{"conversations": [{"role": "user", "content": "What is the average, minimum, and maximum interest_rate for each loan_type among active loans?"}, {"role": "assistant", "content": "SELECT loan_type,\n       AVG(interest_rate) AS avg_interest_rate,\n       MIN(interest_rate) AS min_interest_rate,\n       MAX(interest_rate) AS max_interest_rate\nFROM financial_services.loans\nWHERE status = 'Active'\nGROUP BY loan_type;"}, {"role": "user", "content": "Exclude loan types with fewer than 5 active loans."}, {"role": "assistant", "content": "SELECT loan_type,\n       AVG(interest_rate) AS avg_interest_rate,\n       MIN(interest_rate) AS min_interest_rate,\n       MAX(interest_rate) AS max_interest_rate\nFROM financial_services.loans\nWHERE status = 'Active'\nGROUP BY loan_type\nHAVING COUNT(*) >= 5;"}, {"role": "user", "content": "Sort the result by average_interest_rate descending and only return the top 5 loan types."}, {"role": "assistant", "content": "SELECT loan_type,\n       AVG(interest_rate) AS avg_interest_rate,\n       MIN(interest_rate) AS min_interest_rate,\n       MAX(interest_rate) AS max_interest_rate\nFROM financial_services.loans\nWHERE status = 'Active'\nGROUP BY loan_type\nHAVING COUNT(*) >= 5\nORDER BY avg_interest_rate DESC\nLIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.loans (\n    loan_id character varying(64) NOT NULL, -- unique identifier for the loan, could be same as account_id\n    account_id character varying(64) NOT NULL UNIQUE, -- link to the general account record\n    loan_type character varying(50) NOT NULL, -- e.g., Mortgage, Personal, Auto, Student\n    principal_amount numeric(19, 4) NOT NULL, -- original loan amount\n    current_principal_balance numeric(19, 4) NOT NULL, -- remaining principal\n    interest_rate numeric(6, 4) NOT NULL, -- annual interest rate\n    term_months integer NOT NULL, -- loan term in months\n    origination_date date NOT NULL, -- date the loan was disbursed\n    maturity_date date NOT NULL, -- date the loan is due to be fully repaid\n    monthly_payment numeric(12, 4), -- scheduled monthly payment amount\n    collateral_description text, -- description of collateral, if secured loan\n    status character varying(32) NOT NULL, -- e.g., Active, Paid Off, Defaulted\n    PRIMARY KEY (loan_id),\n    FOREIGN KEY (account_id) REFERENCES financial_services.accounts(account_id)\n)\n"}
{"conversations": [{"role": "user", "content": "What is the average ROI for smart money addresses on the Ethereum chain with a realized profit ratio above 50%?"}, {"role": "assistant", "content": "SELECT AVG(roi) as average_roi\nFROM smart_money_token_performance\nWHERE chain = 'Ethereum'\nAND realized_ratio > 0.5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE project_fundraising_record ( id.text, project_id.text, project_name.text, rounds_name.text, investment_value.numeric, investment_date.text, introduction.text, valuation.numeric )\nCREATE TABLE token_dexpool_info ( pair_address.text, token_name.text, token_symbol.text, chain.text, price.numeric, price_change_percentage_1h.numeric, price_change_percentage_6h.numeric, price_change_percentage_24h.numeric, makers_24h.numeric, volume_24h.numeric, liquidity.numeric, market_cap.numeric, trend_rank.numeric )\nCREATE TABLE smart_money_token_performance ( token_address.text, token_symbol.text, pnl.numeric, net_flow.numeric, avg_cost.numeric, price.numeric, realized_ratio.numeric, roi.numeric, chain.text )\nCREATE TABLE smart_money_token_inflow ( token_address.text, token_symbol.text, token_amount.numeric, usd_value.numeric, avg_price.numeric, type.numeric, address_amount.numeric, narrative.text, chain.text )\n"}
{"conversations": [{"role": "user", "content": "Return the number of top-level comments and the number of replies in the comments table."}, {"role": "assistant", "content": "SELECT\n  SUM(CASE WHEN parent_comment_id IS NULL THEN 1 ELSE 0 END) AS top_level_comments,\n  SUM(CASE WHEN parent_comment_id IS NOT NULL THEN 1 ELSE 0 END) AS reply_comments\nFROM social_media.comments;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id text, username text, email text, password_hash text, full_name text, profile_picture_url text, bio text, location text, created_at timestamp, updated_at timestamp, is_verified boolean )\nCREATE TABLE social_media.posts ( post_id text, user_id text, content text, media_url text, media_type text, created_at timestamp, updated_at timestamp, visibility text, location_lat numeric, location_lon numeric )\nCREATE TABLE social_media.comments ( comment_id text, post_id text, user_id text, parent_comment_id text, content text, created_at timestamp, updated_at timestamp )\nCREATE TABLE social_media.follows ( follow_id text, follower_user_id text, following_user_id text, created_at timestamp )\nCREATE TABLE social_media.post_hashtags ( post_hashtag_id text, post_id text, hashtag_id text )\nCREATE TABLE social_media.conversations ( conversation_id text, created_at timestamp, last_message_at timestamp, is_group_chat boolean, group_name text )\nCREATE TABLE social_media.notifications ( notification_id text, recipient_user_id text, sender_user_id text, notification_type text, target_entity_id text, target_entity_type text, created_at timestamp, read_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show me all patients who have a primary insurance plan from 'Blue Cross', along with their insurance policy numbers and the plan types."}, {"role": "assistant", "content": "SELECT p.patient_id, p.first_name, p.last_name, pi.policy_number, ip.plan_type FROM healthcare.patients p JOIN healthcare.patient_insurance pi ON p.patient_id = pi.patient_id JOIN healthcare.insurance_plans ip ON pi.plan_id = ip.plan_id WHERE ip.insurance_provider = 'Blue Cross' AND pi.is_primary = true;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id text, first_name text, last_name text, date_of_birth date, gender text, address text, phone_number text, email text, emergency_contact_name text, emergency_contact_phone text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.doctors ( doctor_id.text, first_name.text, last_name.text, specialty.text, license_number.text, phone_number.text, email.text, hospital_affiliation_id.text, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE healthcare.medical_records ( record_id text PRIMARY KEY, patient_id text, appointment_id text, doctor_id text, record_date timestamp, chief_complaint text, present_illness_history text, past_medical_history text, physical_examination_notes text, assessment text, treatment_plan text, vitals text, created_at timestamp )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id text PRIMARY KEY, record_id text, patient_id text, doctor_id text, diagnosis_code text, code_type text, description text, diagnosis_date date, status text, is_chronic boolean )\nCREATE TABLE healthcare.medications ( medication_id text, medication_name text, generic_name text, manufacturer text, ndc_code text, description text )\nCREATE TABLE healthcare.insurance_plans (\n    plan_id character varying(64) NOT NULL, -- unique identifier for the insurance plan\n    plan_name character varying(200) NOT NULL, -- name of the insurance plan\n    insurance_provider character varying(100) NOT NULL, -- name of the insurance company\n    plan_type character varying(50), -- e.g., PPO, HMO, EPO\n    contact_phone character varying(20), -- provider contact number\n    website character varying(255), -- provider website\n    PRIMARY KEY (plan_id)\n)\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, plan_id character varying(64) NOT NULL, policy_number character varying(100) NOT NULL, group_number character varying(100), subscriber_name character varying(200), effective_date date NOT NULL, expiration_date date, is_primary boolean NOT NULL DEFAULT true, PRIMARY KEY (patient_insurance_id), UNIQUE (patient_id, plan_id, policy_number) )\n"}
{"conversations": [{"role": "user", "content": "List group conversation names and the number of messages sent in each conversation after January 1, 2023."}, {"role": "assistant", "content": "SELECT c.group_name, COUNT(m.message_id) FROM social_media.conversations c JOIN social_media.messages m ON c.conversation_id = m.conversation_id WHERE c.is_group_chat = true AND m.sent_at >= '2023-01-01' GROUP BY c.conversation_id, c.group_name;"}, {"role": "user", "content": "Only show conversations that have more than 100 messages sent after that date."}, {"role": "assistant", "content": "SELECT c.group_name, COUNT(m.message_id) FROM social_media.conversations c JOIN social_media.messages m ON c.conversation_id = m.conversation_id WHERE c.is_group_chat = true AND m.sent_at >= '2023-01-01' GROUP BY c.conversation_id, c.group_name HAVING COUNT(m.message_id) > 100;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id text, username text, email text, password_hash text, full_name text, profile_picture_url text, bio text, location text, created_at timestamp, updated_at timestamp, is_verified boolean )\nCREATE TABLE social_media.posts ( post_id text, user_id text, content text, media_url text, media_type text, created_at timestamp, updated_at timestamp, visibility text, location_lat numeric, location_lon numeric )\nCREATE TABLE social_media.likes ( like_id text, user_id text, post_id text, comment_id text, created_at timestamp )\nCREATE TABLE social_media.follows ( follow_id text, follower_user_id text, following_user_id text, created_at timestamp )\nCREATE TABLE social_media.post_hashtags ( post_hashtag_id text, post_id text, hashtag_id text )\nCREATE TABLE social_media.messages ( message_id text, conversation_id text, sender_user_id text, content text, media_url text, media_type text, sent_at timestamp, read_at timestamp )\nCREATE TABLE social_media.conversations ( conversation_id text, created_at timestamp, last_message_at timestamp, is_group_chat boolean, group_name text )\nCREATE TABLE social_media.conversation_participants ( participant_id text, conversation_id text, user_id text, joined_at timestamp, last_read_at timestamp )\nCREATE TABLE social_media.notifications ( notification_id text, recipient_user_id text, sender_user_id text, notification_type text, target_entity_id text, target_entity_type text, created_at timestamp, read_at timestamp )\nCREATE TABLE social_media.user_settings ( setting_id text, user_id text, theme text, email_notifications_enabled boolean, push_notifications_enabled boolean, private_profile boolean, updated_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "List all narratives with a trend rank better than 50, showing the narrative name and their listed 'Top 3 Coins'."}, {"role": "assistant", "content": "SELECT narrative, top_3_coins FROM narrative_info WHERE trend_rank < 50"}, {"role": "user", "content": "Could you also include the 24-hour trading volume for these narratives and only show those where the volume is greater than 10,000,000 USD?"}, {"role": "assistant", "content": "SELECT narrative, top_3_coins, volume_24h FROM narrative_info WHERE trend_rank < 50 AND volume_24h > 10000000"}, {"role": "user", "content": "Please order the results by 24-hour trading volume in descending order."}, {"role": "assistant", "content": "SELECT narrative, top_3_coins, volume_24h FROM narrative_info WHERE trend_rank < 50 AND volume_24h > 10000000 ORDER BY volume_24h DESC"}, {"role": "user", "content": "Finally, limit the output to the top 10 and add the total number of tokens for each narrative."}, {"role": "assistant", "content": "SELECT narrative, top_3_coins, volume_24h, token_num FROM narrative_info WHERE trend_rank < 50 AND volume_24h > 10000000 ORDER BY volume_24h DESC LIMIT 10"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE narrative_info ( narrative.text, top_3_coins.text, price_change_percentage_1h.numeric, price_change_percentage_24h.numeric, price_change_percentage_7d.numeric, market_cap.numeric, volume_24h.numeric, trend_rank.numeric, token_num.numeric )\n"}
{"conversations": [{"role": "user", "content": "Could you list the top 5 narratives by their 7-day price change percentage, including the number of tokens and their top 3 coins?"}, {"role": "assistant", "content": "SELECT narrative, price_change_percentage_7d, token_num, top_3_coins FROM narrative_info ORDER BY price_change_percentage_7d DESC LIMIT 5;"}, {"role": "user", "content": "Now, for these narratives, show the token with the highest current price from token_basic_info. Return narrative, token_symbol, and max price."}, {"role": "assistant", "content": "SELECT n.narrative, t.token_symbol, t.price FROM token_basic_info t JOIN narrative_info n ON t.narrative = n.narrative WHERE t.price = (SELECT MAX(price) FROM token_basic_info WHERE narrative = n.narrative);"}, {"role": "user", "content": "Filter to only include narratives where token_num > 10 and volume_24h > 1000000."}, {"role": "assistant", "content": "SELECT n.narrative, t.token_symbol, t.price FROM token_basic_info t JOIN narrative_info n ON t.narrative = n.narrative WHERE t.price = (SELECT MAX(price) FROM token_basic_info WHERE narrative = n.narrative) AND n.token_num > 10 AND n.volume_24h > 1000000;"}, {"role": "user", "content": "Finally, limit to the top 3 narratives by 7-day price change and include volume_24h."}, {"role": "assistant", "content": "SELECT n.narrative, n.price_change_percentage_7d, n.volume_24h, t.token_symbol, t.price FROM token_basic_info t JOIN narrative_info n ON t.narrative = n.narrative WHERE t.price = (SELECT MAX(price) FROM token_basic_info WHERE narrative = n.narrative) AND n.token_num > 10 AND n.volume_24h > 1000000 ORDER BY n.price_change_percentage_7d DESC LIMIT 3;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE project_fundraising_record ( id character varying(32) NOT NULL, project_id character varying(32) NOT NULL, project_name character varying(128) NOT NULL, rounds_name character varying(32), investment_value numeric(38,14), investment_date character varying(128), introduction character varying(128), valuation numeric(38,14) )\nCREATE TABLE token_basic_info ( coin_id character varying(100) NOT NULL, token_name character varying(100) NOT NULL, token_symbol character varying(100) NOT NULL, token_address character varying(100) NOT NULL, chain text, price double precision, price_change_percentage_1h double precision, price_change_percentage_24h double precision, price_change_percentage_7d double precision, highest_price_24h double precision, lowest_price_24h double precision, market_cap double precision, market_cap_rank bigint, market_cap_change_percentage_24h text, total_volume text, narrative text, trend_rank bigint )\nCREATE TABLE narrative_info ( narrative character varying(512) NOT NULL, top_3_coins text, price_change_percentage_1h double precision, price_change_percentage_24h double precision, price_change_percentage_7d double precision, market_cap double precision, volume_24h double precision, trend_rank bigint, token_num bigint )\nCREATE TABLE cex_token_balance ( snapshot_time character varying(32) NOT NULL, chain character varying(128) NOT NULL, address character varying(128) NOT NULL, exchange character varying(512) NOT NULL, token_address character varying(128) NOT NULL, token_symbol character varying(512), balance numeric(38,10), usd_value numeric(38,14), price double precision )\nCREATE TABLE smart_money_profit ( address character varying(100) NOT NULL, rank INT, profit numeric(38,6), roi numeric(38,2), realized_ratio numeric(38,2), most_profit_token character varying(100), last_trade_time character varying(100), chain character varying(100) )\nCREATE TABLE smart_money_token_performance ( token_address character varying(100) NOT NULL, token_symbol character varying(100), pnl numeric(38,2), net_flow numeric(38,2), avg_cost numeric(38,16), price double precision, realized_ratio numeric(10,2), roi numeric(10,2), chain character varying(100) )\nCREATE TABLE smart_money_token_inflow ( token_address character varying(100) NOT NULL, token_symbol character varying(100), token_amount numeric(38,2), usd_value numeric(38,2), avg_price numeric(38,6), type int, address_amount integer, narrative character varying(100), chain character varying(100) )\n"}
{"conversations": [{"role": "user", "content": "Calculate for each player the timespan between their earliest and latest achievement unlocks."}, {"role": "assistant", "content": "SELECT pa_min.player_id,\n       pa_max.max_time - pa_min.min_time AS span\nFROM (\n  SELECT player_id,\n         MIN(unlocked_at) AS min_time\n  FROM gaming_technology.player_achievements\n  GROUP BY player_id\n) pa_min\nJOIN (\n  SELECT player_id,\n         MAX(unlocked_at) AS max_time\n  FROM gaming_technology.player_achievements\n  GROUP BY player_id\n) pa_max\n  ON pa_min.player_id = pa_max.player_id;"}, {"role": "user", "content": "Exclude players who only have one achievement."}, {"role": "assistant", "content": "WITH extremes AS (\n  SELECT player_id,\n         MIN(unlocked_at) AS min_time,\n         MAX(unlocked_at) AS max_time,\n         COUNT(*) AS cnt\n  FROM gaming_technology.player_achievements\n  GROUP BY player_id\n  HAVING COUNT(*) > 1\n)\nSELECT player_id,\n       max_time - min_time AS span\nFROM extremes;"}, {"role": "user", "content": "Also only keep players where the span is greater than 30 days."}, {"role": "assistant", "content": "WITH extremes AS (\n  SELECT player_id,\n         MIN(unlocked_at) AS min_time,\n         MAX(unlocked_at) AS max_time,\n         COUNT(*) AS cnt\n  FROM gaming_technology.player_achievements\n  GROUP BY player_id\n  HAVING COUNT(*) > 1\n)\nSELECT player_id,\n       max_time - min_time AS span\nFROM extremes\nWHERE max_time - min_time > INTERVAL '30 days';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.player_achievements (\n    player_achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for this unlock instance\n    player_id uuid NOT NULL, -- FK linking to the player who unlocked it\n    achievement_id uuid NOT NULL, -- FK linking to the achievement definition\n    unlocked_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the achievement was unlocked\n    PRIMARY KEY (player_achievement_id),\n    UNIQUE (player_id, achievement_id) -- Ensure a player can only unlock an achievement once\n    -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n    -- FOREIGN KEY (achievement_id) REFERENCES gaming_technology.achievements(achievement_id)\n)\n"}
{"conversations": [{"role": "user", "content": "How many medications does each manufacturer have?"}, {"role": "assistant", "content": "SELECT manufacturer, COUNT(*) AS med_count\nFROM healthcare.medications\nGROUP BY manufacturer;"}, {"role": "user", "content": "Only include manufacturers with more than 10 medications."}, {"role": "assistant", "content": "SELECT manufacturer, COUNT(*) AS med_count\nFROM healthcare.medications\nGROUP BY manufacturer\nHAVING COUNT(*) > 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.medications ( medication_id character varying(64) NOT NULL, medication_name character varying(255) NOT NULL, generic_name character varying(255), manufacturer character varying(100), ndc_code character varying(20) UNIQUE, description text, PRIMARY KEY (medication_id) )\n"}
{"conversations": [{"role": "user", "content": "What are the training programs or certifications completed by a staff member with the role of Platform Supervisor?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to information about the training programs or certifications completed by staff members. The data available to me only includes basic staff details such as name, role, and contact information. For details on training or certifications, please refer to the HR department or relevant training records."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.staff ( staff_id text PRIMARY KEY, first_name text, last_name text, role text, primary_station_id text, employee_number text UNIQUE, hire_date date, contact_email text UNIQUE, contact_phone text, is_active boolean )\n"}
