderson", + "label": "negative", + "script": "latin" + }, + { + "name": "jeremy myers", + "label": "negative", + "script": "latin" + }, + { + "name": "natalie bauer", + "label": "negative", + "script": "latin" + }, + { + "name": "lee woods", + "label": "negative", + "script": "latin" + }, + { + "name": "theresa ray", + "label": "negative", + "script": "latin" + }, + { + "name": "eric wilson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Use first name initial with last name.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "initial_only_first_name" + ], + "rule_descriptions": { + "initial_only_first_name": "Use first name initial with last name" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "elizabeth silva", + "label": "negative", + "script": "latin" + }, + { + "name": "claire burgess", + "label": "negative", + "script": "latin" + }, + { + "name": "heather jones", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffrey gonzalez", + "label": "negative", + "script": "latin" + }, + { + "name": "eric bell", + "label": "negative", + "script": "latin" + }, + { + "name": "william whitehead", + "label": "negative", + "script": "latin" + }, + { + "name": "jason reed", + "label": "negative", + "script": "latin" + }, + { + "name": "carolyn mcgee", + "label": "negative", + "script": "latin" + }, + { + "name": "mary stout", + "label": "negative", + "script": "latin" + }, + { + "name": "kara sanchez", + "label": "negative", + "script": "latin" + }, + { + "name": "georgina thompson", + "label": "negative", + "script": "latin" + }, + { + "name": "jacqueline nguyen", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas brown", + "label": "negative", + "script": "latin" + }, + { + "name": "josh martinez", + "label": "negative", + "script": "latin" + }, + { + "name": "theresa barber", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Abbreviate name parts, Remove a random vowel, and Replace random consonants with different consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_abbreviations", + "remove_random_vowel", + "replace_random_consonant_with_random_consonant" + ], + "rule_descriptions": { + "shorten_name_to_abbreviations": "Abbreviate name parts", + "remove_random_vowel": "Remove a random vowel", + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "anne rowe", + "label": "negative", + "script": "latin" + }, + { + "name": "elizabeth sullivan", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda thornton", + "label": "negative", + "script": "latin" + }, + { + "name": "jared rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "kyle bruce", + "label": "negative", + "script": "latin" + }, + { + "name": "karen wong", + "label": "negative", + "script": "latin" + }, + { + "name": "deborah cross", + "label": "negative", + "script": "latin" + }, + { + "name": "kimberly johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "robert smith", + "label": "negative", + "script": "latin" + }, + { + "name": "michael barlow", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher heath", + "label": "negative", + "script": "latin" + }, + { + "name": "james larsen", + "label": "negative", + "script": "latin" + }, + { + "name": "jack ayala", + "label": "negative", + "script": "latin" + }, + { + "name": "zoe johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "eric kim", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Delete a random letter, Duplicate a random letter, and Add a title suffix (Jr., PhD, etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "delete_random_letter", + "duplicate_random_letter_as_double_letter", + "add_random_trailing_title" + ], + "rule_descriptions": { + "delete_random_letter": "Delete a random letter", + "duplicate_random_letter_as_double_letter": "Duplicate a random letter", + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "david sosa", + "label": "negative", + "script": "latin" + }, + { + "name": "charles stephens", + "label": "negative", + "script": "latin" + }, + { + "name": "tracie carter", + "label": "negative", + "script": "latin" + }, + { + "name": "scott rose", + "label": "negative", + "script": "latin" + }, + { + "name": "karen murphy", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher martin", + "label": "negative", + "script": "latin" + }, + { + "name": "scott jones", + "label": "negative", + "script": "latin" + }, + { + "name": "garrett miller", + "label": "negative", + "script": "latin" + }, + { + "name": "annette johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "aaron shaffer", + "label": "negative", + "script": "latin" + }, + { + "name": "lucy garrett", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah harrison", + "label": "negative", + "script": "latin" + }, + { + "name": "gail farley", + "label": "negative", + "script": "latin" + }, + { + "name": "reece brown", + "label": "negative", + "script": "latin" + }, + { + "name": "charles smith", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Abbreviate name parts, Convert name to initials, and Replace random vowels with different vowels.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_abbreviations", + "shorten_name_to_initials", + "replace_random_vowel_with_random_vowel" + ], + "rule_descriptions": { + "shorten_name_to_abbreviations": "Abbreviate name parts", + "shorten_name_to_initials": "Convert name to initials", + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "louis stewart", + "label": "negative", + "script": "latin" + }, + { + "name": "angela taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "jacob preston", + "label": "negative", + "script": "latin" + }, + { + "name": "brenda cooley", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua cox", + "label": "negative", + "script": "latin" + }, + { + "name": "jordan bell", + "label": "negative", + "script": "latin" + }, + { + "name": "erik smith", + "label": "negative", + "script": "latin" + }, + { + "name": "clive hughes", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffrey smith", + "label": "negative", + "script": "latin" + }, + { + "name": "bradley watts", + "label": "negative", + "script": "latin" + }, + { + "name": "theresa sharpe", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew garcia", + "label": "negative", + "script": "latin" + }, + { + "name": "chris patel", + "label": "negative", + "script": "latin" + }, + { + "name": "barbara mccoy", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle diaz", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Abbreviate name parts, Swap adjacent syllables, and Convert name to initials.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_abbreviations", + "swap_adjacent_syllables", + "shorten_name_to_initials" + ], + "rule_descriptions": { + "shorten_name_to_abbreviations": "Abbreviate name parts", + "swap_adjacent_syllables": "Swap adjacent syllables", + "shorten_name_to_initials": "Convert name to initials" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "valerie ward", + "label": "negative", + "script": "latin" + }, + { + "name": "jose maldonado", + "label": "negative", + "script": "latin" + }, + { + "name": "julie hodges", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua rogers", + "label": "negative", + "script": "latin" + }, + { + "name": "kristina reed", + "label": "negative", + "script": "latin" + }, + { + "name": "andrew morgan", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "charles russell", + "label": "negative", + "script": "latin" + }, + { + "name": "maria sellers", + "label": "negative", + "script": "latin" + }, + { + "name": "pamela waters", + "label": "negative", + "script": "latin" + }, + { + "name": "cheryl winters", + "label": "negative", + "script": "latin" + }, + { + "name": "roger flores", + "label": "negative", + "script": "latin" + }, + { + "name": "brandon jones", + "label": "negative", + "script": "latin" + }, + { + "name": "debra moss", + "label": "negative", + "script": "latin" + }, + { + "name": "jacqueline savage", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace spaces with special characters, and Abbreviate name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_spaces_with_random_special_characters", + "shorten_name_to_abbreviations" + ], + "rule_descriptions": { + "replace_spaces_with_random_special_characters": "Replace spaces with special characters", + "shorten_name_to_abbreviations": "Abbreviate name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "susan hansen", + "label": "negative", + "script": "latin" + }, + { + "name": "geraldine stevens", + "label": "negative", + "script": "latin" + }, + { + "name": "james taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "michael bailey", + "label": "negative", + "script": "latin" + }, + { + "name": "victoria wright", + "label": "negative", + "script": "latin" + }, + { + "name": "janet whitehouse", + "label": "negative", + "script": "latin" + }, + { + "name": "david davies", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin hernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "michael massey", + "label": "negative", + "script": "latin" + }, + { + "name": "sheila giles", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffery nunez", + "label": "negative", + "script": "latin" + }, + { + "name": "april atkinson", + "label": "negative", + "script": "latin" + }, + { + "name": "victoria stuart", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffrey rogers", + "label": "negative", + "script": "latin" + }, + { + "name": "adrian williams", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace spaces with special characters, and Delete a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_spaces_with_random_special_characters", + "delete_random_letter" + ], + "rule_descriptions": { + "replace_spaces_with_random_special_characters": "Replace spaces with special characters", + "delete_random_letter": "Delete a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "anthony wood", + "label": "negative", + "script": "latin" + }, + { + "name": "stanley oconnell", + "label": "negative", + "script": "latin" + }, + { + "name": "harry stone", + "label": "negative", + "script": "latin" + }, + { + "name": "brenda hughes", + "label": "negative", + "script": "latin" + }, + { + "name": "michael andrews", + "label": "negative", + "script": "latin" + }, + { + "name": "tyler taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "johnny moore", + "label": "negative", + "script": "latin" + }, + { + "name": "stephen watts", + "label": "negative", + "script": "latin" + }, + { + "name": "jamie kerr", + "label": "negative", + "script": "latin" + }, + { + "name": "christina jackson", + "label": "negative", + "script": "latin" + }, + { + "name": "bernard ryan", + "label": "negative", + "script": "latin" + }, + { + "name": "tracy baker", + "label": "negative", + "script": "latin" + }, + { + "name": "james peterson", + "label": "negative", + "script": "latin" + }, + { + "name": "dustin bowen", + "label": "negative", + "script": "latin" + }, + { + "name": "jason gonzalez", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Insert a random letter, Replace random consonants with different consonants, and Remove a random consonant.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "insert_random_letter", + "replace_random_consonant_with_random_consonant", + "remove_random_consonant" + ], + "rule_descriptions": { + "insert_random_letter": "Insert a random letter", + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants", + "remove_random_consonant": "Remove a random consonant" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "james davila", + "label": "negative", + "script": "latin" + }, + { + "name": "gerard martin", + "label": "negative", + "script": "latin" + }, + { + "name": "valerie saunders", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew wheeler", + "label": "negative", + "script": "latin" + }, + { + "name": "hazel oneal", + "label": "negative", + "script": "latin" + }, + { + "name": "heidi powell", + "label": "negative", + "script": "latin" + }, + { + "name": "william bryant", + "label": "negative", + "script": "latin" + }, + { + "name": "william garcia", + "label": "negative", + "script": "latin" + }, + { + "name": "natalie graham", + "label": "negative", + "script": "latin" + }, + { + "name": "samuel smith", + "label": "negative", + "script": "latin" + }, + { + "name": "justin lawson", + "label": "negative", + "script": "latin" + }, + { + "name": "rachel cross", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer martin", + "label": "negative", + "script": "latin" + }, + { + "name": "emily green", + "label": "negative", + "script": "latin" + }, + { + "name": "cassidy ahmed", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Swap random adjacent letters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_random_letter" + ], + "rule_descriptions": { + "swap_random_letter": "Swap random adjacent letters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "shannon mccarthy", + "label": "negative", + "script": "latin" + }, + { + "name": "aaron brown", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica hudson", + "label": "negative", + "script": "latin" + }, + { + "name": "jesse mitchell", + "label": "negative", + "script": "latin" + }, + { + "name": "dale vasquez", + "label": "negative", + "script": "latin" + }, + { + "name": "robert smith", + "label": "negative", + "script": "latin" + }, + { + "name": "brian diaz", + "label": "negative", + "script": "latin" + }, + { + "name": "holly solomon", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie gutierrez", + "label": "negative", + "script": "latin" + }, + { + "name": "kimberly gallagher", + "label": "negative", + "script": "latin" + }, + { + "name": "julie west", + "label": "negative", + "script": "latin" + }, + { + "name": "brian rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffery pacheco", + "label": "negative", + "script": "latin" + }, + { + "name": "heather lopez", + "label": "negative", + "script": "latin" + }, + { + "name": "patrick barker", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Duplicate a random letter, and Remove a random consonant.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "duplicate_random_letter_as_double_letter", + "remove_random_consonant" + ], + "rule_descriptions": { + "duplicate_random_letter_as_double_letter": "Duplicate a random letter", + "remove_random_consonant": "Remove a random consonant" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "kimberly morgan", + "label": "negative", + "script": "latin" + }, + { + "name": "maria smith", + "label": "negative", + "script": "latin" + }, + { + "name": "brandi powell", + "label": "negative", + "script": "latin" + }, + { + "name": "derek hampton", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony valenzuela", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole baker", + "label": "negative", + "script": "latin" + }, + { + "name": "carole lopez", + "label": "negative", + "script": "latin" + }, + { + "name": "edward lynn", + "label": "negative", + "script": "latin" + }, + { + "name": "deborah gomez", + "label": "negative", + "script": "latin" + }, + { + "name": "brian black", + "label": "negative", + "script": "latin" + }, + { + "name": "erin camacho", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa chambers", + "label": "negative", + "script": "latin" + }, + { + "name": "dennis stewart", + "label": "negative", + "script": "latin" + }, + { + "name": "shannon jones", + "label": "negative", + "script": "latin" + }, + { + "name": "dawn lambert", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove a random consonant, and Remove all spaces.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_consonant", + "remove_all_spaces" + ], + "rule_descriptions": { + "remove_random_consonant": "Remove a random consonant", + "remove_all_spaces": "Remove all spaces" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "seth rasmussen", + "label": "negative", + "script": "latin" + }, + { + "name": "joel holland", + "label": "negative", + "script": "latin" + }, + { + "name": "victoria miller", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer hernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "sydney powers", + "label": "negative", + "script": "latin" + }, + { + "name": "teresa molina", + "label": "negative", + "script": "latin" + }, + { + "name": "trevor mccormick", + "label": "negative", + "script": "latin" + }, + { + "name": "sara garza", + "label": "negative", + "script": "latin" + }, + { + "name": "caitlin clements", + "label": "negative", + "script": "latin" + }, + { + "name": "leslie goddard", + "label": "negative", + "script": "latin" + }, + { + "name": "ronald castillo", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua norton", + "label": "negative", + "script": "latin" + }, + { + "name": "francis cooper", + "label": "negative", + "script": "latin" + }, + { + "name": "hilary golden", + "label": "negative", + "script": "latin" + }, + { + "name": "malcolm goodman", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Abbreviate name parts, Remove all spaces, and Delete a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_abbreviations", + "remove_all_spaces", + "delete_random_letter" + ], + "rule_descriptions": { + "shorten_name_to_abbreviations": "Abbreviate name parts", + "remove_all_spaces": "Remove all spaces", + "delete_random_letter": "Delete a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "kara long", + "label": "negative", + "script": "latin" + }, + { + "name": "nancy gomez", + "label": "negative", + "script": "latin" + }, + { + "name": "dawn hubbard", + "label": "negative", + "script": "latin" + }, + { + "name": "kayla jones", + "label": "negative", + "script": "latin" + }, + { + "name": "russell thomas", + "label": "negative", + "script": "latin" + }, + { + "name": "james durham", + "label": "negative", + "script": "latin" + }, + { + "name": "frederick duran", + "label": "negative", + "script": "latin" + }, + { + "name": "robert hickman", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer walters", + "label": "negative", + "script": "latin" + }, + { + "name": "brittany frazier", + "label": "negative", + "script": "latin" + }, + { + "name": "shirley donovan", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "frank kim", + "label": "negative", + "script": "latin" + }, + { + "name": "john navarro", + "label": "negative", + "script": "latin" + }, + { + "name": "frances reed", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title suffix (Jr., PhD, etc.), and Use first name initial with last name.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_trailing_title", + "initial_only_first_name" + ], + "rule_descriptions": { + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)", + "initial_only_first_name": "Use first name initial with last name" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "judy ibarra", + "label": "negative", + "script": "latin" + }, + { + "name": "anna adams", + "label": "negative", + "script": "latin" + }, + { + "name": "sharon murphy", + "label": "negative", + "script": "latin" + }, + { + "name": "kyle gordon", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah martinez", + "label": "negative", + "script": "latin" + }, + { + "name": "tina robinson", + "label": "negative", + "script": "latin" + }, + { + "name": "kimberly lucas", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "clive smith", + "label": "negative", + "script": "latin" + }, + { + "name": "elliott ruiz", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas williams", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin kim", + "label": "negative", + "script": "latin" + }, + { + "name": "danny reese", + "label": "negative", + "script": "latin" + }, + { + "name": "chase lee", + "label": "negative", + "script": "latin" + }, + { + "name": "darren parks", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove all spaces, Replace random consonants with different consonants, and Swap random adjacent letters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_all_spaces", + "replace_random_consonant_with_random_consonant", + "swap_random_letter" + ], + "rule_descriptions": { + "remove_all_spaces": "Remove all spaces", + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants", + "swap_random_letter": "Swap random adjacent letters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "amber thornton", + "label": "negative", + "script": "latin" + }, + { + "name": "kyle chambers", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa flowers", + "label": "negative", + "script": "latin" + }, + { + "name": "vincent chase", + "label": "negative", + "script": "latin" + }, + { + "name": "anna john", + "label": "negative", + "script": "latin" + }, + { + "name": "david pruitt", + "label": "negative", + "script": "latin" + }, + { + "name": "michael miller", + "label": "negative", + "script": "latin" + }, + { + "name": "marcus johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "justin rivera", + "label": "negative", + "script": "latin" + }, + { + "name": "sydney watkins", + "label": "negative", + "script": "latin" + }, + { + "name": "troy grant", + "label": "negative", + "script": "latin" + }, + { + "name": "pamela brown", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa garner", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda choi", + "label": "negative", + "script": "latin" + }, + { + "name": "rosemary smith", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title suffix (Jr., PhD, etc.), Reorder name parts, and Swap adjacent consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_trailing_title", + "name_parts_permutations", + "swap_adjacent_consonants" + ], + "rule_descriptions": { + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)", + "name_parts_permutations": "Reorder name parts", + "swap_adjacent_consonants": "Swap adjacent consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "cheryl cain", + "label": "negative", + "script": "latin" + }, + { + "name": "nicholas burke", + "label": "negative", + "script": "latin" + }, + { + "name": "nancy collins", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa stevenson", + "label": "negative", + "script": "latin" + }, + { + "name": "shannon villa", + "label": "negative", + "script": "latin" + }, + { + "name": "paige salas", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa ortiz", + "label": "negative", + "script": "latin" + }, + { + "name": "bradley hughes", + "label": "negative", + "script": "latin" + }, + { + "name": "brenda powers", + "label": "negative", + "script": "latin" + }, + { + "name": "heather yates", + "label": "negative", + "script": "latin" + }, + { + "name": "virginia lewis", + "label": "negative", + "script": "latin" + }, + { + "name": "tracey chapman", + "label": "negative", + "script": "latin" + }, + { + "name": "steve harper", + "label": "negative", + "script": "latin" + }, + { + "name": "denis cunningham", + "label": "negative", + "script": "latin" + }, + { + "name": "jason white", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Swap adjacent consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_consonants" + ], + "rule_descriptions": { + "swap_adjacent_consonants": "Swap adjacent consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "cynthia cross", + "label": "negative", + "script": "latin" + }, + { + "name": "anna davies", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffrey wu", + "label": "negative", + "script": "latin" + }, + { + "name": "joe tucker", + "label": "negative", + "script": "latin" + }, + { + "name": "katherine foster", + "label": "negative", + "script": "latin" + }, + { + "name": "hannah bowen", + "label": "negative", + "script": "latin" + }, + { + "name": "michael garner", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley phillips", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley brown", + "label": "negative", + "script": "latin" + }, + { + "name": "andrea moore", + "label": "negative", + "script": "latin" + }, + { + "name": "isaiah gonzalez", + "label": "negative", + "script": "latin" + }, + { + "name": "erica wood", + "label": "negative", + "script": "latin" + }, + { + "name": "leanne baker", + "label": "negative", + "script": "latin" + }, + { + "name": "shane washington", + "label": "negative", + "script": "latin" + }, + { + "name": "kim johnson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove a random vowel, Replace spaces with special characters, and Duplicate a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_vowel", + "replace_spaces_with_random_special_characters", + "duplicate_random_letter_as_double_letter" + ], + "rule_descriptions": { + "remove_random_vowel": "Remove a random vowel", + "replace_spaces_with_random_special_characters": "Replace spaces with special characters", + "duplicate_random_letter_as_double_letter": "Duplicate a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "david moore", + "label": "negative", + "script": "latin" + }, + { + "name": "richard johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "michele rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "valerie davies", + "label": "negative", + "script": "latin" + }, + { + "name": "alexandra smith", + "label": "negative", + "script": "latin" + }, + { + "name": "marc brown", + "label": "negative", + "script": "latin" + }, + { + "name": "bernard leon", + "label": "negative", + "script": "latin" + }, + { + "name": "jackie buckley", + "label": "negative", + "script": "latin" + }, + { + "name": "laura alvarez", + "label": "negative", + "script": "latin" + }, + { + "name": "andrew young", + "label": "negative", + "script": "latin" + }, + { + "name": "rachel savage", + "label": "negative", + "script": "latin" + }, + { + "name": "charles james", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda campbell", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer cooke", + "label": "negative", + "script": "latin" + }, + { + "name": "allan woodward", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove a random vowel, Abbreviate name parts, and Swap adjacent syllables.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_vowel", + "shorten_name_to_abbreviations", + "swap_adjacent_syllables" + ], + "rule_descriptions": { + "remove_random_vowel": "Remove a random vowel", + "shorten_name_to_abbreviations": "Abbreviate name parts", + "swap_adjacent_syllables": "Swap adjacent syllables" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "stuart jones", + "label": "negative", + "script": "latin" + }, + { + "name": "teresa mccoy", + "label": "negative", + "script": "latin" + }, + { + "name": "christine mccarthy", + "label": "negative", + "script": "latin" + }, + { + "name": "marissa hunt", + "label": "negative", + "script": "latin" + }, + { + "name": "guy mcgee", + "label": "negative", + "script": "latin" + }, + { + "name": "lee lane", + "label": "negative", + "script": "latin" + }, + { + "name": "nathan nelson", + "label": "negative", + "script": "latin" + }, + { + "name": "hector barnes", + "label": "negative", + "script": "latin" + }, + { + "name": "chad tucker", + "label": "negative", + "script": "latin" + }, + { + "name": "dave williams", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy hunt", + "label": "negative", + "script": "latin" + }, + { + "name": "shannon reynolds", + "label": "negative", + "script": "latin" + }, + { + "name": "aaron shea", + "label": "negative", + "script": "latin" + }, + { + "name": "jason martinez", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph phillips", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Swap random adjacent letters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_random_letter" + ], + "rule_descriptions": { + "swap_random_letter": "Swap random adjacent letters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "erik rogers", + "label": "negative", + "script": "latin" + }, + { + "name": "amy hamilton", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua abbott", + "label": "negative", + "script": "latin" + }, + { + "name": "charlie griffiths", + "label": "negative", + "script": "latin" + }, + { + "name": "amy mitchell", + "label": "negative", + "script": "latin" + }, + { + "name": "victoria smith", + "label": "negative", + "script": "latin" + }, + { + "name": "wayne mckinney", + "label": "negative", + "script": "latin" + }, + { + "name": "cathy kim", + "label": "negative", + "script": "latin" + }, + { + "name": "tyler valdez", + "label": "negative", + "script": "latin" + }, + { + "name": "debra knox", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley pham", + "label": "negative", + "script": "latin" + }, + { + "name": "alejandro swanson", + "label": "negative", + "script": "latin" + }, + { + "name": "rachel butler", + "label": "negative", + "script": "latin" + }, + { + "name": "kathleen smith", + "label": "negative", + "script": "latin" + }, + { + "name": "kathryn armstrong", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap random adjacent letters, Remove a random consonant, and Replace random vowels with different vowels.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_random_letter", + "remove_random_consonant", + "replace_random_vowel_with_random_vowel" + ], + "rule_descriptions": { + "swap_random_letter": "Swap random adjacent letters", + "remove_random_consonant": "Remove a random consonant", + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "hollie jones", + "label": "negative", + "script": "latin" + }, + { + "name": "patrick vasquez", + "label": "negative", + "script": "latin" + }, + { + "name": "brian smith", + "label": "negative", + "script": "latin" + }, + { + "name": "nicholas cross", + "label": "negative", + "script": "latin" + }, + { + "name": "cynthia lam", + "label": "negative", + "script": "latin" + }, + { + "name": "monica patterson", + "label": "negative", + "script": "latin" + }, + { + "name": "john jenkins", + "label": "negative", + "script": "latin" + }, + { + "name": "abigail knight", + "label": "negative", + "script": "latin" + }, + { + "name": "catherine heath", + "label": "negative", + "script": "latin" + }, + { + "name": "mitchell harding", + "label": "negative", + "script": "latin" + }, + { + "name": "frederick newton", + "label": "negative", + "script": "latin" + }, + { + "name": "blake fox", + "label": "negative", + "script": "latin" + }, + { + "name": "lucas williams", + "label": "negative", + "script": "latin" + }, + { + "name": "benjamin foley", + "label": "negative", + "script": "latin" + }, + { + "name": "stacey miah", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove a random vowel, and Insert a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_vowel", + "insert_random_letter" + ], + "rule_descriptions": { + "remove_random_vowel": "Remove a random vowel", + "insert_random_letter": "Insert a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "matthew reid", + "label": "negative", + "script": "latin" + }, + { + "name": "james butler", + "label": "negative", + "script": "latin" + }, + { + "name": "jonathan hall", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley graham", + "label": "negative", + "script": "latin" + }, + { + "name": "alicia shannon", + "label": "negative", + "script": "latin" + }, + { + "name": "jordan morris", + "label": "negative", + "script": "latin" + }, + { + "name": "jasmin lee", + "label": "negative", + "script": "latin" + }, + { + "name": "jason russell", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "eric williams", + "label": "negative", + "script": "latin" + }, + { + "name": "jonathan wheeler", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie thomas", + "label": "negative", + "script": "latin" + }, + { + "name": "norman ahmed", + "label": "negative", + "script": "latin" + }, + { + "name": "dalton ray", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley fox", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Duplicate a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "duplicate_random_letter_as_double_letter" + ], + "rule_descriptions": { + "duplicate_random_letter_as_double_letter": "Duplicate a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "kara jordan", + "label": "negative", + "script": "latin" + }, + { + "name": "micheal diaz", + "label": "negative", + "script": "latin" + }, + { + "name": "joe reed", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer farmer", + "label": "negative", + "script": "latin" + }, + { + "name": "jean jackson", + "label": "negative", + "script": "latin" + }, + { + "name": "christine hughes", + "label": "negative", + "script": "latin" + }, + { + "name": "jordan lawrence", + "label": "negative", + "script": "latin" + }, + { + "name": "christina keller", + "label": "negative", + "script": "latin" + }, + { + "name": "alec durham", + "label": "negative", + "script": "latin" + }, + { + "name": "guy hansen", + "label": "negative", + "script": "latin" + }, + { + "name": "billy flores", + "label": "negative", + "script": "latin" + }, + { + "name": "catherine miller", + "label": "negative", + "script": "latin" + }, + { + "name": "jasmine green", + "label": "negative", + "script": "latin" + }, + { + "name": "brianna williams", + "label": "negative", + "script": "latin" + }, + { + "name": "kimberley smith", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Replace random vowels with different vowels.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_vowel_with_random_vowel" + ], + "rule_descriptions": { + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "aaron scott", + "label": "negative", + "script": "latin" + }, + { + "name": "heather robinson", + "label": "negative", + "script": "latin" + }, + { + "name": "andrew bailey", + "label": "negative", + "script": "latin" + }, + { + "name": "eric leach", + "label": "negative", + "script": "latin" + }, + { + "name": "jason sykes", + "label": "negative", + "script": "latin" + }, + { + "name": "leah green", + "label": "negative", + "script": "latin" + }, + { + "name": "lauren chapman", + "label": "negative", + "script": "latin" + }, + { + "name": "denise adams", + "label": "negative", + "script": "latin" + }, + { + "name": "samantha duran", + "label": "negative", + "script": "latin" + }, + { + "name": "cheryl tucker", + "label": "negative", + "script": "latin" + }, + { + "name": "mario walker", + "label": "negative", + "script": "latin" + }, + { + "name": "sheila garcia", + "label": "negative", + "script": "latin" + }, + { + "name": "rhys savage", + "label": "negative", + "script": "latin" + }, + { + "name": "laura lee", + "label": "negative", + "script": "latin" + }, + { + "name": "angela miller", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Reorder name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "name_parts_permutations" + ], + "rule_descriptions": { + "name_parts_permutations": "Reorder name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "billy hebert", + "label": "negative", + "script": "latin" + }, + { + "name": "phillip chandler", + "label": "negative", + "script": "latin" + }, + { + "name": "whitney moore", + "label": "negative", + "script": "latin" + }, + { + "name": "danielle winter", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda davies", + "label": "negative", + "script": "latin" + }, + { + "name": "caleb perez", + "label": "negative", + "script": "latin" + }, + { + "name": "veronica reeves", + "label": "negative", + "script": "latin" + }, + { + "name": "samuel norman", + "label": "negative", + "script": "latin" + }, + { + "name": "kimberly townsend", + "label": "negative", + "script": "latin" + }, + { + "name": "david morales", + "label": "negative", + "script": "latin" + }, + { + "name": "maria jones", + "label": "negative", + "script": "latin" + }, + { + "name": "brenda carson", + "label": "negative", + "script": "latin" + }, + { + "name": "edwin gonzalez", + "label": "negative", + "script": "latin" + }, + { + "name": "edward reid", + "label": "negative", + "script": "latin" + }, + { + "name": "danny gardner", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace random consonants with different consonants, and Swap adjacent consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_consonant_with_random_consonant", + "swap_adjacent_consonants" + ], + "rule_descriptions": { + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants", + "swap_adjacent_consonants": "Swap adjacent consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "kevin powers", + "label": "negative", + "script": "latin" + }, + { + "name": "sean smith", + "label": "negative", + "script": "latin" + }, + { + "name": "karen williams", + "label": "negative", + "script": "latin" + }, + { + "name": "walter davies", + "label": "negative", + "script": "latin" + }, + { + "name": "monique rivera", + "label": "negative", + "script": "latin" + }, + { + "name": "laura gutierrez", + "label": "negative", + "script": "latin" + }, + { + "name": "antony barton", + "label": "negative", + "script": "latin" + }, + { + "name": "douglas pugh", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph matthews", + "label": "negative", + "script": "latin" + }, + { + "name": "sean frey", + "label": "negative", + "script": "latin" + }, + { + "name": "kathleen steele", + "label": "negative", + "script": "latin" + }, + { + "name": "allison newman", + "label": "negative", + "script": "latin" + }, + { + "name": "douglas carrillo", + "label": "negative", + "script": "latin" + }, + { + "name": "robert davis", + "label": "negative", + "script": "latin" + }, + { + "name": "scott berry", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Use first name initial with last name, and Insert a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "initial_only_first_name", + "insert_random_letter" + ], + "rule_descriptions": { + "initial_only_first_name": "Use first name initial with last name", + "insert_random_letter": "Insert a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "neil johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "eduardo young", + "label": "negative", + "script": "latin" + }, + { + "name": "john meyer", + "label": "negative", + "script": "latin" + }, + { + "name": "lori brown", + "label": "negative", + "script": "latin" + }, + { + "name": "julie snyder", + "label": "negative", + "script": "latin" + }, + { + "name": "anne matthews", + "label": "negative", + "script": "latin" + }, + { + "name": "paul fields", + "label": "negative", + "script": "latin" + }, + { + "name": "elizabeth fox", + "label": "negative", + "script": "latin" + }, + { + "name": "graham knight", + "label": "negative", + "script": "latin" + }, + { + "name": "juan wilkinson", + "label": "negative", + "script": "latin" + }, + { + "name": "geoffrey douglas", + "label": "negative", + "script": "latin" + }, + { + "name": "kelsey smith", + "label": "negative", + "script": "latin" + }, + { + "name": "hannah ford", + "label": "negative", + "script": "latin" + }, + { + "name": "pamela black", + "label": "negative", + "script": "latin" + }, + { + "name": "mandy dean", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Add a title prefix (Mr., Dr., etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_leading_title" + ], + "rule_descriptions": { + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "wendy murphy", + "label": "negative", + "script": "latin" + }, + { + "name": "laura jones", + "label": "negative", + "script": "latin" + }, + { + "name": "johnny bailey", + "label": "negative", + "script": "latin" + }, + { + "name": "stacey martin", + "label": "negative", + "script": "latin" + }, + { + "name": "victoria black", + "label": "negative", + "script": "latin" + }, + { + "name": "robert yates", + "label": "negative", + "script": "latin" + }, + { + "name": "blake bennett", + "label": "negative", + "script": "latin" + }, + { + "name": "justin kelly", + "label": "negative", + "script": "latin" + }, + { + "name": "jonathan jones", + "label": "negative", + "script": "latin" + }, + { + "name": "julie garcia", + "label": "negative", + "script": "latin" + }, + { + "name": "dennis patrick", + "label": "negative", + "script": "latin" + }, + { + "name": "marcus gonzalez", + "label": "negative", + "script": "latin" + }, + { + "name": "jake hunt", + "label": "negative", + "script": "latin" + }, + { + "name": "corey brown", + "label": "negative", + "script": "latin" + }, + { + "name": "christine hughes", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Duplicate a random letter, Replace random vowels with different vowels, and Swap adjacent syllables.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "duplicate_random_letter_as_double_letter", + "replace_random_vowel_with_random_vowel", + "swap_adjacent_syllables" + ], + "rule_descriptions": { + "duplicate_random_letter_as_double_letter": "Duplicate a random letter", + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels", + "swap_adjacent_syllables": "Swap adjacent syllables" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "destiny allen", + "label": "negative", + "script": "latin" + }, + { + "name": "deborah white", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy turner", + "label": "negative", + "script": "latin" + }, + { + "name": "richard williams", + "label": "negative", + "script": "latin" + }, + { + "name": "clare hernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "martyn maxwell", + "label": "negative", + "script": "latin" + }, + { + "name": "angela thomas", + "label": "negative", + "script": "latin" + }, + { + "name": "jasmine mendoza", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher hall", + "label": "negative", + "script": "latin" + }, + { + "name": "patricia scott", + "label": "negative", + "script": "latin" + }, + { + "name": "jacqueline davidson", + "label": "negative", + "script": "latin" + }, + { + "name": "charles pitts", + "label": "negative", + "script": "latin" + }, + { + "name": "paige leonard", + "label": "negative", + "script": "latin" + }, + { + "name": "christina martin", + "label": "negative", + "script": "latin" + }, + { + "name": "derek richardson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace random vowels with different vowels, and Duplicate a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_vowel_with_random_vowel", + "duplicate_random_letter_as_double_letter" + ], + "rule_descriptions": { + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels", + "duplicate_random_letter_as_double_letter": "Duplicate a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "ashley turner", + "label": "negative", + "script": "latin" + }, + { + "name": "brett wilkins", + "label": "negative", + "script": "latin" + }, + { + "name": "carolyn adams", + "label": "negative", + "script": "latin" + }, + { + "name": "richard lee", + "label": "negative", + "script": "latin" + }, + { + "name": "angela jones", + "label": "negative", + "script": "latin" + }, + { + "name": "brenda savage", + "label": "negative", + "script": "latin" + }, + { + "name": "andrew rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "tyler jones", + "label": "negative", + "script": "latin" + }, + { + "name": "jack walsh", + "label": "negative", + "script": "latin" + }, + { + "name": "tiffany wells", + "label": "negative", + "script": "latin" + }, + { + "name": "josephine mason", + "label": "negative", + "script": "latin" + }, + { + "name": "margaret baker", + "label": "negative", + "script": "latin" + }, + { + "name": "joel owens", + "label": "negative", + "script": "latin" + }, + { + "name": "joe smith", + "label": "negative", + "script": "latin" + }, + { + "name": "paula hinton", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Duplicate a random letter, and Swap adjacent consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "duplicate_random_letter_as_double_letter", + "swap_adjacent_consonants" + ], + "rule_descriptions": { + "duplicate_random_letter_as_double_letter": "Duplicate a random letter", + "swap_adjacent_consonants": "Swap adjacent consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "melissa carter", + "label": "negative", + "script": "latin" + }, + { + "name": "tyler wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "heather logan", + "label": "negative", + "script": "latin" + }, + { + "name": "stacie scott", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "carolyn stokes", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica lane", + "label": "negative", + "script": "latin" + }, + { + "name": "tony coffey", + "label": "negative", + "script": "latin" + }, + { + "name": "calvin gallagher", + "label": "negative", + "script": "latin" + }, + { + "name": "juan nunez", + "label": "negative", + "script": "latin" + }, + { + "name": "barbara hicks", + "label": "negative", + "script": "latin" + }, + { + "name": "jason owens", + "label": "negative", + "script": "latin" + }, + { + "name": "sabrina lopez", + "label": "negative", + "script": "latin" + }, + { + "name": "jeremy edwards", + "label": "negative", + "script": "latin" + }, + { + "name": "scott wilson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title prefix (Mr., Dr., etc.), Use first name initial with last name, and Duplicate a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_leading_title", + "initial_only_first_name", + "duplicate_random_letter_as_double_letter" + ], + "rule_descriptions": { + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)", + "initial_only_first_name": "Use first name initial with last name", + "duplicate_random_letter_as_double_letter": "Duplicate a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "tina flores", + "label": "negative", + "script": "latin" + }, + { + "name": "ian norris", + "label": "negative", + "script": "latin" + }, + { + "name": "mary richardson", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher day", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie williams", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy chung", + "label": "negative", + "script": "latin" + }, + { + "name": "julie murray", + "label": "negative", + "script": "latin" + }, + { + "name": "patricia cross", + "label": "negative", + "script": "latin" + }, + { + "name": "travis richards", + "label": "negative", + "script": "latin" + }, + { + "name": "david andrade", + "label": "negative", + "script": "latin" + }, + { + "name": "stephen martin", + "label": "negative", + "script": "latin" + }, + { + "name": "jimmy hussain", + "label": "negative", + "script": "latin" + }, + { + "name": "oliver gibson", + "label": "negative", + "script": "latin" + }, + { + "name": "gillian miller", + "label": "negative", + "script": "latin" + }, + { + "name": "michael richards", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Abbreviate name parts, Swap adjacent syllables, and Replace spaces with special characters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_abbreviations", + "swap_adjacent_syllables", + "replace_spaces_with_random_special_characters" + ], + "rule_descriptions": { + "shorten_name_to_abbreviations": "Abbreviate name parts", + "swap_adjacent_syllables": "Swap adjacent syllables", + "replace_spaces_with_random_special_characters": "Replace spaces with special characters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "eric hooper", + "label": "negative", + "script": "latin" + }, + { + "name": "charles rogers", + "label": "negative", + "script": "latin" + }, + { + "name": "sean cooper", + "label": "negative", + "script": "latin" + }, + { + "name": "angela levine", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher fernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "samuel johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "sandra howe", + "label": "negative", + "script": "latin" + }, + { + "name": "dominic cole", + "label": "negative", + "script": "latin" + }, + { + "name": "sara sloan", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica moore", + "label": "negative", + "script": "latin" + }, + { + "name": "jamie vaughn", + "label": "negative", + "script": "latin" + }, + { + "name": "josh wilkerson", + "label": "negative", + "script": "latin" + }, + { + "name": "beth gordon", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin mcpherson", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah moore", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Insert a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "insert_random_letter" + ], + "rule_descriptions": { + "insert_random_letter": "Insert a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "regina krause", + "label": "negative", + "script": "latin" + }, + { + "name": "michael sanchez", + "label": "negative", + "script": "latin" + }, + { + "name": "derek adams", + "label": "negative", + "script": "latin" + }, + { + "name": "mohammed martin", + "label": "negative", + "script": "latin" + }, + { + "name": "priscilla edwards", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa arnold", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony flores", + "label": "negative", + "script": "latin" + }, + { + "name": "linda reid", + "label": "negative", + "script": "latin" + }, + { + "name": "philip rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "jake richardson", + "label": "negative", + "script": "latin" + }, + { + "name": "alexander wiley", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley fischer", + "label": "negative", + "script": "latin" + }, + { + "name": "darren davis", + "label": "negative", + "script": "latin" + }, + { + "name": "sheryl small", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole phillips", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Duplicate a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "duplicate_random_letter_as_double_letter" + ], + "rule_descriptions": { + "duplicate_random_letter_as_double_letter": "Duplicate a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "toby green", + "label": "negative", + "script": "latin" + }, + { + "name": "martin thomas", + "label": "negative", + "script": "latin" + }, + { + "name": "curtis moore", + "label": "negative", + "script": "latin" + }, + { + "name": "john smith", + "label": "negative", + "script": "latin" + }, + { + "name": "helen smith", + "label": "negative", + "script": "latin" + }, + { + "name": "martyn dodd", + "label": "negative", + "script": "latin" + }, + { + "name": "brittany manning", + "label": "negative", + "script": "latin" + }, + { + "name": "glenn harris", + "label": "negative", + "script": "latin" + }, + { + "name": "vickie hill", + "label": "negative", + "script": "latin" + }, + { + "name": "rebecca anderson", + "label": "negative", + "script": "latin" + }, + { + "name": "donna odonnell", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda brown", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer maynard", + "label": "negative", + "script": "latin" + }, + { + "name": "ronald martin", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Duplicate a random letter, and Replace random vowels with different vowels.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "duplicate_random_letter_as_double_letter", + "replace_random_vowel_with_random_vowel" + ], + "rule_descriptions": { + "duplicate_random_letter_as_double_letter": "Duplicate a random letter", + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "eugene howe", + "label": "negative", + "script": "latin" + }, + { + "name": "leslie pearson", + "label": "negative", + "script": "latin" + }, + { + "name": "paula holden", + "label": "negative", + "script": "latin" + }, + { + "name": "elaine murray", + "label": "negative", + "script": "latin" + }, + { + "name": "jill harvey", + "label": "negative", + "script": "latin" + }, + { + "name": "debra edwards", + "label": "negative", + "script": "latin" + }, + { + "name": "michael mccormick", + "label": "negative", + "script": "latin" + }, + { + "name": "lori potts", + "label": "negative", + "script": "latin" + }, + { + "name": "heather robinson", + "label": "negative", + "script": "latin" + }, + { + "name": "amy harris", + "label": "negative", + "script": "latin" + }, + { + "name": "cynthia williams", + "label": "negative", + "script": "latin" + }, + { + "name": "sara choi", + "label": "negative", + "script": "latin" + }, + { + "name": "tyler watkins", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffrey barnes", + "label": "negative", + "script": "latin" + }, + { + "name": "josh delgado", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap adjacent syllables, and Convert name to initials.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_syllables", + "shorten_name_to_initials" + ], + "rule_descriptions": { + "swap_adjacent_syllables": "Swap adjacent syllables", + "shorten_name_to_initials": "Convert name to initials" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "jennifer edwards", + "label": "negative", + "script": "latin" + }, + { + "name": "max fox", + "label": "negative", + "script": "latin" + }, + { + "name": "frank jackson", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin jones", + "label": "negative", + "script": "latin" + }, + { + "name": "diana carr", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah barker", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole burton", + "label": "negative", + "script": "latin" + }, + { + "name": "james parker", + "label": "negative", + "script": "latin" + }, + { + "name": "amy boyd", + "label": "negative", + "script": "latin" + }, + { + "name": "gabriel williams", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer smith", + "label": "negative", + "script": "latin" + }, + { + "name": "donna davis", + "label": "negative", + "script": "latin" + }, + { + "name": "tiffany lopez", + "label": "negative", + "script": "latin" + }, + { + "name": "john savage", + "label": "negative", + "script": "latin" + }, + { + "name": "frances knowles", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Add a title prefix (Mr., Dr., etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_leading_title" + ], + "rule_descriptions": { + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "sharon harding", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley hall", + "label": "negative", + "script": "latin" + }, + { + "name": "brian henderson", + "label": "negative", + "script": "latin" + }, + { + "name": "lydia young", + "label": "negative", + "script": "latin" + }, + { + "name": "todd james", + "label": "negative", + "script": "latin" + }, + { + "name": "hugh bauer", + "label": "negative", + "script": "latin" + }, + { + "name": "annette edwards", + "label": "negative", + "script": "latin" + }, + { + "name": "jody owen", + "label": "negative", + "script": "latin" + }, + { + "name": "sandra wong", + "label": "negative", + "script": "latin" + }, + { + "name": "karen ward", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda mason", + "label": "negative", + "script": "latin" + }, + { + "name": "cheryl santos", + "label": "negative", + "script": "latin" + }, + { + "name": "gloria hughes", + "label": "negative", + "script": "latin" + }, + { + "name": "anna richards", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa lee", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Swap random adjacent letters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_random_letter" + ], + "rule_descriptions": { + "swap_random_letter": "Swap random adjacent letters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "ryan jones", + "label": "negative", + "script": "latin" + }, + { + "name": "dylan bennett", + "label": "negative", + "script": "latin" + }, + { + "name": "kristi fraser", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley smith", + "label": "negative", + "script": "latin" + }, + { + "name": "steven sanchez", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffrey ryan", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony chapman", + "label": "negative", + "script": "latin" + }, + { + "name": "alex brown", + "label": "negative", + "script": "latin" + }, + { + "name": "steven bird", + "label": "negative", + "script": "latin" + }, + { + "name": "mark young", + "label": "negative", + "script": "latin" + }, + { + "name": "frank cobb", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica galvan", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer parker", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley hoover", + "label": "negative", + "script": "latin" + }, + { + "name": "adrian gregory", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title suffix (Jr., PhD, etc.), and Use first name initial with last name.