e2e_structures_v2/records/148.json

{"qid": "148", "dataset": "monaco_dev", "question": "Do the official languages of Ethipoia originate from different liguistic families?", "gold_answers": [true], "n_docs": 7, "n_structures": 9, "docs": [{"doc_id": "2ArKmtynQyf27CjXde92JZjuCvdKBw6kxDQdTdP27rUHA2MfiZBSTdAHNy7XMoqB2deM9ZfbXRApohFiV4RbwPER__7__paragraph__0", "is_supporting": true, "n_structures": 1, "contents": "Languages of Ethiopia\nLanguages of Ethiopia >>> Languages >>> Special status of Amharic\nAmharic has been the official working language of Ethiopian courts and its armed forces, trade and everyday communications since the late 12th century. Although now it is only one of the five official languages of Ethiopia, together with Oromo, Somali, Afar, and Tigrinya – until 2020 Amharic was the only Ethiopian working language of the federal government. Amharic is the most widely spoken and written language in Ethiopia. As of 2018, Amharic was spoken by 31.8 million native speakers in Ethiopia with over 25 million secondary speakers in the nation.", "structures": [{"shape_id": "claim_and_theme_summaries", "description": "Curated claim bundles, thematic summaries, interpretations, notable facts, findings, reception notes, and asserted-property/standout-fact classifications that group entities by a claim rather than by full attribute coverage.", "file": "2ArKmtynQyf27CjXde92JZjuCvdKBw6kxDQdTdP27rUHA2MfiZBSTdAHNy7XMoqB2deM9ZfbXRApohFiV4RbwPER__7__paragraph__0__amharic_special_status_in_ethiopia.jsonl", "format": "jsonl", "content": "{\"entity\":\"Amharic\",\"claim\":\"official_working_language_since\",\"value\":\"Official working language of Ethiopian courts, armed forces, trade, and everyday communications since the late 12th century.\",\"source_doc\":\"2ArKmtynQyf27CjXde92JZjuCvdKBw6kxDQdTdP27rUHA2MfiZBSTdAHNy7XMoqB2deM9ZfbXRApohFiV4RbwPER__7__paragraph__0\"}\n{\"entity\":\"Amharic\",\"claim\":\"federal_working_language_until_2020\",\"value\":\"Until 2020, Amharic was the only Ethiopian working language of the federal government.\",\"source_doc\":\"2ArKmtynQyf27CjXde92JZjuCvdKBw6kxDQdTdP27rUHA2MfiZBSTdAHNy7XMoqB2deM9ZfbXRApohFiV4RbwPER__7__paragraph__0\"}\n{\"entity\":\"Ethiopia\",\"claim\":\"official_languages\",\"value\":\"As of the document context, Ethiopia has five official languages: Amharic, Oromo, Somali, Afar, and Tigrinya.\",\"source_doc\":\"2ArKmtynQyf27CjXde92JZjuCvdKBw6kxDQdTdP27rUHA2MfiZBSTdAHNy7XMoqB2deM9ZfbXRApohFiV4RbwPER__7__paragraph__0\"}\n{\"entity\":\"Amharic\",\"claim\":\"most_widely_spoken_and_written\",\"value\":\"Amharic is the most widely spoken and written language in Ethiopia.\",\"source_doc\":\"2ArKmtynQyf27CjXde92JZjuCvdKBw6kxDQdTdP27rUHA2MfiZBSTdAHNy7XMoqB2deM9ZfbXRApohFiV4RbwPER__7__paragraph__0\"}\n{\"entity\":\"Amharic\",\"claim\":\"native_speakers_2018\",\"value\":\"31.8 million native speakers in Ethiopia as of 2018.\",\"source_doc\":\"2ArKmtynQyf27CjXde92JZjuCvdKBw6kxDQdTdP27rUHA2MfiZBSTdAHNy7XMoqB2deM9ZfbXRApohFiV4RbwPER__7__paragraph__0\"}\n{\"entity\":\"Amharic\",\"claim\":\"secondary_speakers_2018\",\"value\":\"Over 25 million secondary speakers in Ethiopia as of 2018.\",\"source_doc\":\"2ArKmtynQyf27CjXde92JZjuCvdKBw6kxDQdTdP27rUHA2MfiZBSTdAHNy7XMoqB2deM9ZfbXRApohFiV4RbwPER__7__paragraph__0\"}\n"}]}, {"doc_id": "2wH31Pk9d9EWLRKn6EXKCu6KgC9rgeEJUyL3juM5kb9EDqbj7gRez2TnCF5exofqWo1SAra3VjMp8pVMF86mDrmv__0__list__0", "is_supporting": true, "n_structures": 1, "contents": "Ethiopia\n  * Afar : |  Itiyoppiya Federalih Demokrasih Ummuno  \n---|---  \nAmharic : |  የኢትዮጵያ ፌዴራላዊ ዴሞክራሲያዊ ሪፐብሊክ [ a ]  \nOromo : |  Rippabliikii Federaalawaa Dimokraatawaa Itoophiyaa  \nSomali : |  Jamhuuriyadda Dimuqraadiga Federaalka Itoobiya  \nTigrinya : |  ናይኢትዮጵያ ፌዴራላዊ ዴሞክራሲያዊ ሪፐብሊክ [ b ]", "structures": [{"shape_id": "tabular_records", "description": "A CSV grid that normalizes any recurring record-with-attributes pattern in the document into a row-by-column table. The source need not itself be tabular -- the triggering condition is repetition: the document describes two or more instances of the same kind of record (matches, brackets, years, measurements, people, films, organizations, events, ...), each ascribed a recurring set of attributes. Sources span explicit tables, infoboxes, and bullet lists, but also flowing prose -- e.g. a paragraph naming five battles a general fought, a biography listing seven employers with dates, a section enumerating annual award winners. Emit one row per record; columns capture the attributes that recur across records. Skip attributes mentioned for only one record -- they are too sparse to warrant a column. The shape promotes scattered prose facts into a grid the agent can filter and join, even when no grid existed in the source.", "file": "2wH31Pk9d9EWLRKn6EXKCu6KgC9rgeEJUyL3juM5kb9EDqbj7gRez2TnCF5exofqWo1SAra3VjMp8pVMF86mDrmv__0__list__0__ethiopia_official_names_by_language.csv", "format": "csv", "content": "source_doc,entity_text,language_text,name_text\n2wH31Pk9d9EWLRKn6EXKCu6KgC9rgeEJUyL3juM5kb9EDqbj7gRez2TnCF5exofqWo1SAra3VjMp8pVMF86mDrmv__0__list__0,Ethiopia,Afar,Itiyoppiya Federalih Demokrasih Ummuno\n2wH31Pk9d9EWLRKn6EXKCu6KgC9rgeEJUyL3juM5kb9EDqbj7gRez2TnCF5exofqWo1SAra3VjMp8pVMF86mDrmv__0__list__0,Ethiopia,Amharic,የኢትዮጵያ ፌዴራላዊ ዴሞክራሲያዊ ሪፐብሊክ [ a ]\n2wH31Pk9d9EWLRKn6EXKCu6KgC9rgeEJUyL3juM5kb9EDqbj7gRez2TnCF5exofqWo1SAra3VjMp8pVMF86mDrmv__0__list__0,Ethiopia,Oromo,Rippabliikii Federaalawaa Dimokraatawaa Itoophiyaa\n2wH31Pk9d9EWLRKn6EXKCu6KgC9rgeEJUyL3juM5kb9EDqbj7gRez2TnCF5exofqWo1SAra3VjMp8pVMF86mDrmv__0__list__0,Ethiopia,Somali,Jamhuuriyadda Dimuqraadiga Federaalka Itoobiya\n2wH31Pk9d9EWLRKn6EXKCu6KgC9rgeEJUyL3juM5kb9EDqbj7gRez2TnCF5exofqWo1SAra3VjMp8pVMF86mDrmv__0__list__0,Ethiopia,Tigrinya,ናይኢትዮጵያ ፌዴራላዊ ዴሞክራሲያዊ ሪፐብሊክ [ b ]\n"}]}, {"doc_id": "4FX3pTWfxxKbrodWj1AyVUa1EK3E9y4zWR83PyRwPta1bbqvfuPKV3Vds35bsEirsuS25idTXFxHCuVJB3FHbscM__0__paragraph__0", "is_supporting": true, "n_structures": 1, "contents": "Afar language\nAfar (Afar: Qafaraf; also known as 'Afar af, Afaraf, Qafar af) is an Afroasiatic language belonging to the Cushitic branch. It is spoken by the Afar people inhabiting Djibouti, Eritrea and Ethiopia.", "structures": [{"shape_id": "claim_and_theme_summaries", "description": "Curated claim bundles, thematic summaries, interpretations, notable facts, findings, reception notes, and asserted-property/standout-fact classifications that group entities by a claim rather than by full attribute coverage.", "file": "4FX3pTWfxxKbrodWj1AyVUa1EK3E9y4zWR83PyRwPta1bbqvfuPKV3Vds35bsEirsuS25idTXFxHCuVJB3FHbscM__0__paragraph__0__afar_language_core_facts.jsonl", "format": "jsonl", "content": "{\"entity\":\"Afar language\",\"claim\":\"native_name\",\"value\":\"Qafaraf\",\"source_doc\":\"4FX3pTWfxxKbrodWj1AyVUa1EK3E9y4zWR83PyRwPta1bbqvfuPKV3Vds35bsEirsuS25idTXFxHCuVJB3FHbscM__0__paragraph__0\"}\n{\"entity\":\"Afar language\",\"claim\":\"also_known_as\",\"value\":\"'Afar af; Afaraf; Qafar af\",\"source_doc\":\"4FX3pTWfxxKbrodWj1AyVUa1EK3E9y4zWR83PyRwPta1bbqvfuPKV3Vds35bsEirsuS25idTXFxHCuVJB3FHbscM__0__paragraph__0\"}\n{\"entity\":\"Afar language\",\"claim\":\"language_family\",\"value\":\"Afroasiatic language, Cushitic branch\",\"source_doc\":\"4FX3pTWfxxKbrodWj1AyVUa1EK3E9y4zWR83PyRwPta1bbqvfuPKV3Vds35bsEirsuS25idTXFxHCuVJB3FHbscM__0__paragraph__0\"}\n{\"entity\":\"Afar language\",\"claim\":\"spoken_by\",\"value\":\"Afar people\",\"source_doc\":\"4FX3pTWfxxKbrodWj1AyVUa1EK3E9y4zWR83PyRwPta1bbqvfuPKV3Vds35bsEirsuS25idTXFxHCuVJB3FHbscM__0__paragraph__0\"}\n{\"entity\":\"Afar