{"conversations": [{"role": "user", "content": "List all trades with their order_id, trade_type, and commission for trades with commission higher than 100."}, {"role": "assistant", "content": "SELECT trade_id, order_id, trade_type, commission FROM financial_services.trades WHERE commission > 100;"}, {"role": "user", "content": "Include the security_name and ticker_symbol for each trade as well."}, {"role": "assistant", "content": "SELECT t.trade_id, t.order_id, t.trade_type, t.commission, s.security_name, s.ticker_symbol FROM financial_services.trades t INNER JOIN financial_services.securities s ON t.security_id = s.security_id WHERE t.commission > 100;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.customers ( customer_id text PRIMARY KEY, first_name text, last_name text, date_of_birth date, ssn_hash text, address text, city text, state text, zip_code text, country text, email text, phone_number text, created_at timestamp, status text, risk_profile text )\nCREATE TABLE financial_services.accounts ( account_id text PRIMARY KEY, customer_id text, account_number text, account_type text, balance numeric, currency text, opened_date date, status text, interest_rate numeric, last_updated_at timestamp )\nCREATE TABLE financial_services.transactions (\n    transaction_id character varying(64) NOT NULL, -- unique identifier for the transaction\n    account_id character varying(64) NOT NULL, -- account involved in the transaction\n    related_account_id character varying(64), -- counterpart account for transfers\n    transaction_type character varying(50) NOT NULL, -- e.g., Deposit, Withdrawal, Transfer, Payment, Fee, Interest\n    amount numeric(19, 4) NOT NULL, -- transaction amount\n    currency character varying(3) NOT NULL, -- transaction currency\n    transaction_date timestamp NOT NULL, -- exact time of the transaction\n    effective_date date NOT NULL, -- date the transaction affects the balance\n    description text, -- description or memo of the transaction\n    status character varying(32) NOT NULL, -- e.g., Pending, Completed, Failed, Reversed\n    reference_number character varying(128), -- external reference if applicable (e.g., check number)\n    PRIMARY KEY (transaction_id),\n    FOREIGN KEY (account_id) REFERENCES financial_services.accounts(account_id),\n    FOREIGN KEY (related_account_id) REFERENCES financial_services.accounts(account_id)\n)\nCREATE TABLE financial_services.securities ( security_id text, ticker_symbol text, isin_code text, cusip_code text, security_name text, security_type text, exchange text, currency text, issuer_name text, sector text, last_updated timestamp )\nCREATE TABLE financial_services.trades ( trade_id character varying(64) NOT NULL, account_id character varying(64) NOT NULL, security_id character varying(64) NOT NULL, order_id character varying(64), trade_type character varying(10) NOT NULL, quantity numeric(19, 8) NOT NULL, price_per_unit numeric(19, 8) NOT NULL, total_amount numeric(19, 4) NOT NULL, commission numeric(10, 4), trade_timestamp timestamp NOT NULL, settlement_date date, status character varying(32) NOT NULL, execution_venue character varying(100), PRIMARY KEY (trade_id), FOREIGN KEY (account_id) REFERENCES financial_services.accounts(account_id), FOREIGN KEY (security_id) REFERENCES financial_services.securities(security_id) )\nCREATE TABLE financial_services.market_data ( data_point_id bigserial NOT NULL, security_id character varying(64) NOT NULL, data_timestamp timestamp NOT NULL, open_price numeric(19, 8), high_price numeric(19, 8), low_price numeric(19, 8), close_price numeric(19, 8) NOT NULL, adjusted_close_price numeric(19, 8), volume bigint, source character varying(50), PRIMARY KEY (data_point_id), UNIQUE (security_id, data_timestamp), FOREIGN KEY (security_id) REFERENCES financial_services.securities(security_id) )\nCREATE TABLE financial_services.employees (\n    employee_id character varying(64) NOT NULL,  -- unique identifier for the employee\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    job_title character varying(100) NOT NULL, -- e.g., Teller, Branch Manager, Financial Advisor, Analyst\n    department character varying(100), -- e.g., Retail Banking, Wealth Management, IT\n    branch_id character varying(64), -- Identifier for the branch they work at (if applicable)\n    email character varying(128) NOT NULL UNIQUE,\n    phone_extension character varying(20),\n    hire_date date NOT NULL,\n    termination_date date, -- Date of termination, null if currently employed\n    manager_id character varying(64), -- Self-referencing key for manager relationship\n    status character varying(32) NOT NULL, -- e.g., Active, Terminated, On Leave\n    PRIMARY KEY (employee_id),\n    FOREIGN KEY (branch_id) REFERENCES financial_services.branches(branch_id), -- Assuming a branches table exists\n    FOREIGN KEY (manager_id) REFERENCES financial_services.employees(employee_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Could you list each developer along with the next developer founded after them in the same country? Return columns current_developer, next_developer, and years_difference."}, {"role": "assistant", "content": "SELECT d1.name AS current_developer,\n       d2.name AS next_developer,\n       d2.founded_year - d1.founded_year AS years_difference\nFROM gaming_technology.developers d1\nJOIN gaming_technology.developers d2\n  ON d1.country = d2.country\n AND d2.founded_year > d1.founded_year\nWHERE NOT EXISTS (\n  SELECT 1\n  FROM gaming_technology.developers dx\n  WHERE dx.country = d1.country\n    AND dx.founded_year > d1.founded_year\n    AND dx.founded_year < d2.founded_year\n);\n"}, {"role": "user", "content": "Actually, exclude pairs where the difference is more than 10 years."}, {"role": "assistant", "content": "SELECT d1.name AS current_developer,\n       d2.name AS next_developer,\n       d2.founded_year - d1.founded_year AS years_difference\nFROM gaming_technology.developers d1\nJOIN gaming_technology.developers d2\n  ON d1.country = d2.country\n AND d2.founded_year > d1.founded_year\nWHERE NOT EXISTS (\n  SELECT 1\n  FROM gaming_technology.developers dx\n  WHERE dx.country = d1.country\n    AND dx.founded_year > d1.founded_year\n    AND dx.founded_year < d2.founded_year\n)\n  AND (d2.founded_year - d1.founded_year) <= 10;\n"}, {"role": "user", "content": "Also, only include countries with at least three developers."}, {"role": "assistant", "content": "SELECT d1.name AS current_developer,\n       d2.name AS next_developer,\n       d2.founded_year - d1.founded_year AS years_difference\nFROM gaming_technology.developers d1\nJOIN gaming_technology.developers d2\n  ON d1.country = d2.country\n AND d2.founded_year > d1.founded_year\nWHERE d1.country IN (\n  SELECT country\n  FROM gaming_technology.developers\n  GROUP BY country\n  HAVING COUNT(*) >= 3\n)\n  AND NOT EXISTS (\n    SELECT 1\n    FROM gaming_technology.developers dx\n    WHERE dx.country = d1.country\n      AND dx.founded_year > d1.founded_year\n      AND dx.founded_year < d2.founded_year\n  )\n  AND (d2.founded_year - d1.founded_year) <= 10\nORDER BY d1.country ASC, years_difference ASC;\n"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.developers ( developer_id uuid, name text, country text, founded_year integer, website text, created_at timestamp with time zone )\n"}
{"conversations": [{"role": "user", "content": "For each developer, can you find the next developer in the same country using a self join, returning developer_ids and names?"}, {"role": "assistant", "content": "SELECT d1.developer_id   AS current_dev,\n       d1.name           AS current_name,\n       d2.developer_id   AS next_dev,\n       d2.name           AS next_name,\n       d2.founded_year - d1.founded_year AS years_diff\nFROM developers d1\nJOIN developers d2\n  ON d1.country = d2.country\n  AND d2.founded_year > d1.founded_year;"}, {"role": "user", "content": "Exclude developers who don't have a next developer, and ensure we only pick the closest next by founded_year."}, {"role": "assistant", "content": "SELECT d1.developer_id   AS current_dev,\n       d1.name           AS current_name,\n       d2.developer_id   AS next_dev,\n       d2.name           AS next_name,\n       d2.founded_year - d1.founded_year AS years_diff\nFROM developers d1\nJOIN LATERAL (\n  SELECT d2.developer_id, d2.name, d2.founded_year\n  FROM developers d2\n  WHERE d2.country = d1.country\n    AND d2.founded_year > d1.founded_year\n  ORDER BY d2.founded_year ASC\n  LIMIT 1\n) d2 ON true;"}, {"role": "user", "content": "Finally, only include pairs where the difference in founded years is at most 5 years."}, {"role": "assistant", "content": "SELECT d1.developer_id   AS current_dev,\n       d1.name           AS current_name,\n       d2.developer_id   AS next_dev,\n       d2.name           AS next_name,\n       d2.founded_year - d1.founded_year AS years_diff\nFROM developers d1\nJOIN LATERAL (\n  SELECT d2.developer_id, d2.name, d2.founded_year\n  FROM developers d2\n  WHERE d2.country = d1.country\n    AND d2.founded_year > d1.founded_year\n  ORDER BY d2.founded_year ASC\n  LIMIT 1\n) d2 ON true\nWHERE (d2.founded_year - d1.founded_year) <= 5\nORDER BY d1.developer_id, years_diff ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.developers ( developer_id uuid PRIMARY KEY, name text, country text, founded_year int, website text, created_at timestamptz )\n"}
{"conversations": [{"role": "user", "content": "Could you provide the total number of game sessions and the number of distinct players for each game genre? Display the genre, session count, and player count."}, {"role": "assistant", "content": "SELECT g.genre, COUNT(gs.session_id) AS session_count, COUNT(DISTINCT gs.player_id) AS player_count FROM gaming_technology.game_sessions AS gs JOIN gaming_technology.games AS g ON gs.game_id = g.game_id WHERE g.genre IS NOT NULL GROUP BY g.genre ORDER BY g.genre;"}, {"role": "user", "content": "Thanks. Can you modify the query to only include games that were released after the year 2020?"}, {"role": "assistant", "content": "SELECT g.genre, COUNT(gs.session_id) AS session_count, COUNT(DISTINCT gs.player_id) AS player_count FROM gaming_technology.game_sessions AS gs JOIN gaming_technology.games AS g ON gs.game_id = g.game_id WHERE g.genre IS NOT NULL AND g.release_date >= '2021-01-01' GROUP BY g.genre ORDER BY g.genre;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.players (\n    player_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the player\n    username character varying(100) NOT NULL UNIQUE, -- player's chosen display name\n    email character varying(255) NOT NULL UNIQUE, -- player's email address for login/recovery\n    password_hash text NOT NULL, -- securely hashed password\n    registration_date timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the player account was created\n    last_login timestamp with time zone, -- timestamp of the last successful login\n    country_code character(2), -- player's country (ISO 3166-1 alpha-2)\n    status character varying(20) NOT NULL DEFAULT 'active', -- account status (e.g., active, banned, suspended)\n    profile_data jsonb, -- flexible field for avatar url, bio, preferences etc.\n    PRIMARY KEY (player_id)\n)\nCREATE TABLE gaming_technology.games (\n    game_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game\n    title character varying(200) NOT NULL, -- official title of the game\n    developer_id uuid NOT NULL, -- FK linking to the developers table\n    publisher_id uuid, -- FK linking to a potential publishers table (optional)\n    genre character varying(100), -- primary genre (e.g., RPG, FPS, Strategy)\n    release_date date, -- official release date\n    description text, -- short description or synopsis of the game\n    platform character varying(50) NOT NULL, -- primary platform (e.g., PC, PlayStation 5, Xbox Series X, Mobile)\n    engine character varying(100), -- game engine used (e.g., Unreal Engine 5, Unity)\n    website character varying(255), -- official website URL\n    PRIMARY KEY (game_id)\n    -- FOREIGN KEY (developer_id) REFERENCES gaming_technology.developers(developer_id) -- Example FK constraint\n)\nCREATE TABLE gaming_technology.game_sessions (\n    session_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game session\n    player_id uuid NOT NULL, -- FK linking to the players table\n    game_id uuid NOT NULL, -- FK linking to the games table\n    server_id uuid, -- FK linking to the servers table (nullable for single-player)\n    start_time timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the session began\n    end_time timestamp with time zone, -- when the session ended (null if ongoing)\n    duration_seconds integer, -- calculated duration of the session in seconds\n    score integer, -- player's score for the session, if applicable\n    session_data jsonb, -- flexible field for session-specific info (e.g., map played, character used)\n    PRIMARY KEY (session_id)\n    -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n    -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id),\n    -- FOREIGN KEY (server_id) REFERENCES gaming_technology.servers(server_id)\n)\nCREATE TABLE gaming_technology.servers (\n    server_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game server instance\n    game_id uuid NOT NULL, -- FK linking to the game this server hosts\n    server_name character varying(150), -- display name for the server\n    region character varying(50) NOT NULL, -- geographical region (e.g., us-east-1, eu-west-2)\n    ip_address character varying(45), -- IP address (IPv4 or IPv6)\n    port integer, -- network port number\n    current_players integer NOT NULL DEFAULT 0, -- number of players currently connected\n    max_players integer NOT NULL, -- maximum player capacity\n    status character varying(30) NOT NULL DEFAULT 'offline', -- server status (e.g., online, offline, maintenance)\n    last_heartbeat timestamp with time zone, -- last time the server reported its status\n    PRIMARY KEY (server_id)\n    -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id)\n)\nCREATE TABLE gaming_technology.achievements (\n    achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for an achievement definition\n    game_id uuid NOT NULL, -- FK linking to the game the achievement belongs to\n    name character varying(150) NOT NULL, -- name of the achievement\n    description text NOT NULL, -- how to unlock the achievement\n    icon_url character varying(255), -- URL for the achievement's icon\n    points integer DEFAULT 0, -- points awarded for unlocking (optional)\n    hidden boolean DEFAULT false, -- whether the achievement details are hidden until unlocked\n    PRIMARY KEY (achievement_id)\n    -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id)\n)\nCREATE TABLE gaming_technology.player_achievements (\n    player_achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for this unlock instance\n    player_id uuid NOT NULL, -- FK linking to the player who unlocked it\n    achievement_id uuid NOT NULL, -- FK linking to the achievement definition\n    unlocked_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the achievement was unlocked\n    PRIMARY KEY (player_achievement_id),\n    UNIQUE (player_id, achievement_id) -- Ensure a player can only unlock an achievement once\n    -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n    -- FOREIGN KEY (achievement_id) REFERENCES gaming_technology.achievements(achievement_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Provide a list of all vehicles and the total quantity of fuel refueled for each vehicle."}, {"role": "assistant", "content": "SELECT T1.license_plate, sum(T2.quantity) FROM transportation.vehicles AS T1 JOIN transportation.fuel_logs AS T2 ON T1.vehicle_id = T2.vehicle_id GROUP BY T1.license_plate"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles ( vehicle_id text PRIMARY KEY, license_plate text, vin text, make text, model text, year int, type text, capacity int, fuel_type text, status text, depot_id text, acquisition_date date )\nCREATE TABLE transportation.drivers ( driver_id text PRIMARY KEY, employee_id text, first_name text, last_name text, license_number text, license_expiry_date date, contact_number text, email text, hire_date date, status text )\nCREATE TABLE transportation.routes ( route_id text PRIMARY KEY, route_number text, description text, origin_location_id text, destination_location_id text, distance_km numeric, estimated_duration_minutes int, type text )\nCREATE TABLE transportation.trips ( trip_id text PRIMARY KEY, route_id text, vehicle_id text, driver_id text, scheduled_departure timestamp, actual_departure timestamp, scheduled_arrival timestamp, actual_arrival timestamp, origin_location_id text, destination_location_id text, status text, passenger_count int, cargo_manifest_id text )\nCREATE TABLE transportation.fuel_logs ( fuel_log_id text PRIMARY KEY, vehicle_id text, trip_id text, log_timestamp timestamp, fuel_type text, quantity numeric, unit text, cost_per_unit numeric, total_cost numeric, odometer_reading int, location_id text )\nCREATE TABLE transportation.passengers ( passenger_id text PRIMARY KEY, first_name text, last_name text, email text, phone_number text, date_of_birth date, loyalty_program_id text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "I’d like to find all pairs of securities that belong to the same sector."}, {"role": "assistant", "content": "SELECT a.security_id, a.ticker_symbol, b.security_id AS pair_security_id, b.ticker_symbol AS pair_ticker_symbol, a.sector\nFROM financial_services.securities a\nJOIN financial_services.securities b ON a.sector = b.sector\nWHERE a.security_id < b.security_id;"}, {"role": "user", "content": "Actually, only include pairs where the two securities are listed on different exchanges."}, {"role": "assistant", "content": "SELECT a.security_id, a.ticker_symbol, a.exchange AS exchange_a, b.security_id AS pair_security_id, b.ticker_symbol AS pair_ticker_symbol, b.exchange AS exchange_b, a.sector\nFROM financial_services.securities a\nJOIN financial_services.securities b ON a.sector = b.sector AND a.security_id < b.security_id\nWHERE a.exchange <> b.exchange;"}, {"role": "user", "content": "Also, I want the results sorted by sector, then by exchange_a."}, {"role": "assistant", "content": "SELECT a.security_id, a.ticker_symbol, a.exchange AS exchange_a, b.security_id AS pair_security_id, b.ticker_symbol AS pair_ticker_symbol, b.exchange AS exchange_b, a.sector\nFROM financial_services.securities a\nJOIN financial_services.securities b ON a.sector = b.sector AND a.security_id < b.security_id\nWHERE a.exchange <> b.exchange\nORDER BY a.sector, a.exchange;"}, {"role": "user", "content": "One more thing: include both exchanges in the ORDER BY so that within each sector it’s sorted by exchange_a then exchange_b."}, {"role": "assistant", "content": "SELECT a.security_id, a.ticker_symbol, a.exchange AS exchange_a, b.security_id AS pair_security_id, b.ticker_symbol AS pair_ticker_symbol, b.exchange AS exchange_b, a.sector\nFROM financial_services.securities a\nJOIN financial_services.securities b ON a.sector = b.sector AND a.security_id < b.security_id\nWHERE a.exchange <> b.exchange\nORDER BY a.sector, a.exchange, b.exchange;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.securities ( security_id text PRIMARY KEY, ticker_symbol text, isin_code text, cusip_code text, security_name text, security_type text, exchange text, currency text, issuer_name text, sector text, last_updated timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show all rooms that are on floor 3."}, {"role": "assistant", "content": "SELECT room_id, property_id, room_number FROM hospitality_technology.rooms WHERE floor = 3;"}, {"role": "user", "content": "For these rooms, include the property name and room number."}, {"role": "assistant", "content": "SELECT r.room_number, p.property_name FROM hospitality_technology.rooms AS r JOIN hospitality_technology.properties AS p ON r.property_id = p.property_id WHERE r.floor = 3;"}, {"role": "user", "content": "Also, include the type name and current status for each room."}, {"role": "assistant", "content": "SELECT r.room_number, p.property_name, rt.type_name, r.status FROM hospitality_technology.rooms AS r JOIN hospitality_technology.properties AS p ON r.property_id = p.property_id JOIN hospitality_technology.room_types AS rt ON r.room_type_id = rt.room_type_id AND r.property_id = rt.property_id WHERE r.floor = 3;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.properties ( property_id text, property_name text, address_line1 text, address_line2 text, city text, state_province text, postal_code text, country_code text, phone_number text, email_address text, property_type text, star_rating numeric, timezone text, manager_staff_id text, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.rooms ( room_id text, property_id text, room_number text, room_type_id text, floor integer, status text, is_smoking boolean, features text, current_condition text, last_cleaned_at timestamp )\nCREATE TABLE hospitality_technology.room_types ( room_type_id text, property_id text, type_name text, description text, base_rate numeric, max_occupancy integer, bed_type text, area_sqft numeric, amenities text )\n"}