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_trailing_title", + "initial_only_first_name" + ], + "rule_descriptions": { + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)", + "initial_only_first_name": "Use first name initial with last name" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "joseph stuart", + "label": "negative", + "script": "latin" + }, + { + "name": "natasha heath", + "label": "negative", + "script": "latin" + }, + { + "name": "emily price", + "label": "negative", + "script": "latin" + }, + { + "name": "william lee", + "label": "negative", + "script": "latin" + }, + { + "name": "henry johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "dawn berry", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph meyer", + "label": "negative", + "script": "latin" + }, + { + "name": "kimberly gomez", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher vasquez", + "label": "negative", + "script": "latin" + }, + { + "name": "stephen munoz", + "label": "negative", + "script": "latin" + }, + { + "name": "maria freeman", + "label": "negative", + "script": "latin" + }, + { + "name": "eric zamora", + "label": "negative", + "script": "latin" + }, + { + "name": "kirk robbins", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffrey alvarez", + "label": "negative", + "script": "latin" + }, + { + "name": "molly hall", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace spaces with special characters, Replace random consonants with different consonants, and Add a title suffix (Jr., PhD, etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_spaces_with_random_special_characters", + "replace_random_consonant_with_random_consonant", + "add_random_trailing_title" + ], + "rule_descriptions": { + "replace_spaces_with_random_special_characters": "Replace spaces with special characters", + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants", + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "michael ball", + "label": "negative", + "script": "latin" + }, + { + "name": "steven lee", + "label": "negative", + "script": "latin" + }, + { + "name": "danielle wilkinson", + "label": "negative", + "script": "latin" + }, + { + "name": "andrew flores", + "label": "negative", + "script": "latin" + }, + { + "name": "amy hussain", + "label": "negative", + "script": "latin" + }, + { + "name": "brandon jones", + "label": "negative", + "script": "latin" + }, + { + "name": "tanya williams", + "label": "negative", + "script": "latin" + }, + { + "name": "jill gallagher", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa gay", + "label": "negative", + "script": "latin" + }, + { + "name": "paul james", + "label": "negative", + "script": "latin" + }, + { + "name": "carl hall", + "label": "negative", + "script": "latin" + }, + { + "name": "leon hughes", + "label": "negative", + "script": "latin" + }, + { + "name": "travis long", + "label": "negative", + "script": "latin" + }, + { + "name": "michael martin", + "label": "negative", + "script": "latin" + }, + { + "name": "benjamin sandoval", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title prefix (Mr., Dr., etc.), Replace random consonants with different consonants, and Abbreviate name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_leading_title", + "replace_random_consonant_with_random_consonant", + "shorten_name_to_abbreviations" + ], + "rule_descriptions": { + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)", + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants", + "shorten_name_to_abbreviations": "Abbreviate name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "jasmine miller", + "label": "negative", + "script": "latin" + }, + { + "name": "allison mann", + "label": "negative", + "script": "latin" + }, + { + "name": "cheryl smith", + "label": "negative", + "script": "latin" + }, + { + "name": "marie munoz", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffrey wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "joan stewart", + "label": "negative", + "script": "latin" + }, + { + "name": "kieran gutierrez", + "label": "negative", + "script": "latin" + }, + { + "name": "vanessa richardson", + "label": "negative", + "script": "latin" + }, + { + "name": "brian swanson", + "label": "negative", + "script": "latin" + }, + { + "name": "simon holland", + "label": "negative", + "script": "latin" + }, + { + "name": "adam holden", + "label": "negative", + "script": "latin" + }, + { + "name": "eleanor cook", + "label": "negative", + "script": "latin" + }, + { + "name": "andrea quinn", + "label": "negative", + "script": "latin" + }, + { + "name": "grant powell", + "label": "negative", + "script": "latin" + }, + { + "name": "allen anderson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Swap adjacent consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_consonants" + ], + "rule_descriptions": { + "swap_adjacent_consonants": "Swap adjacent consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "roy mitchell", + "label": "negative", + "script": "latin" + }, + { + "name": "eric andrews", + "label": "negative", + "script": "latin" + }, + { + "name": "julie warren", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley bishop", + "label": "negative", + "script": "latin" + }, + { + "name": "bradley burton", + "label": "negative", + "script": "latin" + }, + { + "name": "carrie coles", + "label": "negative", + "script": "latin" + }, + { + "name": "nathan miller", + "label": "negative", + "script": "latin" + }, + { + "name": "scott allen", + "label": "negative", + "script": "latin" + }, + { + "name": "holly higgins", + "label": "negative", + "script": "latin" + }, + { + "name": "kelly jones", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin allen", + "label": "negative", + "script": "latin" + }, + { + "name": "zachary wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "kristina hernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "shawn vincent", + "label": "negative", + "script": "latin" + }, + { + "name": "susan perez", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Abbreviate name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_abbreviations" + ], + "rule_descriptions": { + "shorten_name_to_abbreviations": "Abbreviate name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "paul cruz", + "label": "negative", + "script": "latin" + }, + { + "name": "brianna alexander", + "label": "negative", + "script": "latin" + }, + { + "name": "tanya brennan", + "label": "negative", + "script": "latin" + }, + { + "name": "william bevan", + "label": "negative", + "script": "latin" + }, + { + "name": "sean hines", + "label": "negative", + "script": "latin" + }, + { + "name": "robin graham", + "label": "negative", + "script": "latin" + }, + { + "name": "heather mcclain", + "label": "negative", + "script": "latin" + }, + { + "name": "louise campbell", + "label": "negative", + "script": "latin" + }, + { + "name": "crystal torres", + "label": "negative", + "script": "latin" + }, + { + "name": "mark stone", + "label": "negative", + "script": "latin" + }, + { + "name": "nathaniel sharp", + "label": "negative", + "script": "latin" + }, + { + "name": "paige benson", + "label": "negative", + "script": "latin" + }, + { + "name": "mark taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "fernando mcknight", + "label": "negative", + "script": "latin" + }, + { + "name": "crystal hendrix", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace random consonants with different consonants, and Add a title suffix (Jr., PhD, etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_consonant_with_random_consonant", + "add_random_trailing_title" + ], + "rule_descriptions": { + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants", + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "jessica anderson", + "label": "negative", + "script": "latin" + }, + { + "name": "catherine bell", + "label": "negative", + "script": "latin" + }, + { + "name": "jason smith", + "label": "negative", + "script": "latin" + }, + { + "name": "aaron campbell", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer gutierrez", + "label": "negative", + "script": "latin" + }, + { + "name": "lucas bryant", + "label": "negative", + "script": "latin" + }, + { + "name": "dawn alexander", + "label": "negative", + "script": "latin" + }, + { + "name": "breanna medina", + "label": "negative", + "script": "latin" + }, + { + "name": "mary coleman", + "label": "negative", + "script": "latin" + }, + { + "name": "dean stevens", + "label": "negative", + "script": "latin" + }, + { + "name": "claire solis", + "label": "negative", + "script": "latin" + }, + { + "name": "mathew gomez", + "label": "negative", + "script": "latin" + }, + { + "name": "jonathan harris", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel davies", + "label": "negative", + "script": "latin" + }, + { + "name": "steven petersen", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap adjacent consonants, Add a title suffix (Jr., PhD, etc.), and Replace double letters with a single letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_consonants", + "add_random_trailing_title", + "replace_double_letters_with_single_letter" + ], + "rule_descriptions": { + "swap_adjacent_consonants": "Swap adjacent consonants", + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)", + "replace_double_letters_with_single_letter": "Replace double letters with a single letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "diana wolfe", + "label": "negative", + "script": "latin" + }, + { + "name": "laura palmer", + "label": "negative", + "script": "latin" + }, + { + "name": "heather vargas", + "label": "negative", + "script": "latin" + }, + { + "name": "oliver snyder", + "label": "negative", + "script": "latin" + }, + { + "name": "casey chapman", + "label": "negative", + "script": "latin" + }, + { + "name": "kim byrne", + "label": "negative", + "script": "latin" + }, + { + "name": "lauren page", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel davies", + "label": "negative", + "script": "latin" + }, + { + "name": "caitlin taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "jonathan kelly", + "label": "negative", + "script": "latin" + }, + { + "name": "marco george", + "label": "negative", + "script": "latin" + }, + { + "name": "stacey anderson", + "label": "negative", + "script": "latin" + }, + { + "name": "stacey walker", + "label": "negative", + "script": "latin" + }, + { + "name": "janice murray", + "label": "negative", + "script": "latin" + }, + { + "name": "evan hodge", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Replace random consonants with different consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_consonant_with_random_consonant" + ], + "rule_descriptions": { + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "thomas logan", + "label": "negative", + "script": "latin" + }, + { + "name": "marcus dillon", + "label": "negative", + "script": "latin" + }, + { + "name": "amber meyer", + "label": "negative", + "script": "latin" + }, + { + "name": "sylvia armstrong", + "label": "negative", + "script": "latin" + }, + { + "name": "keith petersen", + "label": "negative", + "script": "latin" + }, + { + "name": "andrea holden", + "label": "negative", + "script": "latin" + }, + { + "name": "jeremy knight", + "label": "negative", + "script": "latin" + }, + { + "name": "danielle robertson", + "label": "negative", + "script": "latin" + }, + { + "name": "jayne jones", + "label": "negative", + "script": "latin" + }, + { + "name": "emily scott", + "label": "negative", + "script": "latin" + }, + { + "name": "william johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "jason pratt", + "label": "negative", + "script": "latin" + }, + { + "name": "jason hughes", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica garrison", + "label": "negative", + "script": "latin" + }, + { + "name": "kyle kirk", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove a random vowel, Replace spaces with special characters, and Replace random vowels with different vowels.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_vowel", + "replace_spaces_with_random_special_characters", + "replace_random_vowel_with_random_vowel" + ], + "rule_descriptions": { + "remove_random_vowel": "Remove a random vowel", + "replace_spaces_with_random_special_characters": "Replace spaces with special characters", + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "shannon rocha", + "label": "negative", + "script": "latin" + }, + { + "name": "jonathan craig", + "label": "negative", + "script": "latin" + }, + { + "name": "georgia clarke", + "label": "negative", + "script": "latin" + }, + { + "name": "craig hunt", + "label": "negative", + "script": "latin" + }, + { + "name": "erica steele", + "label": "negative", + "script": "latin" + }, + { + "name": "carlos johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "cassandra woods", + "label": "negative", + "script": "latin" + }, + { + "name": "sara huber", + "label": "negative", + "script": "latin" + }, + { + "name": "dale klein", + "label": "negative", + "script": "latin" + }, + { + "name": "sean smith", + "label": "negative", + "script": "latin" + }, + { + "name": "elizabeth adams", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas hood", + "label": "negative", + "script": "latin" + }, + { + "name": "lorraine pena", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer west", + "label": "negative", + "script": "latin" + }, + { + "name": "damian jones", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Use first name initial with last name.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "initial_only_first_name" + ], + "rule_descriptions": { + "initial_only_first_name": "Use first name initial with last name" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "clive shelton", + "label": "negative", + "script": "latin" + }, + { + "name": "gregory madden", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie rosario", + "label": "negative", + "script": "latin" + }, + { + "name": "devin cruz", + "label": "negative", + "script": "latin" + }, + { + "name": "patricia vargas", + "label": "negative", + "script": "latin" + }, + { + "name": "gabriel mclaughlin", + "label": "negative", + "script": "latin" + }, + { + "name": "courtney davies", + "label": "negative", + "script": "latin" + }, + { + "name": "zachary allan", + "label": "negative", + "script": "latin" + }, + { + "name": "brian ellis", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph hughes", + "label": "negative", + "script": "latin" + }, + { + "name": "ryan robinson", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa ramsey", + "label": "negative", + "script": "latin" + }, + { + "name": "charlie hill", + "label": "negative", + "script": "latin" + }, + { + "name": "theresa jones", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda barajas", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Convert name to initials.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_initials" + ], + "rule_descriptions": { + "shorten_name_to_initials": "Convert name to initials" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "kimberly gamble", + "label": "negative", + "script": "latin" + }, + { + "name": "alyssa soto", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua mcdowell", + "label": "negative", + "script": "latin" + }, + { + "name": "cory robinson", + "label": "negative", + "script": "latin" + }, + { + "name": "marvin floyd", + "label": "negative", + "script": "latin" + }, + { + "name": "donna bell", + "label": "negative", + "script": "latin" + }, + { + "name": "dylan mcclain", + "label": "negative", + "script": "latin" + }, + { + "name": "yvonne vincent", + "label": "negative", + "script": "latin" + }, + { + "name": "nicholas coleman", + "label": "negative", + "script": "latin" + }, + { + "name": "maria murphy", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie butler", + "label": "negative", + "script": "latin" + }, + { + "name": "jay johnston", + "label": "negative", + "script": "latin" + }, + { + "name": "susan burton", + "label": "negative", + "script": "latin" + }, + { + "name": "crystal hinton", + "label": "negative", + "script": "latin" + }, + { + "name": "david oliver", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Duplicate a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "duplicate_random_letter_as_double_letter" + ], + "rule_descriptions": { + "duplicate_random_letter_as_double_letter": "Duplicate a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "michelle martinez", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffery smith", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley wise", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa williams", + "label": "negative", + "script": "latin" + }, + { + "name": "bianca williams", + "label": "negative", + "script": "latin" + }, + { + "name": "jacqueline carter", + "label": "negative", + "script": "latin" + }, + { + "name": "courtney bolton", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher savage", + "label": "negative", + "script": "latin" + }, + { + "name": "yolanda garcia", + "label": "negative", + "script": "latin" + }, + { + "name": "teresa cole", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph randall", + "label": "negative", + "script": "latin" + }, + { + "name": "heidi smith", + "label": "negative", + "script": "latin" + }, + { + "name": "bruce medina", + "label": "negative", + "script": "latin" + }, + { + "name": "john gonzalez", + "label": "negative", + "script": "latin" + }, + { + "name": "diana velez", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace double letters with a single letter, and Replace random vowels with different vowels.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_double_letters_with_single_letter", + "replace_random_vowel_with_random_vowel" + ], + "rule_descriptions": { + "replace_double_letters_with_single_letter": "Replace double letters with a single letter", + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "david stanton", + "label": "negative", + "script": "latin" + }, + { + "name": "shannon patel", + "label": "negative", + "script": "latin" + }, + { + "name": "william perez", + "label": "negative", + "script": "latin" + }, + { + "name": "diana green", + "label": "negative", + "script": "latin" + }, + { + "name": "rebecca banks", + "label": "negative", + "script": "latin" + }, + { + "name": "jacob martin", + "label": "negative", + "script": "latin" + }, + { + "name": "annette berry", + "label": "negative", + "script": "latin" + }, + { + "name": "jason west", + "label": "negative", + "script": "latin" + }, + { + "name": "simon duran", + "label": "negative", + "script": "latin" + }, + { + "name": "katie bartlett", + "label": "negative", + "script": "latin" + }, + { + "name": "jill dean", + "label": "negative", + "script": "latin" + }, + { + "name": "michael lee", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa harris", + "label": "negative", + "script": "latin" + }, + { + "name": "jacqueline slater", + "label": "negative", + "script": "latin" + }, + { + "name": "mark robinson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Swap adjacent syllables.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_syllables" + ], + "rule_descriptions": { + "swap_adjacent_syllables": "Swap adjacent syllables" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "craig ruiz", + "label": "negative", + "script": "latin" + }, + { + "name": "grace bailey", + "label": "negative", + "script": "latin" + }, + { + "name": "scott poole", + "label": "negative", + "script": "latin" + }, + { + "name": "robert miller", + "label": "negative", + "script": "latin" + }, + { + "name": "michael weiss", + "label": "negative", + "script": "latin" + }, + { + "name": "chelsea hartman", + "label": "negative", + "script": "latin" + }, + { + "name": "kenneth welch", + "label": "negative", + "script": "latin" + }, + { + "name": "rhonda young", + "label": "negative", + "script": "latin" + }, + { + "name": "susan hunt", + "label": "negative", + "script": "latin" + }, + { + "name": "ryan manning", + "label": "negative", + "script": "latin" + }, + { + "name": "mark craig", + "label": "negative", + "script": "latin" + }, + { + "name": "michael shepherd", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony avila", + "label": "negative", + "script": "latin" + }, + { + "name": "kathryn gomez", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer turner", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace double letters with a single letter, Duplicate a random letter, and Add a title prefix (Mr., Dr., etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_double_letters_with_single_letter", + "duplicate_random_letter_as_double_letter", + "add_random_leading_title" + ], + "rule_descriptions": { + "replace_double_letters_with_single_letter": "Replace double letters with a single letter", + "duplicate_random_letter_as_double_letter": "Duplicate a random letter", + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "janice johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "shaun juarez", + "label": "negative", + "script": "latin" + }, + { + "name": "bryan moss", + "label": "negative", + "script": "latin" + }, + { + "name": "kaitlyn sanchez", + "label": "negative", + "script": "latin" + }, + { + "name": "donna espinoza", + "label": "negative", + "script": "latin" + }, + { + "name": "steven gray", + "label": "negative", + "script": "latin" + }, + { + "name": "brenda serrano", + "label": "negative", + "script": "latin" + }, + { + "name": "janet jimenez", + "label": "negative", + "script": "latin" + }, + { + "name": "marcus boyd", + "label": "negative", + "script": "latin" + }, + { + "name": "michael cook", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa nicholson", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa carr", + "label": "negative", + "script": "latin" + }, + { + "name": "ryan ward", + "label": "negative", + "script": "latin" + }, + { + "name": "donna cortez", + "label": "negative", + "script": "latin" + }, + { + "name": "shawn pugh", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove a random vowel, Add a title suffix (Jr., PhD, etc.), and Remove a random consonant.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_vowel", + "add_random_trailing_title", + "remove_random_consonant" + ], + "rule_descriptions": { + "remove_random_vowel": "Remove a random vowel", + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)", + "remove_random_consonant": "Remove a random consonant" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "lynda richard", + "label": "negative", + "script": "latin" + }, + { + "name": "brian lin", + "label": "negative", + "script": "latin" + }, + { + "name": "beverley ruiz", + "label": "negative", + "script": "latin" + }, + { + "name": "laura george", + "label": "negative", + "script": "latin" + }, + { + "name": "max vega", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua smith", + "label": "negative", + "script": "latin" + }, + { + "name": "scott parsons", + "label": "negative", + "script": "latin" + }, + { + "name": "erik byrd", + "label": "negative", + "script": "latin" + }, + { + "name": "dominique thompson", + "label": "negative", + "script": "latin" + }, + { + "name": "jason cruz", + "label": "negative", + "script": "latin" + }, + { + "name": "gina reyes", + "label": "negative", + "script": "latin" + }, + { + "name": "brett porter", + "label": "negative", + "script": "latin" + }, + { + "name": "aaron hill", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer gordon", + "label": "negative", + "script": "latin" + }, + { + "name": "danny taylor", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap adjacent consonants, and Duplicate a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_consonants", + "duplicate_random_letter_as_double_letter" + ], + "rule_descriptions": { + "swap_adjacent_consonants": "Swap adjacent consonants", + "duplicate_random_letter_as_double_letter": "Duplicate a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "ricky rogers", + "label": "negative", + "script": "latin" + }, + { + "name": "roy paul", + "label": "negative", + "script": "latin" + }, + { + "name": "gary jones", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa watson", + "label": "negative", + "script": "latin" + }, + { + "name": "mandy morris", + "label": "negative", + "script": "latin" + }, + { + "name": "denise rice", + "label": "negative", + "script": "latin" + }, + { + "name": "holly davis", + "label": "negative", + "script": "latin" + }, + { + "name": "danielle wheeler", + "label": "negative", + "script": "latin" + }, + { + "name": "jamie daniel", + "label": "negative", + "script": "latin" + }, + { + "name": "clive smith", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph murphy", + "label": "negative", + "script": "latin" + }, + { + "name": "steven jordan", + "label": "negative", + "script": "latin" + }, + { + "name": "cynthia smith", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin brooks", + "label": "negative", + "script": "latin" + }, + { + "name": "april kelly", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace random consonants with different consonants, Replace double letters with a single letter, and Reorder name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_consonant_with_random_consonant", + "replace_double_letters_with_single_letter", + "name_parts_permutations" + ], + "rule_descriptions": { + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants", + "replace_double_letters_with_single_letter": "Replace double letters with a single letter", + "name_parts_permutations": "Reorder name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "dean shepherd", + "label": "negative", + "script": "latin" + }, + { + "name": "tammy benson", + "label": "negative", + "script": "latin" + }, + { + "name": "bruce williams", + "label": "negative", + "script": "latin" + }, + { + "name": "julie hood", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew walker", + "label": "negative", + "script": "latin" + }, + { + "name": "dylan allen", + "label": "negative", + "script": "latin" + }, + { + "name": "colleen davies", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel ruiz", + "label": "negative", + "script": "latin" + }, + { + "name": "marie stevens", + "label": "negative", + "script": "latin" + }, + { + "name": "david jones", + "label": "negative", + "script": "latin" + }, + { + "name": "samantha smith", + "label": "negative", + "script": "latin" + }, + { + "name": "paula singh", + "label": "negative", + "script": "latin" + }, + { + "name": "zachary marshall", + "label": "negative", + "script": "latin" + }, + { + "name": "julia luna", + "label": "negative", + "script": "latin" + }, + { + "name": "peter ellison", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Use first name initial with last name.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "initial_only_first_name" + ], + "rule_descriptions": { + "initial_only_first_name": "Use first name initial with last name" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "brandi ortega", + "label": "negative", + "script": "latin" + }, + { + "name": "eric foster", + "label": "negative", + "script": "latin" + }, + { + "name": "shane williams", + "label": "negative", + "script": "latin" + }, + { + "name": "eric smith", + "label": "negative", + "script": "latin" + }, + { + "name": "charlie massey", + "label": "negative", + "script": "latin" + }, + { + "name": "michael henderson", + "label": "negative", + "script": "latin" + }, + { + "name": "william hill", + "label": "negative", + "script": "latin" + }, + { + "name": "shane ingram", + "label": "negative", + "script": "latin" + }, + { + "name": "cory garcia", + "label": "negative", + "script": "latin" + }, + { + "name": "blake hartman", + "label": "negative", + "script": "latin" + }, + { + "name": "adrian gardner", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa snow", + "label": "negative", + "script": "latin" + }, + { + "name": "jodie mathis", + "label": "negative", + "script": "latin" + }, + { + "name": "sara hartman", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony jackson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Duplicate a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "duplicate_random_letter_as_double_letter" + ], + "rule_descriptions": { + "duplicate_random_letter_as_double_letter": "Duplicate a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "jesse booth", + "label": "negative", + "script": "latin" + }, + { + "name": "angela young", + "label": "negative", + "script": "latin" + }, + { + "name": "dennis jackson", + "label": "negative", + "script": "latin" + }, + { + "name": "angela walsh", + "label": "negative", + "script": "latin" + }, + { + "name": "michael wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "alicia meyer", + "label": "negative", + "script": "latin" + }, + { + "name": "john phillips", + "label": "negative", + "script": "latin" + }, + { + "name": "jay taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "kelly lewis", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie mcfarland", + "label": "negative", + "script": "latin" + }, + { + "name": "john jones", + "label": "negative", + "script": "latin" + }, + { + "name": "david phillips", + "label": "negative", + "script": "latin" + }, + { + "name": "susan ryan", + "label": "negative", + "script": "latin" + }, + { + "name": "colton wood", + "label": "negative", + "script": "latin" + }, + { + "name": "anna sanders", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap random adjacent letters, Reorder name parts, and Swap adjacent syllables.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_random_letter", + "name_parts_permutations", + "swap_adjacent_syllables" + ], + "rule_descriptions": { + "swap_random_letter": "Swap random adjacent letters", + "name_parts_permutations": "Reorder name parts", + "swap_adjacent_syllables": "Swap adjacent syllables" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "nicole stevens", + "label": "negative", + "script": "latin" + }, + { + "name": "patrick good", + "label": "negative", + "script": "latin" + }, + { + "name": "stephen price", + "label": "negative", + "script": "latin" + }, + { + "name": "ann harper", + "label": "negative", + "script": "latin" + }, + { + "name": "mandy gutierrez", + "label": "negative", + "script": "latin" + }, + { + "name": "danielle griffiths", + "label": "negative", + "script": "latin" + }, + { + "name": "jerry brewer", + "label": "negative", + "script": "latin" + }, + { + "name": "danielle hill", + "label": "negative", + "script": "latin" + }, + { + "name": "tonya williams", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica burke", + "label": "negative", + "script": "latin" + }, + { + "name": "dominic burton", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher evans", + "label": "negative", + "script": "latin" + }, + { + "name": "amy collier", + "label": "negative", + "script": "latin" + }, + { + "name": "diana archer", + "label": "negative", + "script": "latin" + }, + { + "name": "tammy ford", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title suffix (Jr., PhD, etc.), Replace random vowels with different vowels, and Convert name to initials.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_trailing_title", + "replace_random_vowel_with_random_vowel", + "shorten_name_to_initials" + ], + "rule_descriptions": { + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)", + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels", + "shorten_name_to_initials": "Convert name to initials" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "matthew barajas", + "label": "negative", + "script": "latin" + }, + { + "name": "kelsey chambers", + "label": "negative", + "script": "latin" + }, + { + "name": "jay miller", + "label": "negative", + "script": "latin" + }, + { + "name": "charlie patterson", + "label": "negative", + "script": "latin" + }, + { + "name": "michael fernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "raymond brooks", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin price", + "label": "negative", + "script": "latin" + }, + { + "name": "paul powell", + "label": "negative", + "script": "latin" + }, + { + "name": "connor gordon", + "label": "negative", + "script": "latin" + }, + { + "name": "june ahmed", + "label": "negative", + "script": "latin" + }, + { + "name": "michael bond", + "label": "negative", + "script": "latin" + }, + { + "name": "emily hawkins", + "label": "negative", + "script": "latin" + }, + { + "name": "edward chen", + "label": "negative", + "script": "latin" + }, + { + "name": "terri patrick", + "label": "negative", + "script": "latin" + }, + { + "name": "molly smith", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Convert name to initials, Replace random consonants with different consonants, and Insert a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_initials", + "replace_random_consonant_with_random_consonant", + "insert_random_letter" + ], + "rule_descriptions": { + "shorten_name_to_initials": "Convert name to initials", + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants", + "insert_random_letter": "Insert a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "leonard andersen", + "label": "negative", + "script": "latin" + }, + { + "name": "mathew leblanc", + "label": "negative", + "script": "latin" + }, + { + "name": "kimberly bates", + "label": "negative", + "script": "latin" + }, + { + "name": "kenneth hamilton", + "label": "negative", + "script": "latin" + }, + { + "name": "justin ball", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer lee", + "label": "negative", + "script": "latin" + }, + { + "name": "courtney cooper", + "label": "negative", + "script": "latin" + }, + { + "name": "amy smith", + "label": "negative", + "script": "latin" + }, + { + "name": "tyler read", + "label": "negative", + "script": "latin" + }, + { + "name": "alyssa o'brien", + "label": "negative", + "script": "latin" + }, + { + "name": "heather jones", + "label": "negative", + "script": "latin" + }, + { + "name": "samantha mistry", + "label": "negative", + "script": "latin" + }, + { + "name": "aaron scott", + "label": "negative", + "script": "latin" + }, + { + "name": "megan dale", + "label": "negative", + "script": "latin" + }, + { + "name": "suzanne smith", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Convert name to initials.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_initials" + ], + "rule_descriptions": { + "shorten_name_to_initials": "Convert name to initials" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "dennis graham", + "label": "negative", + "script": "latin" + }, + { + "name": "kaitlin gutierrez", + "label": "negative", + "script": "latin" + }, + { + "name": "richard brooks", + "label": "negative", + "script": "latin" + }, + { + "name": "jacqueline davis", + "label": "negative", + "script": "latin" + }, + { + "name": "emily leonard", + "label": "negative", + "script": "latin" + }, + { + "name": "clive quinn", + "label": "negative", + "script": "latin" + }, + { + "name": "claire gutierrez", + "label": "negative", + "script": "latin" + }, + { + "name": "brian rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "nancy powell", + "label": "negative", + "script": "latin" + }, + { + "name": "tracy ware", + "label": "negative", + "script": "latin" + }, + { + "name": "kelly chapman", + "label": "negative", + "script": "latin" + }, + { + "name": "melanie jones", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa henderson", + "label": "negative", + "script": "latin" + }, + { + "name": "jamie ferguson", + "label": "negative", + "script": "latin" + }, + { + "name": "christian dobson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace double letters with a single letter, Replace random consonants with different consonants, and Use first name initial with last name.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_double_letters_with_single_letter", + "replace_random_consonant_with_random_consonant", + "initial_only_first_name" + ], + "rule_descriptions": { + "replace_double_letters_with_single_letter": "Replace double letters with a single letter", + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants", + "initial_only_first_name": "Use first name initial with last name" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "thomas hodgson", + "label": "negative", + "script": "latin" + }, + { + "name": "erica wilkinson", + "label": "negative", + "script": "latin" + }, + { + "name": "edward larson", + "label": "negative", + "script": "latin" + }, + { + "name": "brenda graves", + "label": "negative", + "script": "latin" + }, + { + "name": "terence nelson", + "label": "negative", + "script": "latin" + }, + { + "name": "nicola gordon", + "label": "negative", + "script": "latin" + }, + { + "name": "raymond fuentes", + "label": "negative", + "script": "latin" + }, + { + "name": "joyce sanders", + "label": "negative", + "script": "latin" + }, + { + "name": "william martinez", + "label": "negative", + "script": "latin" + }, + { + "name": "micheal ellis", + "label": "negative", + "script": "latin" + }, + { + "name": "peter turner", + "label": "negative", + "script": "latin" + }, + { + "name": "stuart navarro", + "label": "negative", + "script": "latin" + }, + { + "name": "natalie kaufman", + "label": "negative", + "script": "latin" + }, + { + "name": "martyn morris", + "label": "negative", + "script": "latin" + }, + { + "name": "allison hall", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Convert name to initials.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_initials" + ], + "rule_descriptions": { + "shorten_name_to_initials": "Convert name to initials" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "rebecca murphy", + "label": "negative", + "script": "latin" + }, + { + "name": "jasmine lopez", + "label": "negative", + "script": "latin" + }, + { + "name": "callum hansen", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua brown", + "label": "negative", + "script": "latin" + }, + { + "name": "john howard", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel smith", + "label": "negative", + "script": "latin" + }, + { + "name": "heather murphy", + "label": "negative", + "script": "latin" + }, + { + "name": "andrew castaneda", + "label": "negative", + "script": "latin" + }, + { + "name": "ryan bennett", + "label": "negative", + "script": "latin" + }, + { + "name": "suzanne juarez", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin miranda", + "label": "negative", + "script": "latin" + }, + { + "name": "harriet bailey", + "label": "negative", + "script": "latin" + }, + { + "name": "christie carter", + "label": "negative", + "script": "latin" + }, + { + "name": "jonathan harrington", + "label": "negative", + "script": "latin" + }, + { + "name": "william benson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Insert a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "insert_random_letter" + ], + "rule_descriptions": { + "insert_random_letter": "Insert a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "jared powell", + "label": "negative", + "script": "latin" + }, + { + "name": "beth walker", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole burns", + "label": "negative", + "script": "latin" + }, + { + "name": "michael manning", + "label": "negative", + "script": "latin" + }, + { + "name": "ruth bennett", + "label": "negative", + "script": "latin" + }, + { + "name": "mohammed black", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin woods", + "label": "negative", + "script": "latin" + }, + { + "name": "cassandra perez", + "label": "negative", + "script": "latin" + }, + { + "name": "andrea roberts", + "label": "negative", + "script": "latin" + }, + { + "name": "michael ward", + "label": "negative", + "script": "latin" + }, + { + "name": "joan pena", + "label": "negative", + "script": "latin" + }, + { + "name": "larry moore", + "label": "negative", + "script": "latin" + }, + { + "name": "andrew brown", + "label": "negative", + "script": "latin" + }, + { + "name": "guy williams", + "label": "negative", + "script": "latin" + }, + { + "name": "travis sellers", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace double letters with a single letter, and Replace spaces with special characters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_double_letters_with_single_letter", + "replace_spaces_with_random_special_characters" + ], + "rule_descriptions": { + "replace_double_letters_with_single_letter": "Replace double letters with a single letter", + "replace_spaces_with_random_special_characters": "Replace spaces with special characters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "rosie fuller", + "label": "negative", + "script": "latin" + }, + { + "name": "tiffany vasquez", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole patterson", + "label": "negative", + "script": "latin" + }, + { + "name": "kari frederick", + "label": "negative", + "script": "latin" + }, + { + "name": "sandra patel", + "label": "negative", + "script": "latin" + }, + { + "name": "michael kennedy", + "label": "negative", + "script": "latin" + }, + { + "name": "kristi roberts", + "label": "negative", + "script": "latin" + }, + { + "name": "holly nash", + "label": "negative", + "script": "latin" + }, + { + "name": "kari johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "zachary harris", + "label": "negative", + "script": "latin" + }, + { + "name": "taylor wallace", + "label": "negative", + "script": "latin" + }, + { + "name": "jacqueline garza", + "label": "negative", + "script": "latin" + }, + { + "name": "george ray", + "label": "negative", + "script": "latin" + }, + { + "name": "peggy dunn", + "label": "negative", + "script": "latin" + }, + { + "name": "briana fischer", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace random vowels with different vowels, and Use first name initial with last name.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_vowel_with_random_vowel", + "initial_only_first_name" + ], + "rule_descriptions": { + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels", + "initial_only_first_name": "Use first name initial with last name" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "melissa lara", + "label": "negative", + "script": "latin" + }, + { + "name": "dwayne sampson", + "label": "negative", + "script": "latin" + }, + { + "name": "richard briggs", + "label": "negative", + "script": "latin" + }, + { + "name": "diane bennett", + "label": "negative", + "script": "latin" + }, + { + "name": "lynne blair", + "label": "negative", + "script": "latin" + }, + { + "name": "michael richards", + "label": "negative", + "script": "latin" + }, + { + "name": "ryan jones", + "label": "negative", + "script": "latin" + }, + { + "name": "caroline jackson", + "label": "negative", + "script": "latin" + }, + { + "name": "kathleen cole", + "label": "negative", + "script": "latin" + }, + { + "name": "alexander mejia", + "label": "negative", + "script": "latin" + }, + { + "name": "barbara allen", + "label": "negative", + "script": "latin" + }, + { + "name": "alice ford", + "label": "negative", + "script": "latin" + }, + { + "name": "donald brown", + "label": "negative", + "script": "latin" + }, + { + "name": "nathaniel schmitt", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer white", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Swap adjacent syllables.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_syllables" + ], + "rule_descriptions": { + "swap_adjacent_syllables": "Swap adjacent syllables" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "hayley hicks", + "label": "negative", + "script": "latin" + }, + { + "name": "brian foster", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer myers", + "label": "negative", + "script": "latin" + }, + { + "name": "katherine davidson", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel edwards", + "label": "negative", + "script": "latin" + }, + { + "name": "philip johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "lee sparks", + "label": "negative", + "script": "latin" + }, + { + "name": "alexandria boyd", + "label": "negative", + "script": "latin" + }, + { + "name": "theresa mitchell", + "label": "negative", + "script": "latin" + }, + { + "name": "noah bishop", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy gallagher", + "label": "negative", + "script": "latin" + }, + { + "name": "cody atkinson", + "label": "negative", + "script": "latin" + }, + { + "name": "heather conrad", + "label": "negative", + "script": "latin" + }, + { + "name": "toni carpenter", + "label": "negative", + "script": "latin" + }, + { + "name": "cheryl mccarty", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Swap adjacent syllables.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_syllables" + ], + "rule_descriptions": { + "swap_adjacent_syllables": "Swap adjacent syllables" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "anita terrell", + "label": "negative", + "script": "latin" + }, + { + "name": "lauren ellis", + "label": "negative", + "script": "latin" + }, + { + "name": "christy montgomery", + "label": "negative", + "script": "latin" + }, + { + "name": "jorge olson", + "label": "negative", + "script": "latin" + }, + { + "name": "michael lane", + "label": "negative", + "script": "latin" + }, + { + "name": "teresa norman", + "label": "negative", + "script": "latin" + }, + { + "name": "karl porter", + "label": "negative", + "script": "latin" + }, + { + "name": "andrew schultz", + "label": "negative", + "script": "latin" + }, + { + "name": "catherine blackburn", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas harris", + "label": "negative", + "script": "latin" + }, + { + "name": "pamela slater", + "label": "negative", + "script": "latin" + }, + { + "name": "robert tucker", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle howard", + "label": "negative", + "script": "latin" + }, + { + "name": "ellie webster", + "label": "negative", + "script": "latin" + }, + { + "name": "ann smith", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace spaces with special characters, and Remove a random vowel.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_spaces_with_random_special_characters", + "remove_random_vowel" + ], + "rule_descriptions": { + "replace_spaces_with_random_special_characters": "Replace spaces with special characters", + "remove_random_vowel": "Remove a random vowel" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "chelsea rivera", + "label": "negative", + "script": "latin" + }, + { + "name": "laura brady", + "label": "negative", + "script": "latin" + }, + { + "name": "maria robinson", + "label": "negative", + "script": "latin" + }, + { + "name": "ray giles", + "label": "negative", + "script": "latin" + }, + { + "name": "jorge beard", + "label": "negative", + "script": "latin" + }, + { + "name": "steven barnett", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda cruz", + "label": "negative", + "script": "latin" + }, + { + "name": "steven turner", + "label": "negative", + "script": "latin" + }, + { + "name": "angela bush", + "label": "negative", + "script": "latin" + }, + { + "name": "marie hansen", + "label": "negative", + "script": "latin" + }, + { + "name": "bryan thompson", + "label": "negative", + "script": "latin" + }, + { + "name": "sam williams", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole tate", + "label": "negative", + "script": "latin" + }, + { + "name": "james brown", + "label": "negative", + "script": "latin" + }, + { + "name": "laura clark", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title prefix (Mr., Dr., etc.), Replace double letters with a single letter, and Remove a random vowel.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_leading_title", + "replace_double_letters_with_single_letter", + "remove_random_vowel" + ], + "rule_descriptions": { + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)", + "replace_double_letters_with_single_letter": "Replace double letters with a single letter", + "remove_random_vowel": "Remove a random vowel" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "stephen park", + "label": "negative", + "script": "latin" + }, + { + "name": "janet luna", + "label": "negative", + "script": "latin" + }, + { + "name": "jonathan watson", + "label": "negative", + "script": "latin" + }, + { + "name": "ethan jenkins", + "label": "negative", + "script": "latin" + }, + { + "name": "megan williams", + "label": "negative", + "script": "latin" + }, + { + "name": "chad torres", + "label": "negative", + "script": "latin" + }, + { + "name": "dawn vaughan", + "label": "negative", + "script": "latin" + }, + { + "name": "edwin howard", + "label": "negative", + "script": "latin" + }, + { + "name": "jared lee", + "label": "negative", + "script": "latin" + }, + { + "name": "michael jackson", + "label": "negative", + "script": "latin" + }, + { + "name": "carol alvarez", + "label": "negative", + "script": "latin" + }, + { + "name": "shane hawkins", + "label": "negative", + "script": "latin" + }, + { + "name": "michael roth", + "label": "negative", + "script": "latin" + }, + { + "name": "karl bennett", + "label": "negative", + "script": "latin" + }, + { + "name": "linda sandoval", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace random vowels with different vowels, Swap adjacent consonants, and Insert a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_vowel_with_random_vowel", + "swap_adjacent_consonants", + "insert_random_letter" + ], + "rule_descriptions": { + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels", + "swap_adjacent_consonants": "Swap adjacent consonants", + "insert_random_letter": "Insert a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "ryan taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole o'connor", + "label": "negative", + "script": "latin" + }, + { + "name": "trevor hernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "paula lee", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony vang", + "label": "negative", + "script": "latin" + }, + { + "name": "cristian smith", + "label": "negative", + "script": "latin" + }, + { + "name": "jared dunn", + "label": "negative", + "script": "latin" + }, + { + "name": "samantha lopez", + "label": "negative", + "script": "latin" + }, + { + "name": "christine johnston", + "label": "negative", + "script": "latin" + }, + { + "name": "james blackwell", + "label": "negative", + "script": "latin" + }, + { + "name": "ann weaver", + "label": "negative", + "script": "latin" + }, + { + "name": "michael nelson", + "label": "negative", + "script": "latin" + }, + { + "name": "patrick west", + "label": "negative", + "script": "latin" + }, + { + "name": "bernard jordan", + "label": "negative", + "script": "latin" + }, + { + "name": "hannah ashley", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Swap adjacent consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_consonants" + ], + "rule_descriptions": { + "swap_adjacent_consonants": "Swap adjacent consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "carl dorsey", + "label": "negative", + "script": "latin" + }, + { + "name": "beverley hughes", + "label": "negative", + "script": "latin" + }, + { + "name": "caleb chambers", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony villa", + "label": "negative", + "script": "latin" + }, + { + "name": "kathleen williams", + "label": "negative", + "script": "latin" + }, + { + "name": "scott thompson", + "label": "negative", + "script": "latin" + }, + { + "name": "susan richard", + "label": "negative", + "script": "latin" + }, + { + "name": "robert miller", + "label": "negative", + "script": "latin" + }, + { + "name": "diane clarke", + "label": "negative", + "script": "latin" + }, + { + "name": "claire white", + "label": "negative", + "script": "latin" + }, + { + "name": "peter johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole matthews", + "label": "negative", + "script": "latin" + }, + { + "name": "jorge reynolds", + "label": "negative", + "script": "latin" + }, + { + "name": "rita carter", + "label": "negative", + "script": "latin" + }, + { + "name": "juan murphy", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Swap adjacent syllables.