people\",\"claim\":\"inhabit_regions\",\"value\":\"Djibouti; Eritrea; Ethiopia\",\"source_doc\":\"4FX3pTWfxxKbrodWj1AyVUa1EK3E9y4zWR83PyRwPta1bbqvfuPKV3Vds35bsEirsuS25idTXFxHCuVJB3FHbscM__0__paragraph__0\"}\n"}]}, {"doc_id": "Q6pyEXYgZKRRhVbaBDhYLsaien9iJYKnurKsNx2CmRYvbCqPrFr9iS3HsyZbrJTZ2TVPKcLDTwPc3nfHeK6a6DC__0__infobox__0", "is_supporting": true, "n_structures": 2, "contents": "Tigrinya language\n\n## Tigrinya\n\n### ትግርኛ (Təgrəñña)\nPronunciation : [tɨɡrɨɲːä] ⓘ\nNative to : Eritrea, Ethiopia\nEthnicity :\nTigrayans  \nTigrinya\nNative speakers : 9.7 million (2022)\nLanguage family :\nAfro-Asiatic\n\n  * Semitic \n    * West Semitic \n      * South Semitic \n        * Ethiopic \n          * North \n            * Tigrinya\nWriting system : Geʽez script (Tigrinya alphabet)\n\n## Official status\nOfficial language in :\nEritrea  \nEthiopia\n\n## Language codes\nISO 639-1 : `ti`\nISO 639-2 : `tir`\nISO 639-3 : `tir`\nGlottolog : `tigr1271`\nCountries where Tigrinya holds official status: Eritrea Ethiopia\n\n---\nThis article contains IPA phonetic symbols. Without proper rendering support, you may see question marks, boxes, or other symbols instead of Unicode characters. For an introductory guide on IPA symbols, see Help:IPA.", "structures": [{"shape_id": "claim_and_theme_summaries", "description": "Curated claim bundles, thematic summaries, interpretations, notable facts, findings, reception notes, and asserted-property/standout-fact classifications that group entities by a claim rather than by full attribute coverage.", "file": "Q6pyEXYgZKRRhVbaBDhYLsaien9iJYKnurKsNx2CmRYvbCqPrFr9iS3HsyZbrJTZ2TVPKcLDTwPc3nfHeK6a6DC__0__infobox__0__tigrinya_language_infobox_claims.jsonl", "format": "jsonl", "content": "{\"entity\":\"Tigrinya language\",\"claim\":\"native_name\",\"value\":\"ትግርኛ (Təgrəñña)\",\"source_doc\":\"Q6pyEXYgZKRRhVbaBDhYLsaien9iJYKnurKsNx2CmRYvbCqPrFr9iS3HsyZbrJTZ2TVPKcLDTwPc3nfHeK6a6DC__0__infobox__0\"}\n{\"entity\":\"Tigrinya language\",\"claim\":\"pronunciation\",\"value\":\"[tɨɡrɨɲːä]\",\"source_doc\":\"Q6pyEXYgZKRRhVbaBDhYLsaien9iJYKnurKsNx2CmRYvbCqPrFr9iS3HsyZbrJTZ2TVPKcLDTwPc3nfHeK6a6DC__0__infobox__0\"}\n{\"entity\":\"Tigrinya language\",\"claim\":\"native_speakers\",\"value\":\"9.7 million (2022)\",\"source_doc\":\"Q6pyEXYgZKRRhVbaBDhYLsaien9iJYKnurKsNx2CmRYvbCqPrFr9iS3HsyZbrJTZ2TVPKcLDTwPc3nfHeK6a6DC__0__infobox__0\"}\n{\"entity\":\"Tigrinya language\",\"claim\":\"iso_639_1\",\"value\":\"ti\",\"source_doc\":\"Q6pyEXYgZKRRhVbaBDhYLsaien9iJYKnurKsNx2CmRYvbCqPrFr9iS3HsyZbrJTZ2TVPKcLDTwPc3nfHeK6a6DC__0__infobox__0\"}\n{\"entity\":\"Tigrinya language\",\"claim\":\"iso_639_2\",\"value\":\"tir\",\"source_doc\":\"Q6pyEXYgZKRRhVbaBDhYLsaien9iJYKnurKsNx2CmRYvbCqPrFr9iS3HsyZbrJTZ2TVPKcLDTwPc3nfHeK6a6DC__0__infobox__0\"}\n{\"entity\":\"Tigrinya language\",\"claim\":\"iso_639_3\",\"value\":\"tir\",\"source_doc\":\"Q6pyEXYgZKRRhVbaBDhYLsaien9iJYKnurKsNx2CmRYvbCqPrFr9iS3HsyZbrJTZ2TVPKcLDTwPc3nfHeK6a6DC__0__infobox__0\"}\n{\"entity\":\"Tigrinya language\",\"claim\":\"glottolog_code\",\"value\":\"tigr1271\",\"source_doc\":\"Q6pyEXYgZKRRhVbaBDhYLsaien9iJYKnurKsNx2CmRYvbCqPrFr9iS3HsyZbrJTZ2TVPKcLDTwPc3nfHeK6a6DC__0__infobox__0\"}\n{\"entity\":\"Article\",\"claim\":\"ipa_rendering_note\",\"value\":\"Contains IPA phonetic symbols; without rendering support, users may see question marks, boxes, or other symbols instead of Unicode characters; Help:IPA is suggested for an introductory guide.