{"conversations": [{"role": "user", "content": "List all guests who have a loyalty member ID, showing their full name (first and last name), email, and loyalty ID."}, {"role": "assistant", "content": "SELECT first_name, last_name, email, loyalty_member_id FROM hospitality_technology.guests WHERE loyalty_member_id IS NOT NULL;"}, {"role": "user", "content": "Can you also include the date they registered as a guest?"}, {"role": "assistant", "content": "SELECT first_name, last_name, email, loyalty_member_id, created_at FROM hospitality_technology.guests WHERE loyalty_member_id IS NOT NULL;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.rooms (\n    room_id character varying(64) NOT NULL,  -- unique identifier for the room\n    property_id character varying(64) NOT NULL, -- FK to properties table\n    room_number character varying(10) NOT NULL, -- room number identifier (e.g., '101', 'Suite 2B')\n    room_type_id character varying(64) NOT NULL, -- FK to room_types table\n    floor integer, -- floor number the room is on\n    status character varying(50) NOT NULL, -- e.g., Available, Occupied, Cleaning, OutOfOrder, Maintenance\n    is_smoking boolean NOT NULL DEFAULT false, -- smoking allowed flag\n    features text, -- description of features (e.g., Balcony, Sea View, Jacuzzi)\n    current_condition text, -- notes on room condition\n    last_cleaned_at timestamp with time zone, -- timestamp of last cleaning\n    PRIMARY KEY (room_id),\n    FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n    FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id)\n)\nCREATE TABLE hospitality_technology.room_types ( room_type_id.text, property_id.text, type_name.text, description.text, base_rate.numeric, max_occupancy.integer, bed_type.text, area_sqft.numeric, amenities.text )\nCREATE TABLE hospitality_technology.guests ( guest_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, email character varying(255) UNIQUE, phone_number character varying(30), date_of_birth date, address_line1 character varying(255), city character varying(100), state_province character varying(100), postal_code character varying(20), country_code character varying(3), preferences text, loyalty_member_id character varying(64) UNIQUE, communication_consent boolean DEFAULT true, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (guest_id) )\nCREATE TABLE hospitality_technology.staff (\n    staff_id character varying(64) NOT NULL,  -- unique identifier for the staff member\n    property_id character varying(64) NOT NULL, -- FK to properties table (primary property)\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    position character varying(100) NOT NULL, -- e.g., Front Desk Agent, Housekeeper, Manager, Concierge\n    work_email character varying(255) UNIQUE, -- staff member's work email\n    work_phone character varying(30),\n    hire_date date NOT NULL,\n    termination_date date, -- date employment ended (if applicable)\n    is_active boolean NOT NULL DEFAULT true, -- currently employed flag\n    access_level integer NOT NULL, -- permission level within systems (e.g., 1=basic, 5=admin)\n    manager_id character varying(64), -- FK to staff table (self-referencing for supervisor)\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (staff_id),\n    FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n    FOREIGN KEY (manager_id) REFERENCES hospitality_technology.staff(staff_id)\n)\nCREATE TABLE hospitality_technology.services ( service_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, service_name character varying(150) NOT NULL, description text, category character varying(100), price numeric(10, 2) NOT NULL, unit character varying(30), is_available boolean NOT NULL DEFAULT true, department character varying(100), PRIMARY KEY (service_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id) )\nCREATE TABLE hospitality_technology.payments (\n    payment_id character varying(64) NOT NULL,  -- unique identifier for the payment transaction\n    reservation_id character varying(64), -- FK to reservations (if payment is for a stay)\n    guest_id character varying(64) NOT NULL, -- FK to guests (who paid)\n    bill_id character varying(64), -- FK to bills/invoices this payment applies to\n    amount numeric(12,2) NOT NULL, -- amount of the payment\n    currency_code character varying(3) NOT NULL, -- ISO currency code (e.g., USD, EUR)\n    payment_method character varying(50) NOT NULL, -- e.g., CreditCard, Cash, BankTransfer, Points, Voucher\n    card_type character varying(50), -- e.g., Visa, MasterCard, Amex (if CC)\n    card_last_four character varying(4), -- last 4 digits of CC (if CC)\n    transaction_ref character varying(128), -- reference ID from payment gateway or processor\n    payment_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, -- when the payment occurred\n    status character varying(50) NOT NULL, -- e.g., Pending, Succeeded, Failed, Refunded, Disputed\n    staff_id_processed character varying(64), -- FK to staff (who processed the payment)\n    notes text, -- notes about the payment\n    PRIMARY KEY (payment_id),\n    FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id),\n    FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id),\n    FOREIGN KEY (staff_id_processed) REFERENCES hospitality_technology.staff(staff_id)\n)\n"}
{"conversations": [{"role": "user", "content": "How many lawyers who are partners were hired in each year? Show the hire year and the count."}, {"role": "assistant", "content": "SELECT strftime('%Y', hire_date) AS hire_year ,  count(lawyer_id) FROM legal_services.lawyers WHERE is_partner  =  true GROUP BY hire_year"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.lawyers (\n    lawyer_id character varying(64) NOT NULL,  -- unique identifier for the lawyer\n    first_name character varying(100) NOT NULL, -- lawyer's first name\n    last_name character varying(100) NOT NULL, -- lawyer's last name\n    bar_number character varying(64) UNIQUE NOT NULL, -- lawyer's bar association number\n    firm_id character varying(64), -- FK to law_firms table\n    email character varying(128) UNIQUE NOT NULL, -- lawyer's professional email\n    phone character varying(32), -- lawyer's contact phone number\n    specialization text, -- areas of legal expertise\n    hire_date timestamp NOT NULL, -- date the lawyer was hired or joined\n    is_partner boolean DEFAULT false, -- flag indicating if the lawyer is a partner\n    PRIMARY KEY (lawyer_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List each claim_handler_id along with the number of claims they've handled and the total settlement_amount they've paid out."}, {"role": "assistant", "content": "SELECT claim_handler_id,\n       COUNT(*) AS total_claims,\n       SUM(settlement_amount) AS total_settlement\nFROM insurance.claims\nGROUP BY claim_handler_id;"}, {"role": "user", "content": "In addition, include the claim_id of the single claim with the highest settlement_amount for each handler."}, {"role": "assistant", "content": "SELECT ag.claim_handler_id,\n       ag.total_claims,\n       ag.total_settlement,\n       c_max.claim_id               AS max_settlement_claim_id,\n       c_max.settlement_amount      AS max_settlement_amount\nFROM (\n  SELECT claim_handler_id,\n         COUNT(*) AS total_claims,\n         SUM(settlement_amount) AS total_settlement\n  FROM insurance.claims\n  GROUP BY claim_handler_id\n) ag\nJOIN insurance.claims c_max\n  ON c_max.claim_handler_id = ag.claim_handler_id\n  AND c_max.settlement_amount = (\n    SELECT MAX(settlement_amount)\n    FROM insurance.claims\n    WHERE claim_handler_id = ag.claim_handler_id\n  );"}, {"role": "user", "content": "Only include handlers who have managed at least 3 claims and have a non-null claim_handler_id."}, {"role": "assistant", "content": "SELECT ag.claim_handler_id,\n       ag.total_claims,\n       ag.total_settlement,\n       c_max.claim_id               AS max_settlement_claim_id,\n       c_max.settlement_amount      AS max_settlement_amount\nFROM (\n  SELECT claim_handler_id,\n         COUNT(*) AS total_claims,\n         SUM(settlement_amount) AS total_settlement\n  FROM insurance.claims\n  GROUP BY claim_handler_id\n  HAVING COUNT(*) >= 3\n     AND claim_handler_id IS NOT NULL\n) ag\nJOIN insurance.claims c_max\n  ON c_max.claim_handler_id = ag.claim_handler_id\n  AND c_max.settlement_amount = (\n    SELECT MAX(settlement_amount)\n    FROM insurance.claims\n    WHERE claim_handler_id = ag.claim_handler_id\n  );"}, {"role": "user", "content": "Finally, sort the results by total_settlement in descending order."}, {"role": "assistant", "content": "SELECT ag.claim_handler_id,\n       ag.total_claims,\n       ag.total_settlement,\n       c_max.claim_id               AS max_settlement_claim_id,\n       c_max.settlement_amount      AS max_settlement_amount\nFROM (\n  SELECT claim_handler_id,\n         COUNT(*) AS total_claims,\n         SUM(settlement_amount) AS total_settlement\n  FROM insurance.claims\n  GROUP BY claim_handler_id\n  HAVING COUNT(*) >= 3\n     AND claim_handler_id IS NOT NULL\n) ag\nJOIN insurance.claims c_max\n  ON c_max.claim_handler_id = ag.claim_handler_id\n  AND c_max.settlement_amount = (\n    SELECT MAX(settlement_amount)\n    FROM insurance.claims\n    WHERE claim_handler_id = ag.claim_handler_id\n  )\nORDER BY ag.total_settlement DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.claims (\n    claim_id character varying(64) NOT NULL, -- unique identifier for the claim\n    policy_id character varying(64) NOT NULL, -- identifier of the policy under which the claim is made (FK to policies)\n    customer_id character varying(64) NOT NULL, -- identifier of the customer making the claim (FK to customers)\n    incident_date timestamp NOT NULL, -- date and time of the incident leading to the claim\n    reported_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- date the claim was reported\n    description text NOT NULL, -- detailed description of the incident and claim\n    estimated_loss numeric(15, 2), -- initial estimated cost of the loss\n    status character varying(30) NOT NULL, -- e.g., Filed, Processing, Under Review, Approved, Denied, Settled\n    settlement_amount numeric(15, 2), -- final amount paid out\n    settlement_date date,\n    claim_handler_id character varying(64), -- identifier for the employee handling the claim (FK to employees/adjusters)\n    police_report_number character varying(100),\n    PRIMARY KEY (claim_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Show the total transaction amount for each customer, including their full name and risk profile. Join customers to accounts and then to transactions."}, {"role": "assistant", "content": "SELECT\n  T2.first_name,\n  T2.last_name,\n  T2.risk_profile,\n  SUM(T1.amount) AS total_transaction_amount\nFROM financial_services.transactions AS T1\nINNER JOIN financial_services.accounts AS T3\n  ON T1.account_id = T3.account_id\nINNER JOIN financial_services.customers AS T2\n  ON T3.customer_id = T2.customer_id\nGROUP BY\n  T2.customer_id,\n  T2.first_name,\n  T2.last_name,\n  T2.risk_profile;"}, {"role": "user", "content": "Filter this report to only include transactions from the last 90 days."}, {"role": "assistant", "content": "SELECT\n  T2.first_name,\n  T2.last_name,\n  T2.risk_profile,\n  SUM(T1.amount) AS total_transaction_amount\nFROM financial_services.transactions AS T1\nINNER JOIN financial_services.accounts AS T3\n  ON T1.account_id = T3.account_id\nINNER JOIN financial_services.customers AS T2\n  ON T3.customer_id = T2.customer_id\nWHERE\n  T1.transaction_date >= CURRENT_DATE - INTERVAL '90 days'\nGROUP BY\n  T2.customer_id,\n  T2.first_name,\n  T2.last_name,\n  T2.risk_profile;"}, {"role": "user", "content": "Also, only include customers whose total transaction amount in this period exceeds 1000."}, {"role": "assistant", "content": "SELECT\n  T2.first_name,\n  T2.last_name,\n  T2.risk_profile,\n  SUM(T1.amount) AS total_transaction_amount\nFROM financial_services.transactions AS T1\nINNER JOIN financial_services.accounts AS T3\n  ON T1.account_id = T3.account_id\nINNER JOIN financial_services.customers AS T2\n  ON T3.customer_id = T2.customer_id\nWHERE\n  T1.transaction_date >= CURRENT_DATE - INTERVAL '90 days'\nGROUP BY\n  T2.customer_id,\n  T2.first_name,\n  T2.last_name,\n  T2.risk_profile\nHAVING\n  SUM(T1.amount) > 1000;"}, {"role": "user", "content": "Sort the results by total transaction amount in descending order and limit to the top 10 customers."}, {"role": "assistant", "content": "SELECT\n  T2.first_name,\n  T2.last_name,\n  T2.risk_profile,\n  SUM(T1.amount) AS total_transaction_amount\nFROM financial_services.transactions AS T1\nINNER JOIN financial_services.accounts AS T3\n  ON T1.account_id = T3.account_id\nINNER JOIN financial_services.customers AS T2\n  ON T3.customer_id = T2.customer_id\nWHERE\n  T1.transaction_date >= CURRENT_DATE - INTERVAL '90 days'\nGROUP BY\n  T2.customer_id,\n  T2.first_name,\n  T2.last_name,\n  T2.risk_profile\nHAVING\n  SUM(T1.amount) > 1000\nORDER BY\n  total_transaction_amount DESC\nLIMIT 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.customers ( customer_id text, first_name text, last_name text, date_of_birth date, ssn_hash text, address text, city text, state text, zip_code text, country text, email text, phone_number text, created_at timestamp, status text, risk_profile text )\nCREATE TABLE financial_services.accounts ( account_id text, customer_id text, account_number text, account_type text, balance numeric, currency text, opened_date date, status text, interest_rate numeric, last_updated_at timestamp )\nCREATE TABLE financial_services.transactions (\n    transaction_id character varying(64) NOT NULL, -- unique identifier for the transaction\n    account_id character varying(64) NOT NULL, -- account involved in the transaction\n    related_account_id character varying(64), -- counterpart account for transfers\n    transaction_type character varying(50) NOT NULL, -- e.g., Deposit, Withdrawal, Transfer, Payment, Fee, Interest\n    amount numeric(19, 4) NOT NULL, -- transaction amount\n    currency character varying(3) NOT NULL, -- transaction currency\n    transaction_date timestamp NOT NULL, -- exact time of the transaction\n    effective_date date NOT NULL, -- date the transaction affects the balance\n    description text, -- description or memo of the transaction\n    status character varying(32) NOT NULL, -- e.g., Pending, Completed, Failed, Reversed\n    reference_number character varying(128), -- external reference if applicable (e.g., check number)\n    PRIMARY KEY (transaction_id),\n    FOREIGN KEY (account_id) REFERENCES financial_services.accounts(account_id),\n    FOREIGN KEY (related_account_id) REFERENCES financial_services.accounts(account_id)\n)\nCREATE TABLE financial_services.securities ( security_id.text, ticker_symbol.text, isin_code.text, cusip_code.text, security_name.text, security_type.text, exchange.text, currency.text, issuer_name.text, sector.text, last_updated.timestamp )\nCREATE TABLE financial_services.trades ( trade_id text PRIMARY KEY, account_id text, security_id text, order_id text, trade_type text, quantity numeric, price_per_unit numeric, total_amount numeric, commission numeric, trade_timestamp timestamp, settlement_date date, status text, execution_venue text )\nCREATE TABLE financial_services.market_data ( data_point_id.bigint, security_id.text, data_timestamp.timestamp, open_price.numeric, high_price.numeric, low_price.numeric, close_price.numeric, adjusted_close_price.numeric, volume.bigint, source.text )\nCREATE TABLE financial_services.employees (\n    employee_id character varying(64) NOT NULL,  -- unique identifier for the employee\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    job_title character varying(100) NOT NULL, -- e.g., Teller, Branch Manager, Financial Advisor, Analyst\n    department character varying(100), -- e.g., Retail Banking, Wealth Management, IT\n    branch_id character varying(64), -- Identifier for the branch they work at (if applicable)\n    email character varying(128) NOT NULL UNIQUE,\n    phone_extension character varying(20),\n    hire_date date NOT NULL,\n    termination_date date, -- Date of termination, null if currently employed\n    manager_id character varying(64), -- Self-referencing key for manager relationship\n    status character varying(32) NOT NULL, -- e.g., Active, Terminated, On Leave\n    PRIMARY KEY (employee_id),\n    FOREIGN KEY (branch_id) REFERENCES financial_services.branches(branch_id), -- Assuming a branches table exists\n    FOREIGN KEY (manager_id) REFERENCES financial_services.employees(employee_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Find all documents of type 'Correspondence' uploaded in 2023. Show the document name, upload timestamp, and the name of the case it belongs to."}, {"role": "assistant", "content": "SELECT T1.document_name, T1.upload_timestamp, T2.case_name FROM legal_services.documents AS T1 JOIN legal_services.cases AS T2 ON T1.case_id = T2.case_id WHERE T1.document_type = 'Correspondence' AND EXTRACT(YEAR FROM T1.upload_timestamp) = 2023;"}, {"role": "user", "content": "Now, only show the documents for cases handled by lawyer with ID 'lawyer_001'."