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_syllables" + ], + "rule_descriptions": { + "swap_adjacent_syllables": "Swap adjacent syllables" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "sarah white", + "label": "negative", + "script": "latin" + }, + { + "name": "jaime dunn", + "label": "negative", + "script": "latin" + }, + { + "name": "john davis", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin ramos", + "label": "negative", + "script": "latin" + }, + { + "name": "susan peterson", + "label": "negative", + "script": "latin" + }, + { + "name": "albert bell", + "label": "negative", + "script": "latin" + }, + { + "name": "lynne murphy", + "label": "negative", + "script": "latin" + }, + { + "name": "hugh young", + "label": "negative", + "script": "latin" + }, + { + "name": "conor vargas", + "label": "negative", + "script": "latin" + }, + { + "name": "joann bailey", + "label": "negative", + "script": "latin" + }, + { + "name": "teresa thompson", + "label": "negative", + "script": "latin" + }, + { + "name": "kathleen oliver", + "label": "negative", + "script": "latin" + }, + { + "name": "jason page", + "label": "negative", + "script": "latin" + }, + { + "name": "john adams", + "label": "negative", + "script": "latin" + }, + { + "name": "keith alexander", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Swap adjacent consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_consonants" + ], + "rule_descriptions": { + "swap_adjacent_consonants": "Swap adjacent consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "donald moreno", + "label": "negative", + "script": "latin" + }, + { + "name": "maureen garza", + "label": "negative", + "script": "latin" + }, + { + "name": "roy miller", + "label": "negative", + "script": "latin" + }, + { + "name": "laura bell", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer roth", + "label": "negative", + "script": "latin" + }, + { + "name": "zachary oconnor", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel key", + "label": "negative", + "script": "latin" + }, + { + "name": "patricia evans", + "label": "negative", + "script": "latin" + }, + { + "name": "tom ortiz", + "label": "negative", + "script": "latin" + }, + { + "name": "paul morales", + "label": "negative", + "script": "latin" + }, + { + "name": "kimberly jones", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher smart", + "label": "negative", + "script": "latin" + }, + { + "name": "linda martin", + "label": "negative", + "script": "latin" + }, + { + "name": "benjamin cross", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley holt", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Abbreviate name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_abbreviations" + ], + "rule_descriptions": { + "shorten_name_to_abbreviations": "Abbreviate name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "julia rivera", + "label": "negative", + "script": "latin" + }, + { + "name": "patrick salazar", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda carrillo", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer hurst", + "label": "negative", + "script": "latin" + }, + { + "name": "johnny olson", + "label": "negative", + "script": "latin" + }, + { + "name": "david taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "emily moore", + "label": "negative", + "script": "latin" + }, + { + "name": "shaun turner", + "label": "negative", + "script": "latin" + }, + { + "name": "linda miller", + "label": "negative", + "script": "latin" + }, + { + "name": "luke adams", + "label": "negative", + "script": "latin" + }, + { + "name": "joanne johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy wise", + "label": "negative", + "script": "latin" + }, + { + "name": "david harding", + "label": "negative", + "script": "latin" + }, + { + "name": "chad jones", + "label": "negative", + "script": "latin" + }, + { + "name": "alfred palmer", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Replace spaces with special characters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_spaces_with_random_special_characters" + ], + "rule_descriptions": { + "replace_spaces_with_random_special_characters": "Replace spaces with special characters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "johnny williams", + "label": "negative", + "script": "latin" + }, + { + "name": "cheryl daniel", + "label": "negative", + "script": "latin" + }, + { + "name": "cody wallace", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle leach", + "label": "negative", + "script": "latin" + }, + { + "name": "linda clarke", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "robert riley", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua davis", + "label": "negative", + "script": "latin" + }, + { + "name": "kenneth king", + "label": "negative", + "script": "latin" + }, + { + "name": "rebecca sandoval", + "label": "negative", + "script": "latin" + }, + { + "name": "glenn hutchinson", + "label": "negative", + "script": "latin" + }, + { + "name": "malcolm padilla", + "label": "negative", + "script": "latin" + }, + { + "name": "april pena", + "label": "negative", + "script": "latin" + }, + { + "name": "john myers", + "label": "negative", + "script": "latin" + }, + { + "name": "nicholas washington", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Swap adjacent consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_consonants" + ], + "rule_descriptions": { + "swap_adjacent_consonants": "Swap adjacent consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "naomi garcia", + "label": "negative", + "script": "latin" + }, + { + "name": "michael murphy", + "label": "negative", + "script": "latin" + }, + { + "name": "dennis patel", + "label": "negative", + "script": "latin" + }, + { + "name": "terrence williams", + "label": "negative", + "script": "latin" + }, + { + "name": "rachel cooke", + "label": "negative", + "script": "latin" + }, + { + "name": "samantha allen", + "label": "negative", + "script": "latin" + }, + { + "name": "monica johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie miller", + "label": "negative", + "script": "latin" + }, + { + "name": "michael jackson", + "label": "negative", + "script": "latin" + }, + { + "name": "lynda barnes", + "label": "negative", + "script": "latin" + }, + { + "name": "michael noble", + "label": "negative", + "script": "latin" + }, + { + "name": "kelly chandler", + "label": "negative", + "script": "latin" + }, + { + "name": "peter gardner", + "label": "negative", + "script": "latin" + }, + { + "name": "tyler hernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "maria mason", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap adjacent syllables, and Add a title prefix (Mr., Dr., etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_syllables", + "add_random_leading_title" + ], + "rule_descriptions": { + "swap_adjacent_syllables": "Swap adjacent syllables", + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "pamela key", + "label": "negative", + "script": "latin" + }, + { + "name": "katherine thomas", + "label": "negative", + "script": "latin" + }, + { + "name": "annette reed", + "label": "negative", + "script": "latin" + }, + { + "name": "steven robertson", + "label": "negative", + "script": "latin" + }, + { + "name": "crystal kelly", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica torres", + "label": "negative", + "script": "latin" + }, + { + "name": "shelly day", + "label": "negative", + "script": "latin" + }, + { + "name": "cameron bray", + "label": "negative", + "script": "latin" + }, + { + "name": "jenna singh", + "label": "negative", + "script": "latin" + }, + { + "name": "michael flynn", + "label": "negative", + "script": "latin" + }, + { + "name": "brian adams", + "label": "negative", + "script": "latin" + }, + { + "name": "douglas davies", + "label": "negative", + "script": "latin" + }, + { + "name": "phillip walker", + "label": "negative", + "script": "latin" + }, + { + "name": "debra warner", + "label": "negative", + "script": "latin" + }, + { + "name": "carl morris", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap adjacent syllables, Reorder name parts, and Add a title suffix (Jr., PhD, etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_syllables", + "name_parts_permutations", + "add_random_trailing_title" + ], + "rule_descriptions": { + "swap_adjacent_syllables": "Swap adjacent syllables", + "name_parts_permutations": "Reorder name parts", + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "john raymond", + "label": "negative", + "script": "latin" + }, + { + "name": "douglas robertson", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua roman", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua harris", + "label": "negative", + "script": "latin" + }, + { + "name": "vincent taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "richard castillo", + "label": "negative", + "script": "latin" + }, + { + "name": "john kramer", + "label": "negative", + "script": "latin" + }, + { + "name": "michael camacho", + "label": "negative", + "script": "latin" + }, + { + "name": "georgina martinez", + "label": "negative", + "script": "latin" + }, + { + "name": "sophie austin", + "label": "negative", + "script": "latin" + }, + { + "name": "elizabeth kim", + "label": "negative", + "script": "latin" + }, + { + "name": "jason white", + "label": "negative", + "script": "latin" + }, + { + "name": "belinda ali", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley washington", + "label": "negative", + "script": "latin" + }, + { + "name": "corey white", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap random adjacent letters, and Add a title suffix (Jr., PhD, etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_random_letter", + "add_random_trailing_title" + ], + "rule_descriptions": { + "swap_random_letter": "Swap random adjacent letters", + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "jack larson", + "label": "negative", + "script": "latin" + }, + { + "name": "vincent harding", + "label": "negative", + "script": "latin" + }, + { + "name": "nicholas macdonald", + "label": "negative", + "script": "latin" + }, + { + "name": "jack hansen", + "label": "negative", + "script": "latin" + }, + { + "name": "megan williams", + "label": "negative", + "script": "latin" + }, + { + "name": "jeff hooper", + "label": "negative", + "script": "latin" + }, + { + "name": "jackie anderson", + "label": "negative", + "script": "latin" + }, + { + "name": "miguel salazar", + "label": "negative", + "script": "latin" + }, + { + "name": "harold harding", + "label": "negative", + "script": "latin" + }, + { + "name": "erin hart", + "label": "negative", + "script": "latin" + }, + { + "name": "angel hall", + "label": "negative", + "script": "latin" + }, + { + "name": "samantha barnes", + "label": "negative", + "script": "latin" + }, + { + "name": "george burns", + "label": "negative", + "script": "latin" + }, + { + "name": "adam moyer", + "label": "negative", + "script": "latin" + }, + { + "name": "zachary crawford", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Insert a random letter, and Swap adjacent consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "insert_random_letter", + "swap_adjacent_consonants" + ], + "rule_descriptions": { + "insert_random_letter": "Insert a random letter", + "swap_adjacent_consonants": "Swap adjacent consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "diana pearce", + "label": "negative", + "script": "latin" + }, + { + "name": "brandon noble", + "label": "negative", + "script": "latin" + }, + { + "name": "brooke campbell", + "label": "negative", + "script": "latin" + }, + { + "name": "cynthia davis", + "label": "negative", + "script": "latin" + }, + { + "name": "joan chase", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah potter", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie spence", + "label": "negative", + "script": "latin" + }, + { + "name": "gerard larsen", + "label": "negative", + "script": "latin" + }, + { + "name": "nathan lopez", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole travis", + "label": "negative", + "script": "latin" + }, + { + "name": "stephen strickland", + "label": "negative", + "script": "latin" + }, + { + "name": "joan west", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua watson", + "label": "negative", + "script": "latin" + }, + { + "name": "julia davis", + "label": "negative", + "script": "latin" + }, + { + "name": "elizabeth butler", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace random vowels with different vowels, and Replace double letters with a single letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_vowel_with_random_vowel", + "replace_double_letters_with_single_letter" + ], + "rule_descriptions": { + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels", + "replace_double_letters_with_single_letter": "Replace double letters with a single letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "brian lopez", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew dodson", + "label": "negative", + "script": "latin" + }, + { + "name": "katherine ayers", + "label": "negative", + "script": "latin" + }, + { + "name": "frank griffith", + "label": "negative", + "script": "latin" + }, + { + "name": "eric wood", + "label": "negative", + "script": "latin" + }, + { + "name": "sara callahan", + "label": "negative", + "script": "latin" + }, + { + "name": "jill compton", + "label": "negative", + "script": "latin" + }, + { + "name": "jon alexander", + "label": "negative", + "script": "latin" + }, + { + "name": "mark ramirez", + "label": "negative", + "script": "latin" + }, + { + "name": "vanessa erickson", + "label": "negative", + "script": "latin" + }, + { + "name": "catherine brown", + "label": "negative", + "script": "latin" + }, + { + "name": "michael hicks", + "label": "negative", + "script": "latin" + }, + { + "name": "linda leblanc", + "label": "negative", + "script": "latin" + }, + { + "name": "mark white", + "label": "negative", + "script": "latin" + }, + { + "name": "sean warner", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Delete a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "delete_random_letter" + ], + "rule_descriptions": { + "delete_random_letter": "Delete a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "holly campbell", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa brown", + "label": "negative", + "script": "latin" + }, + { + "name": "ariel strong", + "label": "negative", + "script": "latin" + }, + { + "name": "sherry taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "hugh carter", + "label": "negative", + "script": "latin" + }, + { + "name": "michael hoffman", + "label": "negative", + "script": "latin" + }, + { + "name": "sean allen", + "label": "negative", + "script": "latin" + }, + { + "name": "jason barton", + "label": "negative", + "script": "latin" + }, + { + "name": "benjamin juarez", + "label": "negative", + "script": "latin" + }, + { + "name": "amber paul", + "label": "negative", + "script": "latin" + }, + { + "name": "david hood", + "label": "negative", + "script": "latin" + }, + { + "name": "adam davies", + "label": "negative", + "script": "latin" + }, + { + "name": "brittany ramirez", + "label": "negative", + "script": "latin" + }, + { + "name": "amber gomez", + "label": "negative", + "script": "latin" + }, + { + "name": "karen taylor", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Reorder name parts, and Swap random adjacent letters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "name_parts_permutations", + "swap_random_letter" + ], + "rule_descriptions": { + "name_parts_permutations": "Reorder name parts", + "swap_random_letter": "Swap random adjacent letters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "robert bryan", + "label": "negative", + "script": "latin" + }, + { + "name": "cathy diaz", + "label": "negative", + "script": "latin" + }, + { + "name": "claire snyder", + "label": "negative", + "script": "latin" + }, + { + "name": "ryan davidson", + "label": "negative", + "script": "latin" + }, + { + "name": "alexandra castillo", + "label": "negative", + "script": "latin" + }, + { + "name": "dustin taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "alex taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "corey watts", + "label": "negative", + "script": "latin" + }, + { + "name": "katie mathews", + "label": "negative", + "script": "latin" + }, + { + "name": "jo johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "sheri robson", + "label": "negative", + "script": "latin" + }, + { + "name": "carl bright", + "label": "negative", + "script": "latin" + }, + { + "name": "brett thompson", + "label": "negative", + "script": "latin" + }, + { + "name": "irene crawford", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie daniels", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Remove a random consonant.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_consonant" + ], + "rule_descriptions": { + "remove_random_consonant": "Remove a random consonant" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "erin lopez", + "label": "negative", + "script": "latin" + }, + { + "name": "john richards", + "label": "negative", + "script": "latin" + }, + { + "name": "donald pollard", + "label": "negative", + "script": "latin" + }, + { + "name": "michael olson", + "label": "negative", + "script": "latin" + }, + { + "name": "cynthia maldonado", + "label": "negative", + "script": "latin" + }, + { + "name": "neil thornton", + "label": "negative", + "script": "latin" + }, + { + "name": "kyle alvarez", + "label": "negative", + "script": "latin" + }, + { + "name": "jesse wheeler", + "label": "negative", + "script": "latin" + }, + { + "name": "michael gonzalez", + "label": "negative", + "script": "latin" + }, + { + "name": "caroline avery", + "label": "negative", + "script": "latin" + }, + { + "name": "arthur owens", + "label": "negative", + "script": "latin" + }, + { + "name": "jason horne", + "label": "negative", + "script": "latin" + }, + { + "name": "russell campbell", + "label": "negative", + "script": "latin" + }, + { + "name": "stuart clarke", + "label": "negative", + "script": "latin" + }, + { + "name": "elizabeth sanders", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title prefix (Mr., Dr., etc.), and Replace spaces with special characters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_leading_title", + "replace_spaces_with_random_special_characters" + ], + "rule_descriptions": { + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)", + "replace_spaces_with_random_special_characters": "Replace spaces with special characters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "andrew baker", + "label": "negative", + "script": "latin" + }, + { + "name": "linda jones", + "label": "negative", + "script": "latin" + }, + { + "name": "darren ball", + "label": "negative", + "script": "latin" + }, + { + "name": "danielle padilla", + "label": "negative", + "script": "latin" + }, + { + "name": "kimberly harrison", + "label": "negative", + "script": "latin" + }, + { + "name": "geraldine martinez", + "label": "negative", + "script": "latin" + }, + { + "name": "louise moore", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph gutierrez", + "label": "negative", + "script": "latin" + }, + { + "name": "cheryl smith", + "label": "negative", + "script": "latin" + }, + { + "name": "betty smith", + "label": "negative", + "script": "latin" + }, + { + "name": "jeremy roy", + "label": "negative", + "script": "latin" + }, + { + "name": "karen howe", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda rogers", + "label": "negative", + "script": "latin" + }, + { + "name": "tanya woods", + "label": "negative", + "script": "latin" + }, + { + "name": "mark fox", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title prefix (Mr., Dr., etc.), and Remove all spaces.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_leading_title", + "remove_all_spaces" + ], + "rule_descriptions": { + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)", + "remove_all_spaces": "Remove all spaces" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "eileen morris", + "label": "negative", + "script": "latin" + }, + { + "name": "caitlin shah", + "label": "negative", + "script": "latin" + }, + { + "name": "paul reynolds", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole flores", + "label": "negative", + "script": "latin" + }, + { + "name": "cristian peterson", + "label": "negative", + "script": "latin" + }, + { + "name": "steven cantrell", + "label": "negative", + "script": "latin" + }, + { + "name": "keith roberts", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy davidson", + "label": "negative", + "script": "latin" + }, + { + "name": "kimberly dawson", + "label": "negative", + "script": "latin" + }, + { + "name": "victor campbell", + "label": "negative", + "script": "latin" + }, + { + "name": "keith blevins", + "label": "negative", + "script": "latin" + }, + { + "name": "destiny cooper", + "label": "negative", + "script": "latin" + }, + { + "name": "dorothy perez", + "label": "negative", + "script": "latin" + }, + { + "name": "dylan smith", + "label": "negative", + "script": "latin" + }, + { + "name": "mark oneal", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Abbreviate name parts, and Replace random vowels with different vowels.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_abbreviations", + "replace_random_vowel_with_random_vowel" + ], + "rule_descriptions": { + "shorten_name_to_abbreviations": "Abbreviate name parts", + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "david smith", + "label": "negative", + "script": "latin" + }, + { + "name": "justin ellis", + "label": "negative", + "script": "latin" + }, + { + "name": "benjamin ford", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew gonzalez", + "label": "negative", + "script": "latin" + }, + { + "name": "jesse fox", + "label": "negative", + "script": "latin" + }, + { + "name": "jamie mills", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle moore", + "label": "negative", + "script": "latin" + }, + { + "name": "robin williams", + "label": "negative", + "script": "latin" + }, + { + "name": "michele reilly", + "label": "negative", + "script": "latin" + }, + { + "name": "becky johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "christie sanchez", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffrey morgan", + "label": "negative", + "script": "latin" + }, + { + "name": "kendra chapman", + "label": "negative", + "script": "latin" + }, + { + "name": "arthur delgado", + "label": "negative", + "script": "latin" + }, + { + "name": "ernest carlson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace random vowels with different vowels, and Abbreviate name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_vowel_with_random_vowel", + "shorten_name_to_abbreviations" + ], + "rule_descriptions": { + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels", + "shorten_name_to_abbreviations": "Abbreviate name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "michelle french", + "label": "negative", + "script": "latin" + }, + { + "name": "william smith", + "label": "negative", + "script": "latin" + }, + { + "name": "arthur hamilton", + "label": "negative", + "script": "latin" + }, + { + "name": "holly mendoza", + "label": "negative", + "script": "latin" + }, + { + "name": "kayla rhodes", + "label": "negative", + "script": "latin" + }, + { + "name": "brian patel", + "label": "negative", + "script": "latin" + }, + { + "name": "jonathan patterson", + "label": "negative", + "script": "latin" + }, + { + "name": "hilary jenkins", + "label": "negative", + "script": "latin" + }, + { + "name": "jonathan cooper", + "label": "negative", + "script": "latin" + }, + { + "name": "christine hernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "andrea spencer", + "label": "negative", + "script": "latin" + }, + { + "name": "sara gonzalez", + "label": "negative", + "script": "latin" + }, + { + "name": "sheila davis", + "label": "negative", + "script": "latin" + }, + { + "name": "john contreras", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew charles", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Swap random adjacent letters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_random_letter" + ], + "rule_descriptions": { + "swap_random_letter": "Swap random adjacent letters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "deborah brennan", + "label": "negative", + "script": "latin" + }, + { + "name": "emily martin", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "sharon miller", + "label": "negative", + "script": "latin" + }, + { + "name": "gregory watson", + "label": "negative", + "script": "latin" + }, + { + "name": "marcia jones", + "label": "negative", + "script": "latin" + }, + { + "name": "kirsty hunter", + "label": "negative", + "script": "latin" + }, + { + "name": "amber joseph", + "label": "negative", + "script": "latin" + }, + { + "name": "david jenkins", + "label": "negative", + "script": "latin" + }, + { + "name": "mary hughes", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel mitchell", + "label": "negative", + "script": "latin" + }, + { + "name": "carole thomas", + "label": "negative", + "script": "latin" + }, + { + "name": "julie hunt", + "label": "negative", + "script": "latin" + }, + { + "name": "eric martin", + "label": "negative", + "script": "latin" + }, + { + "name": "danny yates", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove a random consonant, Duplicate a random letter, and Replace random vowels with different vowels.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_consonant", + "duplicate_random_letter_as_double_letter", + "replace_random_vowel_with_random_vowel" + ], + "rule_descriptions": { + "remove_random_consonant": "Remove a random consonant", + "duplicate_random_letter_as_double_letter": "Duplicate a random letter", + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "kara meyer", + "label": "negative", + "script": "latin" + }, + { + "name": "andrea cooley", + "label": "negative", + "script": "latin" + }, + { + "name": "bethany bautista", + "label": "negative", + "script": "latin" + }, + { + "name": "hunter hale", + "label": "negative", + "script": "latin" + }, + { + "name": "gillian hughes", + "label": "negative", + "script": "latin" + }, + { + "name": "amber knight", + "label": "negative", + "script": "latin" + }, + { + "name": "patrick castillo", + "label": "negative", + "script": "latin" + }, + { + "name": "cheryl king", + "label": "negative", + "script": "latin" + }, + { + "name": "terry johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "albert jones", + "label": "negative", + "script": "latin" + }, + { + "name": "david lee", + "label": "negative", + "script": "latin" + }, + { + "name": "dillon wright", + "label": "negative", + "script": "latin" + }, + { + "name": "shaun mellor", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph sanchez", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffrey smith", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Use first name initial with last name, and Add a title suffix (Jr., PhD, etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "initial_only_first_name", + "add_random_trailing_title" + ], + "rule_descriptions": { + "initial_only_first_name": "Use first name initial with last name", + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "gregory newman", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle brown", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda knowles", + "label": "negative", + "script": "latin" + }, + { + "name": "deborah harmon", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa brooks", + "label": "negative", + "script": "latin" + }, + { + "name": "james miller", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley brown", + "label": "negative", + "script": "latin" + }, + { + "name": "courtney scott", + "label": "negative", + "script": "latin" + }, + { + "name": "sandra brock", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin petersen", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy hernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "lauren robinson", + "label": "negative", + "script": "latin" + }, + { + "name": "katherine fitzpatrick", + "label": "negative", + "script": "latin" + }, + { + "name": "beth richardson", + "label": "negative", + "script": "latin" + }, + { + "name": "ann farrell", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Add a title prefix (Mr., Dr., etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_leading_title" + ], + "rule_descriptions": { + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "miranda smith", + "label": "negative", + "script": "latin" + }, + { + "name": "juan patton", + "label": "negative", + "script": "latin" + }, + { + "name": "amelia moore", + "label": "negative", + "script": "latin" + }, + { + "name": "david warren", + "label": "negative", + "script": "latin" + }, + { + "name": "steven jones", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "glenda walsh", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffrey guerrero", + "label": "negative", + "script": "latin" + }, + { + "name": "beverley johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "lori adams", + "label": "negative", + "script": "latin" + }, + { + "name": "mia booth", + "label": "negative", + "script": "latin" + }, + { + "name": "holly reid", + "label": "negative", + "script": "latin" + }, + { + "name": "sheila duncan", + "label": "negative", + "script": "latin" + }, + { + "name": "brian knight", + "label": "negative", + "script": "latin" + }, + { + "name": "brian jordan", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Insert a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "insert_random_letter" + ], + "rule_descriptions": { + "insert_random_letter": "Insert a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "tom hughes", + "label": "negative", + "script": "latin" + }, + { + "name": "patrick rios", + "label": "negative", + "script": "latin" + }, + { + "name": "gillian chen", + "label": "negative", + "script": "latin" + }, + { + "name": "veronica duffy", + "label": "negative", + "script": "latin" + }, + { + "name": "david scott", + "label": "negative", + "script": "latin" + }, + { + "name": "barbara rogers", + "label": "negative", + "script": "latin" + }, + { + "name": "cynthia stanley", + "label": "negative", + "script": "latin" + }, + { + "name": "andrew spencer", + "label": "negative", + "script": "latin" + }, + { + "name": "jemma schaefer", + "label": "negative", + "script": "latin" + }, + { + "name": "charles rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "dean middleton", + "label": "negative", + "script": "latin" + }, + { + "name": "dylan jones", + "label": "negative", + "script": "latin" + }, + { + "name": "katie reed", + "label": "negative", + "script": "latin" + }, + { + "name": "madeline howell", + "label": "negative", + "script": "latin" + }, + { + "name": "tracy campbell", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove a random consonant, and Use first name initial with last name.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_consonant", + "initial_only_first_name" + ], + "rule_descriptions": { + "remove_random_consonant": "Remove a random consonant", + "initial_only_first_name": "Use first name initial with last name" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "jorge parker", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda larsen", + "label": "negative", + "script": "latin" + }, + { + "name": "callum brewer", + "label": "negative", + "script": "latin" + }, + { + "name": "john reynolds", + "label": "negative", + "script": "latin" + }, + { + "name": "tiffany jackson", + "label": "negative", + "script": "latin" + }, + { + "name": "john moore", + "label": "negative", + "script": "latin" + }, + { + "name": "joyce morales", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas morris", + "label": "negative", + "script": "latin" + }, + { + "name": "angela wheeler", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer castro", + "label": "negative", + "script": "latin" + }, + { + "name": "bethany powell", + "label": "negative", + "script": "latin" + }, + { + "name": "kristen harrison", + "label": "negative", + "script": "latin" + }, + { + "name": "brooke myers", + "label": "negative", + "script": "latin" + }, + { + "name": "jodie davis", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew peck", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove a random consonant, Swap adjacent syllables, and Abbreviate name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_consonant", + "swap_adjacent_syllables", + "shorten_name_to_abbreviations" + ], + "rule_descriptions": { + "remove_random_consonant": "Remove a random consonant", + "swap_adjacent_syllables": "Swap adjacent syllables", + "shorten_name_to_abbreviations": "Abbreviate name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "jason may", + "label": "negative", + "script": "latin" + }, + { + "name": "jean bennett", + "label": "negative", + "script": "latin" + }, + { + "name": "gary hyde", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa dorsey", + "label": "negative", + "script": "latin" + }, + { + "name": "kelly zimmerman", + "label": "negative", + "script": "latin" + }, + { + "name": "andrew miller", + "label": "negative", + "script": "latin" + }, + { + "name": "douglas santos", + "label": "negative", + "script": "latin" + }, + { + "name": "ricky ingram", + "label": "negative", + "script": "latin" + }, + { + "name": "troy leonard", + "label": "negative", + "script": "latin" + }, + { + "name": "hazel long", + "label": "negative", + "script": "latin" + }, + { + "name": "yvette lawson", + "label": "negative", + "script": "latin" + }, + { + "name": "lauren martin", + "label": "negative", + "script": "latin" + }, + { + "name": "morgan carr", + "label": "negative", + "script": "latin" + }, + { + "name": "paige read", + "label": "negative", + "script": "latin" + }, + { + "name": "leigh thomas", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Insert a random letter, and Convert name to initials.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "insert_random_letter", + "shorten_name_to_initials" + ], + "rule_descriptions": { + "insert_random_letter": "Insert a random letter", + "shorten_name_to_initials": "Convert name to initials" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "dennis burke", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas wright", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffrey bishop", + "label": "negative", + "script": "latin" + }, + { + "name": "francis blankenship", + "label": "negative", + "script": "latin" + }, + { + "name": "kimberly mitchell", + "label": "negative", + "script": "latin" + }, + { + "name": "nigel bell", + "label": "negative", + "script": "latin" + }, + { + "name": "james wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "michael aguirre", + "label": "negative", + "script": "latin" + }, + { + "name": "cameron rivera", + "label": "negative", + "script": "latin" + }, + { + "name": "raymond davies", + "label": "negative", + "script": "latin" + }, + { + "name": "kyle lawrence", + "label": "negative", + "script": "latin" + }, + { + "name": "kathy jordan", + "label": "negative", + "script": "latin" + }, + { + "name": "kara calderon", + "label": "negative", + "script": "latin" + }, + { + "name": "brenda sanchez", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda armstrong", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap adjacent syllables, and Swap adjacent consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_syllables", + "swap_adjacent_consonants" + ], + "rule_descriptions": { + "swap_adjacent_syllables": "Swap adjacent syllables", + "swap_adjacent_consonants": "Swap adjacent consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "frances noble", + "label": "negative", + "script": "latin" + }, + { + "name": "emma morrow", + "label": "negative", + "script": "latin" + }, + { + "name": "william duncan", + "label": "negative", + "script": "latin" + }, + { + "name": "maria fuller", + "label": "negative", + "script": "latin" + }, + { + "name": "albert phillips", + "label": "negative", + "script": "latin" + }, + { + "name": "bradley carroll", + "label": "negative", + "script": "latin" + }, + { + "name": "jonathan lewis", + "label": "negative", + "script": "latin" + }, + { + "name": "linda edwards", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer hoffman", + "label": "negative", + "script": "latin" + }, + { + "name": "jacqueline hanson", + "label": "negative", + "script": "latin" + }, + { + "name": "andrew lewis", + "label": "negative", + "script": "latin" + }, + { + "name": "alexander jones", + "label": "negative", + "script": "latin" + }, + { + "name": "joe cooper", + "label": "negative", + "script": "latin" + }, + { + "name": "bryan walton", + "label": "negative", + "script": "latin" + }, + { + "name": "edward tucker", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove all spaces, and Swap adjacent consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_all_spaces", + "swap_adjacent_consonants" + ], + "rule_descriptions": { + "remove_all_spaces": "Remove all spaces", + "swap_adjacent_consonants": "Swap adjacent consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "courtney gregory", + "label": "negative", + "script": "latin" + }, + { + "name": "tracey carson", + "label": "negative", + "script": "latin" + }, + { + "name": "margaret richards", + "label": "negative", + "script": "latin" + }, + { + "name": "peter chandler", + "label": "negative", + "script": "latin" + }, + { + "name": "omar kelly", + "label": "negative", + "script": "latin" + }, + { + "name": "dale phillips", + "label": "negative", + "script": "latin" + }, + { + "name": "johnny fowler", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley shah", + "label": "negative", + "script": "latin" + }, + { + "name": "paige griffiths", + "label": "negative", + "script": "latin" + }, + { + "name": "bethan carter", + "label": "negative", + "script": "latin" + }, + { + "name": "shawna sanchez", + "label": "negative", + "script": "latin" + }, + { + "name": "john smith", + "label": "negative", + "script": "latin" + }, + { + "name": "heather hampton", + "label": "negative", + "script": "latin" + }, + { + "name": "martyn allen", + "label": "negative", + "script": "latin" + }, + { + "name": "gordon gardner", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title suffix (Jr., PhD, etc.), and Replace random vowels with different vowels.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_trailing_title", + "replace_random_vowel_with_random_vowel" + ], + "rule_descriptions": { + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)", + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "rachel montoya", + "label": "negative", + "script": "latin" + }, + { + "name": "kristina barnes", + "label": "negative", + "script": "latin" + }, + { + "name": "alexis baker", + "label": "negative", + "script": "latin" + }, + { + "name": "rebecca smith", + "label": "negative", + "script": "latin" + }, + { + "name": "alice castillo", + "label": "negative", + "script": "latin" + }, + { + "name": "virginia lee", + "label": "negative", + "script": "latin" + }, + { + "name": "george diaz", + "label": "negative", + "script": "latin" + }, + { + "name": "mary simon", + "label": "negative", + "script": "latin" + }, + { + "name": "arthur lewis", + "label": "negative", + "script": "latin" + }, + { + "name": "erin khan", + "label": "negative", + "script": "latin" + }, + { + "name": "janice arnold", + "label": "negative", + "script": "latin" + }, + { + "name": "frederick cook", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle stuart", + "label": "negative", + "script": "latin" + }, + { + "name": "gilbert ross", + "label": "negative", + "script": "latin" + }, + { + "name": "allen wilson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Replace random vowels with different vowels.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_vowel_with_random_vowel" + ], + "rule_descriptions": { + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "christopher rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "arthur ross", + "label": "negative", + "script": "latin" + }, + { + "name": "amber cameron", + "label": "negative", + "script": "latin" + }, + { + "name": "julie o'sullivan", + "label": "negative", + "script": "latin" + }, + { + "name": "debra griffiths", + "label": "negative", + "script": "latin" + }, + { + "name": "michael brown", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffrey lawson", + "label": "negative", + "script": "latin" + }, + { + "name": "beverley finley", + "label": "negative", + "script": "latin" + }, + { + "name": "laura washington", + "label": "negative", + "script": "latin" + }, + { + "name": "nicholas jordan", + "label": "negative", + "script": "latin" + }, + { + "name": "samuel hall", + "label": "negative", + "script": "latin" + }, + { + "name": "holly cole", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley lloyd", + "label": "negative", + "script": "latin" + }, + { + "name": "shane clarke", + "label": "negative", + "script": "latin" + }, + { + "name": "heather brown", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Insert a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "insert_random_letter" + ], + "rule_descriptions": { + "insert_random_letter": "Insert a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "ryan grant", + "label": "negative", + "script": "latin" + }, + { + "name": "adam miller", + "label": "negative", + "script": "latin" + }, + { + "name": "james morgan", + "label": "negative", + "script": "latin" + }, + { + "name": "david delgado", + "label": "negative", + "script": "latin" + }, + { + "name": "brian lutz", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa mcdonald", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffrey bradley", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas morris", + "label": "negative", + "script": "latin" + }, + { + "name": "ryan davis", + "label": "negative", + "script": "latin" + }, + { + "name": "stacie porter", + "label": "negative", + "script": "latin" + }, + { + "name": "kelly smith", + "label": "negative", + "script": "latin" + }, + { + "name": "adam hanson", + "label": "negative", + "script": "latin" + }, + { + "name": "larry ingram", + "label": "negative", + "script": "latin" + }, + { + "name": "damian garcia", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew mitchell", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Insert a random letter, Remove all spaces, and Swap adjacent syllables.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "insert_random_letter", + "remove_all_spaces", + "swap_adjacent_syllables" + ], + "rule_descriptions": { + "insert_random_letter": "Insert a random letter", + "remove_all_spaces": "Remove all spaces", + "swap_adjacent_syllables": "Swap adjacent syllables" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "denise curry", + "label": "negative", + "script": "latin" + }, + { + "name": "desiree duarte", + "label": "negative", + "script": "latin" + }, + { + "name": "marcus rubio", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica wood", + "label": "negative", + "script": "latin" + }, + { + "name": "scott valencia", + "label": "negative", + "script": "latin" + }, + { + "name": "nicholas zuniga", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "michael garcia", + "label": "negative", + "script": "latin" + }, + { + "name": "tyler manning", + "label": "negative", + "script": "latin" + }, + { + "name": "brandi faulkner", + "label": "negative", + "script": "latin" + }, + { + "name": "evan pope", + "label": "negative", + "script": "latin" + }, + { + "name": "cristina ramirez", + "label": "negative", + "script": "latin" + }, + { + "name": "eric vincent", + "label": "negative", + "script": "latin" + }, + { + "name": "hannah butler", + "label": "negative", + "script": "latin" + }, + { + "name": "juan branch", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Add a title prefix (Mr., Dr., etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_leading_title" + ], + "rule_descriptions": { + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "ashley brewer", + "label": "negative", + "script": "latin" + }, + { + "name": "brian price", + "label": "negative", + "script": "latin" + }, + { + "name": "shannon harvey", + "label": "negative", + "script": "latin" + }, + { + "name": "william sullivan", + "label": "negative", + "script": "latin" + }, + { + "name": "ryan hughes", + "label": "negative", + "script": "latin" + }, + { + "name": "vanessa martin", + "label": "negative", + "script": "latin" + }, + { + "name": "ronald knox", + "label": "negative", + "script": "latin" + }, + { + "name": "clifford williams", + "label": "negative", + "script": "latin" + }, + { + "name": "kimberly watson", + "label": "negative", + "script": "latin" + }, + { + "name": "hilary kennedy", + "label": "negative", + "script": "latin" + }, + { + "name": "mary thomas", + "label": "negative", + "script": "latin" + }, + { + "name": "elizabeth duarte", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle bailey", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel romero", + "label": "negative", + "script": "latin" + }, + { + "name": "kayleigh fisher", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Duplicate a random letter, and Abbreviate name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "duplicate_random_letter_as_double_letter", + "shorten_name_to_abbreviations" + ], + "rule_descriptions": { + "duplicate_random_letter_as_double_letter": "Duplicate a random letter", + "shorten_name_to_abbreviations": "Abbreviate name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "john smith", + "label": "negative", + "script": "latin" + }, + { + "name": "jill atkinson", + "label": "negative", + "script": "latin" + }, + { + "name": "laura chambers", + "label": "negative", + "script": "latin" + }, + { + "name": "allen metcalfe", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica stone", + "label": "negative", + "script": "latin" + }, + { + "name": "nancy taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "ricky stanley", + "label": "negative", + "script": "latin" + }, + { + "name": "michael miller", + "label": "negative", + "script": "latin" + }, + { + "name": "declan davis", + "label": "negative", + "script": "latin" + }, + { + "name": "janice stevens", + "label": "negative", + "script": "latin" + }, + { + "name": "michael stephens", + "label": "negative", + "script": "latin" + }, + { + "name": "monica ross", + "label": "negative", + "script": "latin" + }, + { + "name": "deborah brown", + "label": "negative", + "script": "latin" + }, + { + "name": "james norman", + "label": "negative", + "script": "latin" + }, + { + "name": "karen price", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Convert name to initials.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_initials" + ], + "rule_descriptions": { + "shorten_name_to_initials": "Convert name to initials" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "tina king", + "label": "negative", + "script": "latin" + }, + { + "name": "larry black", + "label": "negative", + "script": "latin" + }, + { + "name": "allison copeland", + "label": "negative", + "script": "latin" + }, + { + "name": "susan jimenez", + "label": "negative", + "script": "latin" + }, + { + "name": "albert harper", + "label": "negative", + "script": "latin" + }, + { + "name": "diana baker", + "label": "negative", + "script": "latin" + }, + { + "name": "justin anderson", + "label": "negative", + "script": "latin" + }, + { + "name": "sharon bautista", + "label": "negative", + "script": "latin" + }, + { + "name": "connor richards", + "label": "negative", + "script": "latin" + }, + { + "name": "michael king", + "label": "negative", + "script": "latin" + }, + { + "name": "elaine long", + "label": "negative", + "script": "latin" + }, + { + "name": "brett griffin", + "label": "negative", + "script": "latin" + }, + { + "name": "alex diaz", + "label": "negative", + "script": "latin" + }, + { + "name": "patricia larson", + "label": "negative", + "script": "latin" + }, + { + "name": "catherine schmidt", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace spaces with special characters, and Replace double letters with a single letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_spaces_with_random_special_characters", + "replace_double_letters_with_single_letter" + ], + "rule_descriptions": { + "replace_spaces_with_random_special_characters": "Replace spaces with special characters", + "replace_double_letters_with_single_letter": "Replace double letters with a single letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "colleen cox", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer cohen", + "label": "negative", + "script": "latin" + }, + { + "name": "laura carter", + "label": "negative", + "script": "latin" + }, + { + "name": "donald mercado", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa wyatt", + "label": "negative", + "script": "latin" + }, + { + "name": "crystal klein", + "label": "negative", + "script": "latin" + }, + { + "name": "laura gray", + "label": "negative", + "script": "latin" + }, + { + "name": "nigel williams", + "label": "negative", + "script": "latin" + }, + { + "name": "eric hunt", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua wheeler", + "label": "negative", + "script": "latin" + }, + { + "name": "ryan santos", + "label": "negative", + "script": "latin" + }, + { + "name": "philip randall", + "label": "negative", + "script": "latin" + }, + { + "name": "todd kim", + "label": "negative", + "script": "latin" + }, + { + "name": "jasmine hess", + "label": "negative", + "script": "latin" + }, + { + "name": "nicholas valdez", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Convert name to initials, Duplicate a random letter, and Add a title suffix (Jr., PhD, etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_initials", + "duplicate_random_letter_as_double_letter", + "add_random_trailing_title" + ], + "rule_descriptions": { + "shorten_name_to_initials": "Convert name to initials", + "duplicate_random_letter_as_double_letter": "Duplicate a random letter", + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "rebecca lopez", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffrey weber", + "label": "negative", + "script": "latin" + }, + { + "name": "lucy shepherd", + "label": "negative", + "script": "latin" + }, + { + "name": "john cooper", + "label": "negative", + "script": "latin" + }, + { + "name": "jesse khan", + "label": "negative", + "script": "latin" + }, + { + "name": "mark hall", + "label": "negative", + "script": "latin" + }, + { + "name": "laura krause", + "label": "negative", + "script": "latin" + }, + { + "name": "ronald flores", + "label": "negative", + "script": "latin" + }, + { + "name": "craig lawrence", + "label": "negative", + "script": "latin" + }, + { + "name": "benjamin conner", + "label": "negative", + "script": "latin" + }, + { + "name": "nicholas farmer", + "label": "negative", + "script": "latin" + }, + { + "name": "rodney may", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa drake", + "label": "negative", + "script": "latin" + }, + { + "name": "kimberly johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "cathy brown", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Duplicate a random letter, and Add a title suffix (Jr., PhD, etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "duplicate_random_letter_as_double_letter", + "add_random_trailing_title" + ], + "rule_descriptions": { + "duplicate_random_letter_as_double_letter": "Duplicate a random letter", + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "anthony johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "eric wood", + "label": "negative", + "script": "latin" + }, + { + "name": "karen cain", + "label": "negative", + "script": "latin" + }, + { + "name": "lindsey thompson", + "label": "negative", + "script": "latin" + }, + { + "name": "austin reed", + "label": "negative", + "script": "latin" + }, + { + "name": "jaclyn akhtar", + "label": "negative", + "script": "latin" + }, + { + "name": "lori hull", + "label": "negative", + "script": "latin" + }, + { + "name": "alan rice", + "label": "negative", + "script": "latin" + }, + { + "name": "jason turner", + "label": "negative", + "script": "latin" + }, + { + "name": "brenda burnett", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph smith", + "label": "negative", + "script": "latin" + }, + { + "name": "stacey evans", + "label": "negative", + "script": "latin" + }, + { + "name": "elizabeth robinson", + "label": "negative", + "script": "latin" + }, + { + "name": "alice bowman", + "label": "negative", + "script": "latin" + }, + { + "name": "ann brown", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Delete a random letter, and Convert name to initials.