\",\"source_doc\":\"Q6pyEXYgZKRRhVbaBDhYLsaien9iJYKnurKsNx2CmRYvbCqPrFr9iS3HsyZbrJTZ2TVPKcLDTwPc3nfHeK6a6DC__0__infobox__0\"}\n"}, {"shape_id": "relation_graphs_and_mappings", "description": "Artifacts whose main value is explicit links among entities: triples, affiliations, succession, memberships, adaptations, ownership, cast-role mappings, collaborations, reverse relation lookups, and tupleized fact maps (mini knowledge graphs).", "file": "Q6pyEXYgZKRRhVbaBDhYLsaien9iJYKnurKsNx2CmRYvbCqPrFr9iS3HsyZbrJTZ2TVPKcLDTwPc3nfHeK6a6DC__0__infobox__0__tigrinya_language_entity_relations.edges.jsonl", "format": "jsonl", "content": "{\"head\":\"Tigrinya language\",\"relation\":\"native_to\",\"tail\":\"Eritrea\",\"source_doc\":\"Q6pyEXYgZKRRhVbaBDhYLsaien9iJYKnurKsNx2CmRYvbCqPrFr9iS3HsyZbrJTZ2TVPKcLDTwPc3nfHeK6a6DC__0__infobox__0\"}\n{\"head\":\"Tigrinya language\",\"relation\":\"native_to\",\"tail\":\"Ethiopia\",\"source_doc\":\"Q6pyEXYgZKRRhVbaBDhYLsaien9iJYKnurKsNx2CmRYvbCqPrFr9iS3HsyZbrJTZ2TVPKcLDTwPc3nfHeK6a6DC__0__infobox__0\"}\n{\"head\":\"Tigrinya language\",\"relation\":\"associated_ethnicity\",\"tail\":\"Tigrayans\",\"source_doc\":\"Q6pyEXYgZKRRhVbaBDhYLsaien9iJYKnurKsNx2CmRYvbCqPrFr9iS3HsyZbrJTZ2TVPKcLDTwPc3nfHeK6a6DC__0__infobox__0\"}\n{\"head\":\"Tigrinya language\",\"relation\":\"associated_ethnicity\",\"tail\":\"Tigrinya\",\"source_doc\":\"Q6pyEXYgZKRRhVbaBDhYLsaien9iJYKnurKsNx2CmRYvbCqPrFr9iS3HsyZbrJTZ2TVPKcLDTwPc3nfHeK6a6DC__0__infobox__0\"}\n{\"head\":\"Tigrinya language\",\"relation\":\"uses_writing_system\",\"tail\":\"Geʽez script (Tigrinya alphabet)\",\"source_doc\":\"Q6pyEXYgZKRRhVbaBDhYLsaien9iJYKnurKsNx2CmRYvbCqPrFr9iS3HsyZbrJTZ2TVPKcLDTwPc3nfHeK6a6DC__0__infobox__0\"}\n{\"head\":\"Tigrinya language\",\"relation\":\"official_language_in\",\"tail\":\"Eritrea\",\"source_doc\":\"Q6pyEXYgZKRRhVbaBDhYLsaien9iJYKnurKsNx2CmRYvbCqPrFr9iS3HsyZbrJTZ2TVPKcLDTwPc3nfHeK6a6DC__0__infobox__0\"}\n{\"head\":\"Tigrinya language\",\"relation\":\"official_language_in\",\"tail\":\"Ethiopia\",\"source_doc\":\"Q6pyEXYgZKRRhVbaBDhYLsaien9iJYKnurKsNx2CmRYvbCqPrFr9iS3HsyZbrJTZ2TVPKcLDTwPc3nfHeK6a6DC__0__infobox__0\"}\n{\"head\":\"Tigrinya language\",\"relation\":\"language_family\",\"tail\":\"Afro-Asiatic > Semitic > West Semitic > South Semitic > Ethiopic > North > Tigrinya\",\"source_doc\":\"Q6pyEXYgZKRRhVbaBDhYLsaien9iJYKnurKsNx2CmRYvbCqPrFr9iS3HsyZbrJTZ2TVPKcLDTwPc3nfHeK6a6DC__0__infobox__0\"}\n"}]}, {"doc_id": "2szDJTgvTbMownArZhYfrEvoTemM59JuxJauREJrq9kYYo3M2GfMpb6pM9Px5KWvXXyLg3mpN7kn6kfeCb9GTbMa__0__infobox__0", "is_supporting": true, "n_structures": 2, "contents": "Oromo language\n\n## Oromo\n\n### Afaan Oromoo\nPronunciation : /ˈɒrəmoʊ/ or /ɔːˈroʊmoʊ/\nNative to : Ethiopia, Kenya, Somalia\nRegion : Oromia\nEthnicity : Oromo\nNative speakers : 45.5 million (all countries) (2019–2024)\nLanguage family :\nAfro-Asiatic\n\n  * Cushitic \n    * East \n      * Lowland \n        * Oromoid \n          * Oromo\nWriting system :\n  * Latin (Qubee, Oromo alphabet)\n  * Qubee Sheek Bakrii Saphaloo\n\n## Official status\nOfficial language in : Ethiopia\nRecognised minority language in : Kenya\n\n## Language codes\nISO 639-1 : `om`\nISO 639-2 : `orm`\nISO 639-3 :\n`orm` – inclusive code  \nIndividual codes:  \n`gax` – Borana–Arsi–Guji Oromo  \n`hae` – Eastern Oromo  \n`orc` – Orma  \n`gaz` – West Central Oromo  \n`ssn` – Waata\nGlottolog : `nucl1736`\nAreas in East Africa where Oromo is spoken\n\n---\nThis article contains IPA phonetic symbols. Without proper rendering support, you may see question marks, boxes, or other symbols instead of Unicode characters. For an introductory guide on IPA symbols, see Help:IPA.", "structures": [{"shape_id": "tabular_records", "description": "A CSV grid that normalizes any recurring record-with-attributes pattern in the document into a row-by-column table. The source need not itself be tabular -- the triggering condition is repetition: the document describes two or more instances of the same kind of record (matches, brackets, years, measurements, people, films, organizations, events, ...), each ascribed a recurring set