}, {"role": "assistant", "content": "SELECT T1.document_name, T1.upload_timestamp, T2.case_name FROM legal_services.documents AS T1 JOIN legal_services.cases AS T2 ON T1.case_id = T2.case_id WHERE T1.document_type = 'Correspondence' AND EXTRACT(YEAR FROM T1.upload_timestamp) = 2023 AND T2.lead_lawyer_id = 'lawyer_001';"}, {"role": "user", "content": "Additionally, include the first and last name of the lawyer who actually uploaded the document, and sort the results by upload timestamp descending."}, {"role": "assistant", "content": "SELECT T1.document_name, T1.upload_timestamp, T2.case_name, T3.first_name, T3.last_name FROM legal_services.documents AS T1 JOIN legal_services.cases AS T2 ON T1.case_id = T2.case_id JOIN legal_services.lawyers AS T3 ON T1.uploaded_by_lawyer_id = T3.lawyer_id WHERE T1.document_type = 'Correspondence' AND EXTRACT(YEAR FROM T1.upload_timestamp) = 2023 AND T2.lead_lawyer_id = 'lawyer_001' ORDER BY T1.upload_timestamp DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.clients ( client_id text PRIMARY KEY, first_name text, last_name text, company_name text, email text UNIQUE, phone text, address text, date_registered timestamp, status text )\nCREATE TABLE legal_services.law_firms ( firm_id text PRIMARY KEY, firm_name text, address text, phone text, website text, founded_date date, managing_partner_id text )\nCREATE TABLE legal_services.cases ( case_id.text, case_number.text, case_name.text, client_id.text, lead_lawyer_id.text, case_type.text, status.text, date_opened.timestamp, date_closed.timestamp, description.text, court_jurisdiction.text )\nCREATE TABLE legal_services.documents (\n    document_id character varying(64) NOT NULL,  -- unique identifier for the document\n    case_id character varying(64) NOT NULL, -- FK to cases table\n    document_name character varying(255) NOT NULL, -- name of the document file\n    document_type character varying(100), -- e.g., Pleading, Contract, Evidence, Correspondence\n    storage_path text NOT NULL, -- path or reference to the document storage location\n    uploaded_by_lawyer_id character varying(64), -- FK to lawyers table (who uploaded it)\n    upload_timestamp timestamp NOT NULL, -- time the document was uploaded\n    version integer DEFAULT 1, -- document version number\n    description text, -- brief description or notes about the document\n    PRIMARY KEY (document_id)\n)\nCREATE TABLE legal_services.appointments (\n    appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment\n    client_id character varying(64) NOT NULL, -- FK to clients table\n    lawyer_id character varying(64) NOT NULL, -- FK to lawyers table\n    case_id character varying(64), -- FK to cases table (optional, if related to a specific case)\n    start_time timestamp NOT NULL, -- scheduled start date and time\n    end_time timestamp NOT NULL, -- scheduled end date and time\n    location text, -- location of the meeting (address or virtual link)\n    subject character varying(255), -- subject or purpose of the appointment\n    notes text, -- additional notes for the appointment\n    status character varying(50) NOT NULL, -- e.g., Scheduled, Completed, Canceled, Rescheduled\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n    PRIMARY KEY (appointment_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List the case number, case name, and the full name of the client for cases that have uploaded documents."}, {"role": "assistant", "content": "SELECT T1.case_number ,  T1.case_name ,  T2.full_name FROM legal_services.cases AS T1 JOIN legal_services.clients AS T2 ON T1.client_id  =  T2.client_id WHERE EXISTS ( SELECT 1 FROM legal_services.documents AS T3 WHERE T3.case_id  =  T1.case_id )"}, {"role": "user", "content": "Also include the full name of the lead lawyer for these cases."}, {"role": "assistant", "content": "SELECT T1.case_number ,  T1.case_name ,  T2.full_name AS client_name ,  T4.full_name AS lawyer_name FROM legal_services.cases AS T1 JOIN legal_services.clients AS T2 ON T1.client_id  =  T2.client_id JOIN legal_services.lawyers AS T4 ON T1.lead_lawyer_id  =  T4.lawyer_id WHERE EXISTS ( SELECT 1 FROM legal_services.documents AS T3 WHERE T3.case_id  =  T1.case_id )"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.documents ( document_id.text, case_id.text, document_name.text, document_type.text, storage_path.text, uploaded_by_lawyer_id.text, upload_timestamp.timestamp, version.integer, description.text )\n"}
{"conversations": [{"role": "user", "content": "Show me the average number of current players per server for each region."}, {"role": "assistant", "content": "SELECT region, AVG(current_players) AS avg_current_players\nFROM gaming_technology.servers\nGROUP BY region;"}, {"role": "user", "content": "Only include regions where the average is above 50."}, {"role": "assistant", "content": "SELECT region, AVG(current_players) AS avg_current_players\nFROM gaming_technology.servers\nGROUP BY region\nHAVING AVG(current_players) > 50;"}, {"role": "user", "content": "Also show the total number of servers for each region in the result."}, {"role": "assistant", "content": "SELECT region, AVG(current_players) AS avg_current_players, COUNT(*) AS total_servers\nFROM gaming_technology.servers\nGROUP BY region\nHAVING AVG(current_players) > 50;"}, {"role": "user", "content": "Sort the list by avg_current_players descending."}, {"role": "assistant", "content": "SELECT region, AVG(current_players) AS avg_current_players, COUNT(*) AS total_servers\nFROM gaming_technology.servers\nGROUP BY region\nHAVING AVG(current_players) > 50\nORDER BY avg_current_players DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.games (\n    game_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game\n    title character varying(200) NOT NULL, -- official title of the game\n    developer_id uuid NOT NULL, -- FK linking to the developers table\n    publisher_id uuid, -- FK linking to a potential publishers table (optional)\n    genre character varying(100), -- primary genre (e.g., RPG, FPS, Strategy)\n    release_date date, -- official release date\n    description text, -- short description or synopsis of the game\n    platform character varying(50) NOT NULL, -- primary platform (e.g., PC, PlayStation 5, Xbox Series X, Mobile)\n    engine character varying(100), -- game engine used (e.g., Unreal Engine 5, Unity)\n    website character varying(255), -- official website URL\n    PRIMARY KEY (game_id)\n    -- FOREIGN KEY (developer_id) REFERENCES gaming_technology.developers(developer_id) -- Example FK constraint\n)\nCREATE TABLE gaming_technology.developers ( developer_id uuid, name text, country text, founded_year integer, website text, created_at timestamp with time zone )\nCREATE TABLE gaming_technology.game_sessions (\n    session_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game session\n    player_id uuid NOT NULL, -- FK linking to the players table\n    game_id uuid NOT NULL, -- FK linking to the games table\n    server_id uuid, -- FK linking to the servers table (nullable for single-player)\n    start_time timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the session began\n    end_time timestamp with time zone, -- when the session ended (null if ongoing)\n    duration_seconds integer, -- calculated duration of the session in seconds\n    score integer, -- player's score for the session, if applicable\n    session_data jsonb, -- flexible field for session-specific info (e.g., map played, character used)\n    PRIMARY KEY (session_id)\n    -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n    -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id),\n    -- FOREIGN KEY (server_id) REFERENCES gaming_technology.servers(server_id)\n)\nCREATE TABLE gaming_technology.servers ( server_id uuid NOT NULL DEFAULT gen_random_uuid(), game_id uuid NOT NULL, server_name character varying(150), region character varying(50) NOT NULL, ip_address character varying(45), port integer, current_players integer NOT NULL DEFAULT 0, max_players integer NOT NULL, status character varying(30) NOT NULL DEFAULT 'offline', last_heartbeat timestamp with time zone, PRIMARY KEY (server_id) )\nCREATE TABLE gaming_technology.achievements ( achievement_id uuid, game_id uuid, name text, description text, icon_url text, points integer, hidden boolean )\nCREATE TABLE gaming_technology.player_achievements ( player_achievement_id.uuid, player_id.uuid, achievement_id.uuid, unlocked_at.timestamptz )\nCREATE TABLE gaming_technology.in_game_items ( item_id uuid NOT NULL DEFAULT gen_random_uuid(), game_id uuid NOT NULL, item_name character varying(150) NOT NULL, item_type character varying(50) NOT NULL, description text, rarity character varying(30), cost_currency character varying(10), cost_amount numeric(12, 2), attributes jsonb, PRIMARY KEY (item_id) )\nCREATE TABLE gaming_technology.player_inventory ( inventory_id uuid PRIMARY KEY, player_id uuid, item_id uuid, quantity int, acquired_at timestamptz, instance_data jsonb )\n"}
{"conversations": [{"role": "user", "content": "Find all users who registered with a Yahoo email address, along with their registration dates."}, {"role": "assistant", "content": "SELECT user_id, username, email, password_hash FROM blockchain.users WHERE email LIKE '%@yahoo.com';"}, {"role": "user", "content": "This query doesn't show registration dates. Can you modify it to include the registration date?"}, {"role": "assistant", "content": "I notice the users table doesn't have a registration date column. Would you like me to show other available information from the users table?"}, {"role": "user", "content": "Then just show me the count of Yahoo email users instead."}, {"role": "assistant", "content": "SELECT COUNT(*) as yahoo_user_count FROM blockchain.users WHERE email LIKE '%@yahoo.com';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE blockchain.blocks ( block_id text, previous_block_id text, timestamp timestamp, nonce integer, merkle_root text, difficulty integer )\nCREATE TABLE blockchain.transactions (\n    transaction_id character varying(64) NOT NULL,  -- unique identifier for the transaction\n    block_id character varying(64) NOT NULL, -- identifier of the block containing the transaction\n    sender_address character varying(128) NOT NULL, -- address of the sender\n    receiver_address character varying(128) NOT NULL, -- address of the receiver\n    amount numeric(38,14) NOT NULL, -- amount transferred\n    timestamp timestamp NOT NULL, -- time when the transaction was created\n    signature text NOT NULL, -- digital signature of the transaction\n    PRIMARY KEY (transaction_id)\n)\nCREATE TABLE blockchain.addresses ( address_id text PRIMARY KEY, public_key text, balance numeric )\nCREATE TABLE blockchain.users ( user_id character varying(64) NOT NULL, username character varying(128) NOT NULL, email character varying(128) NOT NULL, password_hash text NOT NULL, PRIMARY KEY (user_id) )\n"}
{"conversations": [{"role": "user", "content": "List claims along with the name of the insurance product associated with the policy under which the claim was filed. Show claim_id, incident_date, and product_name."}, {"role": "assistant", "content": "SELECT T1.claim_id, T1.incident_date, T3.product_name FROM insurance.claims AS T1 JOIN policies AS T2 ON T1.policy_id = T2.policy_id JOIN insurance.insurance_products AS T3 ON T2.product_id = T3.product_id;"}, {"role": "user", "content": "Only show claims related to 'auto' insurance products."}, {"role": "assistant", "content": "SELECT T1.claim_id, T1.incident_date, T3.product_name FROM insurance.claims AS T1 JOIN policies AS T2 ON T1.policy_id = T2.policy_id JOIN insurance.insurance_products AS T3 ON T2.product_id = T3.product_id WHERE T3.product_type = 'Auto';"}, {"role": "user", "content": "Further filter the results to only include claims with status 'Settled' or 'Closed'."}, {"role": "assistant", "content": "SELECT T1.claim_id, T1.incident_date, T3.product_name FROM insurance.claims AS T1 JOIN policies AS T2 ON T1.policy_id = T2.policy_id JOIN insurance.insurance_products AS T3 ON T2.product_id = T3.product_id WHERE T3.product_type = 'Auto' AND T1.status IN ('Settled', 'Closed');"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.claims (\n    claim_id character varying(64) NOT NULL, -- unique identifier for the claim\n    policy_id character varying(64) NOT NULL, -- identifier of the policy under which the claim is made (FK to policies)\n    customer_id character varying(64) NOT NULL, -- identifier of the customer making the claim (FK to customers)\n    incident_date timestamp NOT NULL, -- date and time of the incident leading to the claim\n    reported_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- date the claim was reported\n    description text NOT NULL, -- detailed description of the incident and claim\n    estimated_loss numeric(15, 2), -- initial estimated cost of the loss\n    status character varying(30) NOT NULL, -- e.g., Filed, Processing, Under Review, Approved, Denied, Settled\n    settlement_amount numeric(15, 2), -- final amount paid out\n    settlement_date date,\n    claim_handler_id character varying(64), -- identifier for the employee handling the claim (FK to employees/adjusters)\n    police_report_number character varying(100),\n    PRIMARY KEY (claim_id)\n)\nCREATE TABLE insurance.insurance_products (\n    product_id character varying(64) NOT NULL, -- unique identifier for the insurance product\n    product_name character varying(150) NOT NULL, -- name of the insurance product (e.g., 'Comprehensive Auto Insurance')\n    product_type character varying(50) NOT NULL, -- category like 'Auto', 'Home', 'Life', 'Health', 'Travel'\n    description text, -- detailed description of the product\n    base_premium numeric(10, 2) NOT NULL, -- starting premium before adjustments\n    coverage_details text, -- details about what is covered (could be JSON or structured text)\n    underwriting_rules text, -- rules used for assessing risk and eligibility\n    is_active boolean NOT NULL DEFAULT true, -- whether the product is currently offered\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n    updated_at timestamp,\n    PRIMARY KEY (product_id)\n)\nCREATE TABLE insurance.premium_payments (\n    payment_id character varying(64) NOT NULL, -- unique identifier for the payment\n    policy_id character varying(64) NOT NULL, -- identifier of the policy the payment is for (FK to policies)\n    customer_id character varying(64) NOT NULL, -- identifier of the customer making the payment (FK to customers)\n    payment_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- date the payment was received\n    amount_paid numeric(12, 2) NOT NULL, -- amount of the payment\n    payment_method character varying(50), -- e.g., Credit Card, Bank Transfer, Check\n    transaction_reference character varying(128) UNIQUE, -- reference from payment processor\n    due_date date, -- due date for this payment installment\n    payment_period_start date, -- start date of the period this payment covers\n    payment_period_end date, -- end date of the period this payment covers\n    status character varying(30) NOT NULL DEFAULT 'Completed', -- e.g., Completed, Pending, Failed, Refunded\n    PRIMARY KEY (payment_id)\n)\nCREATE TABLE insurance.policy_beneficiaries (\n    beneficiary_id character varying(64) NOT NULL, -- unique identifier for the beneficiary entry\n    policy_id character varying(64) NOT NULL, -- identifier of the life/relevant policy (FK to policies)\n    customer_id character varying(64) NOT NULL, -- identifier of the beneficiary (could be FK to customers or store info directly)\n    first_name character varying(100) NOT NULL, -- beneficiary first name (if not linking to customers table)\n    last_name character varying(100) NOT NULL, -- beneficiary last name\n    relationship character varying(50) NOT NULL, -- relationship to the policyholder (e.g., Spouse, Child, Parent)\n    percentage_share numeric(5, 2) NOT NULL CHECK (percentage_share > 0 AND percentage_share <= 100), -- percentage of payout\n    contact_info text, -- contact details for the beneficiary\n    added_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n    PRIMARY KEY (beneficiary_id),\n    UNIQUE (policy_id, customer_id) -- Ensure a person is listed only once per policy\n)\n"}
{"conversations": [{"role": "user", "content": "Can you help me retrieve the inventory details for a specific component ID, including the quantity and warehouse location?"}, {"role": "assistant", "content": "HGETALL inv:<inventory_record_id>"}, {"role": "user", "content": "Can you also include the batch number for that inventory record?"}, {"role": "assistant", "content": "HGETALL inv:<inventory_record_id>"}, {"role": "user", "content": "If I want to check the expiry date for this component, how can I retrieve that information?"}, {"role": "assistant", "content": "ZRANGE component_expiry:<component_id> 0 -1 WITHSCORES"}, {"role": "user", "content": "Can you filter the results to show only inventory records with an expiry date after a specific timestamp?"}, {"role": "assistant", "content": "ZRANGEBYSCORE component_expiry:<component_id> <specific_timestamp> +inf WITHSCORES"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nUse Hashes. Key pattern: 'inv:<inventory_record_id>'. Example: HSET inv:INVREC500 component_id \"component:WINGBOLT\" quantity 5000 location_warehouse \"WH3\" batch_number \"BCH778899\" ... Consider Sorted Set by expiry date: ZADD component_expiry:<component_id> <expiry_timestamp> <inventory_record_id>.\n"}
{"conversations": [{"role": "user", "content": "Show me the deployer address and the count of contracts they have deployed on the 'mainnet' network, but only for deployers who have deployed more than 5 contracts on mainnet. Sort the results by the count in descending order."}, {"role": "assistant", "content": "SELECT deployer_address, COUNT(*) FROM web3.contracts WHERE network_id = 'mainnet' GROUP BY deployer_address HAVING COUNT(*) > 5 ORDER BY COUNT(*) DESC;"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nCREATE TABLE web3.contracts ( contract_id text PRIMARY KEY, address text, abi text, bytecode text, deployer_address text, deployed_at timestamp, network_id text, status text )\n"}