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "delete_random_letter", + "shorten_name_to_initials" + ], + "rule_descriptions": { + "delete_random_letter": "Delete a random letter", + "shorten_name_to_initials": "Convert name to initials" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "miranda gray", + "label": "negative", + "script": "latin" + }, + { + "name": "katherine willis", + "label": "negative", + "script": "latin" + }, + { + "name": "kyle davis", + "label": "negative", + "script": "latin" + }, + { + "name": "eric nguyen", + "label": "negative", + "script": "latin" + }, + { + "name": "sophie wells", + "label": "negative", + "script": "latin" + }, + { + "name": "yvonne stevens", + "label": "negative", + "script": "latin" + }, + { + "name": "barbara evans", + "label": "negative", + "script": "latin" + }, + { + "name": "henry garza", + "label": "negative", + "script": "latin" + }, + { + "name": "charles dixon", + "label": "negative", + "script": "latin" + }, + { + "name": "terri greene", + "label": "negative", + "script": "latin" + }, + { + "name": "paul john", + "label": "negative", + "script": "latin" + }, + { + "name": "adam washington", + "label": "negative", + "script": "latin" + }, + { + "name": "stephen johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "lauren coleman", + "label": "negative", + "script": "latin" + }, + { + "name": "erin weeks", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Abbreviate name parts, and Swap adjacent consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_abbreviations", + "swap_adjacent_consonants" + ], + "rule_descriptions": { + "shorten_name_to_abbreviations": "Abbreviate name parts", + "swap_adjacent_consonants": "Swap adjacent consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "danielle grant", + "label": "negative", + "script": "latin" + }, + { + "name": "megan dougherty", + "label": "negative", + "script": "latin" + }, + { + "name": "william barnes", + "label": "negative", + "script": "latin" + }, + { + "name": "tiffany sanders", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley walton", + "label": "negative", + "script": "latin" + }, + { + "name": "larry barnes", + "label": "negative", + "script": "latin" + }, + { + "name": "james garcia", + "label": "negative", + "script": "latin" + }, + { + "name": "john morrison", + "label": "negative", + "script": "latin" + }, + { + "name": "michael wilkins", + "label": "negative", + "script": "latin" + }, + { + "name": "erin cook", + "label": "negative", + "script": "latin" + }, + { + "name": "jermaine henson", + "label": "negative", + "script": "latin" + }, + { + "name": "wyatt brock", + "label": "negative", + "script": "latin" + }, + { + "name": "brittney graham", + "label": "negative", + "script": "latin" + }, + { + "name": "john smith", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer bass", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Insert a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "insert_random_letter" + ], + "rule_descriptions": { + "insert_random_letter": "Insert a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "elizabeth ellis", + "label": "negative", + "script": "latin" + }, + { + "name": "deborah espinoza", + "label": "negative", + "script": "latin" + }, + { + "name": "craig james", + "label": "negative", + "script": "latin" + }, + { + "name": "keith maldonado", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel christian", + "label": "negative", + "script": "latin" + }, + { + "name": "paula taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "alexandra bowers", + "label": "negative", + "script": "latin" + }, + { + "name": "geraldine bennett", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffrey horton", + "label": "negative", + "script": "latin" + }, + { + "name": "gregory sims", + "label": "negative", + "script": "latin" + }, + { + "name": "lindsey cortez", + "label": "negative", + "script": "latin" + }, + { + "name": "ronald lamb", + "label": "negative", + "script": "latin" + }, + { + "name": "brandy mckinney", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa faulkner", + "label": "negative", + "script": "latin" + }, + { + "name": "marie moreno", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Abbreviate name parts, Use first name initial with last name, and Replace random vowels with different vowels.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_abbreviations", + "initial_only_first_name", + "replace_random_vowel_with_random_vowel" + ], + "rule_descriptions": { + "shorten_name_to_abbreviations": "Abbreviate name parts", + "initial_only_first_name": "Use first name initial with last name", + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "andrew wolfe", + "label": "negative", + "script": "latin" + }, + { + "name": "andrew mckee", + "label": "negative", + "script": "latin" + }, + { + "name": "yvonne reeves", + "label": "negative", + "script": "latin" + }, + { + "name": "sharon hancock", + "label": "negative", + "script": "latin" + }, + { + "name": "brittany cook", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa jones", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica lewis", + "label": "negative", + "script": "latin" + }, + { + "name": "stephen barker", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica hall", + "label": "negative", + "script": "latin" + }, + { + "name": "kaitlyn harvey", + "label": "negative", + "script": "latin" + }, + { + "name": "colton owens", + "label": "negative", + "script": "latin" + }, + { + "name": "katie hill", + "label": "negative", + "script": "latin" + }, + { + "name": "raymond ramirez", + "label": "negative", + "script": "latin" + }, + { + "name": "janet santiago", + "label": "negative", + "script": "latin" + }, + { + "name": "juan martin", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Delete a random letter, and Duplicate a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "delete_random_letter", + "duplicate_random_letter_as_double_letter" + ], + "rule_descriptions": { + "delete_random_letter": "Delete a random letter", + "duplicate_random_letter_as_double_letter": "Duplicate a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "david myers", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffrey thomas", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua elliott", + "label": "negative", + "script": "latin" + }, + { + "name": "beth proctor", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda mason", + "label": "negative", + "script": "latin" + }, + { + "name": "stacey dennis", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "angela roberts", + "label": "negative", + "script": "latin" + }, + { + "name": "mohammad roberts", + "label": "negative", + "script": "latin" + }, + { + "name": "nathan richardson", + "label": "negative", + "script": "latin" + }, + { + "name": "carole white", + "label": "negative", + "script": "latin" + }, + { + "name": "reece beard", + "label": "negative", + "script": "latin" + }, + { + "name": "jill sellers", + "label": "negative", + "script": "latin" + }, + { + "name": "robert spencer", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica jones", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace random consonants with different consonants, and Swap random adjacent letters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_consonant_with_random_consonant", + "swap_random_letter" + ], + "rule_descriptions": { + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants", + "swap_random_letter": "Swap random adjacent letters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "holly phillips", + "label": "negative", + "script": "latin" + }, + { + "name": "benjamin peterson", + "label": "negative", + "script": "latin" + }, + { + "name": "karen wang", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffrey short", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica ball", + "label": "negative", + "script": "latin" + }, + { + "name": "stephen swanson", + "label": "negative", + "script": "latin" + }, + { + "name": "linda barnes", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas white", + "label": "negative", + "script": "latin" + }, + { + "name": "william petersen", + "label": "negative", + "script": "latin" + }, + { + "name": "joan lawrence", + "label": "negative", + "script": "latin" + }, + { + "name": "cynthia randall", + "label": "negative", + "script": "latin" + }, + { + "name": "james perkins", + "label": "negative", + "script": "latin" + }, + { + "name": "lawrence baxter", + "label": "negative", + "script": "latin" + }, + { + "name": "norma jones", + "label": "negative", + "script": "latin" + }, + { + "name": "lindsay miller", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace random vowels with different vowels, Duplicate a random letter, and Reorder name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_vowel_with_random_vowel", + "duplicate_random_letter_as_double_letter", + "name_parts_permutations" + ], + "rule_descriptions": { + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels", + "duplicate_random_letter_as_double_letter": "Duplicate a random letter", + "name_parts_permutations": "Reorder name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "keith barnett", + "label": "negative", + "script": "latin" + }, + { + "name": "christine rush", + "label": "negative", + "script": "latin" + }, + { + "name": "gloria pace", + "label": "negative", + "script": "latin" + }, + { + "name": "alicia ellis", + "label": "negative", + "script": "latin" + }, + { + "name": "tyler bell", + "label": "negative", + "script": "latin" + }, + { + "name": "patricia doyle", + "label": "negative", + "script": "latin" + }, + { + "name": "edward patterson", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley hill", + "label": "negative", + "script": "latin" + }, + { + "name": "krista smith", + "label": "negative", + "script": "latin" + }, + { + "name": "yvonne mccarty", + "label": "negative", + "script": "latin" + }, + { + "name": "maria franklin", + "label": "negative", + "script": "latin" + }, + { + "name": "melinda swift", + "label": "negative", + "script": "latin" + }, + { + "name": "josephine mcbride", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer porter", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel herrera", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title prefix (Mr., Dr., etc.), Use first name initial with last name, and Replace random vowels with different vowels.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_leading_title", + "initial_only_first_name", + "replace_random_vowel_with_random_vowel" + ], + "rule_descriptions": { + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)", + "initial_only_first_name": "Use first name initial with last name", + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "james hall", + "label": "negative", + "script": "latin" + }, + { + "name": "kieran joyce", + "label": "negative", + "script": "latin" + }, + { + "name": "ricky powell", + "label": "negative", + "script": "latin" + }, + { + "name": "mark gomez", + "label": "negative", + "script": "latin" + }, + { + "name": "erika chapman", + "label": "negative", + "script": "latin" + }, + { + "name": "neil wright", + "label": "negative", + "script": "latin" + }, + { + "name": "anna bennett", + "label": "negative", + "script": "latin" + }, + { + "name": "lorraine lamb", + "label": "negative", + "script": "latin" + }, + { + "name": "andre watson", + "label": "negative", + "script": "latin" + }, + { + "name": "tammy benson", + "label": "negative", + "script": "latin" + }, + { + "name": "june williams", + "label": "negative", + "script": "latin" + }, + { + "name": "douglas taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "robert martinez", + "label": "negative", + "script": "latin" + }, + { + "name": "steven green", + "label": "negative", + "script": "latin" + }, + { + "name": "shaun clayton", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace spaces with special characters, and Replace random consonants with different consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_spaces_with_random_special_characters", + "replace_random_consonant_with_random_consonant" + ], + "rule_descriptions": { + "replace_spaces_with_random_special_characters": "Replace spaces with special characters", + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "amanda schwartz", + "label": "negative", + "script": "latin" + }, + { + "name": "tyler keller", + "label": "negative", + "script": "latin" + }, + { + "name": "nicholas kemp", + "label": "negative", + "script": "latin" + }, + { + "name": "barbara coleman", + "label": "negative", + "script": "latin" + }, + { + "name": "brittany freeman", + "label": "negative", + "script": "latin" + }, + { + "name": "elizabeth miller", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin burke", + "label": "negative", + "script": "latin" + }, + { + "name": "lori wise", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher salazar", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph williams", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah lambert", + "label": "negative", + "script": "latin" + }, + { + "name": "amy wright", + "label": "negative", + "script": "latin" + }, + { + "name": "katherine mcintyre", + "label": "negative", + "script": "latin" + }, + { + "name": "katherine nguyen", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua burns", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Add a title suffix (Jr., PhD, etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_trailing_title" + ], + "rule_descriptions": { + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "kendra hyde", + "label": "negative", + "script": "latin" + }, + { + "name": "jeanne west", + "label": "negative", + "script": "latin" + }, + { + "name": "jerry brown", + "label": "negative", + "script": "latin" + }, + { + "name": "angela mcdonald", + "label": "negative", + "script": "latin" + }, + { + "name": "richard greene", + "label": "negative", + "script": "latin" + }, + { + "name": "karen armstrong", + "label": "negative", + "script": "latin" + }, + { + "name": "eileen wallace", + "label": "negative", + "script": "latin" + }, + { + "name": "todd sharp", + "label": "negative", + "script": "latin" + }, + { + "name": "joyce price", + "label": "negative", + "script": "latin" + }, + { + "name": "john fleming", + "label": "negative", + "script": "latin" + }, + { + "name": "stuart tomlinson", + "label": "negative", + "script": "latin" + }, + { + "name": "tracey silva", + "label": "negative", + "script": "latin" + }, + { + "name": "hannah johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "marc north", + "label": "negative", + "script": "latin" + }, + { + "name": "jesse ramos", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Replace random consonants with different consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_consonant_with_random_consonant" + ], + "rule_descriptions": { + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "barry davis", + "label": "negative", + "script": "latin" + }, + { + "name": "brooke perry", + "label": "negative", + "script": "latin" + }, + { + "name": "sophie kennedy", + "label": "negative", + "script": "latin" + }, + { + "name": "hector harrison", + "label": "negative", + "script": "latin" + }, + { + "name": "roger adkins", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew wade", + "label": "negative", + "script": "latin" + }, + { + "name": "kenneth roberts", + "label": "negative", + "script": "latin" + }, + { + "name": "robert harrison", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew baker", + "label": "negative", + "script": "latin" + }, + { + "name": "patrick bryant", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy sharp", + "label": "negative", + "script": "latin" + }, + { + "name": "sean vang", + "label": "negative", + "script": "latin" + }, + { + "name": "cameron clark", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph downs", + "label": "negative", + "script": "latin" + }, + { + "name": "jasmine bennett", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove a random vowel, Replace spaces with special characters, and Remove all spaces.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_vowel", + "replace_spaces_with_random_special_characters", + "remove_all_spaces" + ], + "rule_descriptions": { + "remove_random_vowel": "Remove a random vowel", + "replace_spaces_with_random_special_characters": "Replace spaces with special characters", + "remove_all_spaces": "Remove all spaces" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "matthew adams", + "label": "negative", + "script": "latin" + }, + { + "name": "judith edwards", + "label": "negative", + "script": "latin" + }, + { + "name": "henry parkes", + "label": "negative", + "script": "latin" + }, + { + "name": "suzanne joyce", + "label": "negative", + "script": "latin" + }, + { + "name": "karl jones", + "label": "negative", + "script": "latin" + }, + { + "name": "sian jones", + "label": "negative", + "script": "latin" + }, + { + "name": "brandon lewis", + "label": "negative", + "script": "latin" + }, + { + "name": "patrick reynolds", + "label": "negative", + "script": "latin" + }, + { + "name": "kim flores", + "label": "negative", + "script": "latin" + }, + { + "name": "deborah barrett", + "label": "negative", + "script": "latin" + }, + { + "name": "jane west", + "label": "negative", + "script": "latin" + }, + { + "name": "theodore woodward", + "label": "negative", + "script": "latin" + }, + { + "name": "cassandra wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "jonathan wang", + "label": "negative", + "script": "latin" + }, + { + "name": "wesley davies", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Swap adjacent consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_consonants" + ], + "rule_descriptions": { + "swap_adjacent_consonants": "Swap adjacent consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "patricia rowley", + "label": "negative", + "script": "latin" + }, + { + "name": "gabriel myers", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica martin", + "label": "negative", + "script": "latin" + }, + { + "name": "aimee duke", + "label": "negative", + "script": "latin" + }, + { + "name": "sian griffiths", + "label": "negative", + "script": "latin" + }, + { + "name": "brian pace", + "label": "negative", + "script": "latin" + }, + { + "name": "jonathan ramirez", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle greene", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher jones", + "label": "negative", + "script": "latin" + }, + { + "name": "jesse fry", + "label": "negative", + "script": "latin" + }, + { + "name": "geoffrey bailey", + "label": "negative", + "script": "latin" + }, + { + "name": "brian zamora", + "label": "negative", + "script": "latin" + }, + { + "name": "robert ortiz", + "label": "negative", + "script": "latin" + }, + { + "name": "malcolm george", + "label": "negative", + "script": "latin" + }, + { + "name": "jasmin williams", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Abbreviate name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_abbreviations" + ], + "rule_descriptions": { + "shorten_name_to_abbreviations": "Abbreviate name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "lindsey clark", + "label": "negative", + "script": "latin" + }, + { + "name": "michael o'brien", + "label": "negative", + "script": "latin" + }, + { + "name": "marie shaw", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica valentine", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin ward", + "label": "negative", + "script": "latin" + }, + { + "name": "debbie lee", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa warren", + "label": "negative", + "script": "latin" + }, + { + "name": "caroline jones", + "label": "negative", + "script": "latin" + }, + { + "name": "johnny liu", + "label": "negative", + "script": "latin" + }, + { + "name": "marian long", + "label": "negative", + "script": "latin" + }, + { + "name": "robert sims", + "label": "negative", + "script": "latin" + }, + { + "name": "stephen may", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony williams", + "label": "negative", + "script": "latin" + }, + { + "name": "jonathan johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "gabriela cummings", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace random consonants with different consonants, Use first name initial with last name, and Reorder name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_consonant_with_random_consonant", + "initial_only_first_name", + "name_parts_permutations" + ], + "rule_descriptions": { + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants", + "initial_only_first_name": "Use first name initial with last name", + "name_parts_permutations": "Reorder name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "justin hensley", + "label": "negative", + "script": "latin" + }, + { + "name": "ross gibson", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley davis", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel cunningham", + "label": "negative", + "script": "latin" + }, + { + "name": "shelia scott", + "label": "negative", + "script": "latin" + }, + { + "name": "karen glover", + "label": "negative", + "script": "latin" + }, + { + "name": "dana ramsey", + "label": "negative", + "script": "latin" + }, + { + "name": "monica keller", + "label": "negative", + "script": "latin" + }, + { + "name": "dana elliott", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley mitchell", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley walsh", + "label": "negative", + "script": "latin" + }, + { + "name": "emma duncan", + "label": "negative", + "script": "latin" + }, + { + "name": "brandon coles", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer shaw", + "label": "negative", + "script": "latin" + }, + { + "name": "steven williams", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Add a title suffix (Jr., PhD, etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_trailing_title" + ], + "rule_descriptions": { + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "erika banks", + "label": "negative", + "script": "latin" + }, + { + "name": "jeremy o'connor", + "label": "negative", + "script": "latin" + }, + { + "name": "louis wyatt", + "label": "negative", + "script": "latin" + }, + { + "name": "tyler taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "brandon chang", + "label": "negative", + "script": "latin" + }, + { + "name": "jane berger", + "label": "negative", + "script": "latin" + }, + { + "name": "danielle hanson", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer mendez", + "label": "negative", + "script": "latin" + }, + { + "name": "dean ellis", + "label": "negative", + "script": "latin" + }, + { + "name": "crystal higgins", + "label": "negative", + "script": "latin" + }, + { + "name": "johnny austin", + "label": "negative", + "script": "latin" + }, + { + "name": "adam jones", + "label": "negative", + "script": "latin" + }, + { + "name": "jason odonnell", + "label": "negative", + "script": "latin" + }, + { + "name": "elizabeth baker", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa johnson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Reorder name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "name_parts_permutations" + ], + "rule_descriptions": { + "name_parts_permutations": "Reorder name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "joseph harvey", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher lee", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin williams", + "label": "negative", + "script": "latin" + }, + { + "name": "frederick fox", + "label": "negative", + "script": "latin" + }, + { + "name": "kerry miller", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah bauer", + "label": "negative", + "script": "latin" + }, + { + "name": "norman price", + "label": "negative", + "script": "latin" + }, + { + "name": "adrian pena", + "label": "negative", + "script": "latin" + }, + { + "name": "trevor wallace", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa barry", + "label": "negative", + "script": "latin" + }, + { + "name": "leah hernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "georgia hernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "jordan hendricks", + "label": "negative", + "script": "latin" + }, + { + "name": "chase morris", + "label": "negative", + "script": "latin" + }, + { + "name": "diane riggs", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove a random vowel, Swap adjacent consonants, and Replace double letters with a single letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_vowel", + "swap_adjacent_consonants", + "replace_double_letters_with_single_letter" + ], + "rule_descriptions": { + "remove_random_vowel": "Remove a random vowel", + "swap_adjacent_consonants": "Swap adjacent consonants", + "replace_double_letters_with_single_letter": "Replace double letters with a single letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "jessica chan", + "label": "negative", + "script": "latin" + }, + { + "name": "denise brown", + "label": "negative", + "script": "latin" + }, + { + "name": "maurice gilbert", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher gordon", + "label": "negative", + "script": "latin" + }, + { + "name": "jose walters", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole williams", + "label": "negative", + "script": "latin" + }, + { + "name": "benjamin baker", + "label": "negative", + "script": "latin" + }, + { + "name": "katherine nixon", + "label": "negative", + "script": "latin" + }, + { + "name": "julie cartwright", + "label": "negative", + "script": "latin" + }, + { + "name": "paul colon", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffrey o'connor", + "label": "negative", + "script": "latin" + }, + { + "name": "jordan wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer bradford", + "label": "negative", + "script": "latin" + }, + { + "name": "holly jones", + "label": "negative", + "script": "latin" + }, + { + "name": "tyler nguyen", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace double letters with a single letter, and Abbreviate name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_double_letters_with_single_letter", + "shorten_name_to_abbreviations" + ], + "rule_descriptions": { + "replace_double_letters_with_single_letter": "Replace double letters with a single letter", + "shorten_name_to_abbreviations": "Abbreviate name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "matthew hernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "brian suarez", + "label": "negative", + "script": "latin" + }, + { + "name": "julia douglas", + "label": "negative", + "script": "latin" + }, + { + "name": "john thomas", + "label": "negative", + "script": "latin" + }, + { + "name": "michaela herrera", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel turner", + "label": "negative", + "script": "latin" + }, + { + "name": "heather davis", + "label": "negative", + "script": "latin" + }, + { + "name": "nathan moon", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony lyons", + "label": "negative", + "script": "latin" + }, + { + "name": "hugh rivera", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer larson", + "label": "negative", + "script": "latin" + }, + { + "name": "dominic bond", + "label": "negative", + "script": "latin" + }, + { + "name": "lauren brooks", + "label": "negative", + "script": "latin" + }, + { + "name": "elizabeth sanchez", + "label": "negative", + "script": "latin" + }, + { + "name": "luke mason", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Replace double letters with a single letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_double_letters_with_single_letter" + ], + "rule_descriptions": { + "replace_double_letters_with_single_letter": "Replace double letters with a single letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "thomas reynolds", + "label": "negative", + "script": "latin" + }, + { + "name": "amy knox", + "label": "negative", + "script": "latin" + }, + { + "name": "jenny garcia", + "label": "negative", + "script": "latin" + }, + { + "name": "heather sanchez", + "label": "negative", + "script": "latin" + }, + { + "name": "tiffany lees", + "label": "negative", + "script": "latin" + }, + { + "name": "juan jones", + "label": "negative", + "script": "latin" + }, + { + "name": "elizabeth villanueva", + "label": "negative", + "script": "latin" + }, + { + "name": "jacob hester", + "label": "negative", + "script": "latin" + }, + { + "name": "bradley white", + "label": "negative", + "script": "latin" + }, + { + "name": "alan mason", + "label": "negative", + "script": "latin" + }, + { + "name": "christine davies", + "label": "negative", + "script": "latin" + }, + { + "name": "iain pratt", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica craig", + "label": "negative", + "script": "latin" + }, + { + "name": "rachel bell", + "label": "negative", + "script": "latin" + }, + { + "name": "jason graves", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Abbreviate name parts, and Delete a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_abbreviations", + "delete_random_letter" + ], + "rule_descriptions": { + "shorten_name_to_abbreviations": "Abbreviate name parts", + "delete_random_letter": "Delete a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "neil moore", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher marsh", + "label": "negative", + "script": "latin" + }, + { + "name": "randy burke", + "label": "negative", + "script": "latin" + }, + { + "name": "mandy villa", + "label": "negative", + "script": "latin" + }, + { + "name": "duncan romero", + "label": "negative", + "script": "latin" + }, + { + "name": "david davies", + "label": "negative", + "script": "latin" + }, + { + "name": "kyle morrison", + "label": "negative", + "script": "latin" + }, + { + "name": "anna fleming", + "label": "negative", + "script": "latin" + }, + { + "name": "shane hill", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin porter", + "label": "negative", + "script": "latin" + }, + { + "name": "molly romero", + "label": "negative", + "script": "latin" + }, + { + "name": "jacqueline osborn", + "label": "negative", + "script": "latin" + }, + { + "name": "diane rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "richard stone", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole johnson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Reorder name parts, and Remove all spaces.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "name_parts_permutations", + "remove_all_spaces" + ], + "rule_descriptions": { + "name_parts_permutations": "Reorder name parts", + "remove_all_spaces": "Remove all spaces" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "callum villarreal", + "label": "negative", + "script": "latin" + }, + { + "name": "jonathan williams", + "label": "negative", + "script": "latin" + }, + { + "name": "frank jordan", + "label": "negative", + "script": "latin" + }, + { + "name": "christine banks", + "label": "negative", + "script": "latin" + }, + { + "name": "becky connor", + "label": "negative", + "script": "latin" + }, + { + "name": "cynthia rogers", + "label": "negative", + "script": "latin" + }, + { + "name": "darren harris", + "label": "negative", + "script": "latin" + }, + { + "name": "phyllis cole", + "label": "negative", + "script": "latin" + }, + { + "name": "zoe kelley", + "label": "negative", + "script": "latin" + }, + { + "name": "tina taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "kyle quinn", + "label": "negative", + "script": "latin" + }, + { + "name": "heidi white", + "label": "negative", + "script": "latin" + }, + { + "name": "steven adams", + "label": "negative", + "script": "latin" + }, + { + "name": "christina thompson", + "label": "negative", + "script": "latin" + }, + { + "name": "george pierce", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap random adjacent letters, and Remove all spaces.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_random_letter", + "remove_all_spaces" + ], + "rule_descriptions": { + "swap_random_letter": "Swap random adjacent letters", + "remove_all_spaces": "Remove all spaces" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "jason perry", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica martinez", + "label": "negative", + "script": "latin" + }, + { + "name": "jesse ortiz", + "label": "negative", + "script": "latin" + }, + { + "name": "megan huffman", + "label": "negative", + "script": "latin" + }, + { + "name": "lee robson", + "label": "negative", + "script": "latin" + }, + { + "name": "patricia orr", + "label": "negative", + "script": "latin" + }, + { + "name": "katie duarte", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffrey murray", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony gibson", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa gill", + "label": "negative", + "script": "latin" + }, + { + "name": "steven andrews", + "label": "negative", + "script": "latin" + }, + { + "name": "renee williamson", + "label": "negative", + "script": "latin" + }, + { + "name": "todd roman", + "label": "negative", + "script": "latin" + }, + { + "name": "ruth hughes", + "label": "negative", + "script": "latin" + }, + { + "name": "kenneth rees", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Insert a random letter, and Swap adjacent consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "insert_random_letter", + "swap_adjacent_consonants" + ], + "rule_descriptions": { + "insert_random_letter": "Insert a random letter", + "swap_adjacent_consonants": "Swap adjacent consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "laura warren", + "label": "negative", + "script": "latin" + }, + { + "name": "frank gonzalez", + "label": "negative", + "script": "latin" + }, + { + "name": "tracy murphy", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah jones", + "label": "negative", + "script": "latin" + }, + { + "name": "donna welch", + "label": "negative", + "script": "latin" + }, + { + "name": "zachary brady", + "label": "negative", + "script": "latin" + }, + { + "name": "katherine abbott", + "label": "negative", + "script": "latin" + }, + { + "name": "brian forster", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony fox", + "label": "negative", + "script": "latin" + }, + { + "name": "martyn allen", + "label": "negative", + "script": "latin" + }, + { + "name": "mary ramirez", + "label": "negative", + "script": "latin" + }, + { + "name": "mandy long", + "label": "negative", + "script": "latin" + }, + { + "name": "ethan bird", + "label": "negative", + "script": "latin" + }, + { + "name": "andrew brown", + "label": "negative", + "script": "latin" + }, + { + "name": "christina espinoza", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Insert a random letter, Use first name initial with last name, and Replace random vowels with different vowels.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "insert_random_letter", + "initial_only_first_name", + "replace_random_vowel_with_random_vowel" + ], + "rule_descriptions": { + "insert_random_letter": "Insert a random letter", + "initial_only_first_name": "Use first name initial with last name", + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "kimberly murphy", + "label": "negative", + "script": "latin" + }, + { + "name": "priscilla price", + "label": "negative", + "script": "latin" + }, + { + "name": "barry montes", + "label": "negative", + "script": "latin" + }, + { + "name": "anita strong", + "label": "negative", + "script": "latin" + }, + { + "name": "ross russell", + "label": "negative", + "script": "latin" + }, + { + "name": "james good", + "label": "negative", + "script": "latin" + }, + { + "name": "sandra kerr", + "label": "negative", + "script": "latin" + }, + { + "name": "amber young", + "label": "negative", + "script": "latin" + }, + { + "name": "david wilkerson", + "label": "negative", + "script": "latin" + }, + { + "name": "shane coleman", + "label": "negative", + "script": "latin" + }, + { + "name": "ronald williams", + "label": "negative", + "script": "latin" + }, + { + "name": "april burke", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah gallegos", + "label": "negative", + "script": "latin" + }, + { + "name": "henry porter", + "label": "negative", + "script": "latin" + }, + { + "name": "tyler flores", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace spaces with special characters, and Use first name initial with last name.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_spaces_with_random_special_characters", + "initial_only_first_name" + ], + "rule_descriptions": { + "replace_spaces_with_random_special_characters": "Replace spaces with special characters", + "initial_only_first_name": "Use first name initial with last name" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "nicholas carroll", + "label": "negative", + "script": "latin" + }, + { + "name": "gabriel gordon", + "label": "negative", + "script": "latin" + }, + { + "name": "karen hussain", + "label": "negative", + "script": "latin" + }, + { + "name": "charles gutierrez", + "label": "negative", + "script": "latin" + }, + { + "name": "scott steele", + "label": "negative", + "script": "latin" + }, + { + "name": "mohammad curtis", + "label": "negative", + "script": "latin" + }, + { + "name": "sandra slater", + "label": "negative", + "script": "latin" + }, + { + "name": "kara roberts", + "label": "negative", + "script": "latin" + }, + { + "name": "james ortega", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa walker", + "label": "negative", + "script": "latin" + }, + { + "name": "victoria ortiz", + "label": "negative", + "script": "latin" + }, + { + "name": "leanne ware", + "label": "negative", + "script": "latin" + }, + { + "name": "susan thomas", + "label": "negative", + "script": "latin" + }, + { + "name": "carrie brookes", + "label": "negative", + "script": "latin" + }, + { + "name": "heather bryant", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace spaces with special characters, and Remove a random vowel.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_spaces_with_random_special_characters", + "remove_random_vowel" + ], + "rule_descriptions": { + "replace_spaces_with_random_special_characters": "Replace spaces with special characters", + "remove_random_vowel": "Remove a random vowel" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "sandra levine", + "label": "negative", + "script": "latin" + }, + { + "name": "tina benson", + "label": "negative", + "script": "latin" + }, + { + "name": "brandon torres", + "label": "negative", + "script": "latin" + }, + { + "name": "dale chambers", + "label": "negative", + "script": "latin" + }, + { + "name": "krista jackson", + "label": "negative", + "script": "latin" + }, + { + "name": "keith willis", + "label": "negative", + "script": "latin" + }, + { + "name": "richard white", + "label": "negative", + "script": "latin" + }, + { + "name": "kimberly allen", + "label": "negative", + "script": "latin" + }, + { + "name": "kenneth craig", + "label": "negative", + "script": "latin" + }, + { + "name": "jason newton", + "label": "negative", + "script": "latin" + }, + { + "name": "shannon long", + "label": "negative", + "script": "latin" + }, + { + "name": "deborah allen", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin hughes", + "label": "negative", + "script": "latin" + }, + { + "name": "april singh", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie cameron", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Reorder name parts, and Convert name to initials.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "name_parts_permutations", + "shorten_name_to_initials" + ], + "rule_descriptions": { + "name_parts_permutations": "Reorder name parts", + "shorten_name_to_initials": "Convert name to initials" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "donna harper", + "label": "negative", + "script": "latin" + }, + { + "name": "krystal cook", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole coleman", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle simpson", + "label": "negative", + "script": "latin" + }, + { + "name": "david stewart", + "label": "negative", + "script": "latin" + }, + { + "name": "henry jones", + "label": "negative", + "script": "latin" + }, + { + "name": "bridget wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "caitlin obrien", + "label": "negative", + "script": "latin" + }, + { + "name": "sandra ortiz", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer stevens", + "label": "negative", + "script": "latin" + }, + { + "name": "tracey cantrell", + "label": "negative", + "script": "latin" + }, + { + "name": "jimmy hill", + "label": "negative", + "script": "latin" + }, + { + "name": "russell griffiths", + "label": "negative", + "script": "latin" + }, + { + "name": "amy kaiser", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole rowe", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Remove a random vowel.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_vowel" + ], + "rule_descriptions": { + "remove_random_vowel": "Remove a random vowel" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "joseph young", + "label": "negative", + "script": "latin" + }, + { + "name": "marilyn rhodes", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda stone", + "label": "negative", + "script": "latin" + }, + { + "name": "katelyn baker", + "label": "negative", + "script": "latin" + }, + { + "name": "aaron gonzalez", + "label": "negative", + "script": "latin" + }, + { + "name": "antonio rivera", + "label": "negative", + "script": "latin" + }, + { + "name": "michael simon", + "label": "negative", + "script": "latin" + }, + { + "name": "paula todd", + "label": "negative", + "script": "latin" + }, + { + "name": "megan davis", + "label": "negative", + "script": "latin" + }, + { + "name": "jayne cooke", + "label": "negative", + "script": "latin" + }, + { + "name": "brandi bradley", + "label": "negative", + "script": "latin" + }, + { + "name": "marcia ramos", + "label": "negative", + "script": "latin" + }, + { + "name": "jose galloway", + "label": "negative", + "script": "latin" + }, + { + "name": "marcus jenkins", + "label": "negative", + "script": "latin" + }, + { + "name": "diane terry", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Add a title suffix (Jr., PhD, etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_trailing_title" + ], + "rule_descriptions": { + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "ryan santiago", + "label": "negative", + "script": "latin" + }, + { + "name": "ellie wagner", + "label": "negative", + "script": "latin" + }, + { + "name": "wayne myers", + "label": "negative", + "script": "latin" + }, + { + "name": "denise bartlett", + "label": "negative", + "script": "latin" + }, + { + "name": "danielle grimes", + "label": "negative", + "script": "latin" + }, + { + "name": "beth henry", + "label": "negative", + "script": "latin" + }, + { + "name": "erica day", + "label": "negative", + "script": "latin" + }, + { + "name": "nicholas hanna", + "label": "negative", + "script": "latin" + }, + { + "name": "tricia cooper", + "label": "negative", + "script": "latin" + }, + { + "name": "chelsea andrews", + "label": "negative", + "script": "latin" + }, + { + "name": "tony haynes", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "sandra huffman", + "label": "negative", + "script": "latin" + }, + { + "name": "james hicks", + "label": "negative", + "script": "latin" + }, + { + "name": "katie weston", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap adjacent syllables, and Replace spaces with special characters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_syllables", + "replace_spaces_with_random_special_characters" + ], + "rule_descriptions": { + "swap_adjacent_syllables": "Swap adjacent syllables", + "replace_spaces_with_random_special_characters": "Replace spaces with special characters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "mark west", + "label": "negative", + "script": "latin" + }, + { + "name": "colin sims", + "label": "negative", + "script": "latin" + }, + { + "name": "hector lucas", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua stewart", + "label": "negative", + "script": "latin" + }, + { + "name": "marilyn middleton", + "label": "negative", + "script": "latin" + }, + { + "name": "melanie lee", + "label": "negative", + "script": "latin" + }, + { + "name": "kimberley gallegos", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher foster", + "label": "negative", + "script": "latin" + }, + { + "name": "ryan brock", + "label": "negative", + "script": "latin" + }, + { + "name": "tanya mcintyre", + "label": "negative", + "script": "latin" + }, + { + "name": "shannon garrison", + "label": "negative", + "script": "latin" + }, + { + "name": "kate matthews", + "label": "negative", + "script": "latin" + }, + { + "name": "paul richardson", + "label": "negative", + "script": "latin" + }, + { + "name": "diana flores", + "label": "negative", + "script": "latin" + }, + { + "name": "beverley fowler", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove a random consonant, Replace double letters with a single letter, and Add a title suffix (Jr., PhD, etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_consonant", + "replace_double_letters_with_single_letter", + "add_random_trailing_title" + ], + "rule_descriptions": { + "remove_random_consonant": "Remove a random consonant", + "replace_double_letters_with_single_letter": "Replace double letters with a single letter", + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "kevin jones", + "label": "negative", + "script": "latin" + }, + { + "name": "gerald daniel", + "label": "negative", + "script": "latin" + }, + { + "name": "todd hunt", + "label": "negative", + "script": "latin" + }, + { + "name": "sara meyer", + "label": "negative", + "script": "latin" + }, + { + "name": "vincent rogers", + "label": "negative", + "script": "latin" + }, + { + "name": "molly davis", + "label": "negative", + "script": "latin" + }, + { + "name": "peter gregory", + "label": "negative", + "script": "latin" + }, + { + "name": "chad simpson", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas lawson", + "label": "negative", + "script": "latin" + }, + { + "name": "raymond patel", + "label": "negative", + "script": "latin" + }, + { + "name": "jake nicholson", + "label": "negative", + "script": "latin" + }, + { + "name": "natasha harris", + "label": "negative", + "script": "latin" + }, + { + "name": "conor johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "eric mcclain", + "label": "negative", + "script": "latin" + }, + { + "name": "teresa rasmussen", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace random consonants with different consonants, Swap adjacent syllables, and Replace double letters with a single letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_consonant_with_random_consonant", + "swap_adjacent_syllables", + "replace_double_letters_with_single_letter" + ], + "rule_descriptions": { + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants", + "swap_adjacent_syllables": "Swap adjacent syllables", + "replace_double_letters_with_single_letter": "Replace double letters with a single letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "stacey wang", + "label": "negative", + "script": "latin" + }, + { + "name": "kimberly brown", + "label": "negative", + "script": "latin" + }, + { + "name": "brad evans", + "label": "negative", + "script": "latin" + }, + { + "name": "anna brown", + "label": "negative", + "script": "latin" + }, + { + "name": "richard williams", + "label": "negative", + "script": "latin" + }, + { + "name": "katherine williams", + "label": "negative", + "script": "latin" + }, + { + "name": "aimee best", + "label": "negative", + "script": "latin" + }, + { + "name": "david macdonald", + "label": "negative", + "script": "latin" + }, + { + "name": "clifford robinson", + "label": "negative", + "script": "latin" + }, + { + "name": "walter clayton", + "label": "negative", + "script": "latin" + }, + { + "name": "stacey brady", + "label": "negative", + "script": "latin" + }, + { + "name": "michael gardner", + "label": "negative", + "script": "latin" + }, + { + "name": "marissa reynolds", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas doyle", + "label": "negative", + "script": "latin" + }, + { + "name": "juan jackson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove all spaces, Duplicate a random letter, and Replace random vowels with different vowels.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_all_spaces", + "duplicate_random_letter_as_double_letter", + "replace_random_vowel_with_random_vowel" + ], + "rule_descriptions": { + "remove_all_spaces": "Remove all spaces", + "duplicate_random_letter_as_double_letter": "Duplicate a random letter", + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "teresa alvarez", + "label": "negative", + "script": "latin" + }, + { + "name": "peter wyatt", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley bowen", + "label": "negative", + "script": "latin" + }, + { + "name": "robert sanchez", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua wood", + "label": "negative", + "script": "latin" + }, + { + "name": "jerome lee", + "label": "negative", + "script": "latin" + }, + { + "name": "francesca gomez", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley powell", + "label": "negative", + "script": "latin" + }, + { + "name": "bethany brady", + "label": "negative", + "script": "latin" + }, + { + "name": "adam phillips", + "label": "negative", + "script": "latin" + }, + { + "name": "robin brown", + "label": "negative", + "script": "latin" + }, + { + "name": "carolyn gonzales", + "label": "negative", + "script": "latin" + }, + { + "name": "lori richards", + "label": "negative", + "script": "latin" + }, + { + "name": "stacey bates", + "label": "negative", + "script": "latin" + }, + { + "name": "james cross", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap random adjacent letters, Add a title prefix (Mr., Dr., etc.), and Swap adjacent consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_random_letter", + "add_random_leading_title", + "swap_adjacent_consonants" + ], + "rule_descriptions": { + "swap_random_letter": "Swap random adjacent letters", + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)", + "swap_adjacent_consonants": "Swap adjacent consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "kimberly hanson", + "label": "negative", + "script": "latin" + }, + { + "name": "john richards", + "label": "negative", + "script": "latin" + }, + { + "name": "steven gonzalez", + "label": "negative", + "script": "latin" + }, + { + "name": "natalie pena", + "label": "negative", + "script": "latin" + }, + { + "name": "tina oliver", + "label": "negative", + "script": "latin" + }, + { + "name": "holly clark", + "label": "negative", + "script": "latin" + }, + { + "name": "colin rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua watkins", + "label": "negative", + "script": "latin" + }, + { + "name": "robert hayes", + "label": "negative", + "script": "latin" + }, + { + "name": "charles dale", + "label": "negative", + "script": "latin" + }, + { + "name": "kieran todd", + "label": "negative", + "script": "latin" + }, + { + "name": "bryan davenport", + "label": "negative", + "script": "latin" + }, + { + "name": "cheryl barrett", + "label": "negative", + "script": "latin" + }, + { + "name": "pauline winters", + "label": "negative", + "script": "latin" + }, + { + "name": "shaun webb", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title suffix (Jr., PhD, etc.), and Replace spaces with special characters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_trailing_title", + "replace_spaces_with_random_special_characters" + ], + "rule_descriptions": { + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)", + "replace_spaces_with_random_special_characters": "Replace spaces with special characters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "brittany jones", + "label": "negative", + "script": "latin" + }, + { + "name": "jorge chambers", + "label": "negative", + "script": "latin" + }, + { + "name": "benjamin ford", + "label": "negative", + "script": "latin" + }, + { + "name": "dorothy phillips", + "label": "negative", + "script": "latin" + }, + { + "name": "julie phillips", + "label": "negative", + "script": "latin" + }, + { + "name": "jason powell", + "label": "negative", + "script": "latin" + }, + { + "name": "gareth miller", + "label": "negative", + "script": "latin" + }, + { + "name": "alicia harris", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda thomas", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph thompson", + "label": "negative", + "script": "latin" + }, + { + "name": "jacqueline francis", + "label": "negative", + "script": "latin" + }, + { + "name": "kenneth wood", + "label": "negative", + "script": "latin" + }, + { + "name": "amy green", + "label": "negative", + "script": "latin" + }, + { + "name": "amy cooper", + "label": "negative", + "script": "latin" + }, + { + "name": "charles vasquez", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Remove all spaces.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_all_spaces" + ], + "rule_descriptions": { + "remove_all_spaces": "Remove all spaces" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "susan valencia", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica parsons", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph kemp", + "label": "negative", + "script": "latin" + }, + { + "name": "jean singh", + "label": "negative", + "script": "latin" + }, + { + "name": "jamie johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "denise rubio", + "label": "negative", + "script": "latin" + }, + { + "name": "danielle gibson", + "label": "negative", + "script": "latin" + }, + { + "name": "melody estes", + "label": "negative", + "script": "latin" + }, + { + "name": "cody gentry", + "label": "negative", + "script": "latin" + }, + { + "name": "margaret baldwin", + "label": "negative", + "script": "latin" + }, + { + "name": "darren lawson", + "label": "negative", + "script": "latin" + }, + { + "name": "michael pugh", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie davis", + "label": "negative", + "script": "latin" + }, + { + "name": "erin jones", + "label": "negative", + "script": "latin" + }, + { + "name": "julia wiggins", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title suffix (Jr., PhD, etc.), Convert name to initials, and Reorder name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_trailing_title", + "shorten_name_to_initials", + "name_parts_permutations" + ], + "rule_descriptions": { + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)", + "shorten_name_to_initials": "Convert name to initials", + "name_parts_permutations": "Reorder name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "john gonzalez", + "label": "negative", + "script": "latin" + }, + { + "name": "david taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "antony conrad", + "label": "negative", + "script": "latin" + }, + { + "name": "nicholas webb", + "label": "negative", + "script": "latin" + }, + { + "name": "justin stanley", + "label": "negative", + "script": "latin" + }, + { + "name": "laura thomas", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas nguyen", + "label": "negative", + "script": "latin" + }, + { + "name": "jean kent", + "label": "negative", + "script": "latin" + }, + { + "name": "stacey preston", + "label": "negative", + "script": "latin" + }, + { + "name": "caroline zamora", + "label": "negative", + "script": "latin" + }, + { + "name": "shelly young", + "label": "negative", + "script": "latin" + }, + { + "name": "molly little", + "label": "negative", + "script": "latin" + }, + { + "name": "barbara diaz", + "label": "negative", + "script": "latin" + }, + { + "name": "donna perez", + "label": "negative", + "script": "latin" + }, + { + "name": "martin allen", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace double letters with a single letter, and Swap adjacent syllables.