of attributes. Sources span explicit tables, infoboxes, and bullet lists, but also flowing prose -- e.g. a paragraph naming five battles a general fought, a biography listing seven employers with dates, a section enumerating annual award winners. Emit one row per record; columns capture the attributes that recur across records. Skip attributes mentioned for only one record -- they are too sparse to warrant a column. The shape promotes scattered prose facts into a grid the agent can filter and join, even when no grid existed in the source.", "file": "2szDJTgvTbMownArZhYfrEvoTemM59JuxJauREJrq9kYYo3M2GfMpb6pM9Px5KWvXXyLg3mpN7kn6kfeCb9GTbMa__0__infobox__0__oromo_language_codes.csv", "format": "csv", "content": "source_doc,code_system_text,code_text,scope_or_variety_text\n2szDJTgvTbMownArZhYfrEvoTemM59JuxJauREJrq9kYYo3M2GfMpb6pM9Px5KWvXXyLg3mpN7kn6kfeCb9GTbMa__0__infobox__0,ISO 639-1,om,Oromo\n2szDJTgvTbMownArZhYfrEvoTemM59JuxJauREJrq9kYYo3M2GfMpb6pM9Px5KWvXXyLg3mpN7kn6kfeCb9GTbMa__0__infobox__0,ISO 639-2,orm,Oromo\n2szDJTgvTbMownArZhYfrEvoTemM59JuxJauREJrq9kYYo3M2GfMpb6pM9Px5KWvXXyLg3mpN7kn6kfeCb9GTbMa__0__infobox__0,ISO 639-3,orm,inclusive code\n2szDJTgvTbMownArZhYfrEvoTemM59JuxJauREJrq9kYYo3M2GfMpb6pM9Px5KWvXXyLg3mpN7kn6kfeCb9GTbMa__0__infobox__0,ISO 639-3,gax,Borana–Arsi–Guji Oromo\n2szDJTgvTbMownArZhYfrEvoTemM59JuxJauREJrq9kYYo3M2GfMpb6pM9Px5KWvXXyLg3mpN7kn6kfeCb9GTbMa__0__infobox__0,ISO 639-3,hae,Eastern Oromo\n2szDJTgvTbMownArZhYfrEvoTemM59JuxJauREJrq9kYYo3M2GfMpb6pM9Px5KWvXXyLg3mpN7kn6kfeCb9GTbMa__0__infobox__0,ISO 639-3,orc,Orma\n2szDJTgvTbMownArZhYfrEvoTemM59JuxJauREJrq9kYYo3M2GfMpb6pM9Px5KWvXXyLg3mpN7kn6kfeCb9GTbMa__0__infobox__0,ISO 639-3,gaz,West Central Oromo\n2szDJTgvTbMownArZhYfrEvoTemM59JuxJauREJrq9kYYo3M2GfMpb6pM9Px5KWvXXyLg3mpN7kn6kfeCb9GTbMa__0__infobox__0,ISO 639-3,ssn,Waata\n2szDJTgvTbMownArZhYfrEvoTemM59JuxJauREJrq9kYYo3M2GfMpb6pM9Px5KWvXXyLg3mpN7kn6kfeCb9GTbMa__0__infobox__0,Glottolog,nucl1736,Oromo\n"}, {"shape_id": "claim_and_theme_summaries", "description": "Curated claim bundles, thematic summaries, interpretations, notable facts, findings, reception notes, and asserted-property/standout-fact classifications that group entities by a claim rather than by full attribute coverage.", "file": "2szDJTgvTbMownArZhYfrEvoTemM59JuxJauREJrq9kYYo3M2GfMpb6pM9Px5KWvXXyLg3mpN7kn6kfeCb9GTbMa__0__infobox__0__oromo_language_infobox_facts.jsonl", "format": "jsonl", "content": "{\"entity\":\"Oromo language\",\"claim\":\"native_name\",\"value\":\"Afaan Oromoo\",\"source_doc\":\"2szDJTgvTbMownArZhYfrEvoTemM59JuxJauREJrq9kYYo3M2GfMpb6pM9Px5KWvXXyLg3mpN7kn6kfeCb9GTbMa__0__infobox__0\"}\n{\"entity\":\"Oromo language\",\"claim\":\"pronunciation\",\"value\":\"/ˈɒrəmoʊ/ or /ɔːˈroʊmoʊ/\",\"source_doc\":\"2szDJTgvTbMownArZhYfrEvoTemM59JuxJauREJrq9kYYo3M2GfMpb6pM9Px5KWvXXyLg3mpN7kn6kfeCb9GTbMa__0__infobox__0\"}\n{\"entity\":\"Oromo language\",\"claim\":\"native_to\",\"value\":\"Ethiopia, Kenya, Somalia\",\"source_doc\":\"2szDJTgvTbMownArZhYfrEvoTemM59JuxJauREJrq9kYYo3M2GfMpb6pM9Px5KWvXXyLg3mpN7kn6kfeCb9GTbMa__0__infobox__0\"}\n{\"entity\":\"Oromo language\",\"claim\":\"region\",\"value\":\"Oromia\",\"source_doc\":\"2szDJTgvTbMownArZhYfrEvoTemM59JuxJauREJrq9kYYo3M2GfMpb6pM9Px5KWvXXyLg3mpN7kn6kfeCb9GTbMa__0__infobox__0\"}\n{\"entity\":\"Oromo language\",\"claim\":\"ethnicity\",\"value\":\"Oromo\",\"source_doc\":\"2szDJTgvTbMownArZhYfrEvoTemM59JuxJauREJrq9kYYo3M2GfMpb6pM9Px5KWvXXyLg3mpN7kn6kfeCb9GTbMa__0__infobox__0\"}\n{\"entity\":\"Oromo language\",\"claim\":\"native_speakers\",\"value\":\"45.5 million in all countries (2019–2024)\",\"source_doc\":\"2szDJTgvTbMownArZhYfrEvoTemM59JuxJauREJrq9kYYo3M2GfMpb6pM9Px5KWvXXyLg3mpN7kn6kfeCb9GTbMa__0__infobox__0\"}\n{\"entity\":\"Oromo language\",\"claim\":\"language_family\",\"value\":\"Afro-Asiatic > Cushitic > East > Lowland > Oromoid > Oromo\",\"source_doc\":\"2szDJTgvTbMownArZhYfrEvoTemM59JuxJauREJrq9kYYo3M2GfMpb6pM9Px5KWvXXyLg3mpN7kn6kfeCb9GTbMa__0__infobox__0\"}\n{\"entity\":\"Oromo language\",\"claim\":\"writing_system\",\"value\":\"Latin (Qubee, Oromo alphabet); Qubee Sheek Bakrii Saphaloo\",\"source_doc\":\"2szDJTgvTbMownArZhYfrEvoTemM59JuxJauREJrq9kYYo3M2GfMpb6pM9Px5KWvXXyLg3mpN7kn6kfeCb9GTbMa__0__infobox__0\"}\n{\"entity\":\"Oromo language\",\"claim\":\"official_language_in\",\"value\":\"Ethiopia\",\"source_doc\":\"2szDJTgvTbMownArZhYfrEvoTemM59JuxJauREJrq9kYYo3M2GfMpb6pM9Px5KWvXXyLg3mpN7kn6kfeCb9GTbMa__0__infobox__0\"}\n{\"entity\":\"Oromo language\",\"claim\":\"recognised_minority_language_in\",\"value\":\"Kenya\",\"source_doc\":\"2szDJTgvTbMownArZhYfrEvoTemM59JuxJauREJrq9kYYo3M2GfMpb6pM9Px5KWvXXyLg3mpN7kn6kfeCb9GTbMa__0__infobox__0\"}\n{\"entity\":\"Oromo language\",\"claim\":\"spoken_area_note\",\"value\":\"Areas in East Africa where Oromo is spoken\",\"source_doc\":\"2szDJTgvTbMownArZhYfrEvoTemM59JuxJauREJrq9kYYo3M2GfMpb6pM9Px5KWvXXyLg3mpN7kn6kfeCb9GTbMa__0__infobox__0\"}\n"}]}, {"doc_id": "5D4hYyqN8ZAzeCVs8WNL8kP5r14e3uJhbJ1hgjBV5gLcQeQQE7inYmNPv79FionHicVhNEWbP51ED799or8eMK6B__0__paragraph__0", "is_supporting": true, "n_structures": 1, "contents": "Amharic\nAmharic (/æmˈhærɪk/ am-HARR-ik or /ɑːmˈhɑːrɪk/ ahm-HAR-ik; native name: አማርኛ, romanized: Amarəñña, IPA: [amarɨɲːa] i) is an Ethiopian Semitic language, which is a subgrouping within the Semitic branch of the Afroasiatic languages. It is spoken as a first language by the Amharas, and also serves as a lingua franca for all other populations residing in major cities and towns in Ethiopia.", "structures": [{"shape_id": "claim_and_theme_summaries", "description": "Curated claim bundles, thematic summaries, interpretations, notable facts, findings, reception notes, and asserted-property/standout-fact classifications that group entities by a claim rather than by full attribute coverage.", "file": "5D4hYyqN8ZAzeCVs8WNL8kP5r14e3uJhbJ1hgjBV5gLcQeQQE7inYmNPv79FionHicVhNEWbP51ED799or8eMK6B__0__paragraph__0__amharic_language_core_facts.jsonl", "format": "jsonl", "content": "{\"entity\":\"Amharic\",\"claim\":\"english_pronunciations\",\"value\":\"/æmˈhærɪk/ am-HARR-ik; /ɑːmˈhɑːrɪk/ ahm-HAR-ik\",\"source_doc\":\"5D4hYyqN8ZAzeCVs8WNL8kP5r14e3uJhbJ1hgjBV5gLcQeQQE7inYmNPv79FionHicVhNEWbP51ED799or8eMK6B__0__paragraph__0\"}\n{\"entity\":\"Amharic\",\"claim\":\"native_name\",\"value\":\"አማርኛ\",\"source_doc\":\"5D4hYyqN8ZAzeCVs8WNL8kP5r14e3uJhbJ1hgjBV5gLcQeQQE7inYmNPv79FionHicVhNEWbP51ED799or8eMK6B__0__paragraph__0\"}\n{\"entity\":\"Amharic\",\"claim\":\"native_name_romanization\",\"value\":\"Amarəñña\",\"source_doc\":\"5D4hYyqN8ZAzeCVs8WNL8kP5r14e3uJhbJ1hgjBV5gLcQeQQE7inYmNPv79FionHicVhNEWbP51ED799or8eMK6B__0__paragraph__0\"}\n{\"entity\":\"Amharic\",\"claim\":\"native_name_ipa\",\"value\":\"[amarɨɲːa]\",\"source_doc\":\"5D4hYyqN8ZAzeCVs8WNL8kP5r14e3uJhbJ1hgjBV5gLcQeQQE7inYmNPv79FionHicVhNEWbP51ED799or8eMK6B__0__paragraph__0\"}\n{\"entity\":\"Amharic\",\"claim\":\"language_classification\",\"value\":\"An Ethiopian Semitic language, a subgrouping within the Semitic branch of the Afroasiatic languages\",\"source_doc\":\"5D4hYyqN8ZAzeCVs8WNL8kP5r14e3uJhbJ1hgjBV5gLcQeQQE7inYmNPv79FionHicVhNEWbP51ED799or8eMK6B__0__paragraph__0\"}\n{\"entity\":\"Amharic\",\"claim\":\"first_language_speakers\",\"value\":\"Spoken as a first language by the Amharas\",\"source_doc\":\"5D4hYyqN8ZAzeCVs8WNL8kP5r14e3uJhbJ1hgjBV5gLcQeQQE7inYmNPv79FionHicVhNEWbP51ED799or8eMK6B__0__paragraph__0\"}\n{\"entity\":\"Amharic\",\"claim\":\"lingua_franca_role\",\"value\":\"Serves as a lingua franca for all other populations residing in major cities and towns in