{"conversations": [{"role": "user", "content": "Show all appointments with subject containing 'Review' and their corresponding case_id."}, {"role": "assistant", "content": "SELECT appointment_id, subject, case_id\nFROM legal_services.appointments\nWHERE subject ILIKE '%Review%';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.invoices ( invoice_id.text, invoice_number.text, client_id.text, case_id.text, issue_date.date, due_date.date, total_amount.numeric, amount_paid.numeric, status.text, payment_date.timestamp, notes.text, created_at.timestamp )\nCREATE TABLE legal_services.appointments ( appointment_id.text, client_id.text, lawyer_id.text, case_id.text, start_time.timestamp, end_time.timestamp, location.text, subject.text, notes.text, status.text, created_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "List all active SUI coins with their symbol, name, and total balance across all owners."}, {"role": "assistant", "content": "SELECT scm.coin_type, scm.symbol, scm.name, SUM(CAST(sc.balance AS DECIMAL)) AS total_balance\nFROM sui_coins_metadata scm\nJOIN sui_coins sc ON sc.coin_type = scm.coin_type\nWHERE sc.status = 'active' AND scm.status = 'exists'\nGROUP BY scm.coin_type, scm.symbol, scm.name;"}, {"role": "user", "content": "Filter coins with description containing 'staking' and sort by total_balance descending."}, {"role": "assistant", "content": "SELECT sub.coin_type, sub.symbol, sub.name, sub.total_balance\nFROM (\n  SELECT scm.coin_type, scm.symbol, scm.name, SUM(CAST(sc.balance AS DECIMAL)) AS total_balance\n  FROM sui_coins_metadata scm\n  JOIN sui_coins sc ON sc.coin_type = scm.coin_type\n  WHERE sc.status = 'active' AND scm.status = 'exists' AND LOWER(scm.description) LIKE '%staking%'\n  GROUP BY scm.coin_type, scm.symbol, scm.name\n) sub\nORDER BY sub.total_balance DESC;"}, {"role": "user", "content": "Limit the result to the top 3 coins."}, {"role": "assistant", "content": "SELECT sub.coin_type, sub.symbol, sub.name, sub.total_balance\nFROM (\n  SELECT scm.coin_type, scm.symbol, scm.name, SUM(CAST(sc.balance AS DECIMAL)) AS total_balance\n  FROM sui_coins_metadata scm\n  JOIN sui_coins sc ON sc.coin_type = scm.coin_type\n  WHERE sc.status = 'active' AND scm.status = 'exists' AND LOWER(scm.description) LIKE '%staking%'\n  GROUP BY scm.coin_type, scm.symbol, scm.name\n) sub\nORDER BY sub.total_balance DESC\nLIMIT 3;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp.timestamp, block_number.bigint, transaction_hash.text, transaction_index.bigint, from_address.text, contract_address.text, symbol.text, total_supply.text, name.text, decimals.bigint, is_erc20.integer, is_erc721.integer, is_erc1155.integer, is_proxy.integer, extra_info.text, pk.integer )\nCREATE TABLE erc1155_approval_for_all (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the transaction\n    transaction_index integer NOT NULL, -- Index of the transaction within the block\n    transaction_hash varchar(66) NOT NULL, -- Transaction hash\n    log_index integer NOT NULL, -- Log index\n    contract_address varchar(42) NOT NULL  -- Event contract address\n)\nCREATE TABLE erc20_balances ( block_number bigint, contract_address varchar, wallet_address varchar, amount varchar, pk varchar )\nCREATE TABLE nft_holders ( block_number.bigint, contract_address.text, wallet_address.text, token_id.text, contract_type.text, amount.text, pk.text )\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_coins_metadata (\n    object_id varchar NOT NULL, -- object id of the coin metadata object\n    coin_type varchar NOT NULL, -- coin type, eg. 0x...66::reap_token::REAP_TOKEN\n    status varchar NOT NULL, -- coin status, eg. exists, deleted\n    decimals bigint NOT NULL, -- decimals of the coin\n    description varchar NOT NULL, -- description of the coin\n    icon_url varchar NOT NULL, -- icon url of the coin\n    symbol varchar NOT NULL, -- symbol of the coin\n    name varchar NOT NULL  -- name of the coin\n)\nCREATE TABLE nft_collections ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, name varchar NOT NULL, symbol varchar NOT NULL, deploy_block_number bigint NOT NULL, deploy_block_time bigint NOT NULL, erc_type varchar NOT NULL, owner varchar NOT NULL, traits varchar NOT NULL, description varchar NOT NULL, slug varchar NOT NULL, media_info varchar NOT NULL, image_url varchar NOT NULL, banner_image_url varchar NOT NULL, updated_at bigint NOT NULL, banner varchar NOT NULL, token_count bigint NOT NULL, floor_price varchar NOT NULL, floor_price_symbol varchar NOT NULL, floor_price_contract varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_prices ( uuid.text, blockchain.text, address.text, decimals.bigint, symbol.text, price.real, timestamp.timestamp )\nCREATE TABLE erc20_approval ( block_number.bigint, block_timestamp.timestamp, transaction_index.integer, transaction_hash.text, log_index.integer, contract_address.text, pk.integer )\nCREATE TABLE token_balances (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n    tick varchar NOT NULL, -- Token tick\n    wallet_address varchar(42) NOT NULL, -- Address of owner\n    total_supply decimal(38,0) NOT NULL, -- Max supply\n    amount decimal(38,0) NOT NULL  -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE token_activities ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\nCREATE TABLE mud_holesky_redstone ( address text, table_id text, key_bytes text, key0 text, key1 text, static_data text, encoded_lengths text, dynamic_data text, is_deleted boolean, block_number bigint, log_index bigint )\nCREATE TABLE token_balances_bitcoin (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n    tick varchar(255) NOT NULL, -- Ticker: Identifier of the inscription\n    wallet_address varchar(42) NOT NULL, -- Address of owner\n    total_supply varchar NOT NULL, -- Max supply: Set max supply of the inscription\n    amount varchar NOT NULL  -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_balances_avalanche (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n    tick varchar(20) NOT NULL, -- Ticker: Identifier of the inscription\n    wallet_address varchar(42) NOT NULL, -- Address of owner\n    total_supply decimal(38,0) NOT NULL, -- Max supply: Set max supply of the inscription\n    amount decimal(38,0) NOT NULL  -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id varchar )\n"}
{"conversations": [{"role": "user", "content": "List all documents that have multiple versions, including document_name, case_id, and the count of versions."}, {"role": "assistant", "content": "SELECT document_name,\n       case_id,\n       COUNT(*) AS version_count\nFROM legal_services.documents\nGROUP BY document_name, case_id\nHAVING COUNT(*) > 1;"}, {"role": "user", "content": "Actually, I only want to include those with at least three versions."}, {"role": "assistant", "content": "SELECT document_name,\n       case_id,\n       COUNT(*) AS version_count\nFROM legal_services.documents\nGROUP BY document_name, case_id\nHAVING COUNT(*) >= 3;"}, {"role": "user", "content": "Also include the lawyer ID who uploaded the latest version for each document."}, {"role": "assistant", "content": "SELECT d.document_name,\n       d.case_id,\n       m.version_count,\n       d.uploaded_by_lawyer_id\nFROM legal_services.documents d\nJOIN (\n  SELECT document_name,\n         case_id,\n         COUNT(*) AS version_count,\n         MAX(version) AS max_version\n  FROM legal_services.documents\n  GROUP BY document_name, case_id\n  HAVING COUNT(*) >= 3\n) m\n  ON d.document_name = m.document_name\n AND d.case_id = m.case_id\n AND d.version = m.max_version;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.documents ( document_id text, case_id text, document_name text, document_type text, storage_path text, uploaded_by_lawyer_id text, upload_timestamp timestamp, version integer, description text )\n"}
{"conversations": [{"role": "user", "content": "For each event, display its event_id, the event_id of the previous event in the same transaction (if any), and the log_index of both events."}, {"role": "assistant", "content": "SELECT curr.event_id   AS current_event_id,\n       prev.event_id   AS previous_event_id,\n       curr.log_index  AS current_log_index,\n       prev.log_index  AS previous_log_index,\n       curr.transaction_id\nFROM web3.events curr\nLEFT JOIN web3.events prev\n  ON curr.transaction_id = prev.transaction_id\n AND curr.log_index = prev.log_index + 1;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.events ( event_id character varying(64) NOT NULL, contract_id character varying(64) NOT NULL, event_name character varying(128) NOT NULL, data text NOT NULL, emitted_at timestamp NOT NULL, transaction_id character varying(64) NOT NULL, log_index integer NOT NULL, PRIMARY KEY (event_id) )\n"}
{"conversations": [{"role": "user", "content": "Find all pairs of transactions where both transactions have the same nonce and from_address, but different transaction_id. Show both transaction IDs, the shared from_address, shared nonce, and their block numbers."}, {"role": "assistant", "content": "SELECT t1.transaction_id AS transaction_id_1, t2.transaction_id AS transaction_id_2, t1.from_address, t1.nonce, t1.block_number AS block_number_1, t2.block_number AS block_number_2\nFROM web3.transactions t1\nJOIN web3.transactions t2\n  ON t1.from_address = t2.from_address\n AND t1.nonce = t2.nonce\n AND t1.transaction_id < t2.transaction_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.transactions (\n    transaction_id character varying(64) NOT NULL,  -- unique identifier for the transaction\n    from_address character varying(128) NOT NULL, -- address of the sender\n    to_address character varying(128), -- address of the receiver (can be null for contract deployment)\n    value numeric(38,14) NOT NULL, -- value transferred\n    gas_used integer NOT NULL, -- amount of gas used by the transaction\n    gas_price numeric(38,14) NOT NULL, -- price of gas at the time of the transaction\n    block_number integer NOT NULL, -- block number containing the transaction\n    timestamp timestamp NOT NULL, -- time when the transaction was mined\n    input_data text, -- input data of the transaction (can be null)\n    status character varying(32) NOT NULL, -- status of the transaction (e.g., success, failed)\n    nonce integer NOT NULL, -- nonce of the sender at the time of the transaction\n    PRIMARY KEY (transaction_id)\n)\n"}
{"conversations": [{"role": "user", "content": "For each guest, calculate their total spending on delivered service orders and the total number of those orders."}, {"role": "assistant", "content": "SELECT g.guest_id,\n       g.first_name || ' ' || g.last_name AS full_name,\n       SUM(so.total_price) AS total_spent,\n       COUNT(*) AS total_orders\nFROM hospitality_technology.guests g\nJOIN hospitality_technology.service_orders so\n  ON g.guest_id = so.guest_id\nWHERE so.status = 'delivered'\nGROUP BY g.guest_id, full_name;"}, {"role": "user", "content": "I need the breakdown by month for the current year. Show guest ID, month, total spent, and total orders."}, {"role": "assistant", "content": "SELECT so.guest_id,\n       DATE_TRUNC('month', so.delivery_timestamp) AS month,\n       SUM(so.total_price) AS total_spent,\n       COUNT(*) AS total_orders\nFROM hospitality_technology.service_orders so\nWHERE so.status = 'delivered'\n  AND so.delivery_timestamp >= '2024-01-01'\n  AND so.delivery_timestamp < '2025-01-01'\nGROUP BY so.guest_id, month\nORDER BY month;"}, {"role": "user", "content": "Also include the guest’s email and only show months where total spent is greater than 500."}, {"role": "assistant", "content": "SELECT sub.guest_id,\n       g.email,\n       sub.month,\n       sub.total_spent,\n       sub.total_orders\nFROM (\n  SELECT so.guest_id,\n         DATE_TRUNC('month', so.delivery_timestamp) AS month,\n         SUM(so.total_price) AS total_spent,\n         COUNT(*) AS total_orders\n  FROM hospitality_technology.service_orders so\n  WHERE so.status = 'delivered'\n    AND so.delivery_timestamp >= '2024-01-01'\n    AND so.delivery_timestamp < '2025-01-01'\n  GROUP BY so.guest_id, month\n) sub\nJOIN hospitality_technology.guests g\n  ON sub.guest_id = g.guest_id\nWHERE sub.total_spent > 500\nORDER BY sub.month;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.guests ( guest_id text PRIMARY KEY, first_name text, last_name text, email text, phone_number text, date_of_birth date, address_line1 text, city text, state_province text, postal_code text, country_code text, preferences text, loyalty_member_id text, communication_consent boolean, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.reservations ( reservation_id text, property_id text, guest_id text, room_id text, room_type_id text, check_in_date date, check_out_date date, actual_check_in_ts timestamp, actual_check_out_ts timestamp, num_adults integer, num_children integer, status text, booking_source text, rate_plan_id text, total_amount numeric, amount_paid numeric, special_requests text, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.service_orders ( order_id.text, reservation_id.text, guest_id.text, service_id.text, staff_id_ordered.text, staff_id_delivered.text, order_timestamp.timestamp, delivery_timestamp.timestamp, quantity.integer, unit_price.numeric, total_price.numeric, status.text, notes.text, bill_id.text )\nCREATE TABLE hospitality_technology.reviews ( review_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, reservation_id character varying(64) UNIQUE, guest_id character varying(64) NOT NULL, rating_overall integer, rating_cleanliness integer, rating_service integer, rating_location integer, rating_value integer, comment text, review_source character varying(100), review_date timestamp with time zone NOT NULL DEFAULT current_timestamp, is_public boolean DEFAULT true, staff_response text, response_staff_id character varying(64), response_date timestamp with time zone, PRIMARY KEY (review_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (response_staff_id) REFERENCES hospitality_technology.staff(staff_id) )\n"}
{"conversations": [{"role": "user", "content": "Show the prescription ID, medication name, and patient full name for all prescriptions issued in the last 30 days."}, {"role": "assistant", "content": "SELECT pr.prescription_id, m.medication_name, CONCAT(p.first_name, ' ', p.last_name) AS patient_name\nFROM healthcare.prescriptions pr\nJOIN healthcare.medications m ON pr.medication_id = m.medication_id\nJOIN healthcare.patients p ON pr.patient_id = p.patient_id\nWHERE pr.prescription_date >= CURRENT_DATE - INTERVAL '30 days';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, gender character varying(10), address text, phone_number character varying(20), email character varying(128) UNIQUE, emergency_contact_name character varying(200), emergency_contact_phone character varying(20), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (patient_id) )\nCREATE TABLE healthcare.doctors ( doctor_id text, first_name text, last_name text, specialty text, license_number text, phone_number text, email text, hospital_affiliation_id text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.appointments ( appointment_id.text, patient_id.text, doctor_id.text, appointment_time.timestamp, duration_minutes.integer, reason.text, status.text, location_id.text, notes.text, created_at.timestamp )\nCREATE TABLE healthcare.medical_records ( record_id text PRIMARY KEY, patient_id text, appointment_id text, doctor_id text, record_date timestamp, chief_complaint text, present_illness_history text, past_medical_history text, physical_examination_notes text, assessment text, treatment_plan text, vitals text, created_at timestamp )\nCREATE TABLE healthcare.diagnoses (\n    diagnosis_id character varying(64) NOT NULL, -- unique identifier for the diagnosis entry\n    record_id character varying(64) NOT NULL, -- FK linking to the specific medical record entry\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    doctor_id character varying(64) NOT NULL, -- FK to doctors table (diagnosing doctor)\n    diagnosis_code character varying(20) NOT NULL, -- standard code (e.g., ICD-10)\n    code_type character varying(10) NOT NULL DEFAULT 'ICD-10', -- type of code used\n    description text, -- textual description of the diagnosis\n    diagnosis_date date NOT NULL, -- date the diagnosis was made\n    status character varying(32) NOT NULL, -- e.g., Active, Resolved, Ruled Out\n    is_chronic boolean DEFAULT false, -- flag for chronic conditions\n    PRIMARY KEY (diagnosis_id)\n)\nCREATE TABLE healthcare.medications ( medication_id text PRIMARY KEY, medication_name text, generic_name text, manufacturer text, ndc_code text, description text )\nCREATE TABLE healthcare.prescriptions ( prescription_id text, record_id text, patient_id text, doctor_id text, medication_id text, dosage text, frequency text, route text, start_date date, end_date date, quantity_dispensed numeric, refills_allowed integer, prescription_date timestamp )\nCREATE TABLE healthcare.insurance_plans ( plan_id text, plan_name text, insurance_provider text, plan_type text, contact_phone text, website text )\n"}
{"conversations": [{"role": "user", "content": "Show me all transactions (transaction_id, amount, transaction_type) where the transaction_type is 'Transfer' and the status is 'Completed', along with the account_id and related_account_id."}, {"role": "assistant", "content": "SELECT transaction_id, amount, transaction_type, account_id, related_account_id FROM financial_services.transactions WHERE transaction_type = 'Transfer' AND status = 'Completed';"}, {"role": "user", "content": "Now modify the query to include only transfers with amounts greater than $1,000 and sort them by transaction_date in descending order."}, {"role": "assistant", "content": "SELECT transaction_id, amount, transaction_type, account_id, related_account_id FROM financial_services.transactions WHERE transaction_type = 'Transfer' AND status = 'Completed' AND amount > 1000 ORDER BY transaction_date DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.transactions (\n    transaction_id character varying(64) NOT NULL, -- unique identifier for the transaction\n    account_id character varying(64) NOT NULL, -- account involved in the transaction\n    related_account_id character varying(64), -- counterpart account for transfers\n    transaction_type character varying(50) NOT NULL, -- e.g., Deposit, Withdrawal, Transfer, Payment, Fee, Interest\n    amount numeric(19, 4) NOT NULL, -- transaction amount\n    currency character varying(3) NOT NULL, -- transaction currency\n    transaction_date timestamp NOT NULL, -- exact time of the transaction\n    effective_date date NOT NULL, -- date the transaction affects the balance\n    description text, -- description or memo of the transaction\n    status character varying(32) NOT NULL, -- e.g., Pending, Completed, Failed, Reversed\n    reference_number character varying(128), -- external reference if applicable (e.g., check number)\n    PRIMARY KEY (transaction_id),\n    FOREIGN KEY (account_id) REFERENCES financial_services.accounts(account_id),\n    FOREIGN KEY (related_account_id) REFERENCES financial_services.accounts(account_id)\n)\nCREATE TABLE financial_services.trades ( trade_id text, account_id text, security_id text, order_id text, trade_type text, quantity numeric, price_per_unit numeric, total_amount numeric, commission numeric, trade_timestamp timestamp, settlement_date date, status text, execution_venue text )\n"}