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_double_letters_with_single_letter", + "swap_adjacent_syllables" + ], + "rule_descriptions": { + "replace_double_letters_with_single_letter": "Replace double letters with a single letter", + "swap_adjacent_syllables": "Swap adjacent syllables" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "daniel briggs", + "label": "negative", + "script": "latin" + }, + { + "name": "brendan clark", + "label": "negative", + "script": "latin" + }, + { + "name": "carla robinson", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda barry", + "label": "negative", + "script": "latin" + }, + { + "name": "marcus martinez", + "label": "negative", + "script": "latin" + }, + { + "name": "todd frazier", + "label": "negative", + "script": "latin" + }, + { + "name": "lee thompson", + "label": "negative", + "script": "latin" + }, + { + "name": "chris myers", + "label": "negative", + "script": "latin" + }, + { + "name": "william chadwick", + "label": "negative", + "script": "latin" + }, + { + "name": "blake cobb", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa smith", + "label": "negative", + "script": "latin" + }, + { + "name": "veronica cross", + "label": "negative", + "script": "latin" + }, + { + "name": "emily adams", + "label": "negative", + "script": "latin" + }, + { + "name": "kieran sheppard", + "label": "negative", + "script": "latin" + }, + { + "name": "ernest sherman", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Delete a random letter, Duplicate a random letter, and Swap random adjacent letters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "delete_random_letter", + "duplicate_random_letter_as_double_letter", + "swap_random_letter" + ], + "rule_descriptions": { + "delete_random_letter": "Delete a random letter", + "duplicate_random_letter_as_double_letter": "Duplicate a random letter", + "swap_random_letter": "Swap random adjacent letters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "lindsay davis", + "label": "negative", + "script": "latin" + }, + { + "name": "michele owens", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua mercer", + "label": "negative", + "script": "latin" + }, + { + "name": "linda williams", + "label": "negative", + "script": "latin" + }, + { + "name": "allen rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "david barrera", + "label": "negative", + "script": "latin" + }, + { + "name": "dennis russell", + "label": "negative", + "script": "latin" + }, + { + "name": "hannah mullins", + "label": "negative", + "script": "latin" + }, + { + "name": "dale hayes", + "label": "negative", + "script": "latin" + }, + { + "name": "leah thompson", + "label": "negative", + "script": "latin" + }, + { + "name": "gabriel ramirez", + "label": "negative", + "script": "latin" + }, + { + "name": "catherine raymond", + "label": "negative", + "script": "latin" + }, + { + "name": "gemma hogan", + "label": "negative", + "script": "latin" + }, + { + "name": "john martin", + "label": "negative", + "script": "latin" + }, + { + "name": "laura powers", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace random consonants with different consonants, Replace spaces with special characters, and Add a title suffix (Jr., PhD, etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_consonant_with_random_consonant", + "replace_spaces_with_random_special_characters", + "add_random_trailing_title" + ], + "rule_descriptions": { + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants", + "replace_spaces_with_random_special_characters": "Replace spaces with special characters", + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "diana campbell", + "label": "negative", + "script": "latin" + }, + { + "name": "ryan schneider", + "label": "negative", + "script": "latin" + }, + { + "name": "graham patel", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah lowe", + "label": "negative", + "script": "latin" + }, + { + "name": "edward parker", + "label": "negative", + "script": "latin" + }, + { + "name": "james clark", + "label": "negative", + "script": "latin" + }, + { + "name": "barbara allan", + "label": "negative", + "script": "latin" + }, + { + "name": "brooke harrison", + "label": "negative", + "script": "latin" + }, + { + "name": "jack raymond", + "label": "negative", + "script": "latin" + }, + { + "name": "charles hubbard", + "label": "negative", + "script": "latin" + }, + { + "name": "eugene herbert", + "label": "negative", + "script": "latin" + }, + { + "name": "misty griffiths", + "label": "negative", + "script": "latin" + }, + { + "name": "marcus moore", + "label": "negative", + "script": "latin" + }, + { + "name": "andrea cline", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa castro", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Swap random adjacent letters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_random_letter" + ], + "rule_descriptions": { + "swap_random_letter": "Swap random adjacent letters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "holly johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "craig owen", + "label": "negative", + "script": "latin" + }, + { + "name": "bernard mitchell", + "label": "negative", + "script": "latin" + }, + { + "name": "kimberly perry", + "label": "negative", + "script": "latin" + }, + { + "name": "brett evans", + "label": "negative", + "script": "latin" + }, + { + "name": "beverley gutierrez", + "label": "negative", + "script": "latin" + }, + { + "name": "robert francis", + "label": "negative", + "script": "latin" + }, + { + "name": "ellie leach", + "label": "negative", + "script": "latin" + }, + { + "name": "crystal cherry", + "label": "negative", + "script": "latin" + }, + { + "name": "antony love", + "label": "negative", + "script": "latin" + }, + { + "name": "elijah roberts", + "label": "negative", + "script": "latin" + }, + { + "name": "sara lyons", + "label": "negative", + "script": "latin" + }, + { + "name": "brandi sullivan", + "label": "negative", + "script": "latin" + }, + { + "name": "benjamin brooks", + "label": "negative", + "script": "latin" + }, + { + "name": "shirley bailey", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Replace spaces with special characters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_spaces_with_random_special_characters" + ], + "rule_descriptions": { + "replace_spaces_with_random_special_characters": "Replace spaces with special characters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "tiffany sanders", + "label": "negative", + "script": "latin" + }, + { + "name": "angela foster", + "label": "negative", + "script": "latin" + }, + { + "name": "carole smith", + "label": "negative", + "script": "latin" + }, + { + "name": "mary hawkins", + "label": "negative", + "script": "latin" + }, + { + "name": "molly johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "debbie perez", + "label": "negative", + "script": "latin" + }, + { + "name": "david davis", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony pugh", + "label": "negative", + "script": "latin" + }, + { + "name": "rebecca gutierrez", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda patel", + "label": "negative", + "script": "latin" + }, + { + "name": "sara simmons", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher estrada", + "label": "negative", + "script": "latin" + }, + { + "name": "ruben mitchell", + "label": "negative", + "script": "latin" + }, + { + "name": "eileen hatfield", + "label": "negative", + "script": "latin" + }, + { + "name": "luis frey", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Abbreviate name parts, Remove a random vowel, and Reorder name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_abbreviations", + "remove_random_vowel", + "name_parts_permutations" + ], + "rule_descriptions": { + "shorten_name_to_abbreviations": "Abbreviate name parts", + "remove_random_vowel": "Remove a random vowel", + "name_parts_permutations": "Reorder name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "jessica hughes", + "label": "negative", + "script": "latin" + }, + { + "name": "mark reyes", + "label": "negative", + "script": "latin" + }, + { + "name": "lindsey young", + "label": "negative", + "script": "latin" + }, + { + "name": "nigel gonzalez", + "label": "negative", + "script": "latin" + }, + { + "name": "luis johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer wong", + "label": "negative", + "script": "latin" + }, + { + "name": "kelly lawson", + "label": "negative", + "script": "latin" + }, + { + "name": "jodie dawson", + "label": "negative", + "script": "latin" + }, + { + "name": "laura phillips", + "label": "negative", + "script": "latin" + }, + { + "name": "tiffany smith", + "label": "negative", + "script": "latin" + }, + { + "name": "john munoz", + "label": "negative", + "script": "latin" + }, + { + "name": "cody cline", + "label": "negative", + "script": "latin" + }, + { + "name": "maurice jones", + "label": "negative", + "script": "latin" + }, + { + "name": "valerie wallace", + "label": "negative", + "script": "latin" + }, + { + "name": "travis thomas", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Delete a random letter, Use first name initial with last name, and Swap random adjacent letters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "delete_random_letter", + "initial_only_first_name", + "swap_random_letter" + ], + "rule_descriptions": { + "delete_random_letter": "Delete a random letter", + "initial_only_first_name": "Use first name initial with last name", + "swap_random_letter": "Swap random adjacent letters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "brian ferguson", + "label": "negative", + "script": "latin" + }, + { + "name": "dawn woodward", + "label": "negative", + "script": "latin" + }, + { + "name": "patricia clark", + "label": "negative", + "script": "latin" + }, + { + "name": "dale peters", + "label": "negative", + "script": "latin" + }, + { + "name": "cindy greene", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica ward", + "label": "negative", + "script": "latin" + }, + { + "name": "jacob williams", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "dean barajas", + "label": "negative", + "script": "latin" + }, + { + "name": "heather jones", + "label": "negative", + "script": "latin" + }, + { + "name": "justin robinson", + "label": "negative", + "script": "latin" + }, + { + "name": "allison novak", + "label": "negative", + "script": "latin" + }, + { + "name": "mary hill", + "label": "negative", + "script": "latin" + }, + { + "name": "donald cooper", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa marshall", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap random adjacent letters, and Replace spaces with special characters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_random_letter", + "replace_spaces_with_random_special_characters" + ], + "rule_descriptions": { + "swap_random_letter": "Swap random adjacent letters", + "replace_spaces_with_random_special_characters": "Replace spaces with special characters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "amy sheppard", + "label": "negative", + "script": "latin" + }, + { + "name": "jason johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "tiffany raymond", + "label": "negative", + "script": "latin" + }, + { + "name": "edward williams", + "label": "negative", + "script": "latin" + }, + { + "name": "norman wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "samantha carter", + "label": "negative", + "script": "latin" + }, + { + "name": "rhonda dawson", + "label": "negative", + "script": "latin" + }, + { + "name": "cynthia brown", + "label": "negative", + "script": "latin" + }, + { + "name": "pamela ramirez", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy woods", + "label": "negative", + "script": "latin" + }, + { + "name": "annette mcmahon", + "label": "negative", + "script": "latin" + }, + { + "name": "fiona brooks", + "label": "negative", + "script": "latin" + }, + { + "name": "heather pruitt", + "label": "negative", + "script": "latin" + }, + { + "name": "charles gutierrez", + "label": "negative", + "script": "latin" + }, + { + "name": "scott martinez", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove a random consonant, Swap random adjacent letters, and Insert a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_consonant", + "swap_random_letter", + "insert_random_letter" + ], + "rule_descriptions": { + "remove_random_consonant": "Remove a random consonant", + "swap_random_letter": "Swap random adjacent letters", + "insert_random_letter": "Insert a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "martyn johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "patrick jackson", + "label": "negative", + "script": "latin" + }, + { + "name": "john garcia", + "label": "negative", + "script": "latin" + }, + { + "name": "alyssa jackson", + "label": "negative", + "script": "latin" + }, + { + "name": "beth lynn", + "label": "negative", + "script": "latin" + }, + { + "name": "laura rowe", + "label": "negative", + "script": "latin" + }, + { + "name": "lauren arellano", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie white", + "label": "negative", + "script": "latin" + }, + { + "name": "frederick macdonald", + "label": "negative", + "script": "latin" + }, + { + "name": "cassidy cox", + "label": "negative", + "script": "latin" + }, + { + "name": "marisa wallace", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer decker", + "label": "negative", + "script": "latin" + }, + { + "name": "michael ballard", + "label": "negative", + "script": "latin" + }, + { + "name": "tara garcia", + "label": "negative", + "script": "latin" + }, + { + "name": "joe mills", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap adjacent syllables, and Swap random adjacent letters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_syllables", + "swap_random_letter" + ], + "rule_descriptions": { + "swap_adjacent_syllables": "Swap adjacent syllables", + "swap_random_letter": "Swap random adjacent letters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "michael warner", + "label": "negative", + "script": "latin" + }, + { + "name": "katie lee", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley duke", + "label": "negative", + "script": "latin" + }, + { + "name": "bill atkinson", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah nichols", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica ball", + "label": "negative", + "script": "latin" + }, + { + "name": "john ball", + "label": "negative", + "script": "latin" + }, + { + "name": "ryan burke", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica garcia", + "label": "negative", + "script": "latin" + }, + { + "name": "george bennett", + "label": "negative", + "script": "latin" + }, + { + "name": "linda patterson", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph pratt", + "label": "negative", + "script": "latin" + }, + { + "name": "sam glover", + "label": "negative", + "script": "latin" + }, + { + "name": "michael garcia", + "label": "negative", + "script": "latin" + }, + { + "name": "victoria lloyd", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove a random consonant, and Insert a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_consonant", + "insert_random_letter" + ], + "rule_descriptions": { + "remove_random_consonant": "Remove a random consonant", + "insert_random_letter": "Insert a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "sian merritt", + "label": "negative", + "script": "latin" + }, + { + "name": "kurt carter", + "label": "negative", + "script": "latin" + }, + { + "name": "james smith", + "label": "negative", + "script": "latin" + }, + { + "name": "donald watkins", + "label": "negative", + "script": "latin" + }, + { + "name": "debbie harrison", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph maxwell", + "label": "negative", + "script": "latin" + }, + { + "name": "damian watson", + "label": "negative", + "script": "latin" + }, + { + "name": "amber davis", + "label": "negative", + "script": "latin" + }, + { + "name": "judy wood", + "label": "negative", + "script": "latin" + }, + { + "name": "marian bradley", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa valdez", + "label": "negative", + "script": "latin" + }, + { + "name": "nichole johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "stephen garcia", + "label": "negative", + "script": "latin" + }, + { + "name": "leslie martinez", + "label": "negative", + "script": "latin" + }, + { + "name": "sherry jimenez", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap random adjacent letters, Remove a random vowel, and Swap adjacent syllables.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_random_letter", + "remove_random_vowel", + "swap_adjacent_syllables" + ], + "rule_descriptions": { + "swap_random_letter": "Swap random adjacent letters", + "remove_random_vowel": "Remove a random vowel", + "swap_adjacent_syllables": "Swap adjacent syllables" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "james harris", + "label": "negative", + "script": "latin" + }, + { + "name": "lydia russell", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie harris", + "label": "negative", + "script": "latin" + }, + { + "name": "shannon wise", + "label": "negative", + "script": "latin" + }, + { + "name": "eric reese", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah sims", + "label": "negative", + "script": "latin" + }, + { + "name": "isaac benton", + "label": "negative", + "script": "latin" + }, + { + "name": "barbara spencer", + "label": "negative", + "script": "latin" + }, + { + "name": "kristi olsen", + "label": "negative", + "script": "latin" + }, + { + "name": "pamela riley", + "label": "negative", + "script": "latin" + }, + { + "name": "eric snyder", + "label": "negative", + "script": "latin" + }, + { + "name": "heather smith", + "label": "negative", + "script": "latin" + }, + { + "name": "lynne woods", + "label": "negative", + "script": "latin" + }, + { + "name": "eric williams", + "label": "negative", + "script": "latin" + }, + { + "name": "amy pollard", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Swap adjacent syllables.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_syllables" + ], + "rule_descriptions": { + "swap_adjacent_syllables": "Swap adjacent syllables" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "kyle rivas", + "label": "negative", + "script": "latin" + }, + { + "name": "aaron brewer", + "label": "negative", + "script": "latin" + }, + { + "name": "rebecca jones", + "label": "negative", + "script": "latin" + }, + { + "name": "steven gardner", + "label": "negative", + "script": "latin" + }, + { + "name": "victoria murray", + "label": "negative", + "script": "latin" + }, + { + "name": "dawn arellano", + "label": "negative", + "script": "latin" + }, + { + "name": "william clark", + "label": "negative", + "script": "latin" + }, + { + "name": "hilary lewis", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony ortiz", + "label": "negative", + "script": "latin" + }, + { + "name": "alexander tucker", + "label": "negative", + "script": "latin" + }, + { + "name": "patricia dickinson", + "label": "negative", + "script": "latin" + }, + { + "name": "marisa thomas", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua mcdonald", + "label": "negative", + "script": "latin" + }, + { + "name": "holly wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "martyn edwards", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap adjacent consonants, and Delete a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_consonants", + "delete_random_letter" + ], + "rule_descriptions": { + "swap_adjacent_consonants": "Swap adjacent consonants", + "delete_random_letter": "Delete a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "travis ellis", + "label": "negative", + "script": "latin" + }, + { + "name": "shawn riley", + "label": "negative", + "script": "latin" + }, + { + "name": "william keith", + "label": "negative", + "script": "latin" + }, + { + "name": "donna hill", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel mueller", + "label": "negative", + "script": "latin" + }, + { + "name": "julia graham", + "label": "negative", + "script": "latin" + }, + { + "name": "shannon salinas", + "label": "negative", + "script": "latin" + }, + { + "name": "john lopez", + "label": "negative", + "script": "latin" + }, + { + "name": "deborah king", + "label": "negative", + "script": "latin" + }, + { + "name": "paula brown", + "label": "negative", + "script": "latin" + }, + { + "name": "jason o'neill", + "label": "negative", + "script": "latin" + }, + { + "name": "jason copeland", + "label": "negative", + "script": "latin" + }, + { + "name": "sheila morgan", + "label": "negative", + "script": "latin" + }, + { + "name": "brittney whittaker", + "label": "negative", + "script": "latin" + }, + { + "name": "dawn west", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title suffix (Jr., PhD, etc.), Remove all spaces, and Replace double letters with a single letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_trailing_title", + "remove_all_spaces", + "replace_double_letters_with_single_letter" + ], + "rule_descriptions": { + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)", + "remove_all_spaces": "Remove all spaces", + "replace_double_letters_with_single_letter": "Replace double letters with a single letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "joseph webster", + "label": "negative", + "script": "latin" + }, + { + "name": "benjamin ramirez", + "label": "negative", + "script": "latin" + }, + { + "name": "rita banks", + "label": "negative", + "script": "latin" + }, + { + "name": "troy harrison", + "label": "negative", + "script": "latin" + }, + { + "name": "erica chandler", + "label": "negative", + "script": "latin" + }, + { + "name": "elizabeth wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel hicks", + "label": "negative", + "script": "latin" + }, + { + "name": "james bates", + "label": "negative", + "script": "latin" + }, + { + "name": "harry read", + "label": "negative", + "script": "latin" + }, + { + "name": "david lopez", + "label": "negative", + "script": "latin" + }, + { + "name": "stephen long", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew webb", + "label": "negative", + "script": "latin" + }, + { + "name": "patricia patterson", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy clark", + "label": "negative", + "script": "latin" + }, + { + "name": "alexander anderson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Use first name initial with last name, Remove a random vowel, and Remove a random consonant.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "initial_only_first_name", + "remove_random_vowel", + "remove_random_consonant" + ], + "rule_descriptions": { + "initial_only_first_name": "Use first name initial with last name", + "remove_random_vowel": "Remove a random vowel", + "remove_random_consonant": "Remove a random consonant" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "james matthews", + "label": "negative", + "script": "latin" + }, + { + "name": "nathan kline", + "label": "negative", + "script": "latin" + }, + { + "name": "tina kelley", + "label": "negative", + "script": "latin" + }, + { + "name": "ellie hill", + "label": "negative", + "script": "latin" + }, + { + "name": "bruce fox", + "label": "negative", + "script": "latin" + }, + { + "name": "kenneth scott", + "label": "negative", + "script": "latin" + }, + { + "name": "lee holloway", + "label": "negative", + "script": "latin" + }, + { + "name": "james powell", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole sparks", + "label": "negative", + "script": "latin" + }, + { + "name": "alyssa fox", + "label": "negative", + "script": "latin" + }, + { + "name": "laurie jackson", + "label": "negative", + "script": "latin" + }, + { + "name": "pamela watts", + "label": "negative", + "script": "latin" + }, + { + "name": "brady alexander", + "label": "negative", + "script": "latin" + }, + { + "name": "angela pennington", + "label": "negative", + "script": "latin" + }, + { + "name": "laura best", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove a random vowel, Replace spaces with special characters, and Use first name initial with last name.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_vowel", + "replace_spaces_with_random_special_characters", + "initial_only_first_name" + ], + "rule_descriptions": { + "remove_random_vowel": "Remove a random vowel", + "replace_spaces_with_random_special_characters": "Replace spaces with special characters", + "initial_only_first_name": "Use first name initial with last name" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "luke wade", + "label": "negative", + "script": "latin" + }, + { + "name": "jason ross", + "label": "negative", + "script": "latin" + }, + { + "name": "terence villegas", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher dixon", + "label": "negative", + "script": "latin" + }, + { + "name": "bryan mckinney", + "label": "negative", + "script": "latin" + }, + { + "name": "martin saunders", + "label": "negative", + "script": "latin" + }, + { + "name": "robert owens", + "label": "negative", + "script": "latin" + }, + { + "name": "jeremy arias", + "label": "negative", + "script": "latin" + }, + { + "name": "miguel baker", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy vargas", + "label": "negative", + "script": "latin" + }, + { + "name": "jackie howard", + "label": "negative", + "script": "latin" + }, + { + "name": "karen mcguire", + "label": "negative", + "script": "latin" + }, + { + "name": "mohamed duffy", + "label": "negative", + "script": "latin" + }, + { + "name": "abigail nelson", + "label": "negative", + "script": "latin" + }, + { + "name": "keith jones", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Use first name initial with last name, Replace random consonants with different consonants, and Abbreviate name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "initial_only_first_name", + "replace_random_consonant_with_random_consonant", + "shorten_name_to_abbreviations" + ], + "rule_descriptions": { + "initial_only_first_name": "Use first name initial with last name", + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants", + "shorten_name_to_abbreviations": "Abbreviate name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "grace reid", + "label": "negative", + "script": "latin" + }, + { + "name": "elizabeth lloyd", + "label": "negative", + "script": "latin" + }, + { + "name": "kristy berry", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica gordon", + "label": "negative", + "script": "latin" + }, + { + "name": "william estrada", + "label": "negative", + "script": "latin" + }, + { + "name": "scott rogers", + "label": "negative", + "script": "latin" + }, + { + "name": "betty green", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica ray", + "label": "negative", + "script": "latin" + }, + { + "name": "samantha hill", + "label": "negative", + "script": "latin" + }, + { + "name": "caroline sanchez", + "label": "negative", + "script": "latin" + }, + { + "name": "dawn brown", + "label": "negative", + "script": "latin" + }, + { + "name": "sharon robinson", + "label": "negative", + "script": "latin" + }, + { + "name": "jaclyn gilbert", + "label": "negative", + "script": "latin" + }, + { + "name": "pauline saunders", + "label": "negative", + "script": "latin" + }, + { + "name": "dylan campbell", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove a random consonant, Reorder name parts, and Use first name initial with last name.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_consonant", + "name_parts_permutations", + "initial_only_first_name" + ], + "rule_descriptions": { + "remove_random_consonant": "Remove a random consonant", + "name_parts_permutations": "Reorder name parts", + "initial_only_first_name": "Use first name initial with last name" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "laura gonzales", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph townsend", + "label": "negative", + "script": "latin" + }, + { + "name": "douglas hayes", + "label": "negative", + "script": "latin" + }, + { + "name": "richard porter", + "label": "negative", + "script": "latin" + }, + { + "name": "geraldine carlson", + "label": "negative", + "script": "latin" + }, + { + "name": "nichole huff", + "label": "negative", + "script": "latin" + }, + { + "name": "brandon vasquez", + "label": "negative", + "script": "latin" + }, + { + "name": "kara zavala", + "label": "negative", + "script": "latin" + }, + { + "name": "karen mcpherson", + "label": "negative", + "script": "latin" + }, + { + "name": "josh williams", + "label": "negative", + "script": "latin" + }, + { + "name": "guy robinson", + "label": "negative", + "script": "latin" + }, + { + "name": "jemma carlson", + "label": "negative", + "script": "latin" + }, + { + "name": "todd delgado", + "label": "negative", + "script": "latin" + }, + { + "name": "john villegas", + "label": "negative", + "script": "latin" + }, + { + "name": "samantha woods", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove a random consonant, Abbreviate name parts, and Swap adjacent consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_consonant", + "shorten_name_to_abbreviations", + "swap_adjacent_consonants" + ], + "rule_descriptions": { + "remove_random_consonant": "Remove a random consonant", + "shorten_name_to_abbreviations": "Abbreviate name parts", + "swap_adjacent_consonants": "Swap adjacent consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "catherine lloyd", + "label": "negative", + "script": "latin" + }, + { + "name": "david fischer", + "label": "negative", + "script": "latin" + }, + { + "name": "jamie juarez", + "label": "negative", + "script": "latin" + }, + { + "name": "luke christian", + "label": "negative", + "script": "latin" + }, + { + "name": "carlos young", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "chelsea burrows", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie thomas", + "label": "negative", + "script": "latin" + }, + { + "name": "jordan jones", + "label": "negative", + "script": "latin" + }, + { + "name": "guy brown", + "label": "negative", + "script": "latin" + }, + { + "name": "emily cunningham", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas roman", + "label": "negative", + "script": "latin" + }, + { + "name": "samantha torres", + "label": "negative", + "script": "latin" + }, + { + "name": "alice jones", + "label": "negative", + "script": "latin" + }, + { + "name": "frederick miller", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove a random consonant, and Replace spaces with special characters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_consonant", + "replace_spaces_with_random_special_characters" + ], + "rule_descriptions": { + "remove_random_consonant": "Remove a random consonant", + "replace_spaces_with_random_special_characters": "Replace spaces with special characters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "frank george", + "label": "negative", + "script": "latin" + }, + { + "name": "janice herbert", + "label": "negative", + "script": "latin" + }, + { + "name": "ann taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "chad floyd", + "label": "negative", + "script": "latin" + }, + { + "name": "albert gates", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa lloyd", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas hurst", + "label": "negative", + "script": "latin" + }, + { + "name": "susan lopez", + "label": "negative", + "script": "latin" + }, + { + "name": "deborah humphries", + "label": "negative", + "script": "latin" + }, + { + "name": "ryan davenport", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa smith", + "label": "negative", + "script": "latin" + }, + { + "name": "christian nguyen", + "label": "negative", + "script": "latin" + }, + { + "name": "theresa johns", + "label": "negative", + "script": "latin" + }, + { + "name": "richard murphy", + "label": "negative", + "script": "latin" + }, + { + "name": "donna hester", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove all spaces, and Abbreviate name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_all_spaces", + "shorten_name_to_abbreviations" + ], + "rule_descriptions": { + "remove_all_spaces": "Remove all spaces", + "shorten_name_to_abbreviations": "Abbreviate name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "samantha richardson", + "label": "negative", + "script": "latin" + }, + { + "name": "derek davis", + "label": "negative", + "script": "latin" + }, + { + "name": "michael rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer keller", + "label": "negative", + "script": "latin" + }, + { + "name": "callum o'neill", + "label": "negative", + "script": "latin" + }, + { + "name": "frederick cervantes", + "label": "negative", + "script": "latin" + }, + { + "name": "lesley wood", + "label": "negative", + "script": "latin" + }, + { + "name": "adam williams", + "label": "negative", + "script": "latin" + }, + { + "name": "erica phillips", + "label": "negative", + "script": "latin" + }, + { + "name": "robert salazar", + "label": "negative", + "script": "latin" + }, + { + "name": "nigel jennings", + "label": "negative", + "script": "latin" + }, + { + "name": "lee morris", + "label": "negative", + "script": "latin" + }, + { + "name": "frank paul", + "label": "negative", + "script": "latin" + }, + { + "name": "robert torres", + "label": "negative", + "script": "latin" + }, + { + "name": "deborah brown", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Delete a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "delete_random_letter" + ], + "rule_descriptions": { + "delete_random_letter": "Delete a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "ryan ryan", + "label": "negative", + "script": "latin" + }, + { + "name": "shaun barnes", + "label": "negative", + "script": "latin" + }, + { + "name": "margaret guerra", + "label": "negative", + "script": "latin" + }, + { + "name": "rebecca arias", + "label": "negative", + "script": "latin" + }, + { + "name": "aaron fisher", + "label": "negative", + "script": "latin" + }, + { + "name": "ryan rose", + "label": "negative", + "script": "latin" + }, + { + "name": "hayley rose", + "label": "negative", + "script": "latin" + }, + { + "name": "holly moran", + "label": "negative", + "script": "latin" + }, + { + "name": "carolyn massey", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas stevens", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin hill", + "label": "negative", + "script": "latin" + }, + { + "name": "omar nelson", + "label": "negative", + "script": "latin" + }, + { + "name": "nathan williams", + "label": "negative", + "script": "latin" + }, + { + "name": "amy jones", + "label": "negative", + "script": "latin" + }, + { + "name": "ryan galloway", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Remove a random consonant.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_consonant" + ], + "rule_descriptions": { + "remove_random_consonant": "Remove a random consonant" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "lynn casey", + "label": "negative", + "script": "latin" + }, + { + "name": "laura mcdaniel", + "label": "negative", + "script": "latin" + }, + { + "name": "kelly clark", + "label": "negative", + "script": "latin" + }, + { + "name": "patrick bolton", + "label": "negative", + "script": "latin" + }, + { + "name": "rachel whitehead", + "label": "negative", + "script": "latin" + }, + { + "name": "chad bowen", + "label": "negative", + "script": "latin" + }, + { + "name": "mary allen", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua morris", + "label": "negative", + "script": "latin" + }, + { + "name": "alicia gilmore", + "label": "negative", + "script": "latin" + }, + { + "name": "robert evans", + "label": "negative", + "script": "latin" + }, + { + "name": "larry berry", + "label": "negative", + "script": "latin" + }, + { + "name": "michael weaver", + "label": "negative", + "script": "latin" + }, + { + "name": "dean young", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher harris", + "label": "negative", + "script": "latin" + }, + { + "name": "breanna barker", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Replace spaces with special characters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_spaces_with_random_special_characters" + ], + "rule_descriptions": { + "replace_spaces_with_random_special_characters": "Replace spaces with special characters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "sean gill", + "label": "negative", + "script": "latin" + }, + { + "name": "maurice preston", + "label": "negative", + "script": "latin" + }, + { + "name": "nathan moore", + "label": "negative", + "script": "latin" + }, + { + "name": "tracey hernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie barnett", + "label": "negative", + "script": "latin" + }, + { + "name": "kayleigh thomson", + "label": "negative", + "script": "latin" + }, + { + "name": "louis zimmerman", + "label": "negative", + "script": "latin" + }, + { + "name": "robert taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "nathan stephenson", + "label": "negative", + "script": "latin" + }, + { + "name": "victoria giles", + "label": "negative", + "script": "latin" + }, + { + "name": "linda morris", + "label": "negative", + "script": "latin" + }, + { + "name": "mary stephens", + "label": "negative", + "script": "latin" + }, + { + "name": "gary clark", + "label": "negative", + "script": "latin" + }, + { + "name": "gillian harris", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffrey smith", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove a random vowel, and Reorder name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_vowel", + "name_parts_permutations" + ], + "rule_descriptions": { + "remove_random_vowel": "Remove a random vowel", + "name_parts_permutations": "Reorder name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "danielle lam", + "label": "negative", + "script": "latin" + }, + { + "name": "monica meza", + "label": "negative", + "script": "latin" + }, + { + "name": "stacey mccarty", + "label": "negative", + "script": "latin" + }, + { + "name": "alexander gough", + "label": "negative", + "script": "latin" + }, + { + "name": "tami jones", + "label": "negative", + "script": "latin" + }, + { + "name": "robert ortega", + "label": "negative", + "script": "latin" + }, + { + "name": "bradley watts", + "label": "negative", + "script": "latin" + }, + { + "name": "casey garza", + "label": "negative", + "script": "latin" + }, + { + "name": "charlotte walker", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica contreras", + "label": "negative", + "script": "latin" + }, + { + "name": "frank barber", + "label": "negative", + "script": "latin" + }, + { + "name": "patricia oconnor", + "label": "negative", + "script": "latin" + }, + { + "name": "diana hernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "katelyn allen", + "label": "negative", + "script": "latin" + }, + { + "name": "howard smart", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Use first name initial with last name.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "initial_only_first_name" + ], + "rule_descriptions": { + "initial_only_first_name": "Use first name initial with last name" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "daniel bryant", + "label": "negative", + "script": "latin" + }, + { + "name": "dawn graham", + "label": "negative", + "script": "latin" + }, + { + "name": "richard charles", + "label": "negative", + "script": "latin" + }, + { + "name": "karen hill", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy campbell", + "label": "negative", + "script": "latin" + }, + { + "name": "jason carr", + "label": "negative", + "script": "latin" + }, + { + "name": "tina parker", + "label": "negative", + "script": "latin" + }, + { + "name": "rebecca martin", + "label": "negative", + "script": "latin" + }, + { + "name": "natasha richardson", + "label": "negative", + "script": "latin" + }, + { + "name": "robert garcia", + "label": "negative", + "script": "latin" + }, + { + "name": "shirley payne", + "label": "negative", + "script": "latin" + }, + { + "name": "amber miller", + "label": "negative", + "script": "latin" + }, + { + "name": "elizabeth carr", + "label": "negative", + "script": "latin" + }, + { + "name": "rickey bolton", + "label": "negative", + "script": "latin" + }, + { + "name": "megan johnson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Duplicate a random letter, Remove a random consonant, and Convert name to initials.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "duplicate_random_letter_as_double_letter", + "remove_random_consonant", + "shorten_name_to_initials" + ], + "rule_descriptions": { + "duplicate_random_letter_as_double_letter": "Duplicate a random letter", + "remove_random_consonant": "Remove a random consonant", + "shorten_name_to_initials": "Convert name to initials" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "hugh collier", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua ruiz", + "label": "negative", + "script": "latin" + }, + { + "name": "kelly sanchez", + "label": "negative", + "script": "latin" + }, + { + "name": "kim oconnell", + "label": "negative", + "script": "latin" + }, + { + "name": "diana burgess", + "label": "negative", + "script": "latin" + }, + { + "name": "john rodgers", + "label": "negative", + "script": "latin" + }, + { + "name": "john lloyd", + "label": "negative", + "script": "latin" + }, + { + "name": "shannon edwards", + "label": "negative", + "script": "latin" + }, + { + "name": "lindsey gonzalez", + "label": "negative", + "script": "latin" + }, + { + "name": "todd taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "joe lester", + "label": "negative", + "script": "latin" + }, + { + "name": "rhonda andrews", + "label": "negative", + "script": "latin" + }, + { + "name": "debra lewis", + "label": "negative", + "script": "latin" + }, + { + "name": "sara kemp", + "label": "negative", + "script": "latin" + }, + { + "name": "todd stone", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove a random consonant, and Reorder name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_consonant", + "name_parts_permutations" + ], + "rule_descriptions": { + "remove_random_consonant": "Remove a random consonant", + "name_parts_permutations": "Reorder name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "sherry bolton", + "label": "negative", + "script": "latin" + }, + { + "name": "patricia larsen", + "label": "negative", + "script": "latin" + }, + { + "name": "jacob guzman", + "label": "negative", + "script": "latin" + }, + { + "name": "cory lawrence", + "label": "negative", + "script": "latin" + }, + { + "name": "kelly smith", + "label": "negative", + "script": "latin" + }, + { + "name": "brian stanley", + "label": "negative", + "script": "latin" + }, + { + "name": "marilyn reeves", + "label": "negative", + "script": "latin" + }, + { + "name": "alexander hooper", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy williams", + "label": "negative", + "script": "latin" + }, + { + "name": "gina butler", + "label": "negative", + "script": "latin" + }, + { + "name": "amber davis", + "label": "negative", + "script": "latin" + }, + { + "name": "miguel moore", + "label": "negative", + "script": "latin" + }, + { + "name": "cynthia mora", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph lin", + "label": "negative", + "script": "latin" + }, + { + "name": "luis arnold", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Use first name initial with last name, and Remove a random vowel.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "initial_only_first_name", + "remove_random_vowel" + ], + "rule_descriptions": { + "initial_only_first_name": "Use first name initial with last name", + "remove_random_vowel": "Remove a random vowel" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "latasha peterson", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew graves", + "label": "negative", + "script": "latin" + }, + { + "name": "erika colon", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley cannon", + "label": "negative", + "script": "latin" + }, + { + "name": "abigail fletcher", + "label": "negative", + "script": "latin" + }, + { + "name": "jake parker", + "label": "negative", + "script": "latin" + }, + { + "name": "andrew lewis", + "label": "negative", + "script": "latin" + }, + { + "name": "william phillips", + "label": "negative", + "script": "latin" + }, + { + "name": "craig aguilar", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole ross", + "label": "negative", + "script": "latin" + }, + { + "name": "carrie johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "ricky gray", + "label": "negative", + "script": "latin" + }, + { + "name": "tom floyd", + "label": "negative", + "script": "latin" + }, + { + "name": "shelby carr", + "label": "negative", + "script": "latin" + }, + { + "name": "tiffany edwards", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap adjacent consonants, Use first name initial with last name, and Replace double letters with a single letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_consonants", + "initial_only_first_name", + "replace_double_letters_with_single_letter" + ], + "rule_descriptions": { + "swap_adjacent_consonants": "Swap adjacent consonants", + "initial_only_first_name": "Use first name initial with last name", + "replace_double_letters_with_single_letter": "Replace double letters with a single letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "diane hill", + "label": "negative", + "script": "latin" + }, + { + "name": "devin graham", + "label": "negative", + "script": "latin" + }, + { + "name": "steven king", + "label": "negative", + "script": "latin" + }, + { + "name": "andrew foster", + "label": "negative", + "script": "latin" + }, + { + "name": "alan roberts", + "label": "negative", + "script": "latin" + }, + { + "name": "john young", + "label": "negative", + "script": "latin" + }, + { + "name": "scott hardy", + "label": "negative", + "script": "latin" + }, + { + "name": "lesley hill", + "label": "negative", + "script": "latin" + }, + { + "name": "brian hernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "darren allen", + "label": "negative", + "script": "latin" + }, + { + "name": "eduardo turner", + "label": "negative", + "script": "latin" + }, + { + "name": "antony sharpe", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel lutz", + "label": "negative", + "script": "latin" + }, + { + "name": "alyssa jackson", + "label": "negative", + "script": "latin" + }, + { + "name": "alicia haynes", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace spaces with special characters, Remove a random vowel, and Abbreviate name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_spaces_with_random_special_characters", + "remove_random_vowel", + "shorten_name_to_abbreviations" + ], + "rule_descriptions": { + "replace_spaces_with_random_special_characters": "Replace spaces with special characters", + "remove_random_vowel": "Remove a random vowel", + "shorten_name_to_abbreviations": "Abbreviate name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "matthew stephenson", + "label": "negative", + "script": "latin" + }, + { + "name": "michael johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "kent dalton", + "label": "negative", + "script": "latin" + }, + { + "name": "brittany gardner", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas vance", + "label": "negative", + "script": "latin" + }, + { + "name": "suzanne williams", + "label": "negative", + "script": "latin" + }, + { + "name": "robert williamson", + "label": "negative", + "script": "latin" + }, + { + "name": "jacob parrish", + "label": "negative", + "script": "latin" + }, + { + "name": "robin hayes", + "label": "negative", + "script": "latin" + }, + { + "name": "robin lees", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony martin", + "label": "negative", + "script": "latin" + }, + { + "name": "jason collier", + "label": "negative", + "script": "latin" + }, + { + "name": "zachary evans", + "label": "negative", + "script": "latin" + }, + { + "name": "susan robinson", + "label": "negative", + "script": "latin" + }, + { + "name": "connor pope", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title prefix (Mr., Dr., etc.), and Replace double letters with a single letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_leading_title", + "replace_double_letters_with_single_letter" + ], + "rule_descriptions": { + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)", + "replace_double_letters_with_single_letter": "Replace double letters with a single letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "derrick higgins", + "label": "negative", + "script": "latin" + }, + { + "name": "alexandra turner", + "label": "negative", + "script": "latin" + }, + { + "name": "robert hill", + "label": "negative", + "script": "latin" + }, + { + "name": "samantha harrison", + "label": "negative", + "script": "latin" + }, + { + "name": "amy goodwin", + "label": "negative", + "script": "latin" + }, + { + "name": "mary harris", + "label": "negative", + "script": "latin" + }, + { + "name": "emma wells", + "label": "negative", + "script": "latin" + }, + { + "name": "brandi miller", + "label": "negative", + "script": "latin" + }, + { + "name": "monique akhtar", + "label": "negative", + "script": "latin" + }, + { + "name": "sara grant", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa berry", + "label": "negative", + "script": "latin" + }, + { + "name": "glen holland", + "label": "negative", + "script": "latin" + }, + { + "name": "devin stokes", + "label": "negative", + "script": "latin" + }, + { + "name": "samuel ross", + "label": "negative", + "script": "latin" + }, + { + "name": "justin reyes", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Reorder name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "name_parts_permutations" + ], + "rule_descriptions": { + "name_parts_permutations": "Reorder name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "angela marshall", + "label": "negative", + "script": "latin" + }, + { + "name": "barbara russell", + "label": "negative", + "script": "latin" + }, + { + "name": "meagan johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "rachel avila", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas barker", + "label": "negative", + "script": "latin" + }, + { + "name": "jacob stanley", + "label": "negative", + "script": "latin" + }, + { + "name": "michael king", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa dean", + "label": "negative", + "script": "latin" + }, + { + "name": "alison clark", + "label": "negative", + "script": "latin" + }, + { + "name": "jamie holden", + "label": "negative", + "script": "latin" + }, + { + "name": "roy henry", + "label": "negative", + "script": "latin" + }, + { + "name": "kimberly hughes", + "label": "negative", + "script": "latin" + }, + { + "name": "shannon silva", + "label": "negative", + "script": "latin" + }, + { + "name": "leonard davis", + "label": "negative", + "script": "latin" + }, + { + "name": "kimberly clarke", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Abbreviate name parts, Replace random consonants with different consonants, and Use first name initial with last name.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_abbreviations", + "replace_random_consonant_with_random_consonant", + "initial_only_first_name" + ], + "rule_descriptions": { + "shorten_name_to_abbreviations": "Abbreviate name parts", + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants", + "initial_only_first_name": "Use first name initial with last name" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "samantha johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "james brennan", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle james", + "label": "negative", + "script": "latin" + }, + { + "name": "dale gillespie", + "label": "negative", + "script": "latin" + }, + { + "name": "lawrence curtis", + "label": "negative", + "script": "latin" + }, + { + "name": "jason sexton", + "label": "negative", + "script": "latin" + }, + { + "name": "chad jones", + "label": "negative", + "script": "latin" + }, + { + "name": "claire mitchell", + "label": "negative", + "script": "latin" + }, + { + "name": "catherine hall", + "label": "negative", + "script": "latin" + }, + { + "name": "penny foster", + "label": "negative", + "script": "latin" + }, + { + "name": "andrew ramos", + "label": "negative", + "script": "latin" + }, + { + "name": "zoe nolan", + "label": "negative", + "script": "latin" + }, + { + "name": "david fernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "george sloan", + "label": "negative", + "script": "latin" + }, + { + "name": "rachael fleming", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap adjacent consonants, Add a title prefix (Mr., Dr., etc.), and Reorder name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_consonants", + "add_random_leading_title", + "name_parts_permutations" + ], + "rule_descriptions": { + "swap_adjacent_consonants": "Swap adjacent consonants", + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)", + "name_parts_permutations": "Reorder name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "patricia hall", + "label": "negative", + "script": "latin" + }, + { + "name": "neil gibbs", + "label": "negative", + "script": "latin" + }, + { + "name": "rita barker", + "label": "negative", + "script": "latin" + }, + { + "name": "casey taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "oscar sutton", + "label": "negative", + "script": "latin" + }, + { + "name": "anna bell", + "label": "negative", + "script": "latin" + }, + { + "name": "michael bell", + "label": "negative", + "script": "latin" + }, + { + "name": "jared wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "linda wheeler", + "label": "negative", + "script": "latin" + }, + { + "name": "carolyn fox", + "label": "negative", + "script": "latin" + }, + { + "name": "jeremy mitchell", + "label": "negative", + "script": "latin" + }, + { + "name": "raymond stone", + "label": "negative", + "script": "latin" + }, + { + "name": "wendy kelly", + "label": "negative", + "script": "latin" + }, + { + "name": "jesse smith", + "label": "negative", + "script": "latin" + }, + { + "name": "grace ray", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Convert name to initials, Abbreviate name parts, and Swap random adjacent letters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_initials", + "shorten_name_to_abbreviations", + "swap_random_letter" + ], + "rule_descriptions": { + "shorten_name_to_initials": "Convert name to initials", + "shorten_name_to_abbreviations": "Abbreviate name parts", + "swap_random_letter": "Swap random adjacent letters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "joel kemp", + "label": "negative", + "script": "latin" + }, + { + "name": "madison salas", + "label": "negative", + "script": "latin" + }, + { + "name": "christina wood", + "label": "negative", + "script": "latin" + }, + { + "name": "tonya bell", + "label": "negative", + "script": "latin" + }, + { + "name": "laura perez", + "label": "negative", + "script": "latin" + }, + { + "name": "elaine farmer", + "label": "negative", + "script": "latin" + }, + { + "name": "christian garcia", + "label": "negative", + "script": "latin" + }, + { + "name": "jason abbott", + "label": "negative", + "script": "latin" + }, + { + "name": "stephen robinson", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole clark", + "label": "negative", + "script": "latin" + }, + { + "name": "william johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "benjamin ellis", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas wall", + "label": "negative", + "script": "latin" + }, + { + "name": "jonathan stephens", + "label": "negative", + "script": "latin" + }, + { + "name": "shirley huerta", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace random vowels with different vowels, Swap adjacent consonants, and Remove a random consonant.