Ethiopia\",\"source_doc\":\"5D4hYyqN8ZAzeCVs8WNL8kP5r14e3uJhbJ1hgjBV5gLcQeQQE7inYmNPv79FionHicVhNEWbP51ED799or8eMK6B__0__paragraph__0\"}\n"}]}, {"doc_id": "5Ja2BY9LEcJBJCvfSb9XVqCJCTmbLoSdcYH7cRK3jMkgdSNh6y7TeGUVVphwhF18XWtSrHqG53YfxX4Mjx4RYj7Y__0__infobox__0", "is_supporting": true, "n_structures": 1, "contents": "Somali language\n\n## Somali\n\n### Af Soomaali, Soomaali 𐒖𐒍 𐒈𐒝𐒑𐒛𐒐𐒘, 𐒈𐒝𐒑𐒛𐒐𐒘 اف صومالِ, صومالِ,\nPronunciation : [af soːmaːli]\nRegion : Horn of Africa\nEthnicity : Somalis\nNative speakers : 24 million (2019–2023)\nLanguage family :\nAfro-Asiatic\n\n  * Cushitic \n    * Lowland East \n      * Macro-Somali \n        * Somali languages \n          * Somali\nDialects :\n  * Northern\n  * Benadiri\n  * Ashraf\nWriting system :\nSomali Latin alphabet (Latin script; official)  \nWadaad's writing (Arabic script)  \nOsmanya alphabet  \nBorama alphabet  \nKaddare alphabet\n\n## Official status\nOfficial language in :\nSomalia  \nSomaliland  \nDjibouti  \nEthiopia\nRecognised minority language in : Kenya\nRegulated by : Regional Somali Language Academy\n\n## Language codes\nISO 639-1 : `so`\nISO 639-2 : `som`\nISO 639-3 : `som`\nGlottolog : `soma1255`\nLinguasphere : `14-GAG-a`\nPrimary Somali Sprachraum\n\n---\nThis article contains IPA phonetic symbols. Without proper rendering support, you may see question marks, boxes, or other symbols instead of Unicode characters. For an introductory guide on IPA symbols, see Help:IPA.", "structures": [{"shape_id": "tabular_records", "description": "A CSV grid that normalizes any recurring record-with-attributes pattern in the document into a row-by-column table. The source need not itself be tabular -- the triggering condition is repetition: the document describes two or more instances of the same kind of record (matches, brackets, years, measurements, people, films, organizations, events, ...), each ascribed a recurring set of attributes. Sources span explicit tables, infoboxes, and bullet lists, but also flowing prose -- e.g. a paragraph naming five battles a general fought, a biography listing seven employers with dates, a section enumerating annual award winners. Emit one row per record; columns capture the attributes that recur across records. Skip attributes mentioned for only one record -- they are too sparse to warrant a column. The shape promotes scattered prose facts into a grid the agent can filter and join, even when no grid existed in the source.", "file": "5Ja2BY9LEcJBJCvfSb9XVqCJCTmbLoSdcYH7cRK3jMkgdSNh6y7TeGUVVphwhF18XWtSrHqG53YfxX4Mjx4RYj7Y__0__infobox__0__somali_language_infobox_records.csv", "format": "csv", "content": "source_doc,record_type,field_name,value\n5Ja2BY9LEcJBJCvfSb9XVqCJCTmbLoSdcYH7cRK3jMkgdSNh6y7TeGUVVphwhF18XWtSrHqG53YfxX4Mjx4RYj7Y__0__infobox__0,language_name,english,Somali\n5Ja2BY9LEcJBJCvfSb9XVqCJCTmbLoSdcYH7cRK3jMkgdSNh6y7TeGUVVphwhF18XWtSrHqG53YfxX4Mjx4RYj7Y__0__infobox__0,language_name,endonym,\"Af Soomaali, Soomaali\"\n5Ja2BY9LEcJBJCvfSb9XVqCJCTmbLoSdcYH7cRK3jMkgdSNh6y7TeGUVVphwhF18XWtSrHqG53YfxX4Mjx4RYj7Y__0__infobox__0,language_name,osmanya,\"𐒖𐒍 𐒈𐒝𐒑𐒛𐒐𐒘, 𐒈𐒝𐒑𐒛𐒐𐒘\"\n5Ja2BY9LEcJBJCvfSb9XVqCJCTmbLoSdcYH7cRK3jMkgdSNh6y7TeGUVVphwhF18XWtSrHqG53YfxX4Mjx4RYj7Y__0__infobox__0,language_name,arabic_script,\"اف صومالِ, صومالِ\"\n5Ja2BY9LEcJBJCvfSb9XVqCJCTmbLoSdcYH7cRK3jMkgdSNh6y7TeGUVVphwhF18XWtSrHqG53YfxX4Mjx4RYj7Y__0__infobox__0,pronunciation,ipa,[af soːmaːli]\n5Ja2BY9LEcJBJCvfSb9XVqCJCTmbLoSdcYH7cRK3jMkgdSNh6y7TeGUVVphwhF18XWtSrHqG53YfxX4Mjx4RYj7Y__0__infobox__0,region,spoken_region,Horn of Africa\n5Ja2BY9LEcJBJCvfSb9XVqCJCTmbLoSdcYH7cRK3jMkgdSNh6y7TeGUVVphwhF18XWtSrHqG53YfxX4Mjx4RYj7Y__0__infobox__0,ethnicity,associated_ethnicity,Somalis\n5Ja2BY9LEcJBJCvfSb9XVqCJCTmbLoSdcYH7cRK3jMkgdSNh6y7TeGUVVphwhF18XWtSrHqG53YfxX4Mjx4RYj7Y__0__infobox__0,native_speakers,count_and_period,24 