{"conversations": [{"role": "user", "content": "List all wallet addresses that have unspent UTXOs with amounts greater than 100, along with the total unspent amount for each address."}, {"role": "assistant", "content": "SELECT w.address, SUM(u.amount) AS total_unspent FROM trading_platform.wallets w JOIN trading_platform.utxos u ON w.address = u.address WHERE u.spent = false AND u.amount > 100 GROUP BY w.address;"}, {"role": "user", "content": "Now modify the query to only include wallets created in the last year."}, {"role": "assistant", "content": "SELECT w.address, SUM(u.amount) AS total_unspent FROM trading_platform.wallets w JOIN trading_platform.utxos u ON w.address = u.address WHERE u.spent = false AND u.amount > 100 AND w.created_at >= NOW() - INTERVAL '1 year' GROUP BY w.address;"}, {"role": "user", "content": "I notice the query has a typo in 'INTERVAL'. Also, can you include the user's email address in the results?"}, {"role": "assistant", "content": "SELECT w.address, u.email, SUM(ut.amount) AS total_unspent FROM trading_platform.wallets w JOIN trading_platform.users u ON w.user_id = u.user_id JOIN trading_platform.utxos ut ON w.address = ut.address WHERE ut.spent = false AND ut.amount > 100 AND w.created_at >= NOW() - INTERVAL '1 year' GROUP BY w.address, u.email;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.users ( user_id text PRIMARY KEY, username text, email text, password_hash text, created_at timestamp )\nCREATE TABLE trading_platform.wallets ( wallet_id text PRIMARY KEY, user_id text, address text, private_key text, created_at timestamp )\nCREATE TABLE trading_platform.orders ( order_id text PRIMARY KEY, user_id text, wallet_id text, asset_id text, order_type text, quantity numeric, price numeric, status text, created_at timestamp )\nCREATE TABLE trading_platform.trades ( trade_id text PRIMARY KEY, order_id text, buyer_id text, seller_id text, asset_id text, quantity numeric, price numeric, traded_at timestamp )\nCREATE TABLE trading_platform.utxos ( utxo_id text PRIMARY KEY, transaction_id text, output_index int, address text, amount numeric, spent boolean )\nCREATE TABLE trading_platform.dapps ( dapp_id text PRIMARY KEY, name text, description text, url text )\nCREATE TABLE trading_platform.metadata ( metadata_id text PRIMARY KEY, asset_id text, key text, value text )\nCREATE TABLE trading_platform.notifications ( notification_id text PRIMARY KEY, user_id text, message text, sent_at timestamp, read_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Count the number of logs for each action type."}, {"role": "assistant", "content": "SELECT action,\n       COUNT(*) AS count\nFROM trading_platform.logs\nGROUP BY action;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.logs ( log_id text PRIMARY KEY, user_id text, action text, details text, logged_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "List lawyers who have any unbilled time entries. Show their first name, last name, and the count of their unbilled entries."}, {"role": "assistant", "content": "SELECT T1.first_name, T1.last_name, COUNT(T2.entry_id) FROM lawyers AS T1 JOIN time_entries AS T2 ON T1.lawyer_id = T2.lawyer_id WHERE T2.is_billed = false GROUP BY T1.lawyer_id, T1.first_name, T1.last_name;"}, {"role": "user", "content": "Modify that query to only include entries marked as billable, and instead show the total hours spent rather than the count."}, {"role": "assistant", "content": "SELECT T1.first_name, T1.last_name, SUM(T2.hours_spent) FROM lawyers AS T1 JOIN time_entries AS T2 ON T1.lawyer_id = T2.lawyer_id WHERE T2.is_billed = false AND T2.is_billable = true GROUP BY T1.lawyer_id, T1.first_name, T1.last_name;"}, {"role": "user", "content": "Now, only show lawyers with more than 10 unbilled billable hours in total, and sort the results by the total hours descending."}, {"role": "assistant", "content": "SELECT T1.first_name, T1.last_name, SUM(T2.hours_spent) FROM lawyers AS T1 JOIN time_entries AS T2 ON T1.lawyer_id = T2.lawyer_id WHERE T2.is_billed = false AND T2.is_billable = true GROUP BY T1.lawyer_id, T1.first_name, T1.last_name HAVING SUM(T2.hours_spent) > 10 ORDER BY SUM(T2.hours_spent) DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.lawyers ( lawyer_id text PRIMARY KEY, first_name text, last_name text, bar_number text UNIQUE, firm_id text, email text UNIQUE, phone text, specialization text, hire_date timestamp, is_partner bool )\nCREATE TABLE legal_services.law_firms ( firm_id text PRIMARY KEY, firm_name text, address text, phone text, website text, founded_date date, managing_partner_id text )\nCREATE TABLE legal_services.documents ( document_id text PRIMARY KEY, case_id text, document_name text, document_type text, storage_path text, uploaded_by_lawyer_id text, upload_timestamp timestamp, version int, description text )\nCREATE TABLE legal_services.time_entries ( entry_id text PRIMARY KEY, case_id text, lawyer_id text, date_worked date, hours_spent numeric, billing_rate numeric, description text, is_billable bool, is_billed bool, invoice_id text, created_at timestamp )\nCREATE TABLE legal_services.invoices ( invoice_id text PRIMARY KEY, invoice_number text UNIQUE, client_id text, case_id text, issue_date date, due_date date, total_amount numeric, amount_paid numeric, status text, payment_date timestamp, notes text, created_at timestamp )\nCREATE TABLE legal_services.appointments ( appointment_id text PRIMARY KEY, client_id text, lawyer_id text, case_id text, start_time timestamp, end_time timestamp, location text, subject text, notes text, status text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Count how many posts have media attachments."}, {"role": "assistant", "content": "SELECT count(*) FROM social_media.posts WHERE media_url IS NOT NULL"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id text PRIMARY KEY, username text, email text, password_hash text, full_name text, profile_picture_url text, bio text, location text, created_at timestamp, updated_at timestamp, is_verified bool )\nCREATE TABLE social_media.posts ( post_id.text, user_id.text, content.text, media_url.text, media_type.text, created_at.timestamp, updated_at.timestamp, visibility.text, location_lat.numeric, location_lon.numeric )\nCREATE TABLE social_media.comments ( comment_id text PRIMARY KEY, post_id text, user_id text, parent_comment_id text, content text, created_at timestamp, updated_at timestamp )\nCREATE TABLE social_media.follows ( follow_id text PRIMARY KEY, follower_user_id text, following_user_id text, created_at timestamp )\nCREATE TABLE social_media.hashtags ( hashtag_id.text, tag_name.text, created_at.timestamp )\nCREATE TABLE social_media.post_hashtags ( post_hashtag_id character varying(64) NOT NULL, post_id character varying(64) NOT NULL, hashtag_id character varying(64) NOT NULL, PRIMARY KEY (post_hashtag_id), CONSTRAINT unique_post_hashtag UNIQUE (post_id, hashtag_id) )\nCREATE TABLE social_media.messages ( message_id text PRIMARY KEY, conversation_id text, sender_user_id text, content text, media_url text, media_type text, sent_at timestamp, read_at timestamp )\nCREATE TABLE social_media.conversations ( conversation_id text, created_at timestamp, last_message_at timestamp, is_group_chat boolean, group_name text )\nCREATE TABLE social_media.conversation_participants ( participant_id text, conversation_id text, user_id text, joined_at timestamp, last_read_at timestamp )\nCREATE TABLE social_media.notifications (\n    notification_id character varying(64) NOT NULL, -- unique identifier for the notification\n    recipient_user_id character varying(64) NOT NULL, -- user receiving the notification (FK to users.user_id)\n    sender_user_id character varying(64), -- user triggering the notification (FK to users.user_id, can be null for system notifications)\n    notification_type character varying(30) NOT NULL, -- type of notification ('like', 'comment', 'follow', 'mention', 'message')\n    target_entity_id character varying(64), -- ID of the related entity (post_id, comment_id, user_id, conversation_id)\n    target_entity_type character varying(20), -- type of the related entity ('post', 'comment', 'user', 'conversation')\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp notification was created\n    read_at timestamp, -- timestamp notification was marked as read\n    PRIMARY KEY (notification_id)\n)\nCREATE TABLE social_media.user_settings ( setting_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL UNIQUE, theme character varying(20) DEFAULT 'light', email_notifications_enabled boolean DEFAULT true, push_notifications_enabled boolean DEFAULT true, private_profile boolean DEFAULT false, updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (setting_id) )\n"}
{"conversations": [{"role": "user", "content": "List all time entries for lawyers specializing in 'Criminal Law'. Show the entry ID, the date worked, hours spent, and the first and last name of the lawyer who performed the work."}, {"role": "assistant", "content": "SELECT te.entry_id, te.date_worked, te.hours_spent, l.first_name, l.last_name FROM legal_services.time_entries te JOIN legal_services.lawyers l ON te.lawyer_id = l.lawyer_id WHERE l.specialization = 'Criminal Law';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.lawyers (\n    lawyer_id character varying(64) NOT NULL,  -- unique identifier for the lawyer\n    first_name character varying(100) NOT NULL, -- lawyer's first name\n    last_name character varying(100) NOT NULL, -- lawyer's last name\n    bar_number character varying(64) UNIQUE NOT NULL, -- lawyer's bar association number\n    firm_id character varying(64), -- FK to law_firms table\n    email character varying(128) UNIQUE NOT NULL, -- lawyer's professional email\n    phone character varying(32), -- lawyer's contact phone number\n    specialization text, -- areas of legal expertise\n    hire_date timestamp NOT NULL, -- date the lawyer was hired or joined\n    is_partner boolean DEFAULT false, -- flag indicating if the lawyer is a partner\n    PRIMARY KEY (lawyer_id)\n)\nCREATE TABLE legal_services.time_entries (\n    entry_id character varying(64) NOT NULL,  -- unique identifier for the time entry\n    case_id character varying(64) NOT NULL, -- FK to cases table\n    lawyer_id character varying(64) NOT NULL, -- FK to lawyers table (who performed the work)\n    date_worked date NOT NULL, -- date the work was performed\n    hours_spent numeric(5, 2) NOT NULL CHECK (hours_spent > 0), -- duration of work in hours (e.g., 1.5 for 1h 30m)\n    billing_rate numeric(10, 2) NOT NULL, -- hourly rate applied for this entry\n    description text NOT NULL, -- detailed description of the work performed\n    is_billable boolean DEFAULT true, -- whether this time entry is billable to the client\n    is_billed boolean DEFAULT false, -- whether this entry has been included in an invoice\n    invoice_id character varying(64), -- FK to invoices table (once billed)\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the entry was recorded\n    PRIMARY KEY (entry_id)\n)\nCREATE TABLE legal_services.invoices (\n    invoice_id character varying(64) NOT NULL,  -- unique identifier for the invoice\n    invoice_number character varying(100) UNIQUE NOT NULL, -- user-facing invoice number\n    client_id character varying(64) NOT NULL, -- FK to clients table\n    case_id character varying(64), -- FK to cases table (optional, could be general retainer)\n    issue_date date NOT NULL, -- date the invoice was generated\n    due_date date NOT NULL, -- date the payment is due\n    total_amount numeric(12, 2) NOT NULL, -- total amount due on the invoice\n    amount_paid numeric(12, 2) DEFAULT 0.00, -- amount already paid\n    status character varying(50) NOT NULL, -- e.g., Draft, Sent, Paid, Partially Paid, Overdue, Void\n    payment_date timestamp, -- date the invoice was fully paid (nullable)\n    notes text, -- additional notes or terms on the invoice\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n    PRIMARY KEY (invoice_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Find all NFTs with a rarity rank less than 100 and show their name and the name of their collection."}, {"role": "assistant", "content": "SELECT nm.name AS nft_name, nc.name AS collection_name FROM nft_metadata nm JOIN nft_collections nc ON nm.contract_address = nc.contract_address WHERE nm.rarity_rank < 100;"}, {"role": "user", "content": "Filter that further to only include NFTs from collections named 'Bored Ape Yacht Club'."}, {"role": "assistant", "content": "SELECT nm.name AS nft_name, nc.name AS collection_name FROM nft_metadata nm JOIN nft_collections nc ON nm.contract_address = nc.contract_address WHERE nm.rarity_rank < 100 AND nc.name = 'Bored Ape Yacht Club';"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nCREATE TABLE token_metas ( block_timestamp timestamp, block_number bigint, transaction_hash varchar, transaction_index bigint, from_address varchar, contract_address varchar, symbol varchar, total_supply varchar, name varchar, decimals bigint, is_erc20 integer, is_erc721 integer, is_erc1155 integer, is_proxy integer, extra_info varchar, pk integer )\nCREATE TABLE erc1155_approval_for_all ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash varchar, log_index integer, contract_address varchar )\nCREATE TABLE erc20_balances ( block_number bigint, contract_address varchar, wallet_address varchar, amount varchar, pk varchar )\nCREATE TABLE nft_holders ( block_number bigint, contract_address varchar, wallet_address varchar, token_id varchar, contract_type varchar, amount varchar, pk varchar )\nCREATE TABLE nft_holder_historical ( block_number bigint, contract_address varchar, wallet_address varchar, token_id varchar, contract_type varchar, amount varchar, pk integer )\nCREATE TABLE sui_coins ( object_id varchar, status varchar, coin_type varchar, balance varchar, owner varchar )\nCREATE TABLE sui_nfts ( object_id varchar, status varchar, collection_type varchar, package_id varchar, previous_transaction varchar, display varchar, owner varchar, name varchar )\nCREATE TABLE nft_metadata ( blockchain varchar, contract_address varchar, token_id varchar, contract_name varchar, erc_type varchar, amount bigint, minter varchar, owner varchar, mint_block_number bigint, mint_time bigint, mint_transaction_hash varchar, mint_price varchar, token_uri varchar, metadata varchar, name varchar, image_uri varchar, traits varchar, updated_at bigint, status varchar, rarity_score real, rarity_rank integer, unique_attribute_count integer, pk integer )\nCREATE TABLE nft_collections ( blockchain varchar, contract_address varchar, name varchar, symbol varchar, deploy_block_number bigint, deploy_block_time bigint, erc_type varchar, owner varchar, traits varchar, description varchar, slug varchar, media_info varchar, image_url varchar, banner_image_url varchar, updated_at bigint, banner varchar, token_count bigint, floor_price varchar, floor_price_symbol varchar, floor_price_contract varchar, pk integer )\nCREATE TABLE token_prices ( uuid varchar, blockchain varchar, address varchar, decimals bigint, symbol varchar, price real, timestamp timestamp )\nCREATE TABLE token_prices_latest ( blockchain varchar, address varchar, decimals bigint, symbol varchar, price real, timestamp timestamp )\nCREATE TABLE erc20_approval ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash varchar, log_index integer, contract_address varchar, pk integer )\nCREATE TABLE token_balances ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply decimal, amount decimal )\nCREATE TABLE token_info ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar )\nCREATE TABLE token_activities ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\nCREATE TABLE mud_holesky_redstone ( address varchar, table_id varchar, key_bytes varchar, key0 varchar, key1 varchar, static_data varchar, encoded_lengths varchar, dynamic_data varchar, is_deleted boolean, block_number bigint, log_index bigint )\nCREATE TABLE token_balances_bitcoin ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply varchar, amount varchar )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\nCREATE TABLE token_balances_avalanche ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply decimal, amount decimal )\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id varchar )\n"}
{"conversations": [{"role": "user", "content": "Show me all terminated drivers who had worked for the company for more than 5 years before termination."}, {"role": "assistant", "content": "SELECT driver_id, first_name, last_name, hire_date FROM transportation.drivers WHERE status = 'Terminated' AND (hire_date < (CURRENT_DATE - INTERVAL '5 years'));"}, {"role": "user", "content": "Can you include their license numbers and calculate how many years they worked before termination?"}, {"role": "assistant", "content": "SELECT driver_id, first_name, last_name, license_number, hire_date, EXTRACT(YEAR FROM AGE(CURRENT_DATE, hire_date)) AS years_worked FROM transportation.drivers WHERE status = 'Terminated' AND (hire_date < (CURRENT_DATE - INTERVAL '5 years'));"}, {"role": "user", "content": "Now order the results by years worked in descending order, showing those who worked the longest first."}, {"role": "assistant", "content": "SELECT driver_id, first_name, last_name, license_number, hire_date, EXTRACT(YEAR FROM AGE(CURRENT_DATE, hire_date)) AS years_worked FROM transportation.drivers WHERE status = 'Terminated' AND (hire_date < (CURRENT_DATE - INTERVAL '5 years')) ORDER BY years_worked DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.drivers (\n    driver_id character varying(64) NOT NULL,  -- unique identifier for the driver\n    employee_id character varying(64) NOT NULL UNIQUE, -- employee reference number\n    first_name character varying(128) NOT NULL, -- driver's first name\n    last_name character varying(128) NOT NULL, -- driver's last name\n    license_number character varying(64) NOT NULL UNIQUE, -- driving license number\n    license_expiry_date date NOT NULL, -- expiry date of the license\n    contact_number character varying(32), -- phone number\n    email character varying(128) UNIQUE, -- email address\n    hire_date date NOT NULL, -- date the driver was hired\n    status character varying(32) NOT NULL, -- e.g., Active, On Leave, Terminated\n    PRIMARY KEY (driver_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List all managers (employees who have other employees reporting to them) along with the count of their direct reports, showing only those with more than 5 reports."}, {"role": "assistant", "content": "SELECT e.employee_id, e.first_name, e.last_name, COUNT(r.employee_id) as direct_reports_count FROM financial_services.employees e JOIN financial_services.employees r ON e.employee_id = r.manager_id WHERE e.status = 'Active' GROUP BY e.employee_id, e.first_name, e.last_name HAVING COUNT(r.employee_id) > 5 ORDER BY direct_reports_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.employees ( employee_id text PRIMARY KEY, first_name text, last_name text, job_title text, department text, branch_id text, email text, phone_extension text, hire_date date, termination_date date, manager_id text, status text )\n"}
{"conversations": [{"role": "user", "content": "What are the fuel consumption rates per hour for the Boeing 747-8 model?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information on the fuel consumption rates for the Boeing 747-8 model as this data is not included in the aircraft_models table. The table contains details such as model name, manufacturer, passenger capacity, and other specifications, but fuel consumption data is not available. If you have another question or need assistance with something else related to the table, I'm happy to help."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE manufacturing.aircraft_models ( model_id.text, model_name.text, manufacturer.text, passenger_capacity.integer, max_range_km.integer, engine_type.text, wingspan_m.numeric, status.text, first_flight_date.date )\n"}