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_vowel_with_random_vowel", + "swap_adjacent_consonants", + "remove_random_consonant" + ], + "rule_descriptions": { + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels", + "swap_adjacent_consonants": "Swap adjacent consonants", + "remove_random_consonant": "Remove a random consonant" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "william martin", + "label": "negative", + "script": "latin" + }, + { + "name": "lorraine jackson", + "label": "negative", + "script": "latin" + }, + { + "name": "lawrence sullivan", + "label": "negative", + "script": "latin" + }, + { + "name": "crystal edwards", + "label": "negative", + "script": "latin" + }, + { + "name": "ronald palmer", + "label": "negative", + "script": "latin" + }, + { + "name": "andrew green", + "label": "negative", + "script": "latin" + }, + { + "name": "gary jones", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew doyle", + "label": "negative", + "script": "latin" + }, + { + "name": "david robertson", + "label": "negative", + "script": "latin" + }, + { + "name": "jimmy hill", + "label": "negative", + "script": "latin" + }, + { + "name": "kristi rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "marc moss", + "label": "negative", + "script": "latin" + }, + { + "name": "natalie johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "elizabeth robertson", + "label": "negative", + "script": "latin" + }, + { + "name": "rhys graham", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Abbreviate name parts, and Convert name to initials.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_abbreviations", + "shorten_name_to_initials" + ], + "rule_descriptions": { + "shorten_name_to_abbreviations": "Abbreviate name parts", + "shorten_name_to_initials": "Convert name to initials" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "amber allen", + "label": "negative", + "script": "latin" + }, + { + "name": "jason shaw", + "label": "negative", + "script": "latin" + }, + { + "name": "justin wallace", + "label": "negative", + "script": "latin" + }, + { + "name": "jason brown", + "label": "negative", + "script": "latin" + }, + { + "name": "angela freeman", + "label": "negative", + "script": "latin" + }, + { + "name": "melanie rowland", + "label": "negative", + "script": "latin" + }, + { + "name": "charles walters", + "label": "negative", + "script": "latin" + }, + { + "name": "dylan cook", + "label": "negative", + "script": "latin" + }, + { + "name": "sara patel", + "label": "negative", + "script": "latin" + }, + { + "name": "diana bibi", + "label": "negative", + "script": "latin" + }, + { + "name": "kathryn jones", + "label": "negative", + "script": "latin" + }, + { + "name": "michael ibarra", + "label": "negative", + "script": "latin" + }, + { + "name": "allison morris", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy jordan", + "label": "negative", + "script": "latin" + }, + { + "name": "laura salazar", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Abbreviate name parts, and Remove a random vowel.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_abbreviations", + "remove_random_vowel" + ], + "rule_descriptions": { + "shorten_name_to_abbreviations": "Abbreviate name parts", + "remove_random_vowel": "Remove a random vowel" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "andrew alvarez", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle horton", + "label": "negative", + "script": "latin" + }, + { + "name": "francisco archer", + "label": "negative", + "script": "latin" + }, + { + "name": "cassandra dyer", + "label": "negative", + "script": "latin" + }, + { + "name": "stacy rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa mcguire", + "label": "negative", + "script": "latin" + }, + { + "name": "mary lyons", + "label": "negative", + "script": "latin" + }, + { + "name": "fred singleton", + "label": "negative", + "script": "latin" + }, + { + "name": "charles crawford", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony gibson", + "label": "negative", + "script": "latin" + }, + { + "name": "elizabeth martinez", + "label": "negative", + "script": "latin" + }, + { + "name": "debra nash", + "label": "negative", + "script": "latin" + }, + { + "name": "joe best", + "label": "negative", + "script": "latin" + }, + { + "name": "valerie long", + "label": "negative", + "script": "latin" + }, + { + "name": "garry parker", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Reorder name parts, and Delete a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "name_parts_permutations", + "delete_random_letter" + ], + "rule_descriptions": { + "name_parts_permutations": "Reorder name parts", + "delete_random_letter": "Delete a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "ashley moore", + "label": "negative", + "script": "latin" + }, + { + "name": "kelly salas", + "label": "negative", + "script": "latin" + }, + { + "name": "nicholas rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "debra brown", + "label": "negative", + "script": "latin" + }, + { + "name": "victoria scott", + "label": "negative", + "script": "latin" + }, + { + "name": "rebecca fox", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew gallegos", + "label": "negative", + "script": "latin" + }, + { + "name": "lesley mitchell", + "label": "negative", + "script": "latin" + }, + { + "name": "michael houghton", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole kirby", + "label": "negative", + "script": "latin" + }, + { + "name": "james butler", + "label": "negative", + "script": "latin" + }, + { + "name": "donna moses", + "label": "negative", + "script": "latin" + }, + { + "name": "joyce anderson", + "label": "negative", + "script": "latin" + }, + { + "name": "lauren collins", + "label": "negative", + "script": "latin" + }, + { + "name": "stacey morris", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace random consonants with different consonants, and Replace spaces with special characters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_consonant_with_random_consonant", + "replace_spaces_with_random_special_characters" + ], + "rule_descriptions": { + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants", + "replace_spaces_with_random_special_characters": "Replace spaces with special characters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "christian mcconnell", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer porter", + "label": "negative", + "script": "latin" + }, + { + "name": "julia warner", + "label": "negative", + "script": "latin" + }, + { + "name": "patrick lopez", + "label": "negative", + "script": "latin" + }, + { + "name": "mary goodwin", + "label": "negative", + "script": "latin" + }, + { + "name": "william hicks", + "label": "negative", + "script": "latin" + }, + { + "name": "wendy dodd", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew griffin", + "label": "negative", + "script": "latin" + }, + { + "name": "michael davis", + "label": "negative", + "script": "latin" + }, + { + "name": "lance estrada", + "label": "negative", + "script": "latin" + }, + { + "name": "john marquez", + "label": "negative", + "script": "latin" + }, + { + "name": "joyce lane", + "label": "negative", + "script": "latin" + }, + { + "name": "jane moore", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua brown", + "label": "negative", + "script": "latin" + }, + { + "name": "briana mayo", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Delete a random letter, and Swap adjacent consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "delete_random_letter", + "swap_adjacent_consonants" + ], + "rule_descriptions": { + "delete_random_letter": "Delete a random letter", + "swap_adjacent_consonants": "Swap adjacent consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "richard robinson", + "label": "negative", + "script": "latin" + }, + { + "name": "brianna conway", + "label": "negative", + "script": "latin" + }, + { + "name": "joe hill", + "label": "negative", + "script": "latin" + }, + { + "name": "charles thompson", + "label": "negative", + "script": "latin" + }, + { + "name": "noah sherman", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher cunningham", + "label": "negative", + "script": "latin" + }, + { + "name": "luis fisher", + "label": "negative", + "script": "latin" + }, + { + "name": "kyle king", + "label": "negative", + "script": "latin" + }, + { + "name": "tracey henderson", + "label": "negative", + "script": "latin" + }, + { + "name": "robert jordan", + "label": "negative", + "script": "latin" + }, + { + "name": "anne edwards", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie williams", + "label": "negative", + "script": "latin" + }, + { + "name": "kelsey johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "elizabeth williams", + "label": "negative", + "script": "latin" + }, + { + "name": "heather phillips", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Remove all spaces.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_all_spaces" + ], + "rule_descriptions": { + "remove_all_spaces": "Remove all spaces" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "lauren becker", + "label": "negative", + "script": "latin" + }, + { + "name": "monica hale", + "label": "negative", + "script": "latin" + }, + { + "name": "david lopez", + "label": "negative", + "script": "latin" + }, + { + "name": "david morrison", + "label": "negative", + "script": "latin" + }, + { + "name": "shelia james", + "label": "negative", + "script": "latin" + }, + { + "name": "steven smith", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie ray", + "label": "negative", + "script": "latin" + }, + { + "name": "rick clarke", + "label": "negative", + "script": "latin" + }, + { + "name": "carolyn wright", + "label": "negative", + "script": "latin" + }, + { + "name": "reginald harris", + "label": "negative", + "script": "latin" + }, + { + "name": "john rojas", + "label": "negative", + "script": "latin" + }, + { + "name": "donna rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "olivia rivera", + "label": "negative", + "script": "latin" + }, + { + "name": "carl nicholls", + "label": "negative", + "script": "latin" + }, + { + "name": "martha grant", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Delete a random letter, Replace spaces with special characters, and Add a title prefix (Mr., Dr., etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "delete_random_letter", + "replace_spaces_with_random_special_characters", + "add_random_leading_title" + ], + "rule_descriptions": { + "delete_random_letter": "Delete a random letter", + "replace_spaces_with_random_special_characters": "Replace spaces with special characters", + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "marcus hicks", + "label": "negative", + "script": "latin" + }, + { + "name": "bernard pierce", + "label": "negative", + "script": "latin" + }, + { + "name": "eleanor matthews", + "label": "negative", + "script": "latin" + }, + { + "name": "larry sanchez", + "label": "negative", + "script": "latin" + }, + { + "name": "wendy cain", + "label": "negative", + "script": "latin" + }, + { + "name": "raymond martin", + "label": "negative", + "script": "latin" + }, + { + "name": "paul carter", + "label": "negative", + "script": "latin" + }, + { + "name": "frank ford", + "label": "negative", + "script": "latin" + }, + { + "name": "keith young", + "label": "negative", + "script": "latin" + }, + { + "name": "kara baker", + "label": "negative", + "script": "latin" + }, + { + "name": "kirsty avery", + "label": "negative", + "script": "latin" + }, + { + "name": "eileen warner", + "label": "negative", + "script": "latin" + }, + { + "name": "christian matthews", + "label": "negative", + "script": "latin" + }, + { + "name": "william carter", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley bailey", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Abbreviate name parts, Replace random consonants with different consonants, and Swap adjacent syllables.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_abbreviations", + "replace_random_consonant_with_random_consonant", + "swap_adjacent_syllables" + ], + "rule_descriptions": { + "shorten_name_to_abbreviations": "Abbreviate name parts", + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants", + "swap_adjacent_syllables": "Swap adjacent syllables" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "thomas patrick", + "label": "negative", + "script": "latin" + }, + { + "name": "david richards", + "label": "negative", + "script": "latin" + }, + { + "name": "lauren patterson", + "label": "negative", + "script": "latin" + }, + { + "name": "mary vega", + "label": "negative", + "script": "latin" + }, + { + "name": "laura davies", + "label": "negative", + "script": "latin" + }, + { + "name": "nathan vargas", + "label": "negative", + "script": "latin" + }, + { + "name": "benjamin wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "robert webster", + "label": "negative", + "script": "latin" + }, + { + "name": "chris carney", + "label": "negative", + "script": "latin" + }, + { + "name": "jordan molina", + "label": "negative", + "script": "latin" + }, + { + "name": "kenneth jordan", + "label": "negative", + "script": "latin" + }, + { + "name": "raymond williams", + "label": "negative", + "script": "latin" + }, + { + "name": "jonathan powell", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie mills", + "label": "negative", + "script": "latin" + }, + { + "name": "todd kidd", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace random consonants with different consonants, and Add a title suffix (Jr., PhD, etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_consonant_with_random_consonant", + "add_random_trailing_title" + ], + "rule_descriptions": { + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants", + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "joann clark", + "label": "negative", + "script": "latin" + }, + { + "name": "laura keller", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa lam", + "label": "negative", + "script": "latin" + }, + { + "name": "wayne elliott", + "label": "negative", + "script": "latin" + }, + { + "name": "megan david", + "label": "negative", + "script": "latin" + }, + { + "name": "natasha newman", + "label": "negative", + "script": "latin" + }, + { + "name": "geraldine alvarez", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas fletcher", + "label": "negative", + "script": "latin" + }, + { + "name": "frederick pollard", + "label": "negative", + "script": "latin" + }, + { + "name": "rachel sullivan", + "label": "negative", + "script": "latin" + }, + { + "name": "elliot singleton", + "label": "negative", + "script": "latin" + }, + { + "name": "tricia stevens", + "label": "negative", + "script": "latin" + }, + { + "name": "dawn savage", + "label": "negative", + "script": "latin" + }, + { + "name": "danny armstrong", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew wood", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Reorder name parts, Convert name to initials, and Add a title suffix (Jr., PhD, etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "name_parts_permutations", + "shorten_name_to_initials", + "add_random_trailing_title" + ], + "rule_descriptions": { + "name_parts_permutations": "Reorder name parts", + "shorten_name_to_initials": "Convert name to initials", + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "sarah hicks", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer harris", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel sims", + "label": "negative", + "script": "latin" + }, + { + "name": "graham fitzgerald", + "label": "negative", + "script": "latin" + }, + { + "name": "michele rose", + "label": "negative", + "script": "latin" + }, + { + "name": "teresa martin", + "label": "negative", + "script": "latin" + }, + { + "name": "chloe campbell", + "label": "negative", + "script": "latin" + }, + { + "name": "john boyer", + "label": "negative", + "script": "latin" + }, + { + "name": "megan hall", + "label": "negative", + "script": "latin" + }, + { + "name": "richard gibbons", + "label": "negative", + "script": "latin" + }, + { + "name": "scott powell", + "label": "negative", + "script": "latin" + }, + { + "name": "justin mendez", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle pearson", + "label": "negative", + "script": "latin" + }, + { + "name": "liam peterson", + "label": "negative", + "script": "latin" + }, + { + "name": "glen cooper", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Delete a random letter, and Swap random adjacent letters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "delete_random_letter", + "swap_random_letter" + ], + "rule_descriptions": { + "delete_random_letter": "Delete a random letter", + "swap_random_letter": "Swap random adjacent letters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "sophia naylor", + "label": "negative", + "script": "latin" + }, + { + "name": "lydia sutton", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas jimenez", + "label": "negative", + "script": "latin" + }, + { + "name": "julie patel", + "label": "negative", + "script": "latin" + }, + { + "name": "rachael jackson", + "label": "negative", + "script": "latin" + }, + { + "name": "christina berry", + "label": "negative", + "script": "latin" + }, + { + "name": "zachary miller", + "label": "negative", + "script": "latin" + }, + { + "name": "dennis lawson", + "label": "negative", + "script": "latin" + }, + { + "name": "donna rhodes", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer baker", + "label": "negative", + "script": "latin" + }, + { + "name": "dale johns", + "label": "negative", + "script": "latin" + }, + { + "name": "brenda lang", + "label": "negative", + "script": "latin" + }, + { + "name": "willie hansen", + "label": "negative", + "script": "latin" + }, + { + "name": "blake reeves", + "label": "negative", + "script": "latin" + }, + { + "name": "wayne james", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Replace spaces with special characters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_spaces_with_random_special_characters" + ], + "rule_descriptions": { + "replace_spaces_with_random_special_characters": "Replace spaces with special characters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "michelle haynes", + "label": "negative", + "script": "latin" + }, + { + "name": "caroline dominguez", + "label": "negative", + "script": "latin" + }, + { + "name": "charles watson", + "label": "negative", + "script": "latin" + }, + { + "name": "hunter anthony", + "label": "negative", + "script": "latin" + }, + { + "name": "arthur luna", + "label": "negative", + "script": "latin" + }, + { + "name": "marc clark", + "label": "negative", + "script": "latin" + }, + { + "name": "charles underwood", + "label": "negative", + "script": "latin" + }, + { + "name": "jonathan mckee", + "label": "negative", + "script": "latin" + }, + { + "name": "david perez", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie long", + "label": "negative", + "script": "latin" + }, + { + "name": "amber carlson", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley cook", + "label": "negative", + "script": "latin" + }, + { + "name": "mark smith", + "label": "negative", + "script": "latin" + }, + { + "name": "robert hall", + "label": "negative", + "script": "latin" + }, + { + "name": "barry erickson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap adjacent syllables, Replace double letters with a single letter, and Replace random consonants with different consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_syllables", + "replace_double_letters_with_single_letter", + "replace_random_consonant_with_random_consonant" + ], + "rule_descriptions": { + "swap_adjacent_syllables": "Swap adjacent syllables", + "replace_double_letters_with_single_letter": "Replace double letters with a single letter", + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "jessica paul", + "label": "negative", + "script": "latin" + }, + { + "name": "brent fletcher", + "label": "negative", + "script": "latin" + }, + { + "name": "michael smith", + "label": "negative", + "script": "latin" + }, + { + "name": "jonathan olson", + "label": "negative", + "script": "latin" + }, + { + "name": "jacqueline lee", + "label": "negative", + "script": "latin" + }, + { + "name": "edward guzman", + "label": "negative", + "script": "latin" + }, + { + "name": "susan hart", + "label": "negative", + "script": "latin" + }, + { + "name": "malcolm callahan", + "label": "negative", + "script": "latin" + }, + { + "name": "robert perry", + "label": "negative", + "script": "latin" + }, + { + "name": "kim humphrey", + "label": "negative", + "script": "latin" + }, + { + "name": "david lowe", + "label": "negative", + "script": "latin" + }, + { + "name": "brandy gonzalez", + "label": "negative", + "script": "latin" + }, + { + "name": "ian harris", + "label": "negative", + "script": "latin" + }, + { + "name": "eddie washington", + "label": "negative", + "script": "latin" + }, + { + "name": "chad banks", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Convert name to initials.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_initials" + ], + "rule_descriptions": { + "shorten_name_to_initials": "Convert name to initials" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "christopher hurst", + "label": "negative", + "script": "latin" + }, + { + "name": "liam kaufman", + "label": "negative", + "script": "latin" + }, + { + "name": "samuel long", + "label": "negative", + "script": "latin" + }, + { + "name": "chase jones", + "label": "negative", + "script": "latin" + }, + { + "name": "harriet thompson", + "label": "negative", + "script": "latin" + }, + { + "name": "christian booth", + "label": "negative", + "script": "latin" + }, + { + "name": "simon richardson", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah richardson", + "label": "negative", + "script": "latin" + }, + { + "name": "cheryl bond", + "label": "negative", + "script": "latin" + }, + { + "name": "justin hancock", + "label": "negative", + "script": "latin" + }, + { + "name": "shane chung", + "label": "negative", + "script": "latin" + }, + { + "name": "zachary garcia", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin anderson", + "label": "negative", + "script": "latin" + }, + { + "name": "richard ramirez", + "label": "negative", + "script": "latin" + }, + { + "name": "devin white", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace double letters with a single letter, and Swap adjacent syllables.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_double_letters_with_single_letter", + "swap_adjacent_syllables" + ], + "rule_descriptions": { + "replace_double_letters_with_single_letter": "Replace double letters with a single letter", + "swap_adjacent_syllables": "Swap adjacent syllables" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "alexandra gill", + "label": "negative", + "script": "latin" + }, + { + "name": "abigail mckee", + "label": "negative", + "script": "latin" + }, + { + "name": "jason perry", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole peterson", + "label": "negative", + "script": "latin" + }, + { + "name": "karen hernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "max brown", + "label": "negative", + "script": "latin" + }, + { + "name": "victor cannon", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa dale", + "label": "negative", + "script": "latin" + }, + { + "name": "karen perry", + "label": "negative", + "script": "latin" + }, + { + "name": "richard flynn", + "label": "negative", + "script": "latin" + }, + { + "name": "todd hernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "sian brown", + "label": "negative", + "script": "latin" + }, + { + "name": "dennis montgomery", + "label": "negative", + "script": "latin" + }, + { + "name": "tristan williams", + "label": "negative", + "script": "latin" + }, + { + "name": "patty browning", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Duplicate a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "duplicate_random_letter_as_double_letter" + ], + "rule_descriptions": { + "duplicate_random_letter_as_double_letter": "Duplicate a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "tracy montgomery", + "label": "negative", + "script": "latin" + }, + { + "name": "kenneth hoover", + "label": "negative", + "script": "latin" + }, + { + "name": "shane harris", + "label": "negative", + "script": "latin" + }, + { + "name": "judy powell", + "label": "negative", + "script": "latin" + }, + { + "name": "andrew wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "john beasley", + "label": "negative", + "script": "latin" + }, + { + "name": "malcolm williams", + "label": "negative", + "script": "latin" + }, + { + "name": "james bryant", + "label": "negative", + "script": "latin" + }, + { + "name": "david brown", + "label": "negative", + "script": "latin" + }, + { + "name": "jose howell", + "label": "negative", + "script": "latin" + }, + { + "name": "martin scott", + "label": "negative", + "script": "latin" + }, + { + "name": "philip castillo", + "label": "negative", + "script": "latin" + }, + { + "name": "mathew smith", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa hoffman", + "label": "negative", + "script": "latin" + }, + { + "name": "leah roberts", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap adjacent consonants, and Reorder name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_consonants", + "name_parts_permutations" + ], + "rule_descriptions": { + "swap_adjacent_consonants": "Swap adjacent consonants", + "name_parts_permutations": "Reorder name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "michael meyer", + "label": "negative", + "script": "latin" + }, + { + "name": "trevor holland", + "label": "negative", + "script": "latin" + }, + { + "name": "tracy taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "cassandra newman", + "label": "negative", + "script": "latin" + }, + { + "name": "kristine tucker", + "label": "negative", + "script": "latin" + }, + { + "name": "andrew wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffery harris", + "label": "negative", + "script": "latin" + }, + { + "name": "kristina marsh", + "label": "negative", + "script": "latin" + }, + { + "name": "martyn davis", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa martin", + "label": "negative", + "script": "latin" + }, + { + "name": "john ryan", + "label": "negative", + "script": "latin" + }, + { + "name": "ruth nguyen", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle bishop", + "label": "negative", + "script": "latin" + }, + { + "name": "william powell", + "label": "negative", + "script": "latin" + }, + { + "name": "gregory stevens", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title suffix (Jr., PhD, etc.), and Swap random adjacent letters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_trailing_title", + "swap_random_letter" + ], + "rule_descriptions": { + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)", + "swap_random_letter": "Swap random adjacent letters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "shannon sutton", + "label": "negative", + "script": "latin" + }, + { + "name": "brian richardson", + "label": "negative", + "script": "latin" + }, + { + "name": "james fleming", + "label": "negative", + "script": "latin" + }, + { + "name": "william kim", + "label": "negative", + "script": "latin" + }, + { + "name": "monica mcmahon", + "label": "negative", + "script": "latin" + }, + { + "name": "charlie pearce", + "label": "negative", + "script": "latin" + }, + { + "name": "michael ramirez", + "label": "negative", + "script": "latin" + }, + { + "name": "darrell buckley", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah roberts", + "label": "negative", + "script": "latin" + }, + { + "name": "nancy pena", + "label": "negative", + "script": "latin" + }, + { + "name": "rebecca davis", + "label": "negative", + "script": "latin" + }, + { + "name": "michael smith", + "label": "negative", + "script": "latin" + }, + { + "name": "angel allen", + "label": "negative", + "script": "latin" + }, + { + "name": "darrell rhodes", + "label": "negative", + "script": "latin" + }, + { + "name": "jamie mejia", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Insert a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "insert_random_letter" + ], + "rule_descriptions": { + "insert_random_letter": "Insert a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "richard barlow", + "label": "negative", + "script": "latin" + }, + { + "name": "jeremy rivers", + "label": "negative", + "script": "latin" + }, + { + "name": "tom sharp", + "label": "negative", + "script": "latin" + }, + { + "name": "martin price", + "label": "negative", + "script": "latin" + }, + { + "name": "wendy oliver", + "label": "negative", + "script": "latin" + }, + { + "name": "lori bush", + "label": "negative", + "script": "latin" + }, + { + "name": "marvin peters", + "label": "negative", + "script": "latin" + }, + { + "name": "iain morris", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew williams", + "label": "negative", + "script": "latin" + }, + { + "name": "katherine kirk", + "label": "negative", + "script": "latin" + }, + { + "name": "ben mills", + "label": "negative", + "script": "latin" + }, + { + "name": "laura jimenez", + "label": "negative", + "script": "latin" + }, + { + "name": "danielle taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "nathaniel wallace", + "label": "negative", + "script": "latin" + }, + { + "name": "jeanette gordon", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove a random vowel, Duplicate a random letter, and Replace spaces with special characters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_vowel", + "duplicate_random_letter_as_double_letter", + "replace_spaces_with_random_special_characters" + ], + "rule_descriptions": { + "remove_random_vowel": "Remove a random vowel", + "duplicate_random_letter_as_double_letter": "Duplicate a random letter", + "replace_spaces_with_random_special_characters": "Replace spaces with special characters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "gregory flores", + "label": "negative", + "script": "latin" + }, + { + "name": "janet jones", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel burns", + "label": "negative", + "script": "latin" + }, + { + "name": "jimmy perry", + "label": "negative", + "script": "latin" + }, + { + "name": "frank king", + "label": "negative", + "script": "latin" + }, + { + "name": "gary spencer", + "label": "negative", + "script": "latin" + }, + { + "name": "mary clarke", + "label": "negative", + "script": "latin" + }, + { + "name": "elizabeth brown", + "label": "negative", + "script": "latin" + }, + { + "name": "gerald barnes", + "label": "negative", + "script": "latin" + }, + { + "name": "caroline salazar", + "label": "negative", + "script": "latin" + }, + { + "name": "amber smith", + "label": "negative", + "script": "latin" + }, + { + "name": "jon mercado", + "label": "negative", + "script": "latin" + }, + { + "name": "edwin bailey", + "label": "negative", + "script": "latin" + }, + { + "name": "marcus pena", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher mclaughlin", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Use first name initial with last name, and Swap random adjacent letters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "initial_only_first_name", + "swap_random_letter" + ], + "rule_descriptions": { + "initial_only_first_name": "Use first name initial with last name", + "swap_random_letter": "Swap random adjacent letters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "joseph watson", + "label": "negative", + "script": "latin" + }, + { + "name": "charles goodwin", + "label": "negative", + "script": "latin" + }, + { + "name": "william harrison", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher callahan", + "label": "negative", + "script": "latin" + }, + { + "name": "jonathan schofield", + "label": "negative", + "script": "latin" + }, + { + "name": "teresa burgess", + "label": "negative", + "script": "latin" + }, + { + "name": "russell wong", + "label": "negative", + "script": "latin" + }, + { + "name": "clifford rosario", + "label": "negative", + "script": "latin" + }, + { + "name": "paul gardner", + "label": "negative", + "script": "latin" + }, + { + "name": "mary stephens", + "label": "negative", + "script": "latin" + }, + { + "name": "rachel ruiz", + "label": "negative", + "script": "latin" + }, + { + "name": "edwin johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "ashleigh stanton", + "label": "negative", + "script": "latin" + }, + { + "name": "steve thompson", + "label": "negative", + "script": "latin" + }, + { + "name": "hilary ryan", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap adjacent consonants, and Delete a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_consonants", + "delete_random_letter" + ], + "rule_descriptions": { + "swap_adjacent_consonants": "Swap adjacent consonants", + "delete_random_letter": "Delete a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "derek bryant", + "label": "negative", + "script": "latin" + }, + { + "name": "jasmine huffman", + "label": "negative", + "script": "latin" + }, + { + "name": "cameron miller", + "label": "negative", + "script": "latin" + }, + { + "name": "lorraine wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "alexander davies", + "label": "negative", + "script": "latin" + }, + { + "name": "charlotte walton", + "label": "negative", + "script": "latin" + }, + { + "name": "ruben wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "diana sims", + "label": "negative", + "script": "latin" + }, + { + "name": "mohammad scott", + "label": "negative", + "script": "latin" + }, + { + "name": "isabella taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "andrea powers", + "label": "negative", + "script": "latin" + }, + { + "name": "amber trujillo", + "label": "negative", + "script": "latin" + }, + { + "name": "derrick morgan", + "label": "negative", + "script": "latin" + }, + { + "name": "dakota wilkerson", + "label": "negative", + "script": "latin" + }, + { + "name": "pauline wilson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap adjacent syllables, and Abbreviate name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_syllables", + "shorten_name_to_abbreviations" + ], + "rule_descriptions": { + "swap_adjacent_syllables": "Swap adjacent syllables", + "shorten_name_to_abbreviations": "Abbreviate name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "kevin potts", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew lara", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie gonzalez", + "label": "negative", + "script": "latin" + }, + { + "name": "hayley jones", + "label": "negative", + "script": "latin" + }, + { + "name": "patricia farley", + "label": "negative", + "script": "latin" + }, + { + "name": "david roberts", + "label": "negative", + "script": "latin" + }, + { + "name": "eduardo rahman", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica tran", + "label": "negative", + "script": "latin" + }, + { + "name": "cory henderson", + "label": "negative", + "script": "latin" + }, + { + "name": "barbara fletcher", + "label": "negative", + "script": "latin" + }, + { + "name": "craig miller", + "label": "negative", + "script": "latin" + }, + { + "name": "andrea wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "deborah lee", + "label": "negative", + "script": "latin" + }, + { + "name": "cynthia oneill", + "label": "negative", + "script": "latin" + }, + { + "name": "david jackson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Abbreviate name parts, and Remove all spaces.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_abbreviations", + "remove_all_spaces" + ], + "rule_descriptions": { + "shorten_name_to_abbreviations": "Abbreviate name parts", + "remove_all_spaces": "Remove all spaces" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "diana roach", + "label": "negative", + "script": "latin" + }, + { + "name": "jason holland", + "label": "negative", + "script": "latin" + }, + { + "name": "gregory oliver", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin bull", + "label": "negative", + "script": "latin" + }, + { + "name": "clive rollins", + "label": "negative", + "script": "latin" + }, + { + "name": "bethany williams", + "label": "negative", + "script": "latin" + }, + { + "name": "kayla branch", + "label": "negative", + "script": "latin" + }, + { + "name": "andrea farley", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie horne", + "label": "negative", + "script": "latin" + }, + { + "name": "russell wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "teresa harrison", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica jones", + "label": "negative", + "script": "latin" + }, + { + "name": "gavin smith", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony carter", + "label": "negative", + "script": "latin" + }, + { + "name": "ian ryan", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove a random consonant, and Reorder name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_consonant", + "name_parts_permutations" + ], + "rule_descriptions": { + "remove_random_consonant": "Remove a random consonant", + "name_parts_permutations": "Reorder name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "cassandra dixon", + "label": "negative", + "script": "latin" + }, + { + "name": "clifford salazar", + "label": "negative", + "script": "latin" + }, + { + "name": "zoe lamb", + "label": "negative", + "script": "latin" + }, + { + "name": "jeremy morton", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "russell flores", + "label": "negative", + "script": "latin" + }, + { + "name": "gemma dawson", + "label": "negative", + "script": "latin" + }, + { + "name": "james jones", + "label": "negative", + "script": "latin" + }, + { + "name": "victoria esparza", + "label": "negative", + "script": "latin" + }, + { + "name": "william burnett", + "label": "negative", + "script": "latin" + }, + { + "name": "brittany smith", + "label": "negative", + "script": "latin" + }, + { + "name": "michele kim", + "label": "negative", + "script": "latin" + }, + { + "name": "julie brown", + "label": "negative", + "script": "latin" + }, + { + "name": "chad reed", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher brown", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap adjacent syllables, and Replace double letters with a single letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_syllables", + "replace_double_letters_with_single_letter" + ], + "rule_descriptions": { + "swap_adjacent_syllables": "Swap adjacent syllables", + "replace_double_letters_with_single_letter": "Replace double letters with a single letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "christian perry", + "label": "negative", + "script": "latin" + }, + { + "name": "rachel alexander", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph gonzalez", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa nicholson", + "label": "negative", + "script": "latin" + }, + { + "name": "denise pierce", + "label": "negative", + "script": "latin" + }, + { + "name": "michael silva", + "label": "negative", + "script": "latin" + }, + { + "name": "kelsey collier", + "label": "negative", + "script": "latin" + }, + { + "name": "ryan morton", + "label": "negative", + "script": "latin" + }, + { + "name": "lawrence tucker", + "label": "negative", + "script": "latin" + }, + { + "name": "emily thomas", + "label": "negative", + "script": "latin" + }, + { + "name": "megan perry", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy russell", + "label": "negative", + "script": "latin" + }, + { + "name": "aimee lucas", + "label": "negative", + "script": "latin" + }, + { + "name": "elizabeth jackson", + "label": "negative", + "script": "latin" + }, + { + "name": "zachary carpenter", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Convert name to initials, and Insert a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_initials", + "insert_random_letter" + ], + "rule_descriptions": { + "shorten_name_to_initials": "Convert name to initials", + "insert_random_letter": "Insert a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "cody shaw", + "label": "negative", + "script": "latin" + }, + { + "name": "roy davis", + "label": "negative", + "script": "latin" + }, + { + "name": "kyle thomas", + "label": "negative", + "script": "latin" + }, + { + "name": "lindsey brown", + "label": "negative", + "script": "latin" + }, + { + "name": "keith olson", + "label": "negative", + "script": "latin" + }, + { + "name": "janet charles", + "label": "negative", + "script": "latin" + }, + { + "name": "eric hunter", + "label": "negative", + "script": "latin" + }, + { + "name": "maria howard", + "label": "negative", + "script": "latin" + }, + { + "name": "frank cooper", + "label": "negative", + "script": "latin" + }, + { + "name": "mary pierce", + "label": "negative", + "script": "latin" + }, + { + "name": "andrea brown", + "label": "negative", + "script": "latin" + }, + { + "name": "richard walters", + "label": "negative", + "script": "latin" + }, + { + "name": "mohamed burton", + "label": "negative", + "script": "latin" + }, + { + "name": "julia hernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "angela price", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap adjacent consonants, and Abbreviate name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_consonants", + "shorten_name_to_abbreviations" + ], + "rule_descriptions": { + "swap_adjacent_consonants": "Swap adjacent consonants", + "shorten_name_to_abbreviations": "Abbreviate name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "sierra reed", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas mason", + "label": "negative", + "script": "latin" + }, + { + "name": "luis bryant", + "label": "negative", + "script": "latin" + }, + { + "name": "henry davis", + "label": "negative", + "script": "latin" + }, + { + "name": "bryan knight", + "label": "negative", + "script": "latin" + }, + { + "name": "gavin huffman", + "label": "negative", + "script": "latin" + }, + { + "name": "brooke sanchez", + "label": "negative", + "script": "latin" + }, + { + "name": "ronald nichols", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley evans", + "label": "negative", + "script": "latin" + }, + { + "name": "darius key", + "label": "negative", + "script": "latin" + }, + { + "name": "fernando klein", + "label": "negative", + "script": "latin" + }, + { + "name": "heather vaughn", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle hodges", + "label": "negative", + "script": "latin" + }, + { + "name": "edward hansen", + "label": "negative", + "script": "latin" + }, + { + "name": "elizabeth barron", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace double letters with a single letter, and Remove all spaces.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_double_letters_with_single_letter", + "remove_all_spaces" + ], + "rule_descriptions": { + "replace_double_letters_with_single_letter": "Replace double letters with a single letter", + "remove_all_spaces": "Remove all spaces" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "austin jones", + "label": "negative", + "script": "latin" + }, + { + "name": "debra johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "louis johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "katherine tucker", + "label": "negative", + "script": "latin" + }, + { + "name": "angela mann", + "label": "negative", + "script": "latin" + }, + { + "name": "luis frederick", + "label": "negative", + "script": "latin" + }, + { + "name": "karen harris", + "label": "negative", + "script": "latin" + }, + { + "name": "amelia espinoza", + "label": "negative", + "script": "latin" + }, + { + "name": "michael parker", + "label": "negative", + "script": "latin" + }, + { + "name": "ruth donaldson", + "label": "negative", + "script": "latin" + }, + { + "name": "heather gomez", + "label": "negative", + "script": "latin" + }, + { + "name": "leah shaw", + "label": "negative", + "script": "latin" + }, + { + "name": "gina harrison", + "label": "negative", + "script": "latin" + }, + { + "name": "lindsey yang", + "label": "negative", + "script": "latin" + }, + { + "name": "michael turner", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Use first name initial with last name, and Swap random adjacent letters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "initial_only_first_name", + "swap_random_letter" + ], + "rule_descriptions": { + "initial_only_first_name": "Use first name initial with last name", + "swap_random_letter": "Swap random adjacent letters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "michelle warren", + "label": "negative", + "script": "latin" + }, + { + "name": "douglas fox", + "label": "negative", + "script": "latin" + }, + { + "name": "wanda smith", + "label": "negative", + "script": "latin" + }, + { + "name": "brent dennis", + "label": "negative", + "script": "latin" + }, + { + "name": "stephen barnett", + "label": "negative", + "script": "latin" + }, + { + "name": "holly davies", + "label": "negative", + "script": "latin" + }, + { + "name": "brett walton", + "label": "negative", + "script": "latin" + }, + { + "name": "kayla cooper", + "label": "negative", + "script": "latin" + }, + { + "name": "eileen henderson", + "label": "negative", + "script": "latin" + }, + { + "name": "janet elliott", + "label": "negative", + "script": "latin" + }, + { + "name": "amy moore", + "label": "negative", + "script": "latin" + }, + { + "name": "glenn davis", + "label": "negative", + "script": "latin" + }, + { + "name": "patricia martinez", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua burke", + "label": "negative", + "script": "latin" + }, + { + "name": "gregory peterson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Duplicate a random letter, and Convert name to initials.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "duplicate_random_letter_as_double_letter", + "shorten_name_to_initials" + ], + "rule_descriptions": { + "duplicate_random_letter_as_double_letter": "Duplicate a random letter", + "shorten_name_to_initials": "Convert name to initials" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "melissa moses", + "label": "negative", + "script": "latin" + }, + { + "name": "malcolm campos", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer reynolds", + "label": "negative", + "script": "latin" + }, + { + "name": "henry spencer", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa ochoa", + "label": "negative", + "script": "latin" + }, + { + "name": "william mccormick", + "label": "negative", + "script": "latin" + }, + { + "name": "douglas maldonado", + "label": "negative", + "script": "latin" + }, + { + "name": "kelli sharp", + "label": "negative", + "script": "latin" + }, + { + "name": "melvin boyd", + "label": "negative", + "script": "latin" + }, + { + "name": "charles walker", + "label": "negative", + "script": "latin" + }, + { + "name": "clive jones", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher ward", + "label": "negative", + "script": "latin" + }, + { + "name": "andrew brown", + "label": "negative", + "script": "latin" + }, + { + "name": "connor henry", + "label": "negative", + "script": "latin" + }, + { + "name": "stacey quinn", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title prefix (Mr., Dr., etc.), and Duplicate a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_leading_title", + "duplicate_random_letter_as_double_letter" + ], + "rule_descriptions": { + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)", + "duplicate_random_letter_as_double_letter": "Duplicate a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "maureen arnold", + "label": "negative", + "script": "latin" + }, + { + "name": "brittney brown", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua smith", + "label": "negative", + "script": "latin" + }, + { + "name": "keith martin", + "label": "negative", + "script": "latin" + }, + { + "name": "angela schroeder", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda owen", + "label": "negative", + "script": "latin" + }, + { + "name": "hayley phillips", + "label": "negative", + "script": "latin" + }, + { + "name": "scott rosario", + "label": "negative", + "script": "latin" + }, + { + "name": "virginia lawrence", + "label": "negative", + "script": "latin" + }, + { + "name": "peter hawkins", + "label": "negative", + "script": "latin" + }, + { + "name": "laura green", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin griffiths", + "label": "negative", + "script": "latin" + }, + { + "name": "kelly morris", + "label": "negative", + "script": "latin" + }, + { + "name": "andre begum", + "label": "negative", + "script": "latin" + }, + { + "name": "stephen hanson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Use first name initial with last name.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "initial_only_first_name" + ], + "rule_descriptions": { + "initial_only_first_name": "Use first name initial with last name" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "juan lang", + "label": "negative", + "script": "latin" + }, + { + "name": "christian wood", + "label": "negative", + "script": "latin" + }, + { + "name": "james navarro", + "label": "negative", + "script": "latin" + }, + { + "name": "benjamin gonzalez", + "label": "negative", + "script": "latin" + }, + { + "name": "robin luna", + "label": "negative", + "script": "latin" + }, + { + "name": "justin evans", + "label": "negative", + "script": "latin" + }, + { + "name": "kim bailey", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher owens", + "label": "negative", + "script": "latin" + }, + { + "name": "mary jennings", + "label": "negative", + "script": "latin" + }, + { + "name": "ruben benjamin", + "label": "negative", + "script": "latin" + }, + { + "name": "bradley dalton", + "label": "negative", + "script": "latin" + }, + { + "name": "darren wells", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua wade", + "label": "negative", + "script": "latin" + }, + { + "name": "preston jensen", + "label": "negative", + "script": "latin" + }, + { + "name": "alexander hamilton", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Remove a random consonant.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_consonant" + ], + "rule_descriptions": { + "remove_random_consonant": "Remove a random consonant" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "gavin meyer", + "label": "negative", + "script": "latin" + }, + { + "name": "alexander rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy williams", + "label": "negative", + "script": "latin" + }, + { + "name": "laura dean", + "label": "negative", + "script": "latin" + }, + { + "name": "andrea stewart", + "label": "negative", + "script": "latin" + }, + { + "name": "kristen potter", + "label": "negative", + "script": "latin" + }, + { + "name": "kate ochoa", + "label": "negative", + "script": "latin" + }, + { + "name": "june nelson", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "jonathan carr", + "label": "negative", + "script": "latin" + }, + { + "name": "lorraine brown", + "label": "negative", + "script": "latin" + }, + { + "name": "rhonda davies", + "label": "negative", + "script": "latin" + }, + { + "name": "deborah brown", + "label": "negative", + "script": "latin" + }, + { + "name": "damian hudson", + "label": "negative", + "script": "latin" + }, + { + "name": "kerry morales", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Remove a random vowel.