million (2019–2023)\n5Ja2BY9LEcJBJCvfSb9XVqCJCTmbLoSdcYH7cRK3jMkgdSNh6y7TeGUVVphwhF18XWtSrHqG53YfxX4Mjx4RYj7Y__0__infobox__0,language_family,level_1,Afro-Asiatic\n5Ja2BY9LEcJBJCvfSb9XVqCJCTmbLoSdcYH7cRK3jMkgdSNh6y7TeGUVVphwhF18XWtSrHqG53YfxX4Mjx4RYj7Y__0__infobox__0,language_family,level_2,Cushitic\n5Ja2BY9LEcJBJCvfSb9XVqCJCTmbLoSdcYH7cRK3jMkgdSNh6y7TeGUVVphwhF18XWtSrHqG53YfxX4Mjx4RYj7Y__0__infobox__0,language_family,level_3,Lowland East\n5Ja2BY9LEcJBJCvfSb9XVqCJCTmbLoSdcYH7cRK3jMkgdSNh6y7TeGUVVphwhF18XWtSrHqG53YfxX4Mjx4RYj7Y__0__infobox__0,language_family,level_4,Macro-Somali\n5Ja2BY9LEcJBJCvfSb9XVqCJCTmbLoSdcYH7cRK3jMkgdSNh6y7TeGUVVphwhF18XWtSrHqG53YfxX4Mjx4RYj7Y__0__infobox__0,language_family,level_5,Somali languages\n5Ja2BY9LEcJBJCvfSb9XVqCJCTmbLoSdcYH7cRK3jMkgdSNh6y7TeGUVVphwhF18XWtSrHqG53YfxX4Mjx4RYj7Y__0__infobox__0,language_family,level_6,Somali\n5Ja2BY9LEcJBJCvfSb9XVqCJCTmbLoSdcYH7cRK3jMkgdSNh6y7TeGUVVphwhF18XWtSrHqG53YfxX4Mjx4RYj7Y__0__infobox__0,dialect,name,Northern\n5Ja2BY9LEcJBJCvfSb9XVqCJCTmbLoSdcYH7cRK3jMkgdSNh6y7TeGUVVphwhF18XWtSrHqG53YfxX4Mjx4RYj7Y__0__infobox__0,dialect,name,Benadiri\n5Ja2BY9LEcJBJCvfSb9XVqCJCTmbLoSdcYH7cRK3jMkgdSNh6y7TeGUVVphwhF18XWtSrHqG53YfxX4Mjx4RYj7Y__0__infobox__0,dialect,name,Ashraf\n5Ja2BY9LEcJBJCvfSb9XVqCJCTmbLoSdcYH7cRK3jMkgdSNh6y7TeGUVVphwhF18XWtSrHqG53YfxX4Mjx4RYj7Y__0__infobox__0,writing_system,name,Somali Latin alphabet (Latin script; official)\n5Ja2BY9LEcJBJCvfSb9XVqCJCTmbLoSdcYH7cRK3jMkgdSNh6y7TeGUVVphwhF18XWtSrHqG53YfxX4Mjx4RYj7Y__0__infobox__0,writing_system,name,Wadaad's writing (Arabic script)\n5Ja2BY9LEcJBJCvfSb9XVqCJCTmbLoSdcYH7cRK3jMkgdSNh6y7TeGUVVphwhF18XWtSrHqG53YfxX4Mjx4RYj7Y__0__infobox__0,writing_system,name,Osmanya alphabet\n5Ja2BY9LEcJBJCvfSb9XVqCJCTmbLoSdcYH7cRK3jMkgdSNh6y7TeGUVVphwhF18XWtSrHqG53YfxX4Mjx4RYj7Y__0__infobox__0,writing_system,name,Borama alphabet\n5Ja2BY9LEcJBJCvfSb9XVqCJCTmbLoSdcYH7cRK3jMkgdSNh6y7TeGUVVphwhF18XWtSrHqG53YfxX4Mjx4RYj7Y__0__infobox__0,writing_system,name,Kaddare alphabet\n5Ja2BY9LEcJBJCvfSb9XVqCJCTmbLoSdcYH7cRK3jMkgdSNh6y7TeGUVVphwhF18XWtSrHqG53YfxX4Mjx4RYj7Y__0__infobox__0,official_status,official_language_in,Somalia\n5Ja2BY9LEcJBJCvfSb9XVqCJCTmbLoSdcYH7cRK3jMkgdSNh6y7TeGUVVphwhF18XWtSrHqG53YfxX4Mjx4RYj7Y__0__infobox__0,official_status,official_language_in,Somaliland\n5Ja2BY9LEcJBJCvfSb9XVqCJCTmbLoSdcYH7cRK3jMkgdSNh6y7TeGUVVphwhF18XWtSrHqG53YfxX4Mjx4RYj7Y__0__infobox__0,official_status,official_language_in,Djibouti\n5Ja2BY9LEcJBJCvfSb9XVqCJCTmbLoSdcYH7cRK3jMkgdSNh6y7TeGUVVphwhF18XWtSrHqG53YfxX4Mjx4RYj7Y__0__infobox__0,official_status,official_language_in,Ethiopia\n5Ja2BY9LEcJBJCvfSb9XVqCJCTmbLoSdcYH7cRK3jMkgdSNh6y7TeGUVVphwhF18XWtSrHqG53YfxX4Mjx4RYj7Y__0__infobox__0,official_status,recognised_minority_language_in,Kenya\n5Ja2BY9LEcJBJCvfSb9XVqCJCTmbLoSdcYH7cRK3jMkgdSNh6y7TeGUVVphwhF18XWtSrHqG53YfxX4Mjx4RYj7Y__0__infobox__0,regulator,name,Regional Somali Language Academy\n5Ja2BY9LEcJBJCvfSb9XVqCJCTmbLoSdcYH7cRK3jMkgdSNh6y7TeGUVVphwhF18XWtSrHqG53YfxX4Mjx4RYj7Y__0__infobox__0,language_code,ISO 639-1,so\n5Ja2BY9LEcJBJCvfSb9XVqCJCTmbLoSdcYH7cRK3jMkgdSNh6y7TeGUVVphwhF18XWtSrHqG53YfxX4Mjx4RYj7Y__0__infobox__0,language_code,ISO 639-2,som\n5Ja2BY9LEcJBJCvfSb9XVqCJCTmbLoSdcYH7cRK3jMkgdSNh6y7TeGUVVphwhF18XWtSrHqG53YfxX4Mjx4RYj7Y__0__infobox__0,language_code,ISO 639-3,som\n5Ja2BY9LEcJBJCvfSb9XVqCJCTmbLoSdcYH7cRK3jMkgdSNh6y7TeGUVVphwhF18XWtSrHqG53YfxX4Mjx4RYj7Y__0__infobox__0,language_code,Glottolog,soma1255\n5Ja2BY9LEcJBJCvfSb9XVqCJCTmbLoSdcYH7cRK3jMkgdSNh6y7TeGUVVphwhF18XWtSrHqG53YfxX4Mjx4RYj7Y__0__infobox__0,language_code,Linguasphere,14-GAG-a\n5Ja2BY9LEcJBJCvfSb9XVqCJCTmbLoSdcYH7cRK3jMkgdSNh6y7TeGUVVphwhF18XWtSrHqG53YfxX4Mjx4RYj7Y__0__infobox__0,sprachraum,description,Primary Somali Sprachraum\n"}]}]}