{"conversations": [{"role": "user", "content": "Get each user's ID, the count of wallets they own, and the total amount of their unspent UTXOs across all wallets."}, {"role": "assistant", "content": "SELECT w.user_id,\n       COUNT(DISTINCT w.wallet_id)                               AS wallet_count,\n       COALESCE(SUM(u.amount), 0)                                AS total_unspent\nFROM trading_platform.wallets w\nLEFT JOIN trading_platform.utxos u\n  ON w.address = u.address\n  AND u.spent = false\nGROUP BY w.user_id;"}, {"role": "user", "content": "Only include users who have more than one wallet."}, {"role": "assistant", "content": "SELECT w.user_id,\n       COUNT(DISTINCT w.wallet_id)                               AS wallet_count,\n       COALESCE(SUM(u.amount), 0)                                AS total_unspent\nFROM trading_platform.wallets w\nLEFT JOIN trading_platform.utxos u\n  ON w.address = u.address\n  AND u.spent = false\nGROUP BY w.user_id\nHAVING COUNT(DISTINCT w.wallet_id) > 1;"}, {"role": "user", "content": "Also include the date of the earliest wallet created by each user."}, {"role": "assistant", "content": "SELECT w.user_id,\n       COUNT(DISTINCT w.wallet_id)                               AS wallet_count,\n       COALESCE(SUM(u.amount), 0)                                AS total_unspent,\n       MIN(w.created_at)                                        AS first_wallet_date\nFROM trading_platform.wallets w\nLEFT JOIN trading_platform.utxos u\n  ON w.address = u.address\n  AND u.spent = false\nGROUP BY w.user_id\nHAVING COUNT(DISTINCT w.wallet_id) > 1;"}, {"role": "user", "content": "Sort the results by total_unspent descending and limit to the top 10."}, {"role": "assistant", "content": "SELECT w.user_id,\n       COUNT(DISTINCT w.wallet_id)                               AS wallet_count,\n       COALESCE(SUM(u.amount), 0)                                AS total_unspent,\n       MIN(w.created_at)                                        AS first_wallet_date\nFROM trading_platform.wallets w\nLEFT JOIN trading_platform.utxos u\n  ON w.address = u.address\n  AND u.spent = false\nGROUP BY w.user_id\nHAVING COUNT(DISTINCT w.wallet_id) > 1\nORDER BY total_unspent DESC\nLIMIT 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.wallets (\n    wallet_id character varying(64) NOT NULL,  -- unique identifier for the wallet\n    user_id character varying(64) NOT NULL, -- identifier of the user owning the wallet\n    address character varying(128) NOT NULL, -- address of the wallet\n    private_key text NOT NULL, -- private key of the wallet\n    created_at timestamp NOT NULL, -- time when the wallet was created\n    PRIMARY KEY (wallet_id)\n)\nCREATE TABLE trading_platform.orders (\n    order_id character varying(64) NOT NULL,  -- unique identifier for the order\n    user_id character varying(64) NOT NULL, -- identifier of the user placing the order\n    wallet_id character varying(64) NOT NULL, -- identifier of the wallet used for the order\n    asset_id character varying(64) NOT NULL, -- identifier of the asset being traded\n    order_type character varying(32) NOT NULL, -- type of the order (e.g., buy, sell)\n    quantity numeric(38,14) NOT NULL, -- quantity of the asset in the order\n    price numeric(38,14) NOT NULL, -- price per unit of the asset\n    status character varying(32) NOT NULL, -- status of the order (e.g., open, filled, canceled)\n    created_at timestamp NOT NULL, -- time when the order was created\n    PRIMARY KEY (order_id)\n)\nCREATE TABLE trading_platform.assets (\n    asset_id character varying(64) NOT NULL,  -- unique identifier for the asset\n    name character varying(128) NOT NULL, -- name of the asset\n    symbol character varying(32) NOT NULL, -- symbol of the asset\n    type character varying(32) NOT NULL, -- type of the asset (e.g., cryptocurrency, stock)\n    PRIMARY KEY (asset_id)\n)\nCREATE TABLE trading_platform.utxos (\n    utxo_id character varying(64) NOT NULL,  -- unique identifier for the UTXO\n    transaction_id character varying(64) NOT NULL, -- identifier of the transaction that created the UTXO\n    output_index integer NOT NULL, -- index of the output in the transaction\n    address character varying(128) NOT NULL, -- address that can spend the UTXO\n    amount numeric(38,14) NOT NULL, -- amount of the asset in the UTXO\n    spent boolean NOT NULL, -- whether the UTXO has been spent\n    PRIMARY KEY (utxo_id)\n)\nCREATE TABLE trading_platform.dapps (\n    dapp_id character varying(64) NOT NULL,  -- unique identifier for the DApp\n    name character varying(128) NOT NULL, -- name of the DApp\n    description text NOT NULL, -- description of the DApp\n    url character varying(256) NOT NULL, -- URL of the DApp\n    PRIMARY KEY (dapp_id)\n)\nCREATE TABLE trading_platform.peers (\n    peer_id character varying(64) NOT NULL,  -- unique identifier for the peer\n    ip_address character varying(15) NOT NULL, -- IP address of the peer\n    port integer NOT NULL, -- port number of the peer\n    last_seen timestamp NOT NULL, -- last time the peer was active\n    PRIMARY KEY (peer_id)\n)\nCREATE TABLE trading_platform.metadata (\n    metadata_id character varying(64) NOT NULL,  -- unique identifier for the metadata\n    asset_id character varying(64) NOT NULL, -- identifier of the asset the metadata is associated with\n    key character varying(128) NOT NULL, -- key of the metadata\n    value text NOT NULL, -- value of the metadata\n    PRIMARY KEY (metadata_id)\n)\nCREATE TABLE trading_platform.kyc_audit (\n    kyc_audit_id character varying(64) NOT NULL,  -- unique identifier for the KYC audit\n    user_id character varying(64) NOT NULL, -- identifier of the user being audited\n    status character varying(32) NOT NULL, -- status of the KYC audit (e.g., pending, approved, rejected)\n    reviewed_at timestamp NOT NULL, -- time when the KYC audit was reviewed\n    PRIMARY KEY (kyc_audit_id)\n)\nCREATE TABLE trading_platform.notifications (\n    notification_id character varying(64) NOT NULL,  -- unique identifier for the notification\n    user_id character varying(64) NOT NULL, -- identifier of the user receiving the notification\n    message text NOT NULL, -- message of the notification\n    sent_at timestamp NOT NULL, -- time when the notification was sent\n    read_at timestamp, -- time when the notification was read\n    PRIMARY KEY (notification_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Show the latest version number of each document_name for every case."}, {"role": "assistant", "content": "SELECT case_id,\n       document_name,\n       MAX(version) AS latest_version\nFROM legal_services.documents\nGROUP BY case_id, document_name;"}, {"role": "user", "content": "Actually, I also need the upload_timestamp of that latest version."}, {"role": "assistant", "content": "SELECT d.case_id,\n       d.document_name,\n       d.version AS latest_version,\n       d.upload_timestamp\nFROM legal_services.documents d\nJOIN (\n  SELECT case_id,\n         document_name,\n         MAX(version) AS latest_version\n  FROM legal_services.documents\n  GROUP BY case_id, document_name\n) sub\n  ON d.case_id = sub.case_id\n AND d.document_name = sub.document_name\n AND d.version = sub.latest_version;"}, {"role": "user", "content": "Also include the uploaded_by_lawyer_id for each latest version."}, {"role": "assistant", "content": "SELECT d.case_id,\n       d.document_name,\n       d.version AS latest_version,\n       d.upload_timestamp,\n       d.uploaded_by_lawyer_id\nFROM legal_services.documents d\nJOIN (\n  SELECT case_id,\n         document_name,\n         MAX(version) AS latest_version\n  FROM legal_services.documents\n  GROUP BY case_id, document_name\n) sub\n  ON d.case_id = sub.case_id\n AND d.document_name = sub.document_name\n AND d.version = sub.latest_version;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.documents ( document_id text, case_id text, document_name text, document_type text, storage_path text, uploaded_by_lawyer_id text, upload_timestamp timestamp, version integer, description text )\n"}
{"conversations": [{"role": "user", "content": "Find all contracts where the deployer address is the same as the contract address, indicating self-deployed contracts."}, {"role": "assistant", "content": "SELECT address, deployer_address FROM web3.contracts WHERE address = deployer_address;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.contracts ( contract_id text, address text, abi text, bytecode text, deployer_address text, deployed_at timestamp, network_id text, status text )\n"}
{"conversations": [{"role": "user", "content": "I need a report of patients who have received prescriptions for medications manufactured by 'Pfizer'. Include patient ID, first name, last name, medication_name, and prescription_date."}, {"role": "assistant", "content": "SELECT p.patient_id,\n       p.first_name,\n       p.last_name,\n       m.medication_name,\n       pr.prescription_date\nFROM healthcare.patients AS p\nJOIN healthcare.prescriptions AS pr ON p.patient_id = pr.patient_id\nJOIN healthcare.medications AS m ON pr.medication_id = m.medication_id\nWHERE m.manufacturer = 'Pfizer';"}, {"role": "user", "content": "Actually, only include prescriptions with a dosage containing 'mg' and sort by prescription_date descending."}, {"role": "assistant", "content": "SELECT p.patient_id,\n       p.first_name,\n       p.last_name,\n       m.medication_name,\n       pr.prescription_date\nFROM healthcare.patients AS p\nJOIN healthcare.prescriptions AS pr ON p.patient_id = pr.patient_id\nJOIN healthcare.medications AS m ON pr.medication_id = m.medication_id\nWHERE m.manufacturer = 'Pfizer'\n  AND pr.dosage ILIKE '%mg%'\nORDER BY pr.prescription_date DESC;"}, {"role": "user", "content": "Also, include the patient's primary insurance policy number and plan name in the report."}, {"role": "assistant", "content": "SELECT p.patient_id,\n       p.first_name,\n       p.last_name,\n       m.medication_name,\n       pr.prescription_date,\n       pi.policy_number,\n       ip.plan_name\nFROM healthcare.patients AS p\nJOIN healthcare.prescriptions AS pr ON p.patient_id = pr.patient_id\nJOIN healthcare.medications AS m ON pr.medication_id = m.medication_id\nJOIN healthcare.patient_insurance AS pi\n  ON p.patient_id = pi.patient_id AND pi.is_primary = true\nJOIN healthcare.insurance_plans AS ip ON pi.plan_id = ip.plan_id\nWHERE m.manufacturer = 'Pfizer'\n  AND pr.dosage ILIKE '%mg%'\nORDER BY pr.prescription_date DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, gender character varying(10), address text, phone_number character varying(20), email character varying(128) UNIQUE, emergency_contact_name character varying(200), emergency_contact_phone character varying(20), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (patient_id) )\nCREATE TABLE healthcare.appointments ( appointment_id text, patient_id text, doctor_id text, appointment_time timestamp, duration_minutes integer, reason text, status text, location_id text, notes text, created_at timestamp )\nCREATE TABLE healthcare.medical_records ( record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, appointment_id character varying(64) UNIQUE, doctor_id character varying(64) NOT NULL, record_date timestamp with time zone NOT NULL, chief_complaint text, present_illness_history text, past_medical_history text, physical_examination_notes text, assessment text, treatment_plan text, vitals jsonb, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (record_id) )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id text PRIMARY KEY, record_id text, patient_id text, doctor_id text, diagnosis_code text, code_type text, description text, diagnosis_date date, status text, is_chronic boolean )\nCREATE TABLE healthcare.medications ( medication_id text, medication_name text, generic_name text, manufacturer text, ndc_code text, description text )\nCREATE TABLE healthcare.prescriptions ( prescription_id.text, record_id.text, patient_id.text, doctor_id.text, medication_id.text, dosage.text, frequency.text, route.text, start_date.date, end_date.date, quantity_dispensed.numeric, refills_allowed.integer, prescription_date.timestamp )\nCREATE TABLE healthcare.insurance_plans ( plan_id.text, plan_name.text, insurance_provider.text, plan_type.text, contact_phone.text, website.text )\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, plan_id character varying(64) NOT NULL, policy_number character varying(100) NOT NULL, group_number character varying(100), subscriber_name character varying(200), effective_date date NOT NULL, expiration_date date, is_primary boolean NOT NULL DEFAULT true, PRIMARY KEY (patient_insurance_id), UNIQUE (patient_id, plan_id, policy_number) )\n"}
{"conversations": [{"role": "user", "content": "Show me the top 5 buyers by total trade volume (quantity * price) in the last 30 days, along with their trade count."}, {"role": "assistant", "content": "SELECT buyer_id, COUNT(trade_id) AS trade_count, SUM(quantity * price) AS total_volume FROM trading_platform.trades WHERE traded_at >= NOW() - INTERVAL '30 days' GROUP BY buyer_id ORDER BY total_volume DESC LIMIT 5"}, {"role": "user", "content": "Now modify the query to also include the average trade price for each buyer."}, {"role": "assistant", "content": "SELECT buyer_id, COUNT(trade_id) AS trade_count, SUM(quantity * price) AS total_volume, AVG(price) AS avg_price FROM trading_platform.trades WHERE traded_at >= NOW() - INTERVAL '30 days' GROUP BY buyer_id ORDER BY total_volume DESC LIMIT 5"}, {"role": "user", "content": "Actually, I want to see the results for sellers instead of buyers, and include the distinct asset count they traded."}, {"role": "assistant", "content": "SELECT seller_id, COUNT(trade_id) AS trade_count, COUNT(DISTINCT asset_id) AS distinct_assets, SUM(quantity * price) AS total_volume, AVG(price) AS avg_price FROM trading_platform.trades WHERE traded_at >= NOW() - INTERVAL '30 days' GROUP BY seller_id ORDER BY total_volume DESC LIMIT 5"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.trades ( trade_id character varying(64) NOT NULL, order_id character varying(64) NOT NULL, buyer_id character varying(64) NOT NULL, seller_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, quantity numeric(38,14) NOT NULL, price numeric(38,14) NOT NULL, traded_at timestamp NOT NULL, PRIMARY KEY (trade_id) )\n"}
{"conversations": [{"role": "user", "content": "For each contract, can you list the token symbols and total supply of all tokens created by that contract, along with the contract's current status?"}, {"role": "assistant", "content": "SELECT c.contract_id, c.address AS contract_address, c.status, t.token_symbol, t.total_supply\nFROM web3.contracts c\nJOIN web3.tokens t ON c.address = t.contract_address\nORDER BY c.contract_id, t.token_symbol;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.contracts ( contract_id text, address text, abi text, bytecode text, deployer_address text, deployed_at timestamp, network_id text, status text )\nCREATE TABLE web3.events ( event_id text, contract_id text, event_name text, data text, emitted_at timestamp, transaction_id text, log_index integer )\nCREATE TABLE web3.transactions ( transaction_id text, from_address text, to_address text, value numeric, gas_used integer, gas_price numeric, block_number integer, timestamp timestamp, input_data text, status text, nonce integer )\nCREATE TABLE web3.tokens ( token_id text, contract_address text, token_name text, token_symbol text, decimals integer, total_supply numeric )\nCREATE TABLE web3.token_transfers ( transfer_id text, token_id text, from_address text, to_address text, value numeric, transaction_id text, log_index integer )\nCREATE TABLE web3.users ( user_id text, username text, email text, password_hash text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "I need to identify pairs of verified documents submitted by the same citizen. For each pair, display the citizen_id, the earlier document_id with its verification timestamp, and the later document_id with its verification timestamp."}, {"role": "assistant", "content": "SELECT\n  d1.citizen_id,\n  d1.document_id AS earlier_document_id,\n  d1.verification_timestamp AS earlier_verification,\n  d2.document_id AS later_document_id,\n  d2.verification_timestamp AS later_verification\nFROM government_services.documents d1\nJOIN government_services.documents d2\n  ON d1.citizen_id = d2.citizen_id\n  AND d1.verification_timestamp < d2.verification_timestamp\nWHERE d1.verification_status = 'Verified'\n  AND d2.verification_status = 'Verified';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.documents ( document_id character varying(64) NOT NULL, application_id character varying(64), citizen_id character varying(64) NOT NULL, document_type character varying(100) NOT NULL, file_reference text NOT NULL, upload_timestamp timestamp NOT NULL, expiry_date date, verification_status character varying(30) DEFAULT 'Pending', verified_by_employee_id character varying(64), verification_timestamp timestamp, PRIMARY KEY (document_id) )\n"}
{"conversations": [{"role": "user", "content": "Can you narrow this down to only show cases where the case type is 'Criminal'?"}, {"role": "assistant", "content": "SELECT case_name, case_number, date_opened FROM legal_services.cases WHERE lead_lawyer_id = 'lawyer_abc' AND status = 'Open' AND case_type = 'Criminal';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.cases ( case_id.text, case_number.text, case_name.text, client_id.text, lead_lawyer_id.text, case_type.text, status.text, date_opened.timestamp, date_closed.timestamp, description.text, court_jurisdiction.text )\n"}
{"conversations": [{"role": "user", "content": "Show me the usernames and email addresses of users who commented on any post tagged with the hashtag 'H777'."}, {"role": "assistant", "content": "SELECT DISTINCT u.username, u.email\nFROM social_media.comments c\nJOIN social_media.users u ON c.user_id = u.user_id\nJOIN social_media.post_hashtags ph ON c.post_id = ph.post_id\nWHERE ph.hashtag_id = 'H777';"}, {"role": "user", "content": "Please also include the comment content and when each comment was created."}, {"role": "assistant", "content": "SELECT DISTINCT u.username, u.email, c.content, c.created_at\nFROM social_media.comments c\nJOIN social_media.users u ON c.user_id = u.user_id\nJOIN social_media.post_hashtags ph ON c.post_id = ph.post_id\nWHERE ph.hashtag_id = 'H777';"}, {"role": "user", "content": "Now, only include comments created after April 1, 2024."}, {"role": "assistant", "content": "SELECT DISTINCT u.username, u.email, c.content, c.created_at\nFROM social_media.comments c\nJOIN social_media.users u ON c.user_id = u.user_id\nJOIN social_media.post_hashtags ph ON c.post_id = ph.post_id\nWHERE ph.hashtag_id = 'H777'\n  AND c.created_at > '2024-04-01';"}, {"role": "user", "content": "Instead of email, show the user's full name, and sort by comment creation time descending."}, {"role": "assistant", "content": "SELECT DISTINCT u.username, u.full_name, c.content, c.created_at\nFROM social_media.comments c\nJOIN social_media.users u ON c.user_id = u.user_id\nJOIN social_media.post_hashtags ph ON c.post_id = ph.post_id\nWHERE ph.hashtag_id = 'H777'\n  AND c.created_at > '2024-04-01'\nORDER BY c.created_at DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id character varying(64) NOT NULL, username character varying(50) NOT NULL UNIQUE, email character varying(128) NOT NULL UNIQUE, password_hash text NOT NULL, full_name character varying(100), profile_picture_url text, bio text, location character varying(100), created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, is_verified boolean NOT NULL DEFAULT false, PRIMARY KEY (user_id) )\nCREATE TABLE social_media.comments ( comment_id text, post_id text, user_id text, parent_comment_id text, content text, created_at timestamp, updated_at timestamp )\nCREATE TABLE social_media.hashtags ( hashtag_id text, tag_name text, created_at timestamp )\nCREATE TABLE social_media.notifications (\n    notification_id character varying(64) NOT NULL, -- unique identifier for the notification\n    recipient_user_id character varying(64) NOT NULL, -- user receiving the notification (FK to users.user_id)\n    sender_user_id character varying(64), -- user triggering the notification (FK to users.user_id, can be null for system notifications)\n    notification_type character varying(30) NOT NULL, -- type of notification ('like', 'comment', 'follow', 'mention', 'message')\n    target_entity_id character varying(64), -- ID of the related entity (post_id, comment_id, user_id, conversation_id)\n    target_entity_type character varying(20), -- type of the related entity ('post', 'comment', 'user', 'conversation')\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp notification was created\n    read_at timestamp, -- timestamp notification was marked as read\n    PRIMARY KEY (notification_id)\n)\nCREATE TABLE social_media.user_settings ( setting_id text PRIMARY KEY, user_id text, theme text, email_notifications_enabled bool, push_notifications_enabled bool, private_profile bool, updated_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Can you show me all developers along with the year they were founded and their website, grouped by country?"}, {"role": "assistant", "content": "SELECT country, array_agg(name) AS developers, array_agg(founded_year) AS founded_years, array_agg(website) AS websites FROM gaming_technology.developers GROUP BY country;"}, {"role": "user", "content": "Can you add the number of developers per country to the result?"}, {"role": "assistant", "content": "SELECT country, COUNT(*) AS developer_count, array_agg(name) AS developers, array_agg(founded_year) AS founded_years, array_agg(website) AS websites FROM gaming_technology.developers GROUP BY country;"}, {"role": "user", "content": "I'd like to see only countries with at least two developers. Can you modify the query?"}, {"role": "assistant", "content": "SELECT country, COUNT(*) AS developer_count, array_agg(name) AS developers, array_agg(founded_year) AS founded_years, array_agg(website) AS websites FROM gaming_technology.developers GROUP BY country HAVING COUNT(*) >= 2;"}, {"role": "user", "content": "Actually, could you also include the earliest founded year of a developer in each country?"}, {"role": "assistant", "content": "SELECT country, COUNT(*) AS developer_count, MIN(founded_year) AS earliest_founded_year, array_agg(name) AS developers, array_agg(founded_year) AS founded_years, array_agg(website) AS websites FROM gaming_technology.developers GROUP BY country HAVING COUNT(*) >= 2;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.developers ( developer_id.uuid, name.text, country.text, founded_year.integer, website.text, created_at.timestamptz )\n"}