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_vowel" + ], + "rule_descriptions": { + "remove_random_vowel": "Remove a random vowel" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "frank heath", + "label": "negative", + "script": "latin" + }, + { + "name": "lee holland", + "label": "negative", + "script": "latin" + }, + { + "name": "diana patterson", + "label": "negative", + "script": "latin" + }, + { + "name": "tammy mcdonald", + "label": "negative", + "script": "latin" + }, + { + "name": "nathan rogers", + "label": "negative", + "script": "latin" + }, + { + "name": "shannon owen", + "label": "negative", + "script": "latin" + }, + { + "name": "sandra donovan", + "label": "negative", + "script": "latin" + }, + { + "name": "jason marquez", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica bell", + "label": "negative", + "script": "latin" + }, + { + "name": "aaron martinez", + "label": "negative", + "script": "latin" + }, + { + "name": "travis duncan", + "label": "negative", + "script": "latin" + }, + { + "name": "carla horton", + "label": "negative", + "script": "latin" + }, + { + "name": "janice taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "robert thompson", + "label": "negative", + "script": "latin" + }, + { + "name": "garry rogers", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Remove all spaces.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_all_spaces" + ], + "rule_descriptions": { + "remove_all_spaces": "Remove all spaces" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "frances wood", + "label": "negative", + "script": "latin" + }, + { + "name": "ian hobbs", + "label": "negative", + "script": "latin" + }, + { + "name": "clive fox", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle lloyd", + "label": "negative", + "script": "latin" + }, + { + "name": "kenneth white", + "label": "negative", + "script": "latin" + }, + { + "name": "john norman", + "label": "negative", + "script": "latin" + }, + { + "name": "dorothy morgan", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda walsh", + "label": "negative", + "script": "latin" + }, + { + "name": "norman smith", + "label": "negative", + "script": "latin" + }, + { + "name": "dawn howell", + "label": "negative", + "script": "latin" + }, + { + "name": "raymond gilbert", + "label": "negative", + "script": "latin" + }, + { + "name": "joanne roberts", + "label": "negative", + "script": "latin" + }, + { + "name": "paul davis", + "label": "negative", + "script": "latin" + }, + { + "name": "fiona leblanc", + "label": "negative", + "script": "latin" + }, + { + "name": "keith kelley", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace double letters with a single letter, Add a title prefix (Mr., Dr., etc.), and Replace spaces with special characters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_double_letters_with_single_letter", + "add_random_leading_title", + "replace_spaces_with_random_special_characters" + ], + "rule_descriptions": { + "replace_double_letters_with_single_letter": "Replace double letters with a single letter", + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)", + "replace_spaces_with_random_special_characters": "Replace spaces with special characters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "laura hughes", + "label": "negative", + "script": "latin" + }, + { + "name": "valerie stout", + "label": "negative", + "script": "latin" + }, + { + "name": "sandra chamberlain", + "label": "negative", + "script": "latin" + }, + { + "name": "hannah hendrix", + "label": "negative", + "script": "latin" + }, + { + "name": "kathy sanchez", + "label": "negative", + "script": "latin" + }, + { + "name": "cesar pittman", + "label": "negative", + "script": "latin" + }, + { + "name": "clare coates", + "label": "negative", + "script": "latin" + }, + { + "name": "sandra hill", + "label": "negative", + "script": "latin" + }, + { + "name": "dawn fields", + "label": "negative", + "script": "latin" + }, + { + "name": "kenneth hooper", + "label": "negative", + "script": "latin" + }, + { + "name": "michael wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "tammy johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "robert todd", + "label": "negative", + "script": "latin" + }, + { + "name": "zoe anderson", + "label": "negative", + "script": "latin" + }, + { + "name": "janet perez", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace spaces with special characters, and Delete a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_spaces_with_random_special_characters", + "delete_random_letter" + ], + "rule_descriptions": { + "replace_spaces_with_random_special_characters": "Replace spaces with special characters", + "delete_random_letter": "Delete a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "lindsey hernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "kelly phillips", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah davis", + "label": "negative", + "script": "latin" + }, + { + "name": "connie cervantes", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin moore", + "label": "negative", + "script": "latin" + }, + { + "name": "jonathan moyer", + "label": "negative", + "script": "latin" + }, + { + "name": "dalton mccoy", + "label": "negative", + "script": "latin" + }, + { + "name": "richard thompson", + "label": "negative", + "script": "latin" + }, + { + "name": "james jones", + "label": "negative", + "script": "latin" + }, + { + "name": "maureen terry", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah gordon", + "label": "negative", + "script": "latin" + }, + { + "name": "ethan jacobs", + "label": "negative", + "script": "latin" + }, + { + "name": "stuart snyder", + "label": "negative", + "script": "latin" + }, + { + "name": "andrew kramer", + "label": "negative", + "script": "latin" + }, + { + "name": "sandra burke", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Insert a random letter, Add a title prefix (Mr., Dr., etc.), and Delete a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "insert_random_letter", + "add_random_leading_title", + "delete_random_letter" + ], + "rule_descriptions": { + "insert_random_letter": "Insert a random letter", + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)", + "delete_random_letter": "Delete a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "james brooks", + "label": "negative", + "script": "latin" + }, + { + "name": "damien taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "virginia bennett", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffrey bender", + "label": "negative", + "script": "latin" + }, + { + "name": "francis gill", + "label": "negative", + "script": "latin" + }, + { + "name": "robert hill", + "label": "negative", + "script": "latin" + }, + { + "name": "ryan brown", + "label": "negative", + "script": "latin" + }, + { + "name": "abdul flynn", + "label": "negative", + "script": "latin" + }, + { + "name": "philip castaneda", + "label": "negative", + "script": "latin" + }, + { + "name": "ian hayes", + "label": "negative", + "script": "latin" + }, + { + "name": "tracy mcdaniel", + "label": "negative", + "script": "latin" + }, + { + "name": "adam mccoy", + "label": "negative", + "script": "latin" + }, + { + "name": "kathryn richardson", + "label": "negative", + "script": "latin" + }, + { + "name": "jeremy reed", + "label": "negative", + "script": "latin" + }, + { + "name": "jeremiah stone", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Insert a random letter, Delete a random letter, and Abbreviate name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "insert_random_letter", + "delete_random_letter", + "shorten_name_to_abbreviations" + ], + "rule_descriptions": { + "insert_random_letter": "Insert a random letter", + "delete_random_letter": "Delete a random letter", + "shorten_name_to_abbreviations": "Abbreviate name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "alexander jackson", + "label": "negative", + "script": "latin" + }, + { + "name": "emily hilton", + "label": "negative", + "script": "latin" + }, + { + "name": "joyce kim", + "label": "negative", + "script": "latin" + }, + { + "name": "julie henson", + "label": "negative", + "script": "latin" + }, + { + "name": "james stevens", + "label": "negative", + "script": "latin" + }, + { + "name": "jemma kelley", + "label": "negative", + "script": "latin" + }, + { + "name": "mark brennan", + "label": "negative", + "script": "latin" + }, + { + "name": "jeanne torres", + "label": "negative", + "script": "latin" + }, + { + "name": "sylvia pierce", + "label": "negative", + "script": "latin" + }, + { + "name": "benjamin wood", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah gordon", + "label": "negative", + "script": "latin" + }, + { + "name": "rosemary roberts", + "label": "negative", + "script": "latin" + }, + { + "name": "billy martinez", + "label": "negative", + "script": "latin" + }, + { + "name": "shari jones", + "label": "negative", + "script": "latin" + }, + { + "name": "elliot archer", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Remove a random consonant.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_consonant" + ], + "rule_descriptions": { + "remove_random_consonant": "Remove a random consonant" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "joseph davies", + "label": "negative", + "script": "latin" + }, + { + "name": "shirley ramirez", + "label": "negative", + "script": "latin" + }, + { + "name": "misty smith", + "label": "negative", + "script": "latin" + }, + { + "name": "samantha wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "gary jones", + "label": "negative", + "script": "latin" + }, + { + "name": "rhys boyd", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel williams", + "label": "negative", + "script": "latin" + }, + { + "name": "david keller", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa mcknight", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel jenkins", + "label": "negative", + "script": "latin" + }, + { + "name": "eugene crawford", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher turner", + "label": "negative", + "script": "latin" + }, + { + "name": "shelley freeman", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole walker", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Reorder name parts, and Use first name initial with last name.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "name_parts_permutations", + "initial_only_first_name" + ], + "rule_descriptions": { + "name_parts_permutations": "Reorder name parts", + "initial_only_first_name": "Use first name initial with last name" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "donald taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "jamie wall", + "label": "negative", + "script": "latin" + }, + { + "name": "maria silva", + "label": "negative", + "script": "latin" + }, + { + "name": "paula garcia", + "label": "negative", + "script": "latin" + }, + { + "name": "robert kaufman", + "label": "negative", + "script": "latin" + }, + { + "name": "stanley sims", + "label": "negative", + "script": "latin" + }, + { + "name": "heather cole", + "label": "negative", + "script": "latin" + }, + { + "name": "michael vasquez", + "label": "negative", + "script": "latin" + }, + { + "name": "charles miller", + "label": "negative", + "script": "latin" + }, + { + "name": "madison carroll", + "label": "negative", + "script": "latin" + }, + { + "name": "lindsey butler", + "label": "negative", + "script": "latin" + }, + { + "name": "ashleigh nelson", + "label": "negative", + "script": "latin" + }, + { + "name": "elliot richardson", + "label": "negative", + "script": "latin" + }, + { + "name": "noah morrison", + "label": "negative", + "script": "latin" + }, + { + "name": "julian may", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Insert a random letter, Replace spaces with special characters, and Abbreviate name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "insert_random_letter", + "replace_spaces_with_random_special_characters", + "shorten_name_to_abbreviations" + ], + "rule_descriptions": { + "insert_random_letter": "Insert a random letter", + "replace_spaces_with_random_special_characters": "Replace spaces with special characters", + "shorten_name_to_abbreviations": "Abbreviate name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "jonathan byrd", + "label": "negative", + "script": "latin" + }, + { + "name": "colleen meyer", + "label": "negative", + "script": "latin" + }, + { + "name": "rachel jennings", + "label": "negative", + "script": "latin" + }, + { + "name": "marian jackson", + "label": "negative", + "script": "latin" + }, + { + "name": "sheila lowe", + "label": "negative", + "script": "latin" + }, + { + "name": "jody cox", + "label": "negative", + "script": "latin" + }, + { + "name": "chase wallace", + "label": "negative", + "script": "latin" + }, + { + "name": "kirsty powell", + "label": "negative", + "script": "latin" + }, + { + "name": "philip williams", + "label": "negative", + "script": "latin" + }, + { + "name": "abigail dixon", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer mckee", + "label": "negative", + "script": "latin" + }, + { + "name": "david mcdonald", + "label": "negative", + "script": "latin" + }, + { + "name": "richard gardner", + "label": "negative", + "script": "latin" + }, + { + "name": "kayleigh evans", + "label": "negative", + "script": "latin" + }, + { + "name": "robert jones", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace random vowels with different vowels, and Replace random consonants with different consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_vowel_with_random_vowel", + "replace_random_consonant_with_random_consonant" + ], + "rule_descriptions": { + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels", + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "maureen kelly", + "label": "negative", + "script": "latin" + }, + { + "name": "rebecca herbert", + "label": "negative", + "script": "latin" + }, + { + "name": "rosie green", + "label": "negative", + "script": "latin" + }, + { + "name": "sonia cook", + "label": "negative", + "script": "latin" + }, + { + "name": "megan barry", + "label": "negative", + "script": "latin" + }, + { + "name": "lorraine horn", + "label": "negative", + "script": "latin" + }, + { + "name": "miranda smith", + "label": "negative", + "script": "latin" + }, + { + "name": "david anderson", + "label": "negative", + "script": "latin" + }, + { + "name": "william wilkinson", + "label": "negative", + "script": "latin" + }, + { + "name": "taylor howard", + "label": "negative", + "script": "latin" + }, + { + "name": "steven davis", + "label": "negative", + "script": "latin" + }, + { + "name": "carolyn doyle", + "label": "negative", + "script": "latin" + }, + { + "name": "justin walker", + "label": "negative", + "script": "latin" + }, + { + "name": "larry keller", + "label": "negative", + "script": "latin" + }, + { + "name": "chad hernandez", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title prefix (Mr., Dr., etc.), and Insert a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_leading_title", + "insert_random_letter" + ], + "rule_descriptions": { + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)", + "insert_random_letter": "Insert a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "molly bryan", + "label": "negative", + "script": "latin" + }, + { + "name": "kelsey castaneda", + "label": "negative", + "script": "latin" + }, + { + "name": "sian foster", + "label": "negative", + "script": "latin" + }, + { + "name": "kimberly ferguson", + "label": "negative", + "script": "latin" + }, + { + "name": "donald davis", + "label": "negative", + "script": "latin" + }, + { + "name": "emily bond", + "label": "negative", + "script": "latin" + }, + { + "name": "howard delgado", + "label": "negative", + "script": "latin" + }, + { + "name": "molly johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "michael jensen", + "label": "negative", + "script": "latin" + }, + { + "name": "frank fuentes", + "label": "negative", + "script": "latin" + }, + { + "name": "todd ballard", + "label": "negative", + "script": "latin" + }, + { + "name": "brittany mack", + "label": "negative", + "script": "latin" + }, + { + "name": "david hussain", + "label": "negative", + "script": "latin" + }, + { + "name": "jake abbott", + "label": "negative", + "script": "latin" + }, + { + "name": "zachary harrison", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove a random consonant, Abbreviate name parts, and Use first name initial with last name.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_consonant", + "shorten_name_to_abbreviations", + "initial_only_first_name" + ], + "rule_descriptions": { + "remove_random_consonant": "Remove a random consonant", + "shorten_name_to_abbreviations": "Abbreviate name parts", + "initial_only_first_name": "Use first name initial with last name" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "joseph allen", + "label": "negative", + "script": "latin" + }, + { + "name": "peggy brown", + "label": "negative", + "script": "latin" + }, + { + "name": "melvin cole", + "label": "negative", + "script": "latin" + }, + { + "name": "alyssa wood", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie lopez", + "label": "negative", + "script": "latin" + }, + { + "name": "tyler rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "ana fleming", + "label": "negative", + "script": "latin" + }, + { + "name": "carl smith", + "label": "negative", + "script": "latin" + }, + { + "name": "rebecca deleon", + "label": "negative", + "script": "latin" + }, + { + "name": "kyle anderson", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew reed", + "label": "negative", + "script": "latin" + }, + { + "name": "darren dunlap", + "label": "negative", + "script": "latin" + }, + { + "name": "mandy evans", + "label": "negative", + "script": "latin" + }, + { + "name": "christian lloyd", + "label": "negative", + "script": "latin" + }, + { + "name": "bryan flores", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Abbreviate name parts, and Remove a random consonant.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_abbreviations", + "remove_random_consonant" + ], + "rule_descriptions": { + "shorten_name_to_abbreviations": "Abbreviate name parts", + "remove_random_consonant": "Remove a random consonant" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "daniel francis", + "label": "negative", + "script": "latin" + }, + { + "name": "denise walters", + "label": "negative", + "script": "latin" + }, + { + "name": "allan mitchell", + "label": "negative", + "script": "latin" + }, + { + "name": "blake harris", + "label": "negative", + "script": "latin" + }, + { + "name": "lindsay brown", + "label": "negative", + "script": "latin" + }, + { + "name": "michael henry", + "label": "negative", + "script": "latin" + }, + { + "name": "crystal mendoza", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda rowe", + "label": "negative", + "script": "latin" + }, + { + "name": "anna trujillo", + "label": "negative", + "script": "latin" + }, + { + "name": "brooke pham", + "label": "negative", + "script": "latin" + }, + { + "name": "sherry simpson", + "label": "negative", + "script": "latin" + }, + { + "name": "gabriel sullivan", + "label": "negative", + "script": "latin" + }, + { + "name": "miguel cox", + "label": "negative", + "script": "latin" + }, + { + "name": "brandon garcia", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle clayton", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Abbreviate name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_abbreviations" + ], + "rule_descriptions": { + "shorten_name_to_abbreviations": "Abbreviate name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "carrie nicholson", + "label": "negative", + "script": "latin" + }, + { + "name": "tom williams", + "label": "negative", + "script": "latin" + }, + { + "name": "susan foster", + "label": "negative", + "script": "latin" + }, + { + "name": "steven salazar", + "label": "negative", + "script": "latin" + }, + { + "name": "kristin kelley", + "label": "negative", + "script": "latin" + }, + { + "name": "kyle douglas", + "label": "negative", + "script": "latin" + }, + { + "name": "erin lopez", + "label": "negative", + "script": "latin" + }, + { + "name": "jason smith", + "label": "negative", + "script": "latin" + }, + { + "name": "douglas burrows", + "label": "negative", + "script": "latin" + }, + { + "name": "dale rojas", + "label": "negative", + "script": "latin" + }, + { + "name": "jonathan oliver", + "label": "negative", + "script": "latin" + }, + { + "name": "jemma hunter", + "label": "negative", + "script": "latin" + }, + { + "name": "janice mcgrath", + "label": "negative", + "script": "latin" + }, + { + "name": "katherine rodgers", + "label": "negative", + "script": "latin" + }, + { + "name": "mandy mendez", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace random consonants with different consonants, Use first name initial with last name, and Replace random vowels with different vowels.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_consonant_with_random_consonant", + "initial_only_first_name", + "replace_random_vowel_with_random_vowel" + ], + "rule_descriptions": { + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants", + "initial_only_first_name": "Use first name initial with last name", + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "amy carlson", + "label": "negative", + "script": "latin" + }, + { + "name": "kristi moore", + "label": "negative", + "script": "latin" + }, + { + "name": "lacey mcknight", + "label": "negative", + "script": "latin" + }, + { + "name": "adam white", + "label": "negative", + "script": "latin" + }, + { + "name": "alexis black", + "label": "negative", + "script": "latin" + }, + { + "name": "simon sawyer", + "label": "negative", + "script": "latin" + }, + { + "name": "denise carter", + "label": "negative", + "script": "latin" + }, + { + "name": "emily hamilton", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda ingram", + "label": "negative", + "script": "latin" + }, + { + "name": "aaron haley", + "label": "negative", + "script": "latin" + }, + { + "name": "angela knight", + "label": "negative", + "script": "latin" + }, + { + "name": "andrew andrews", + "label": "negative", + "script": "latin" + }, + { + "name": "chad jenkins", + "label": "negative", + "script": "latin" + }, + { + "name": "geraldine banks", + "label": "negative", + "script": "latin" + }, + { + "name": "darryl thompson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Remove a random consonant.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_consonant" + ], + "rule_descriptions": { + "remove_random_consonant": "Remove a random consonant" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "lesley martin", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer carpenter", + "label": "negative", + "script": "latin" + }, + { + "name": "sean manning", + "label": "negative", + "script": "latin" + }, + { + "name": "gerard robinson", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin jones", + "label": "negative", + "script": "latin" + }, + { + "name": "joel hines", + "label": "negative", + "script": "latin" + }, + { + "name": "lauren kelly", + "label": "negative", + "script": "latin" + }, + { + "name": "sheila blake", + "label": "negative", + "script": "latin" + }, + { + "name": "roger matthews", + "label": "negative", + "script": "latin" + }, + { + "name": "jim simmons", + "label": "negative", + "script": "latin" + }, + { + "name": "renee wells", + "label": "negative", + "script": "latin" + }, + { + "name": "nicholas rivera", + "label": "negative", + "script": "latin" + }, + { + "name": "allison scott", + "label": "negative", + "script": "latin" + }, + { + "name": "sheila whitehead", + "label": "negative", + "script": "latin" + }, + { + "name": "reece anderson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Insert a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "insert_random_letter" + ], + "rule_descriptions": { + "insert_random_letter": "Insert a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "alexander wallace", + "label": "negative", + "script": "latin" + }, + { + "name": "gary burton", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa nelson", + "label": "negative", + "script": "latin" + }, + { + "name": "chloe mosley", + "label": "negative", + "script": "latin" + }, + { + "name": "joel garcia", + "label": "negative", + "script": "latin" + }, + { + "name": "john phillips", + "label": "negative", + "script": "latin" + }, + { + "name": "joy henderson", + "label": "negative", + "script": "latin" + }, + { + "name": "cassandra scott", + "label": "negative", + "script": "latin" + }, + { + "name": "courtney schwartz", + "label": "negative", + "script": "latin" + }, + { + "name": "paul hicks", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer jennings", + "label": "negative", + "script": "latin" + }, + { + "name": "mark carr", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa martin", + "label": "negative", + "script": "latin" + }, + { + "name": "cynthia harrell", + "label": "negative", + "script": "latin" + }, + { + "name": "william brown", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Replace random vowels with different vowels.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_vowel_with_random_vowel" + ], + "rule_descriptions": { + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "ethan king", + "label": "negative", + "script": "latin" + }, + { + "name": "dominic davis", + "label": "negative", + "script": "latin" + }, + { + "name": "james simmons", + "label": "negative", + "script": "latin" + }, + { + "name": "marcia schwartz", + "label": "negative", + "script": "latin" + }, + { + "name": "austin carter", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy bennett", + "label": "negative", + "script": "latin" + }, + { + "name": "deborah thompson", + "label": "negative", + "script": "latin" + }, + { + "name": "pamela bartlett", + "label": "negative", + "script": "latin" + }, + { + "name": "rachel white", + "label": "negative", + "script": "latin" + }, + { + "name": "diane horn", + "label": "negative", + "script": "latin" + }, + { + "name": "wendy knight", + "label": "negative", + "script": "latin" + }, + { + "name": "mitchell evans", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica brown", + "label": "negative", + "script": "latin" + }, + { + "name": "patrick reed", + "label": "negative", + "script": "latin" + }, + { + "name": "ellie flores", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Replace random consonants with different consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_consonant_with_random_consonant" + ], + "rule_descriptions": { + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "lesley tyler", + "label": "negative", + "script": "latin" + }, + { + "name": "lindsay ryan", + "label": "negative", + "script": "latin" + }, + { + "name": "sophie hewitt", + "label": "negative", + "script": "latin" + }, + { + "name": "jason watkins", + "label": "negative", + "script": "latin" + }, + { + "name": "rose hughes", + "label": "negative", + "script": "latin" + }, + { + "name": "candace livingston", + "label": "negative", + "script": "latin" + }, + { + "name": "trevor brady", + "label": "negative", + "script": "latin" + }, + { + "name": "willie avila", + "label": "negative", + "script": "latin" + }, + { + "name": "christine king", + "label": "negative", + "script": "latin" + }, + { + "name": "caleb smith", + "label": "negative", + "script": "latin" + }, + { + "name": "alan carrillo", + "label": "negative", + "script": "latin" + }, + { + "name": "hayden johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "charles wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "darrell young", + "label": "negative", + "script": "latin" + }, + { + "name": "shawn brown", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace random consonants with different consonants, and Reorder name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_consonant_with_random_consonant", + "name_parts_permutations" + ], + "rule_descriptions": { + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants", + "name_parts_permutations": "Reorder name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "lisa martin", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew mueller", + "label": "negative", + "script": "latin" + }, + { + "name": "maria walls", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher henry", + "label": "negative", + "script": "latin" + }, + { + "name": "veronica vega", + "label": "negative", + "script": "latin" + }, + { + "name": "gregory hamilton", + "label": "negative", + "script": "latin" + }, + { + "name": "robert williams", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica wolf", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin frank", + "label": "negative", + "script": "latin" + }, + { + "name": "bruce anderson", + "label": "negative", + "script": "latin" + }, + { + "name": "jay leonard", + "label": "negative", + "script": "latin" + }, + { + "name": "steven webb", + "label": "negative", + "script": "latin" + }, + { + "name": "andrea diaz", + "label": "negative", + "script": "latin" + }, + { + "name": "william flowers", + "label": "negative", + "script": "latin" + }, + { + "name": "dana sanders", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove all spaces, Reorder name parts, and Add a title prefix (Mr., Dr., etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_all_spaces", + "name_parts_permutations", + "add_random_leading_title" + ], + "rule_descriptions": { + "remove_all_spaces": "Remove all spaces", + "name_parts_permutations": "Reorder name parts", + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "dennis valentine", + "label": "negative", + "script": "latin" + }, + { + "name": "derek mendez", + "label": "negative", + "script": "latin" + }, + { + "name": "lance sparks", + "label": "negative", + "script": "latin" + }, + { + "name": "eric clay", + "label": "negative", + "script": "latin" + }, + { + "name": "cindy hamilton", + "label": "negative", + "script": "latin" + }, + { + "name": "adam rivera", + "label": "negative", + "script": "latin" + }, + { + "name": "juan cross", + "label": "negative", + "script": "latin" + }, + { + "name": "hayley clay", + "label": "negative", + "script": "latin" + }, + { + "name": "william harding", + "label": "negative", + "script": "latin" + }, + { + "name": "wendy chapman", + "label": "negative", + "script": "latin" + }, + { + "name": "randall hernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "arthur hernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "amy martin", + "label": "negative", + "script": "latin" + }, + { + "name": "richard middleton", + "label": "negative", + "script": "latin" + }, + { + "name": "brian owens", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap adjacent syllables, Delete a random letter, and Swap adjacent consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_syllables", + "delete_random_letter", + "swap_adjacent_consonants" + ], + "rule_descriptions": { + "swap_adjacent_syllables": "Swap adjacent syllables", + "delete_random_letter": "Delete a random letter", + "swap_adjacent_consonants": "Swap adjacent consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "jennifer lewis", + "label": "negative", + "script": "latin" + }, + { + "name": "michael hughes", + "label": "negative", + "script": "latin" + }, + { + "name": "sheila andrews", + "label": "negative", + "script": "latin" + }, + { + "name": "kathleen connor", + "label": "negative", + "script": "latin" + }, + { + "name": "cesar rose", + "label": "negative", + "script": "latin" + }, + { + "name": "robert cook", + "label": "negative", + "script": "latin" + }, + { + "name": "ryan terry", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle james", + "label": "negative", + "script": "latin" + }, + { + "name": "annette romero", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew reyes", + "label": "negative", + "script": "latin" + }, + { + "name": "jose rivas", + "label": "negative", + "script": "latin" + }, + { + "name": "aaron hickman", + "label": "negative", + "script": "latin" + }, + { + "name": "margaret evans", + "label": "negative", + "script": "latin" + }, + { + "name": "jason hawkins", + "label": "negative", + "script": "latin" + }, + { + "name": "maurice hughes", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap adjacent consonants, Replace spaces with special characters, and Convert name to initials.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_consonants", + "replace_spaces_with_random_special_characters", + "shorten_name_to_initials" + ], + "rule_descriptions": { + "swap_adjacent_consonants": "Swap adjacent consonants", + "replace_spaces_with_random_special_characters": "Replace spaces with special characters", + "shorten_name_to_initials": "Convert name to initials" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "mary maynard", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph fischer", + "label": "negative", + "script": "latin" + }, + { + "name": "sean gardner", + "label": "negative", + "script": "latin" + }, + { + "name": "darren hanna", + "label": "negative", + "script": "latin" + }, + { + "name": "garrett smith", + "label": "negative", + "script": "latin" + }, + { + "name": "carolyn blackburn", + "label": "negative", + "script": "latin" + }, + { + "name": "dale williams", + "label": "negative", + "script": "latin" + }, + { + "name": "gavin moore", + "label": "negative", + "script": "latin" + }, + { + "name": "mark romero", + "label": "negative", + "script": "latin" + }, + { + "name": "megan rodgers", + "label": "negative", + "script": "latin" + }, + { + "name": "caroline johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "david crawford", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua doyle", + "label": "negative", + "script": "latin" + }, + { + "name": "anita parker", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer turner", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Delete a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "delete_random_letter" + ], + "rule_descriptions": { + "delete_random_letter": "Delete a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "kaitlyn lopez", + "label": "negative", + "script": "latin" + }, + { + "name": "olivia powell", + "label": "negative", + "script": "latin" + }, + { + "name": "corey francis", + "label": "negative", + "script": "latin" + }, + { + "name": "megan davis", + "label": "negative", + "script": "latin" + }, + { + "name": "karen short", + "label": "negative", + "script": "latin" + }, + { + "name": "andrew hussain", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica hussain", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "katherine dodd", + "label": "negative", + "script": "latin" + }, + { + "name": "erin blackwell", + "label": "negative", + "script": "latin" + }, + { + "name": "lauren caldwell", + "label": "negative", + "script": "latin" + }, + { + "name": "paul jones", + "label": "negative", + "script": "latin" + }, + { + "name": "carolyn jenkins", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer jones", + "label": "negative", + "script": "latin" + }, + { + "name": "angela mcguire", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Add a title prefix (Mr., Dr., etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_leading_title" + ], + "rule_descriptions": { + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "andrea jones", + "label": "negative", + "script": "latin" + }, + { + "name": "andrea marsden", + "label": "negative", + "script": "latin" + }, + { + "name": "ruth moreno", + "label": "negative", + "script": "latin" + }, + { + "name": "erika hodges", + "label": "negative", + "script": "latin" + }, + { + "name": "debra jones", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah moore", + "label": "negative", + "script": "latin" + }, + { + "name": "carolyn newman", + "label": "negative", + "script": "latin" + }, + { + "name": "lindsey chavez", + "label": "negative", + "script": "latin" + }, + { + "name": "arthur jordan", + "label": "negative", + "script": "latin" + }, + { + "name": "katherine rivera", + "label": "negative", + "script": "latin" + }, + { + "name": "annette bennett", + "label": "negative", + "script": "latin" + }, + { + "name": "mary mccann", + "label": "negative", + "script": "latin" + }, + { + "name": "darlene bass", + "label": "negative", + "script": "latin" + }, + { + "name": "stewart shields", + "label": "negative", + "script": "latin" + }, + { + "name": "clifford davis", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove a random consonant, Insert a random letter, and Add a title prefix (Mr., Dr., etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_consonant", + "insert_random_letter", + "add_random_leading_title" + ], + "rule_descriptions": { + "remove_random_consonant": "Remove a random consonant", + "insert_random_letter": "Insert a random letter", + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "teresa sanchez", + "label": "negative", + "script": "latin" + }, + { + "name": "kirsty goodman", + "label": "negative", + "script": "latin" + }, + { + "name": "alyssa curtis", + "label": "negative", + "script": "latin" + }, + { + "name": "miguel schwartz", + "label": "negative", + "script": "latin" + }, + { + "name": "kathy lloyd", + "label": "negative", + "script": "latin" + }, + { + "name": "brian cunningham", + "label": "negative", + "script": "latin" + }, + { + "name": "debra nelson", + "label": "negative", + "script": "latin" + }, + { + "name": "gabrielle reyes", + "label": "negative", + "script": "latin" + }, + { + "name": "mike freeman", + "label": "negative", + "script": "latin" + }, + { + "name": "pamela wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "josephine patel", + "label": "negative", + "script": "latin" + }, + { + "name": "susan payne", + "label": "negative", + "script": "latin" + }, + { + "name": "lori boyd", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph barrett", + "label": "negative", + "script": "latin" + }, + { + "name": "jasmine wilson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove a random vowel, Swap adjacent consonants, and Duplicate a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_vowel", + "swap_adjacent_consonants", + "duplicate_random_letter_as_double_letter" + ], + "rule_descriptions": { + "remove_random_vowel": "Remove a random vowel", + "swap_adjacent_consonants": "Swap adjacent consonants", + "duplicate_random_letter_as_double_letter": "Duplicate a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "judith smith", + "label": "negative", + "script": "latin" + }, + { + "name": "jesse clark", + "label": "negative", + "script": "latin" + }, + { + "name": "joyce burns", + "label": "negative", + "script": "latin" + }, + { + "name": "gregory williams", + "label": "negative", + "script": "latin" + }, + { + "name": "jeremy torres", + "label": "negative", + "script": "latin" + }, + { + "name": "luke jimenez", + "label": "negative", + "script": "latin" + }, + { + "name": "rosemary anderson", + "label": "negative", + "script": "latin" + }, + { + "name": "morgan walker", + "label": "negative", + "script": "latin" + }, + { + "name": "kenneth snyder", + "label": "negative", + "script": "latin" + }, + { + "name": "lee miller", + "label": "negative", + "script": "latin" + }, + { + "name": "karen anderson", + "label": "negative", + "script": "latin" + }, + { + "name": "dylan ramirez", + "label": "negative", + "script": "latin" + }, + { + "name": "ricky vincent", + "label": "negative", + "script": "latin" + }, + { + "name": "patricia smith", + "label": "negative", + "script": "latin" + }, + { + "name": "francis martin", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap adjacent consonants, and Remove a random vowel.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_consonants", + "remove_random_vowel" + ], + "rule_descriptions": { + "swap_adjacent_consonants": "Swap adjacent consonants", + "remove_random_vowel": "Remove a random vowel" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "jennifer christensen", + "label": "negative", + "script": "latin" + }, + { + "name": "dalton tanner", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph walker", + "label": "negative", + "script": "latin" + }, + { + "name": "johnny york", + "label": "negative", + "script": "latin" + }, + { + "name": "kimberly howard", + "label": "negative", + "script": "latin" + }, + { + "name": "alan wilcox", + "label": "negative", + "script": "latin" + }, + { + "name": "robert powell", + "label": "negative", + "script": "latin" + }, + { + "name": "edward smith", + "label": "negative", + "script": "latin" + }, + { + "name": "eric wright", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda cooper", + "label": "negative", + "script": "latin" + }, + { + "name": "erin robertson", + "label": "negative", + "script": "latin" + }, + { + "name": "nicholas zhang", + "label": "negative", + "script": "latin" + }, + { + "name": "david lane", + "label": "negative", + "script": "latin" + }, + { + "name": "owen crosby", + "label": "negative", + "script": "latin" + }, + { + "name": "teresa harris", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Remove a random consonant.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_consonant" + ], + "rule_descriptions": { + "remove_random_consonant": "Remove a random consonant" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "connie harris", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas harris", + "label": "negative", + "script": "latin" + }, + { + "name": "laura morris", + "label": "negative", + "script": "latin" + }, + { + "name": "mitchell haas", + "label": "negative", + "script": "latin" + }, + { + "name": "rebecca fischer", + "label": "negative", + "script": "latin" + }, + { + "name": "robert green", + "label": "negative", + "script": "latin" + }, + { + "name": "diana jacobs", + "label": "negative", + "script": "latin" + }, + { + "name": "jason nguyen", + "label": "negative", + "script": "latin" + }, + { + "name": "karen anderson", + "label": "negative", + "script": "latin" + }, + { + "name": "michael adams", + "label": "negative", + "script": "latin" + }, + { + "name": "linda chen", + "label": "negative", + "script": "latin" + }, + { + "name": "donna davis", + "label": "negative", + "script": "latin" + }, + { + "name": "catherine martin", + "label": "negative", + "script": "latin" + }, + { + "name": "connie fisher", + "label": "negative", + "script": "latin" + }, + { + "name": "brent alexander", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace random consonants with different consonants, and Remove a random consonant.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_consonant_with_random_consonant", + "remove_random_consonant" + ], + "rule_descriptions": { + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants", + "remove_random_consonant": "Remove a random consonant" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "lance blake", + "label": "negative", + "script": "latin" + }, + { + "name": "justin webster", + "label": "negative", + "script": "latin" + }, + { + "name": "linda quinn", + "label": "negative", + "script": "latin" + }, + { + "name": "cameron clarke", + "label": "negative", + "script": "latin" + }, + { + "name": "austin donaldson", + "label": "negative", + "script": "latin" + }, + { + "name": "cheryl gray", + "label": "negative", + "script": "latin" + }, + { + "name": "jamie valdez", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony brown", + "label": "negative", + "script": "latin" + }, + { + "name": "sandra king", + "label": "negative", + "script": "latin" + }, + { + "name": "john sullivan", + "label": "negative", + "script": "latin" + }, + { + "name": "patrick shaw", + "label": "negative", + "script": "latin" + }, + { + "name": "jackson norman", + "label": "negative", + "script": "latin" + }, + { + "name": "chad rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "michael smith", + "label": "negative", + "script": "latin" + }, + { + "name": "shannon wilkins", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove a random consonant, Duplicate a random letter, and Replace spaces with special characters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_consonant", + "duplicate_random_letter_as_double_letter", + "replace_spaces_with_random_special_characters" + ], + "rule_descriptions": { + "remove_random_consonant": "Remove a random consonant", + "duplicate_random_letter_as_double_letter": "Duplicate a random letter", + "replace_spaces_with_random_special_characters": "Replace spaces with special characters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "nicole landry", + "label": "negative", + "script": "latin" + }, + { + "name": "monica johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "timothy daniels", + "label": "negative", + "script": "latin" + }, + { + "name": "nathan tapia", + "label": "negative", + "script": "latin" + }, + { + "name": "jay fisher", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew norman", + "label": "negative", + "script": "latin" + }, + { + "name": "sean parker", + "label": "negative", + "script": "latin" + }, + { + "name": "rachel harris", + "label": "negative", + "script": "latin" + }, + { + "name": "cynthia massey", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffrey smith", + "label": "negative", + "script": "latin" + }, + { + "name": "christian bennett", + "label": "negative", + "script": "latin" + }, + { + "name": "brian clark", + "label": "negative", + "script": "latin" + }, + { + "name": "amber mullins", + "label": "negative", + "script": "latin" + }, + { + "name": "shane martinez", + "label": "negative", + "script": "latin" + }, + { + "name": "deborah white", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Use first name initial with last name.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "initial_only_first_name" + ], + "rule_descriptions": { + "initial_only_first_name": "Use first name initial with last name" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "brandon russell", + "label": "negative", + "script": "latin" + }, + { + "name": "michele perez", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua watson", + "label": "negative", + "script": "latin" + }, + { + "name": "ryan cooper", + "label": "negative", + "script": "latin" + }, + { + "name": "megan cohen", + "label": "negative", + "script": "latin" + }, + { + "name": "rita perkins", + "label": "negative", + "script": "latin" + }, + { + "name": "rita sullivan", + "label": "negative", + "script": "latin" + }, + { + "name": "edward james", + "label": "negative", + "script": "latin" + }, + { + "name": "nicholas white", + "label": "negative", + "script": "latin" + }, + { + "name": "lauren garza", + "label": "negative", + "script": "latin" + }, + { + "name": "jemma mitchell", + "label": "negative", + "script": "latin" + }, + { + "name": "cole shannon", + "label": "negative", + "script": "latin" + }, + { + "name": "samantha brooks", + "label": "negative", + "script": "latin" + }, + { + "name": "shannon huang", + "label": "negative", + "script": "latin" + }, + { + "name": "angela ray", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap random adjacent letters, and Insert a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_random_letter", + "insert_random_letter" + ], + "rule_descriptions": { + "swap_random_letter": "Swap random adjacent letters", + "insert_random_letter": "Insert a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "keith hayes", + "label": "negative", + "script": "latin" + }, + { + "name": "christy soto", + "label": "negative", + "script": "latin" + }, + { + "name": "cameron ruiz", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew barker", + "label": "negative", + "script": "latin" + }, + { + "name": "mathew harvey", + "label": "negative", + "script": "latin" + }, + { + "name": "emma dunn", + "label": "negative", + "script": "latin" + }, + { + "name": "brian romero", + "label": "negative", + "script": "latin" + }, + { + "name": "andrew nelson", + "label": "negative", + "script": "latin" + }, + { + "name": "frances watkins", + "label": "negative", + "script": "latin" + }, + { + "name": "jerome camacho", + "label": "negative", + "script": "latin" + }, + { + "name": "traci meadows", + "label": "negative", + "script": "latin" + }, + { + "name": "gary walsh", + "label": "negative", + "script": "latin" + }, + { + "name": "david oconnor", + "label": "negative", + "script": "latin" + }, + { + "name": "richard hicks", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas espinoza", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title prefix (Mr., Dr., etc.), and Swap adjacent syllables.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_leading_title", + "swap_adjacent_syllables" + ], + "rule_descriptions": { + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)", + "swap_adjacent_syllables": "Swap adjacent syllables" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "tiffany braun", + "label": "negative", + "script": "latin" + }, + { + "name": "james murray", + "label": "negative", + "script": "latin" + }, + { + "name": "paul jones", + "label": "negative", + "script": "latin" + }, + { + "name": "brandon mendoza", + "label": "negative", + "script": "latin" + }, + { + "name": "gina hartman", + "label": "negative", + "script": "latin" + }, + { + "name": "lauren reynolds", + "label": "negative", + "script": "latin" + }, + { + "name": "alejandro wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "joel martinez", + "label": "negative", + "script": "latin" + }, + { + "name": "keith fernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "karen hernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "dale cooper", + "label": "negative", + "script": "latin" + }, + { + "name": "christian rodgers", + "label": "negative", + "script": "latin" + }, + { + "name": "rachel turner", + "label": "negative", + "script": "latin" + }, + { + "name": "catherine wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "yvonne diaz", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Replace random vowels with different vowels.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_vowel_with_random_vowel" + ], + "rule_descriptions": { + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "scott mclean", + "label": "negative", + "script": "latin" + }, + { + "name": "daisy williams", + "label": "negative", + "script": "latin" + }, + { + "name": "julian montgomery", + "label": "negative", + "script": "latin" + }, + { + "name": "jay hernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "holly turner", + "label": "negative", + "script": "latin" + }, + { + "name": "lynne parker", + "label": "negative", + "script": "latin" + }, + { + "name": "edward collins", + "label": "negative", + "script": "latin" + }, + { + "name": "dawn tate", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew clark", + "label": "negative", + "script": "latin" + }, + { + "name": "lauren gutierrez", + "label": "negative", + "script": "latin" + }, + { + "name": "kimberly taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher lewis", + "label": "negative", + "script": "latin" + }, + { + "name": "katherine wyatt", + "label": "negative", + "script": "latin" + }, + { + "name": "leanne clarke", + "label": "negative", + "script": "latin" + }, + { + "name": "brad cooper", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Abbreviate name parts, and Duplicate a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_abbreviations", + "duplicate_random_letter_as_double_letter" + ], + "rule_descriptions": { + "shorten_name_to_abbreviations": "Abbreviate name parts", + "duplicate_random_letter_as_double_letter": "Duplicate a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "erica stevenson", + "label": "negative", + "script": "latin" + }, + { + "name": "brandon russell", + "label": "negative", + "script": "latin" + }, + { + "name": "karen sanchez", + "label": "negative", + "script": "latin" + }, + { + "name": "barbara holland", + "label": "negative", + "script": "latin" + }, + { + "name": "susan brady", + "label": "negative", + "script": "latin" + }, + { + "name": "mohammad garrison", + "label": "negative", + "script": "latin" + }, + { + "name": "peter collins", + "label": "negative", + "script": "latin" + }, + { + "name": "victoria johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "jacqueline ryan", + "label": "negative", + "script": "latin" + }, + { + "name": "chad alexander", + "label": "negative", + "script": "latin" + }, + { + "name": "gary thompson", + "label": "negative", + "script": "latin" + }, + { + "name": "clifford taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie kline", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley davis", + "label": "negative", + "script": "latin" + }, + { + "name": "beverly kennedy", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Swap adjacent consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_consonants" + ], + "rule_descriptions": { + "swap_adjacent_consonants": "Swap adjacent consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "wendy morales", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer fuller", + "label": "negative", + "script": "latin" + }, + { + "name": "kelly best", + "label": "negative", + "script": "latin" + }, + { + "name": "tara burton", + "label": "negative", + "script": "latin" + }, + { + "name": "robert torres", + "label": "negative", + "script": "latin" + }, + { + "name": "annette martin", + "label": "negative", + "script": "latin" + }, + { + "name": "miguel frazier", + "label": "negative", + "script": "latin" + }, + { + "name": "dustin walker", + "label": "negative", + "script": "latin" + }, + { + "name": "jesse odom", + "label": "negative", + "script": "latin" + }, + { + "name": "george taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "stacey williams", + "label": "negative", + "script": "latin" + }, + { + "name": "austin lawrence", + "label": "negative", + "script": "latin" + }, + { + "name": "theresa nichols", + "label": "negative", + "script": "latin" + }, + { + "name": "mathew castro", + "label": "negative", + "script": "latin" + }, + { + "name": "hannah page", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title suffix (Jr., PhD, etc.), Reorder name parts, and Abbreviate name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_trailing_title", + "name_parts_permutations", + "shorten_name_to_abbreviations" + ], + "rule_descriptions": { + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)", + "name_parts_permutations": "Reorder name parts", + "shorten_name_to_abbreviations": "Abbreviate name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "trevor brown", + "label": "negative", + "script": "latin" + }, + { + "name": "martin burke", + "label": "negative", + "script": "latin" + }, + { + "name": "sandra potter", + "label": "negative", + "script": "latin" + }, + { + "name": "miranda mitchell", + "label": "negative", + "script": "latin" + }, + { + "name": "stanley rogers", + "label": "negative", + "script": "latin" + }, + { + "name": "stacey green", + "label": "negative", + "script": "latin" + }, + { + "name": "james richardson", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas graham", + "label": "negative", + "script": "latin" + }, + { + "name": "danielle owen", + "label": "negative", + "script": "latin" + }, + { + "name": "henry kennedy", + "label": "negative", + "script": "latin" + }, + { + "name": "james davis", + "label": "negative", + "script": "latin" + }, + { + "name": "penny wright", + "label": "negative", + "script": "latin" + }, + { + "name": "jason butler", + "label": "negative", + "script": "latin" + }, + { + "name": "mitchell fleming", + "label": "negative", + "script": "latin" + }, + { + "name": "tanya prince", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Insert a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "insert_random_letter" + ], + "rule_descriptions": { + "insert_random_letter": "Insert a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "rebecca johnston", + "label": "negative", + "script": "latin" + }, + { + "name": "roy gates", + "label": "negative", + "script": "latin" + }, + { + "name": "megan parkes", + "label": "negative", + "script": "latin" + }, + { + "name": "beth davis", + "label": "negative", + "script": "latin" + }, + { + "name": "david rowe", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew stevens", + "label": "negative", + "script": "latin" + }, + { + "name": "david cole", + "label": "negative", + "script": "latin" + }, + { + "name": "kyle ruiz", + "label": "negative", + "script": "latin" + }, + { + "name": "owen mckay", + "label": "negative", + "script": "latin" + }, + { + "name": "caitlin brown", + "label": "negative", + "script": "latin" + }, + { + "name": "lori wright", + "label": "negative", + "script": "latin" + }, + { + "name": "luke lloyd", + "label": "negative", + "script": "latin" + }, + { + "name": "jacob ward", + "label": "negative", + "script": "latin" + }, + { + "name": "benjamin jones", + "label": "negative", + "script": "latin" + }, + { + "name": "kayla anderson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove all spaces, Swap adjacent consonants, and Insert a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_all_spaces", + "swap_adjacent_consonants", + "insert_random_letter" + ], + "rule_descriptions": { + "remove_all_spaces": "Remove all spaces", + "swap_adjacent_consonants": "Swap adjacent consonants", + "insert_random_letter": "Insert a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "david little", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew garcia", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin hayes", + "label": "negative", + "script": "latin" + }, + { + "name": "elliot graham", + "label": "negative", + "script": "latin" + }, + { + "name": "cameron perez", + "label": "negative", + "script": "latin" + }, + { + "name": "margaret ortiz", + "label": "negative", + "script": "latin" + }, + { + "name": "patricia bailey", + "label": "negative", + "script": "latin" + }, + { + "name": "brittany lopez", + "label": "negative", + "script": "latin" + }, + { + "name": "justin khan", + "label": "negative", + "script": "latin" + }, + { + "name": "tanya ford", + "label": "negative", + "script": "latin" + }, + { + "name": "sara bailey", + "label": "negative", + "script": "latin" + }, + { + "name": "angela jordan", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer anderson", + "label": "negative", + "script": "latin" + }, + { + "name": "andrea reynolds", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin bates", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Delete a random letter, and Convert name to initials.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "delete_random_letter", + "shorten_name_to_initials" + ], + "rule_descriptions": { + "delete_random_letter": "Delete a random letter", + "shorten_name_to_initials": "Convert name to initials" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "thomas griffin", + "label": "negative", + "script": "latin" + }, + { + "name": "nancy terry", + "label": "negative", + "script": "latin" + }, + { + "name": "michael patel", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel smith", + "label": "negative", + "script": "latin" + }, + { + "name": "geraldine ruiz", + "label": "negative", + "script": "latin" + }, + { + "name": "mary walker", + "label": "negative", + "script": "latin" + }, + { + "name": "dennis robbins", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda mccarty", + "label": "negative", + "script": "latin" + }, + { + "name": "christian williams", + "label": "negative", + "script": "latin" + }, + { + "name": "william hale", + "label": "negative", + "script": "latin" + }, + { + "name": "mary reeves", + "label": "negative", + "script": "latin" + }, + { + "name": "deborah bell", + "label": "negative", + "script": "latin" + }, + { + "name": "james clark", + "label": "negative", + "script": "latin" + }, + { + "name": "richard o'brien", + "label": "negative", + "script": "latin" + }, + { + "name": "william shaw", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title suffix (Jr., PhD, etc.), Insert a random letter, and Duplicate a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_trailing_title", + "insert_random_letter", + "duplicate_random_letter_as_double_letter" + ], + "rule_descriptions": { + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)", + "insert_random_letter": "Insert a random letter", + "duplicate_random_letter_as_double_letter": "Duplicate a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "kelly austin", + "label": "negative", + "script": "latin" + }, + { + "name": "brian wolf", + "label": "negative", + "script": "latin" + }, + { + "name": "clayton lewis", + "label": "negative", + "script": "latin" + }, + { + "name": "natalie cooper", + "label": "negative", + "script": "latin" + }, + { + "name": "karen bennett", + "label": "negative", + "script": "latin" + }, + { + "name": "paul brown", + "label": "negative", + "script": "latin" + }, + { + "name": "andrew rivera", + "label": "negative", + "script": "latin" + }, + { + "name": "elizabeth wilkinson", + "label": "negative", + "script": "latin" + }, + { + "name": "billy washington", + "label": "negative", + "script": "latin" + }, + { + "name": "eric santos", + "label": "negative", + "script": "latin" + }, + { + "name": "sandra ferrell", + "label": "negative", + "script": "latin" + }, + { + "name": "mason williams", + "label": "negative", + "script": "latin" + }, + { + "name": "david hill", + "label": "negative", + "script": "latin" + }, + { + "name": "kate barrett", + "label": "negative", + "script": "latin" + }, + { + "name": "robert wilson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Duplicate a random letter, Add a title suffix (Jr., PhD, etc.), and Reorder name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "duplicate_random_letter_as_double_letter", + "add_random_trailing_title", + "name_parts_permutations" + ], + "rule_descriptions": { + "duplicate_random_letter_as_double_letter": "Duplicate a random letter", + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)", + "name_parts_permutations": "Reorder name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "kathleen watts", + "label": "negative", + "script": "latin" + }, + { + "name": "rita wagner", + "label": "negative", + "script": "latin" + }, + { + "name": "monique herrera", + "label": "negative", + "script": "latin" + }, + { + "name": "valerie carlson", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher jones", + "label": "negative", + "script": "latin" + }, + { + "name": "kelly king", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "brent jones", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer williams", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer wallace", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher lee", + "label": "negative", + "script": "latin" + }, + { + "name": "christine gibbs", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa mckenzie", + "label": "negative", + "script": "latin" + }, + { + "name": "sam williams", + "label": "negative", + "script": "latin" + }, + { + "name": "kathy pearson", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove all spaces, and Convert name to initials.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_all_spaces", + "shorten_name_to_initials" + ], + "rule_descriptions": { + "remove_all_spaces": "Remove all spaces", + "shorten_name_to_initials": "Convert name to initials" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "robert wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "richard johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "graham cox", + "label": "negative", + "script": "latin" + }, + { + "name": "kelly jacobson", + "label": "negative", + "script": "latin" + }, + { + "name": "mark aguilar", + "label": "negative", + "script": "latin" + }, + { + "name": "kelly malone", + "label": "negative", + "script": "latin" + }, + { + "name": "brian myers", + "label": "negative", + "script": "latin" + }, + { + "name": "allan nichols", + "label": "negative", + "script": "latin" + }, + { + "name": "tyler davis", + "label": "negative", + "script": "latin" + }, + { + "name": "kimberly thompson", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel kelly", + "label": "negative", + "script": "latin" + }, + { + "name": "rebecca barrett", + "label": "negative", + "script": "latin" + }, + { + "name": "alex watson", + "label": "negative", + "script": "latin" + }, + { + "name": "susan stone", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Remove a random vowel.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_vowel" + ], + "rule_descriptions": { + "remove_random_vowel": "Remove a random vowel" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "cassandra williamson", + "label": "negative", + "script": "latin" + }, + { + "name": "amy baker", + "label": "negative", + "script": "latin" + }, + { + "name": "jake little", + "label": "negative", + "script": "latin" + }, + { + "name": "lauren baldwin", + "label": "negative", + "script": "latin" + }, + { + "name": "michelle harris", + "label": "negative", + "script": "latin" + }, + { + "name": "angela roberts", + "label": "negative", + "script": "latin" + }, + { + "name": "lucy scott", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley brown", + "label": "negative", + "script": "latin" + }, + { + "name": "colin wiley", + "label": "negative", + "script": "latin" + }, + { + "name": "tracy levine", + "label": "negative", + "script": "latin" + }, + { + "name": "andrew pham", + "label": "negative", + "script": "latin" + }, + { + "name": "donald sanchez", + "label": "negative", + "script": "latin" + }, + { + "name": "holly moore", + "label": "negative", + "script": "latin" + }, + { + "name": "robert wall", + "label": "negative", + "script": "latin" + }, + { + "name": "maureen kent", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Reorder name parts, and Swap adjacent consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "name_parts_permutations", + "swap_adjacent_consonants" + ], + "rule_descriptions": { + "name_parts_permutations": "Reorder name parts", + "swap_adjacent_consonants": "Swap adjacent consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "sophie wise", + "label": "negative", + "script": "latin" + }, + { + "name": "diane kelly", + "label": "negative", + "script": "latin" + }, + { + "name": "derek roberts", + "label": "negative", + "script": "latin" + }, + { + "name": "james salazar", + "label": "negative", + "script": "latin" + }, + { + "name": "dennis riley", + "label": "negative", + "script": "latin" + }, + { + "name": "don farrell", + "label": "negative", + "script": "latin" + }, + { + "name": "kelly warren", + "label": "negative", + "script": "latin" + }, + { + "name": "amy arnold", + "label": "negative", + "script": "latin" + }, + { + "name": "samantha kaiser", + "label": "negative", + "script": "latin" + }, + { + "name": "diana tyler", + "label": "negative", + "script": "latin" + }, + { + "name": "philip mccarthy", + "label": "negative", + "script": "latin" + }, + { + "name": "andrea lee", + "label": "negative", + "script": "latin" + }, + { + "name": "mike heath", + "label": "negative", + "script": "latin" + }, + { + "name": "caitlyn burgess", + "label": "negative", + "script": "latin" + }, + { + "name": "kristen baird", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title prefix (Mr., Dr., etc.), Replace random vowels with different vowels, and Swap random adjacent letters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_leading_title", + "replace_random_vowel_with_random_vowel", + "swap_random_letter" + ], + "rule_descriptions": { + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)", + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels", + "swap_random_letter": "Swap random adjacent letters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "paige delgado", + "label": "negative", + "script": "latin" + }, + { + "name": "hunter tucker", + "label": "negative", + "script": "latin" + }, + { + "name": "bryan wright", + "label": "negative", + "script": "latin" + }, + { + "name": "marcus baldwin", + "label": "negative", + "script": "latin" + }, + { + "name": "barbara grant", + "label": "negative", + "script": "latin" + }, + { + "name": "harriet lambert", + "label": "negative", + "script": "latin" + }, + { + "name": "hollie turner", + "label": "negative", + "script": "latin" + }, + { + "name": "jay sanchez", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda price", + "label": "negative", + "script": "latin" + }, + { + "name": "rachel jones", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffrey harris", + "label": "negative", + "script": "latin" + }, + { + "name": "michael kennedy", + "label": "negative", + "script": "latin" + }, + { + "name": "shaun carrillo", + "label": "negative", + "script": "latin" + }, + { + "name": "amy hall", + "label": "negative", + "script": "latin" + }, + { + "name": "kristy smith", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace random vowels with different vowels, and Swap adjacent syllables.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_vowel_with_random_vowel", + "swap_adjacent_syllables" + ], + "rule_descriptions": { + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels", + "swap_adjacent_syllables": "Swap adjacent syllables" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "stephen potts", + "label": "negative", + "script": "latin" + }, + { + "name": "grace brown", + "label": "negative", + "script": "latin" + }, + { + "name": "andrew gonzalez", + "label": "negative", + "script": "latin" + }, + { + "name": "james williams", + "label": "negative", + "script": "latin" + }, + { + "name": "daniel bennett", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph williams", + "label": "negative", + "script": "latin" + }, + { + "name": "debra simmons", + "label": "negative", + "script": "latin" + }, + { + "name": "maria tran", + "label": "negative", + "script": "latin" + }, + { + "name": "gregory abbott", + "label": "negative", + "script": "latin" + }, + { + "name": "dale coleman", + "label": "negative", + "script": "latin" + }, + { + "name": "mark wright", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph powell", + "label": "negative", + "script": "latin" + }, + { + "name": "mariah neal", + "label": "negative", + "script": "latin" + }, + { + "name": "mohamed barker", + "label": "negative", + "script": "latin" + }, + { + "name": "george jones", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Swap adjacent consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_consonants" + ], + "rule_descriptions": { + "swap_adjacent_consonants": "Swap adjacent consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "daniel cole", + "label": "negative", + "script": "latin" + }, + { + "name": "pamela smith", + "label": "negative", + "script": "latin" + }, + { + "name": "amber o'connor", + "label": "negative", + "script": "latin" + }, + { + "name": "elizabeth vazquez", + "label": "negative", + "script": "latin" + }, + { + "name": "jared harding", + "label": "negative", + "script": "latin" + }, + { + "name": "ronald rogers", + "label": "negative", + "script": "latin" + }, + { + "name": "gary johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "tiffany chandler", + "label": "negative", + "script": "latin" + }, + { + "name": "denise hill", + "label": "negative", + "script": "latin" + }, + { + "name": "danielle larson", + "label": "negative", + "script": "latin" + }, + { + "name": "frederick wood", + "label": "negative", + "script": "latin" + }, + { + "name": "harriet hawkins", + "label": "negative", + "script": "latin" + }, + { + "name": "katherine watts", + "label": "negative", + "script": "latin" + }, + { + "name": "mario henderson", + "label": "negative", + "script": "latin" + }, + { + "name": "gregory jordan", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove a random consonant, Use first name initial with last name, and Remove a random vowel.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_consonant", + "initial_only_first_name", + "remove_random_vowel" + ], + "rule_descriptions": { + "remove_random_consonant": "Remove a random consonant", + "initial_only_first_name": "Use first name initial with last name", + "remove_random_vowel": "Remove a random vowel" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "daniel ramirez", + "label": "negative", + "script": "latin" + }, + { + "name": "alan alvarez", + "label": "negative", + "script": "latin" + }, + { + "name": "katherine thompson", + "label": "negative", + "script": "latin" + }, + { + "name": "heather wu", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah andrade", + "label": "negative", + "script": "latin" + }, + { + "name": "paula mercado", + "label": "negative", + "script": "latin" + }, + { + "name": "john matthews", + "label": "negative", + "script": "latin" + }, + { + "name": "sara miranda", + "label": "negative", + "script": "latin" + }, + { + "name": "brandon bennett", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer kelly", + "label": "negative", + "script": "latin" + }, + { + "name": "richard montgomery", + "label": "negative", + "script": "latin" + }, + { + "name": "terri gonzalez", + "label": "negative", + "script": "latin" + }, + { + "name": "david brown", + "label": "negative", + "script": "latin" + }, + { + "name": "brian iqbal", + "label": "negative", + "script": "latin" + }, + { + "name": "jared brown", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove a random vowel, and Use first name initial with last name.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_random_vowel", + "initial_only_first_name" + ], + "rule_descriptions": { + "remove_random_vowel": "Remove a random vowel", + "initial_only_first_name": "Use first name initial with last name" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "leah copeland", + "label": "negative", + "script": "latin" + }, + { + "name": "sean garza", + "label": "negative", + "script": "latin" + }, + { + "name": "aaron hancock", + "label": "negative", + "script": "latin" + }, + { + "name": "debra bailey", + "label": "negative", + "script": "latin" + }, + { + "name": "shari o'neill", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley fitzgerald", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher powell", + "label": "negative", + "script": "latin" + }, + { + "name": "neil bradley", + "label": "negative", + "script": "latin" + }, + { + "name": "tiffany frank", + "label": "negative", + "script": "latin" + }, + { + "name": "ben clark", + "label": "negative", + "script": "latin" + }, + { + "name": "danielle smith", + "label": "negative", + "script": "latin" + }, + { + "name": "norman smith", + "label": "negative", + "script": "latin" + }, + { + "name": "randall evans", + "label": "negative", + "script": "latin" + }, + { + "name": "ashley lee", + "label": "negative", + "script": "latin" + }, + { + "name": "autumn green", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title suffix (Jr., PhD, etc.), and Swap adjacent syllables.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_trailing_title", + "swap_adjacent_syllables" + ], + "rule_descriptions": { + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)", + "swap_adjacent_syllables": "Swap adjacent syllables" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "james gordon", + "label": "negative", + "script": "latin" + }, + { + "name": "amanda mcdonald", + "label": "negative", + "script": "latin" + }, + { + "name": "joe cooke", + "label": "negative", + "script": "latin" + }, + { + "name": "jessica fowler", + "label": "negative", + "script": "latin" + }, + { + "name": "jenna klein", + "label": "negative", + "script": "latin" + }, + { + "name": "nicole anderson", + "label": "negative", + "script": "latin" + }, + { + "name": "mohammed anderson", + "label": "negative", + "script": "latin" + }, + { + "name": "brian smith", + "label": "negative", + "script": "latin" + }, + { + "name": "stephen crawford", + "label": "negative", + "script": "latin" + }, + { + "name": "leah mccall", + "label": "negative", + "script": "latin" + }, + { + "name": "william pennington", + "label": "negative", + "script": "latin" + }, + { + "name": "paige moody", + "label": "negative", + "script": "latin" + }, + { + "name": "michael burton", + "label": "negative", + "script": "latin" + }, + { + "name": "tiffany sanders", + "label": "negative", + "script": "latin" + }, + { + "name": "ryan garcia", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap adjacent consonants, Remove all spaces, and Convert name to initials.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_consonants", + "remove_all_spaces", + "shorten_name_to_initials" + ], + "rule_descriptions": { + "swap_adjacent_consonants": "Swap adjacent consonants", + "remove_all_spaces": "Remove all spaces", + "shorten_name_to_initials": "Convert name to initials" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "darren oliver", + "label": "negative", + "script": "latin" + }, + { + "name": "michael bartlett", + "label": "negative", + "script": "latin" + }, + { + "name": "jeanette jenkins", + "label": "negative", + "script": "latin" + }, + { + "name": "jon roberson", + "label": "negative", + "script": "latin" + }, + { + "name": "william browning", + "label": "negative", + "script": "latin" + }, + { + "name": "christy allen", + "label": "negative", + "script": "latin" + }, + { + "name": "nicholas hernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "kathleen o'brien", + "label": "negative", + "script": "latin" + }, + { + "name": "caroline stanley", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin thomas", + "label": "negative", + "script": "latin" + }, + { + "name": "victor larson", + "label": "negative", + "script": "latin" + }, + { + "name": "leslie gutierrez", + "label": "negative", + "script": "latin" + }, + { + "name": "howard navarro", + "label": "negative", + "script": "latin" + }, + { + "name": "richard griffin", + "label": "negative", + "script": "latin" + }, + { + "name": "eleanor mccarthy", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Duplicate a random letter, Replace random vowels with different vowels, and Add a title prefix (Mr., Dr., etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "duplicate_random_letter_as_double_letter", + "replace_random_vowel_with_random_vowel", + "add_random_leading_title" + ], + "rule_descriptions": { + "duplicate_random_letter_as_double_letter": "Duplicate a random letter", + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels", + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "jeremy evans", + "label": "negative", + "script": "latin" + }, + { + "name": "william turner", + "label": "negative", + "script": "latin" + }, + { + "name": "marcus barrett", + "label": "negative", + "script": "latin" + }, + { + "name": "melanie taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "michael barry", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah garcia", + "label": "negative", + "script": "latin" + }, + { + "name": "elizabeth stein", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew williams", + "label": "negative", + "script": "latin" + }, + { + "name": "glen parker", + "label": "negative", + "script": "latin" + }, + { + "name": "abigail frey", + "label": "negative", + "script": "latin" + }, + { + "name": "dean pearson", + "label": "negative", + "script": "latin" + }, + { + "name": "alex gonzalez", + "label": "negative", + "script": "latin" + }, + { + "name": "rachel duran", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin phillips", + "label": "negative", + "script": "latin" + }, + { + "name": "wayne williams", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Reorder name parts, Add a title suffix (Jr., PhD, etc.), and Remove a random vowel.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "name_parts_permutations", + "add_random_trailing_title", + "remove_random_vowel" + ], + "rule_descriptions": { + "name_parts_permutations": "Reorder name parts", + "add_random_trailing_title": "Add a title suffix (Jr., PhD, etc.)", + "remove_random_vowel": "Remove a random vowel" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "andrew pierce", + "label": "negative", + "script": "latin" + }, + { + "name": "megan shah", + "label": "negative", + "script": "latin" + }, + { + "name": "judy diaz", + "label": "negative", + "script": "latin" + }, + { + "name": "john pineda", + "label": "negative", + "script": "latin" + }, + { + "name": "chelsea potts", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie garza", + "label": "negative", + "script": "latin" + }, + { + "name": "william little", + "label": "negative", + "script": "latin" + }, + { + "name": "christian sparks", + "label": "negative", + "script": "latin" + }, + { + "name": "steven lindsey", + "label": "negative", + "script": "latin" + }, + { + "name": "alex moore", + "label": "negative", + "script": "latin" + }, + { + "name": "justin sanders", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa bryant", + "label": "negative", + "script": "latin" + }, + { + "name": "cynthia ruiz", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew hayes", + "label": "negative", + "script": "latin" + }, + { + "name": "spencer harris", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Duplicate a random letter, and Remove all spaces.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "duplicate_random_letter_as_double_letter", + "remove_all_spaces" + ], + "rule_descriptions": { + "duplicate_random_letter_as_double_letter": "Duplicate a random letter", + "remove_all_spaces": "Remove all spaces" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "julie terry", + "label": "negative", + "script": "latin" + }, + { + "name": "dominic hernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "david wright", + "label": "negative", + "script": "latin" + }, + { + "name": "david kramer", + "label": "negative", + "script": "latin" + }, + { + "name": "lindsey davies", + "label": "negative", + "script": "latin" + }, + { + "name": "george martin", + "label": "negative", + "script": "latin" + }, + { + "name": "nicholas mitchell", + "label": "negative", + "script": "latin" + }, + { + "name": "tammie mcdonald", + "label": "negative", + "script": "latin" + }, + { + "name": "zoe taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "michael ritter", + "label": "negative", + "script": "latin" + }, + { + "name": "renee wu", + "label": "negative", + "script": "latin" + }, + { + "name": "justin mendez", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer knight", + "label": "negative", + "script": "latin" + }, + { + "name": "gregory adams", + "label": "negative", + "script": "latin" + }, + { + "name": "patrick smith", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Use first name initial with last name, Convert name to initials, and Remove a random vowel.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "initial_only_first_name", + "shorten_name_to_initials", + "remove_random_vowel" + ], + "rule_descriptions": { + "initial_only_first_name": "Use first name initial with last name", + "shorten_name_to_initials": "Convert name to initials", + "remove_random_vowel": "Remove a random vowel" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "claire schwartz", + "label": "negative", + "script": "latin" + }, + { + "name": "michele holden", + "label": "negative", + "script": "latin" + }, + { + "name": "joshua snyder", + "label": "negative", + "script": "latin" + }, + { + "name": "robert henry", + "label": "negative", + "script": "latin" + }, + { + "name": "lorraine gilmore", + "label": "negative", + "script": "latin" + }, + { + "name": "pamela martinez", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer gray", + "label": "negative", + "script": "latin" + }, + { + "name": "charlie harper", + "label": "negative", + "script": "latin" + }, + { + "name": "troy allen", + "label": "negative", + "script": "latin" + }, + { + "name": "brandy wagner", + "label": "negative", + "script": "latin" + }, + { + "name": "paula reed", + "label": "negative", + "script": "latin" + }, + { + "name": "tracy rosario", + "label": "negative", + "script": "latin" + }, + { + "name": "duncan begum", + "label": "negative", + "script": "latin" + }, + { + "name": "rachel ayers", + "label": "negative", + "script": "latin" + }, + { + "name": "stuart miller", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Swap adjacent syllables.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_syllables" + ], + "rule_descriptions": { + "swap_adjacent_syllables": "Swap adjacent syllables" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "christopher shaw", + "label": "negative", + "script": "latin" + }, + { + "name": "malcolm lang", + "label": "negative", + "script": "latin" + }, + { + "name": "lynn figueroa", + "label": "negative", + "script": "latin" + }, + { + "name": "lauren kim", + "label": "negative", + "script": "latin" + }, + { + "name": "kari elliott", + "label": "negative", + "script": "latin" + }, + { + "name": "catherine barber", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew hooper", + "label": "negative", + "script": "latin" + }, + { + "name": "catherine baker", + "label": "negative", + "script": "latin" + }, + { + "name": "erica smith", + "label": "negative", + "script": "latin" + }, + { + "name": "stephen wilson", + "label": "negative", + "script": "latin" + }, + { + "name": "blake gentry", + "label": "negative", + "script": "latin" + }, + { + "name": "roger myers", + "label": "negative", + "script": "latin" + }, + { + "name": "christine byrd", + "label": "negative", + "script": "latin" + }, + { + "name": "dennis torres", + "label": "negative", + "script": "latin" + }, + { + "name": "robert green", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace double letters with a single letter, and Replace random consonants with different consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_double_letters_with_single_letter", + "replace_random_consonant_with_random_consonant" + ], + "rule_descriptions": { + "replace_double_letters_with_single_letter": "Replace double letters with a single letter", + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "nicholas mcgee", + "label": "negative", + "script": "latin" + }, + { + "name": "rhonda kerr", + "label": "negative", + "script": "latin" + }, + { + "name": "william jones", + "label": "negative", + "script": "latin" + }, + { + "name": "kathleen bass", + "label": "negative", + "script": "latin" + }, + { + "name": "sarah turner", + "label": "negative", + "script": "latin" + }, + { + "name": "jacqueline monroe", + "label": "negative", + "script": "latin" + }, + { + "name": "paul russell", + "label": "negative", + "script": "latin" + }, + { + "name": "dawn hahn", + "label": "negative", + "script": "latin" + }, + { + "name": "stewart coleman", + "label": "negative", + "script": "latin" + }, + { + "name": "gerard weeks", + "label": "negative", + "script": "latin" + }, + { + "name": "abigail o'connor", + "label": "negative", + "script": "latin" + }, + { + "name": "taylor miller", + "label": "negative", + "script": "latin" + }, + { + "name": "brian smith", + "label": "negative", + "script": "latin" + }, + { + "name": "jesse oliver", + "label": "negative", + "script": "latin" + }, + { + "name": "christian cook", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace random vowels with different vowels, Add a title prefix (Mr., Dr., etc.), and Reorder name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_vowel_with_random_vowel", + "add_random_leading_title", + "name_parts_permutations" + ], + "rule_descriptions": { + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels", + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)", + "name_parts_permutations": "Reorder name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "jessica combs", + "label": "negative", + "script": "latin" + }, + { + "name": "taylor taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "autumn cross", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin garza", + "label": "negative", + "script": "latin" + }, + { + "name": "ryan moore", + "label": "negative", + "script": "latin" + }, + { + "name": "erik williams", + "label": "negative", + "script": "latin" + }, + { + "name": "garry bryant", + "label": "negative", + "script": "latin" + }, + { + "name": "peggy alexander", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony murray", + "label": "negative", + "script": "latin" + }, + { + "name": "kent winters", + "label": "negative", + "script": "latin" + }, + { + "name": "sara hicks", + "label": "negative", + "script": "latin" + }, + { + "name": "pauline watts", + "label": "negative", + "script": "latin" + }, + { + "name": "jean thomas", + "label": "negative", + "script": "latin" + }, + { + "name": "brian martinez", + "label": "negative", + "script": "latin" + }, + { + "name": "eleanor harvey", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Swap random adjacent letters, and Replace spaces with special characters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_random_letter", + "replace_spaces_with_random_special_characters" + ], + "rule_descriptions": { + "swap_random_letter": "Swap random adjacent letters", + "replace_spaces_with_random_special_characters": "Replace spaces with special characters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "brett cook", + "label": "negative", + "script": "latin" + }, + { + "name": "james brown", + "label": "negative", + "script": "latin" + }, + { + "name": "denise jenkins", + "label": "negative", + "script": "latin" + }, + { + "name": "malcolm scott", + "label": "negative", + "script": "latin" + }, + { + "name": "brandon patton", + "label": "negative", + "script": "latin" + }, + { + "name": "shane cabrera", + "label": "negative", + "script": "latin" + }, + { + "name": "tyler bradley", + "label": "negative", + "script": "latin" + }, + { + "name": "hayley jones", + "label": "negative", + "script": "latin" + }, + { + "name": "amber horne", + "label": "negative", + "script": "latin" + }, + { + "name": "heather beard", + "label": "negative", + "script": "latin" + }, + { + "name": "sean hunt", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph rogers", + "label": "negative", + "script": "latin" + }, + { + "name": "dorothy cuevas", + "label": "negative", + "script": "latin" + }, + { + "name": "adam larson", + "label": "negative", + "script": "latin" + }, + { + "name": "veronica roth", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Insert a random letter, and Delete a random letter.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "insert_random_letter", + "delete_random_letter" + ], + "rule_descriptions": { + "insert_random_letter": "Insert a random letter", + "delete_random_letter": "Delete a random letter" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "april escobar", + "label": "negative", + "script": "latin" + }, + { + "name": "angela hawkins", + "label": "negative", + "script": "latin" + }, + { + "name": "samuel blair", + "label": "negative", + "script": "latin" + }, + { + "name": "brian shaffer", + "label": "negative", + "script": "latin" + }, + { + "name": "robert sullivan", + "label": "negative", + "script": "latin" + }, + { + "name": "kathryn kelly", + "label": "negative", + "script": "latin" + }, + { + "name": "tina kim", + "label": "negative", + "script": "latin" + }, + { + "name": "gregory phillips", + "label": "negative", + "script": "latin" + }, + { + "name": "renee torres", + "label": "negative", + "script": "latin" + }, + { + "name": "heather shea", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew bryant", + "label": "negative", + "script": "latin" + }, + { + "name": "david roberts", + "label": "negative", + "script": "latin" + }, + { + "name": "arthur castro", + "label": "negative", + "script": "latin" + }, + { + "name": "danielle rose", + "label": "negative", + "script": "latin" + }, + { + "name": "maria king", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace random consonants with different consonants, Duplicate a random letter, and Replace spaces with special characters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_consonant_with_random_consonant", + "duplicate_random_letter_as_double_letter", + "replace_spaces_with_random_special_characters" + ], + "rule_descriptions": { + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants", + "duplicate_random_letter_as_double_letter": "Duplicate a random letter", + "replace_spaces_with_random_special_characters": "Replace spaces with special characters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "david cole", + "label": "negative", + "script": "latin" + }, + { + "name": "kim cook", + "label": "negative", + "script": "latin" + }, + { + "name": "roy cooper", + "label": "negative", + "script": "latin" + }, + { + "name": "debra valencia", + "label": "negative", + "script": "latin" + }, + { + "name": "laura anderson", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa rogers", + "label": "negative", + "script": "latin" + }, + { + "name": "jade anderson", + "label": "negative", + "script": "latin" + }, + { + "name": "bobby torres", + "label": "negative", + "script": "latin" + }, + { + "name": "robin myers", + "label": "negative", + "script": "latin" + }, + { + "name": "theresa aguirre", + "label": "negative", + "script": "latin" + }, + { + "name": "melody hunter", + "label": "negative", + "script": "latin" + }, + { + "name": "lance fleming", + "label": "negative", + "script": "latin" + }, + { + "name": "dalton moore", + "label": "negative", + "script": "latin" + }, + { + "name": "susan moore", + "label": "negative", + "script": "latin" + }, + { + "name": "alex glass", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Abbreviate name parts, and Replace random consonants with different consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_abbreviations", + "replace_random_consonant_with_random_consonant" + ], + "rule_descriptions": { + "shorten_name_to_abbreviations": "Abbreviate name parts", + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "amber navarro", + "label": "negative", + "script": "latin" + }, + { + "name": "eric owen", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph rogers", + "label": "negative", + "script": "latin" + }, + { + "name": "peter williams", + "label": "negative", + "script": "latin" + }, + { + "name": "danielle tran", + "label": "negative", + "script": "latin" + }, + { + "name": "james gray", + "label": "negative", + "script": "latin" + }, + { + "name": "phillip sanchez", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa patterson", + "label": "negative", + "script": "latin" + }, + { + "name": "victoria tran", + "label": "negative", + "script": "latin" + }, + { + "name": "malcolm scott", + "label": "negative", + "script": "latin" + }, + { + "name": "kimberley robinson", + "label": "negative", + "script": "latin" + }, + { + "name": "zoe robinson", + "label": "negative", + "script": "latin" + }, + { + "name": "jose diaz", + "label": "negative", + "script": "latin" + }, + { + "name": "suzanne johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "virginia lynch", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Insert a random letter, Reorder name parts, and Convert name to initials.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "insert_random_letter", + "name_parts_permutations", + "shorten_name_to_initials" + ], + "rule_descriptions": { + "insert_random_letter": "Insert a random letter", + "name_parts_permutations": "Reorder name parts", + "shorten_name_to_initials": "Convert name to initials" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "justin barnett", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph quinn", + "label": "negative", + "script": "latin" + }, + { + "name": "melanie suarez", + "label": "negative", + "script": "latin" + }, + { + "name": "ruth barrett", + "label": "negative", + "script": "latin" + }, + { + "name": "scott ray", + "label": "negative", + "script": "latin" + }, + { + "name": "lynn pratt", + "label": "negative", + "script": "latin" + }, + { + "name": "kelly campbell", + "label": "negative", + "script": "latin" + }, + { + "name": "lacey costa", + "label": "negative", + "script": "latin" + }, + { + "name": "george morales", + "label": "negative", + "script": "latin" + }, + { + "name": "mariah hall", + "label": "negative", + "script": "latin" + }, + { + "name": "shirley bowman", + "label": "negative", + "script": "latin" + }, + { + "name": "james rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "alexander smith", + "label": "negative", + "script": "latin" + }, + { + "name": "ronald allen", + "label": "negative", + "script": "latin" + }, + { + "name": "david harrison", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove all spaces, Remove a random consonant, and Add a title prefix (Mr., Dr., etc.).. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_all_spaces", + "remove_random_consonant", + "add_random_leading_title" + ], + "rule_descriptions": { + "remove_all_spaces": "Remove all spaces", + "remove_random_consonant": "Remove a random consonant", + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "alison taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "tony cooke", + "label": "negative", + "script": "latin" + }, + { + "name": "karen andrade", + "label": "negative", + "script": "latin" + }, + { + "name": "crystal reynolds", + "label": "negative", + "script": "latin" + }, + { + "name": "amelia mccarthy", + "label": "negative", + "script": "latin" + }, + { + "name": "elliot humphries", + "label": "negative", + "script": "latin" + }, + { + "name": "joanne hodge", + "label": "negative", + "script": "latin" + }, + { + "name": "sean price", + "label": "negative", + "script": "latin" + }, + { + "name": "stephanie taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "brandon thompson", + "label": "negative", + "script": "latin" + }, + { + "name": "dale collins", + "label": "negative", + "script": "latin" + }, + { + "name": "felicia burgess", + "label": "negative", + "script": "latin" + }, + { + "name": "tiffany johnston", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew johnson", + "label": "negative", + "script": "latin" + }, + { + "name": "ryan santiago", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Remove all spaces, Replace random consonants with different consonants, and Replace random vowels with different vowels.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "remove_all_spaces", + "replace_random_consonant_with_random_consonant", + "replace_random_vowel_with_random_vowel" + ], + "rule_descriptions": { + "remove_all_spaces": "Remove all spaces", + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants", + "replace_random_vowel_with_random_vowel": "Replace random vowels with different vowels" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "tom davis", + "label": "negative", + "script": "latin" + }, + { + "name": "jamie dyer", + "label": "negative", + "script": "latin" + }, + { + "name": "kristen mason", + "label": "negative", + "script": "latin" + }, + { + "name": "kristen cooper", + "label": "negative", + "script": "latin" + }, + { + "name": "amy hernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "jackie taylor", + "label": "negative", + "script": "latin" + }, + { + "name": "dustin griffin", + "label": "negative", + "script": "latin" + }, + { + "name": "beverly day", + "label": "negative", + "script": "latin" + }, + { + "name": "jeremy fowler", + "label": "negative", + "script": "latin" + }, + { + "name": "casey harris", + "label": "negative", + "script": "latin" + }, + { + "name": "michele harrell", + "label": "negative", + "script": "latin" + }, + { + "name": "caleb lee", + "label": "negative", + "script": "latin" + }, + { + "name": "caleb patrick", + "label": "negative", + "script": "latin" + }, + { + "name": "ellie cochran", + "label": "negative", + "script": "latin" + }, + { + "name": "hannah ibarra", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Insert a random letter, and Swap adjacent syllables.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "insert_random_letter", + "swap_adjacent_syllables" + ], + "rule_descriptions": { + "insert_random_letter": "Insert a random letter", + "swap_adjacent_syllables": "Swap adjacent syllables" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "faith thompson", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa torres", + "label": "negative", + "script": "latin" + }, + { + "name": "ronald pierce", + "label": "negative", + "script": "latin" + }, + { + "name": "stacey rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "alex russell", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin robinson", + "label": "negative", + "script": "latin" + }, + { + "name": "beth hunter", + "label": "negative", + "script": "latin" + }, + { + "name": "scott chan", + "label": "negative", + "script": "latin" + }, + { + "name": "susan edwards", + "label": "negative", + "script": "latin" + }, + { + "name": "james bradshaw", + "label": "negative", + "script": "latin" + }, + { + "name": "robert cox", + "label": "negative", + "script": "latin" + }, + { + "name": "kayla sanderson", + "label": "negative", + "script": "latin" + }, + { + "name": "ebony day", + "label": "negative", + "script": "latin" + }, + { + "name": "brian manning", + "label": "negative", + "script": "latin" + }, + { + "name": "gregory solis", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Convert name to initials, Swap random adjacent letters, and Reorder name parts.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "shorten_name_to_initials", + "swap_random_letter", + "name_parts_permutations" + ], + "rule_descriptions": { + "shorten_name_to_initials": "Convert name to initials", + "swap_random_letter": "Swap random adjacent letters", + "name_parts_permutations": "Reorder name parts" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "jared reyes", + "label": "negative", + "script": "latin" + }, + { + "name": "glenn james", + "label": "negative", + "script": "latin" + }, + { + "name": "chad todd", + "label": "negative", + "script": "latin" + }, + { + "name": "carlos williams", + "label": "negative", + "script": "latin" + }, + { + "name": "jack massey", + "label": "negative", + "script": "latin" + }, + { + "name": "anthony west", + "label": "negative", + "script": "latin" + }, + { + "name": "frances little", + "label": "negative", + "script": "latin" + }, + { + "name": "gail goodwin", + "label": "negative", + "script": "latin" + }, + { + "name": "paul rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin hernandez", + "label": "negative", + "script": "latin" + }, + { + "name": "luis james", + "label": "negative", + "script": "latin" + }, + { + "name": "lindsey stokes", + "label": "negative", + "script": "latin" + }, + { + "name": "judith guerrero", + "label": "negative", + "script": "latin" + }, + { + "name": "matthew calderon", + "label": "negative", + "script": "latin" + }, + { + "name": "alexandra alexander", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Swap random adjacent letters.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_random_letter" + ], + "rule_descriptions": { + "swap_random_letter": "Swap random adjacent letters" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "jorge torres", + "label": "negative", + "script": "latin" + }, + { + "name": "veronica sanchez", + "label": "negative", + "script": "latin" + }, + { + "name": "kirsty jones", + "label": "negative", + "script": "latin" + }, + { + "name": "mohamed coleman", + "label": "negative", + "script": "latin" + }, + { + "name": "vincent wolf", + "label": "negative", + "script": "latin" + }, + { + "name": "samuel morris", + "label": "negative", + "script": "latin" + }, + { + "name": "alyssa miller", + "label": "negative", + "script": "latin" + }, + { + "name": "theresa reed", + "label": "negative", + "script": "latin" + }, + { + "name": "dennis stephens", + "label": "negative", + "script": "latin" + }, + { + "name": "susan miller", + "label": "negative", + "script": "latin" + }, + { + "name": "angela white", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas griffin", + "label": "negative", + "script": "latin" + }, + { + "name": "angela dixon", + "label": "negative", + "script": "latin" + }, + { + "name": "leon molina", + "label": "negative", + "script": "latin" + }, + { + "name": "laura page", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Add a title prefix (Mr., Dr., etc.), and Convert name to initials.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "add_random_leading_title", + "shorten_name_to_initials" + ], + "rule_descriptions": { + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)", + "shorten_name_to_initials": "Convert name to initials" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "emily jones", + "label": "negative", + "script": "latin" + }, + { + "name": "andre griffiths", + "label": "negative", + "script": "latin" + }, + { + "name": "adam rodriguez", + "label": "negative", + "script": "latin" + }, + { + "name": "teresa herrera", + "label": "negative", + "script": "latin" + }, + { + "name": "angela watts", + "label": "negative", + "script": "latin" + }, + { + "name": "kenneth ray", + "label": "negative", + "script": "latin" + }, + { + "name": "bethan pena", + "label": "negative", + "script": "latin" + }, + { + "name": "melissa hebert", + "label": "negative", + "script": "latin" + }, + { + "name": "denise hurley", + "label": "negative", + "script": "latin" + }, + { + "name": "dennis rose", + "label": "negative", + "script": "latin" + }, + { + "name": "steven rivera", + "label": "negative", + "script": "latin" + }, + { + "name": "rachel gentry", + "label": "negative", + "script": "latin" + }, + { + "name": "jeffrey melton", + "label": "negative", + "script": "latin" + }, + { + "name": "david bender", + "label": "negative", + "script": "latin" + }, + { + "name": "emily williams", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that: Swap adjacent consonants.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "swap_adjacent_consonants" + ], + "rule_descriptions": { + "swap_adjacent_consonants": "Swap adjacent consonants" + }, + "percentage": 30 + } + } + }, + { + "seed_identities_with_labels": [ + { + "name": "elijah cole", + "label": "negative", + "script": "latin" + }, + { + "name": "kelly byrne", + "label": "negative", + "script": "latin" + }, + { + "name": "isaiah richardson", + "label": "negative", + "script": "latin" + }, + { + "name": "lisa reed", + "label": "negative", + "script": "latin" + }, + { + "name": "jesse brown", + "label": "negative", + "script": "latin" + }, + { + "name": "katelyn washington", + "label": "negative", + "script": "latin" + }, + { + "name": "thomas williams", + "label": "negative", + "script": "latin" + }, + { + "name": "kevin harding", + "label": "negative", + "script": "latin" + }, + { + "name": "cindy morton", + "label": "negative", + "script": "latin" + }, + { + "name": "craig rogers", + "label": "negative", + "script": "latin" + }, + { + "name": "amy villarreal", + "label": "negative", + "script": "latin" + }, + { + "name": "joseph stewart", + "label": "negative", + "script": "latin" + }, + { + "name": "hollie edwards", + "label": "negative", + "script": "latin" + }, + { + "name": "christopher smith", + "label": "negative", + "script": "latin" + }, + { + "name": "jennifer copeland", + "label": "negative", + "script": "latin" + } + ], + "query_template": "The following name is the seed name to generate variations for: {name}. Generate 15 variations of the name {name}, ensuring phonetic similarity: {'Medium': 0.5}, and orthographic similarity: {'Medium': 0.5}, and also include 30% of variations that follow: Additionally, generate variations that perform these transformations: Replace random consonants with different consonants, Add a title prefix (Mr., Dr., etc.), and Remove a random vowel.. The following address is the seed country/city to generate address variations for: {address}. Generate unique real addresses within the specified country/city for each variation. The following date of birth is the seed DOB to generate variations for: {dob}.\n\n[ADDITIONAL CONTEXT]:\n- Address variations should be realistic addresses within the specified country/city\n- DOB variations ATLEAST one in each category (±1 day, ±3 days, ±30 days, ±90 days, ±365 days, year+month only)\n- Each variation must have a different, realistic address and DOB", + "query_labels": { + "variation_count": 15, + "phonetic_similarity": { + "Medium": 0.5 + }, + "orthographic_similarity": { + "Medium": 0.5 + }, + "rule_based": { + "rule_percentage": 30, + "selected_rules": [ + "replace_random_consonant_with_random_consonant", + "add_random_leading_title", + "remove_random_vowel" + ], + "rule_descriptions": { + "replace_random_consonant_with_random_consonant": "Replace random consonants with different consonants", + "add_random_leading_title": "Add a title prefix (Mr., Dr., etc.)", + "remove_random_vowel": "Remove a random vowel" + }, + "percentage": 30 + } + } + } +] \ No newline at end of file