{"conversations": [{"role": "user", "content": "Give me the total billed amount for each invoice in 2024."}, {"role": "assistant", "content": "SELECT invoice_id, SUM(hours_spent * billing_rate) AS total_billed_amount FROM legal_services.time_entries WHERE is_billed = TRUE AND EXTRACT(YEAR FROM date_worked) = 2024 GROUP BY invoice_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.time_entries ( entry_id text PRIMARY KEY, case_id text, lawyer_id text, date_worked date, hours_spent numeric, billing_rate numeric, description text, is_billable bool, is_billed bool, invoice_id text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show all routes including their number, type, and description."}, {"role": "assistant", "content": "SELECT route_number ,  type ,  description FROM transportation.routes"}, {"role": "user", "content": "Only show routes of type 'City Bus'."}, {"role": "assistant", "content": "SELECT route_number ,  type ,  description FROM transportation.routes WHERE type  =  'City Bus'"}, {"role": "user", "content": "For these 'City Bus' routes, include the origin and destination city names."}, {"role": "assistant", "content": "SELECT T1.route_number ,  T1.type ,  T1.description ,  T2.city AS origin_city ,  T3.city AS destination_city FROM transportation.routes AS T1 JOIN transportation.locations AS T2 ON T1.origin_location_id  =  T2.location_id JOIN transportation.locations AS T3 ON T1.destination_location_id  =  T3.location_id WHERE T1.type  =  'City Bus'"}, {"role": "user", "content": "Order the results by route number in ascending order and limit to the first 10."}, {"role": "assistant", "content": "SELECT T1.route_number ,  T1.type ,  T1.description ,  T2.city AS origin_city ,  T3.city AS destination_city FROM transportation.routes AS T1 JOIN transportation.locations AS T2 ON T1.origin_location_id  =  T2.location_id JOIN transportation.locations AS T3 ON T1.destination_location_id  =  T3.location_id WHERE T1.type  =  'City Bus' ORDER BY T1.route_number ASC LIMIT 10"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles (\n    vehicle_id character varying(64) NOT NULL,  -- unique identifier for the vehicle\n    license_plate character varying(32) NOT NULL UNIQUE, -- vehicle license plate\n    vin character varying(17) UNIQUE, -- vehicle identification number\n    make character varying(64) NOT NULL, -- manufacturer of the vehicle\n    model character varying(64) NOT NULL, -- model of the vehicle\n    year integer NOT NULL, -- manufacturing year\n    type character varying(32) NOT NULL, -- type of vehicle (e.g., Bus, Train, Truck, Car, Van)\n    capacity integer, -- passenger or cargo capacity\n    fuel_type character varying(32) NOT NULL, -- e.g., Diesel, Gasoline, Electric, Hydrogen\n    status character varying(32) NOT NULL, -- e.g., Active, Maintenance, Decommissioned\n    depot_id character varying(64), -- identifier of the home depot/base\n    acquisition_date date, -- date the vehicle was acquired\n    PRIMARY KEY (vehicle_id)\n)\nCREATE TABLE transportation.drivers (\n    driver_id character varying(64) NOT NULL,  -- unique identifier for the driver\n    employee_id character varying(64) NOT NULL UNIQUE, -- employee reference number\n    first_name character varying(128) NOT NULL, -- driver's first name\n    last_name character varying(128) NOT NULL, -- driver's last name\n    license_number character varying(64) NOT NULL UNIQUE, -- driving license number\n    license_expiry_date date NOT NULL, -- expiry date of the license\n    contact_number character varying(32), -- phone number\n    email character varying(128) UNIQUE, -- email address\n    hire_date date NOT NULL, -- date the driver was hired\n    status character varying(32) NOT NULL, -- e.g., Active, On Leave, Terminated\n    PRIMARY KEY (driver_id)\n)\nCREATE TABLE transportation.routes (\n    route_id character varying(64) NOT NULL,  -- unique identifier for the route\n    route_number character varying(32) NOT NULL UNIQUE, -- public-facing route number/name\n    description text, -- description of the route\n    origin_location_id character varying(64) NOT NULL, -- identifier of the starting location\n    destination_location_id character varying(64) NOT NULL, -- identifier of the ending location\n    distance_km numeric(10, 2), -- estimated distance in kilometers\n    estimated_duration_minutes integer, -- estimated travel time in minutes\n    type character varying(32) NOT NULL, -- e.g., City Bus, Intercity Train, Cargo Delivery\n    PRIMARY KEY (route_id)\n)\nCREATE TABLE transportation.locations (\n    location_id character varying(64) NOT NULL,  -- unique identifier for the location\n    name character varying(255) NOT NULL, -- name of the location (e.g., Central Station, Depot Alpha, Pier 7)\n    type character varying(64) NOT NULL, -- e.g., Station, Stop, Depot, Port, Airport, Customer Address\n    address_line1 character varying(255), -- street address\n    city character varying(128), -- city name\n    state_province character varying(128), -- state or province\n    postal_code character varying(32), -- postal code\n    country character varying(64) NOT NULL, -- country name\n    latitude numeric(9, 6), -- geographic latitude\n    longitude numeric(9, 6), -- geographic longitude\n    timezone character varying(64), -- IANA timezone name (e.g., America/New_York)\n    PRIMARY KEY (location_id)\n)\nCREATE TABLE transportation.fuel_logs (\n    fuel_log_id character varying(64) NOT NULL,  -- unique identifier for the fuel log entry\n    vehicle_id character varying(64) NOT NULL, -- identifier of the vehicle fueled\n    trip_id character varying(64), -- optional: identifier of the trip during which fueling occurred\n    log_timestamp timestamp with time zone NOT NULL, -- time when fueling occurred\n    fuel_type character varying(32) NOT NULL, -- type of fuel added (matches vehicle's fuel type)\n    quantity numeric(10, 3) NOT NULL, -- amount of fuel added (e.g., Liters, Gallons, kWh)\n    unit character varying(16) NOT NULL, -- unit of quantity (e.g., L, gal, kWh)\n    cost_per_unit numeric(8, 4), -- price per unit of fuel\n    total_cost numeric(10, 2) NOT NULL, -- total cost of the fuel purchase\n    odometer_reading integer, -- vehicle mileage at time of fueling\n    location_id character varying(64), -- identifier of the fueling station/location\n    PRIMARY KEY (fuel_log_id)\n)\n"}
{"conversations": [{"role": "user", "content": "How many unique patient records are there for each gender?"}, {"role": "assistant", "content": "SELECT gender, COUNT(DISTINCT patient_id) AS patient_count FROM healthcare.patients GROUP BY gender;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id.text, first_name.text, last_name.text, date_of_birth.date, gender.text, address.text, phone_number.text, email.text, emergency_contact_name.text, emergency_contact_phone.text, created_at.timestamp, updated_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show me a summary of all clients with the total number of invoices they've received and the sum of total_amount for those invoices."}, {"role": "assistant", "content": "SELECT cl.client_id,\n       CONCAT(cl.first_name, ' ', cl.last_name) AS client_name,\n       COUNT(inv.invoice_id) AS invoice_count,\n       SUM(inv.total_amount) AS total_amount_sum\nFROM legal_services.clients cl\nLEFT JOIN legal_services.invoices inv ON cl.client_id = inv.client_id\nGROUP BY cl.client_id, cl.first_name, cl.last_name;"}, {"role": "user", "content": "I'd like to consider only invoices issued in the year 2023."}, {"role": "assistant", "content": "SELECT cl.client_id,\n       CONCAT(cl.first_name, ' ', cl.last_name) AS client_name,\n       COUNT(inv.invoice_id) AS invoice_count,\n       SUM(inv.total_amount) AS total_amount_sum\nFROM legal_services.clients cl\nLEFT JOIN legal_services.invoices inv ON cl.client_id = inv.client_id\nWHERE inv.issue_date BETWEEN '2023-01-01' AND '2023-12-31'\nGROUP BY cl.client_id, cl.first_name, cl.last_name;"}, {"role": "user", "content": "And exclude clients who have not paid any amount on any of their invoices."}, {"role": "assistant", "content": "SELECT cl.client_id,\n       CONCAT(cl.first_name, ' ', cl.last_name) AS client_name,\n       COUNT(inv.invoice_id) AS invoice_count,\n       SUM(inv.total_amount) AS total_amount_sum,\n       SUM(inv.amount_paid) AS amount_paid_sum\nFROM legal_services.clients cl\nLEFT JOIN legal_services.invoices inv ON cl.client_id = inv.client_id\nWHERE inv.issue_date BETWEEN '2023-01-01' AND '2023-12-31'\nGROUP BY cl.client_id, cl.first_name, cl.last_name\nHAVING SUM(inv.amount_paid) > 0;"}, {"role": "user", "content": "Finally, order the results by the sum of total_amount in descending order."}, {"role": "assistant", "content": "SELECT cl.client_id,\n       CONCAT(cl.first_name, ' ', cl.last_name) AS client_name,\n       COUNT(inv.invoice_id) AS invoice_count,\n       SUM(inv.total_amount) AS total_amount_sum,\n       SUM(inv.amount_paid) AS amount_paid_sum\nFROM legal_services.clients cl\nLEFT JOIN legal_services.invoices inv ON cl.client_id = inv.client_id\nWHERE inv.issue_date BETWEEN '2023-01-01' AND '2023-12-31'\nGROUP BY cl.client_id, cl.first_name, cl.last_name\nHAVING SUM(inv.amount_paid) > 0\nORDER BY total_amount_sum DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.clients ( client_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, company_name character varying(200), email character varying(128) UNIQUE NOT NULL, phone character varying(32), address text, date_registered timestamp NOT NULL, status character varying(32) NOT NULL, PRIMARY KEY (client_id) )\nCREATE TABLE legal_services.law_firms ( firm_id character varying(64) NOT NULL, firm_name character varying(200) NOT NULL, address text NOT NULL, phone character varying(32), website character varying(255), founded_date date, managing_partner_id character varying(64), PRIMARY KEY (firm_id) )\nCREATE TABLE legal_services.cases ( case_id character varying(64) NOT NULL, case_number character varying(100) UNIQUE, case_name text NOT NULL, client_id character varying(64) NOT NULL, lead_lawyer_id character varying(64) NOT NULL, case_type character varying(100) NOT NULL, status character varying(50) NOT NULL, date_opened timestamp NOT NULL, date_closed timestamp, description text, court_jurisdiction character varying(128), PRIMARY KEY (case_id) )\nCREATE TABLE legal_services.documents ( document_id character varying(64) NOT NULL, case_id character varying(64) NOT NULL, document_name character varying(255) NOT NULL, document_type character varying(100), storage_path text NOT NULL, uploaded_by_lawyer_id character varying(64), upload_timestamp timestamp NOT NULL, version integer DEFAULT 1, description text, PRIMARY KEY (document_id) )\nCREATE TABLE legal_services.invoices ( invoice_id character varying(64) NOT NULL, invoice_number character varying(100) UNIQUE NOT NULL, client_id character varying(64) NOT NULL, case_id character varying(64), issue_date date NOT NULL, due_date date NOT NULL, total_amount numeric(12, 2) NOT NULL, amount_paid numeric(12, 2) DEFAULT 0.00, status character varying(50) NOT NULL, payment_date timestamp, notes text, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (invoice_id) )\nCREATE TABLE legal_services.appointments ( appointment_id character varying(64) NOT NULL, client_id character varying(64) NOT NULL, lawyer_id character varying(64) NOT NULL, case_id character varying(64), start_time timestamp NOT NULL, end_time timestamp NOT NULL, location text, subject character varying(255), notes text, status character varying(50) NOT NULL, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (appointment_id) )\n"}
{"conversations": [{"role": "user", "content": "List all orders, showing order ID, type, quantity, and the asset name."}, {"role": "assistant", "content": "SELECT o.order_id, o.order_type, o.quantity, a.name FROM trading_platform.orders o JOIN trading_platform.assets a ON o.asset_id = a.asset_id;"}, {"role": "user", "content": "Now, only include orders with 'completed' status and a quantity greater than 10."}, {"role": "assistant", "content": "SELECT o.order_id, o.order_type, o.quantity, a.name FROM trading_platform.orders o JOIN trading_platform.assets a ON o.asset_id = a.asset_id WHERE o.status = 'completed' AND o.quantity > 10;"}, {"role": "user", "content": "Actually, I also want to see the user ID of the user who placed the order."}, {"role": "assistant", "content": "SELECT o.order_id, o.order_type, o.quantity, a.name, w.user_id FROM trading_platform.orders o JOIN trading_platform.assets a ON o.asset_id = a.asset_id JOIN trading_platform.wallets w ON o.wallet_id = w.wallet_id WHERE o.status = 'completed' AND o.quantity > 10;"}, {"role": "user", "content": "The previous query didn't work because some completed orders might not be linked to a wallet? Can you show the order ID, type, quantity, asset name, but also include the user ID if available through the wallet linkage, and still filter by 'completed' status and quantity > 10?"}, {"role": "assistant", "content": "SELECT o.order_id, o.order_type, o.quantity, a.name, w.user_id FROM trading_platform.orders o JOIN trading_platform.assets a ON o.asset_id = a.asset_id LEFT JOIN trading_platform.wallets w ON o.wallet_id = w.wallet_id WHERE o.status = 'completed' AND o.quantity > 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.wallets ( wallet_id text, user_id text, address text, private_key text, created_at timestamp )\nCREATE TABLE trading_platform.orders ( order_id text, user_id text, wallet_id text, asset_id text, order_type text, quantity numeric, price numeric, status text, created_at timestamp )\nCREATE TABLE trading_platform.trades ( trade_id text, order_id text, buyer_id text, seller_id text, asset_id text, quantity numeric, price numeric, traded_at timestamp )\nCREATE TABLE trading_platform.assets ( asset_id text, name text, symbol text, type text )\nCREATE TABLE trading_platform.utxos ( utxo_id text, transaction_id text, output_index integer, address text, amount numeric, spent boolean )\nCREATE TABLE trading_platform.dapps ( dapp_id text, name text, description text, url text )\nCREATE TABLE trading_platform.peers ( peer_id text, ip_address text, port integer, last_seen timestamp )\nCREATE TABLE trading_platform.metadata ( metadata_id text, asset_id text, key text, value text )\nCREATE TABLE trading_platform.logs ( log_id text, user_id text, action text, details text, logged_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show the first and last names, email, and phone number for all patients who were added to the system in the last 90 days along with their emergency contact name."}, {"role": "assistant", "content": "SELECT first_name, last_name, email, phone_number, emergency_contact_name FROM healthcare.patients WHERE created_at >= NOW() - INTERVAL '90 days';"}, {"role": "user", "content": "Actually, can you also include the emergency contact phone number in the results?"}, {"role": "assistant", "content": "SELECT first_name, last_name, email, phone_number, emergency_contact_name, emergency_contact_phone FROM healthcare.patients WHERE created_at >= NOW() - INTERVAL '90 days';"}, {"role": "user", "content": "Now filter to only patients whose emergency_contact_phone is not null."}, {"role": "assistant", "content": "SELECT first_name, last_name, email, phone_number, emergency_contact_name, emergency_contact_phone FROM healthcare.patients WHERE created_at >= NOW() - INTERVAL '90 days' AND emergency_contact_phone IS NOT NULL;"}, {"role": "user", "content": "Sorry, I only want patients whose phone_number field is empty. Can you update the query?"}, {"role": "assistant", "content": "SELECT first_name, last_name, email, phone_number, emergency_contact_name, emergency_contact_phone FROM healthcare.patients WHERE created_at >= NOW() - INTERVAL '90 days' AND emergency_contact_phone IS NOT NULL AND (phone_number IS NULL OR phone_number = '');"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id.text, first_name.text, last_name.text, date_of_birth.date, gender.text, address.text, phone_number.text, email.text, emergency_contact_name.text, emergency_contact_phone.text, created_at.timestamp, updated_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show me the list of hashtags that have been used, along with the time they were first used."}, {"role": "assistant", "content": "SELECT tag_name, created_at \nFROM social_media.hashtags;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users (\n    user_id character varying(64) NOT NULL,  -- unique identifier for the user\n    username character varying(50) NOT NULL UNIQUE, -- user's unique handle\n    email character varying(128) NOT NULL UNIQUE, -- user's email address\n    password_hash text NOT NULL, -- hashed password\n    full_name character varying(100), -- user's full name\n    profile_picture_url text, -- URL to the profile picture\n    bio text, -- short user biography\n    location character varying(100), -- user's location\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of account creation\n    updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last profile update\n    is_verified boolean NOT NULL DEFAULT false, -- verification status\n    PRIMARY KEY (user_id)\n)\nCREATE TABLE social_media.comments (\n    comment_id character varying(64) NOT NULL, -- unique identifier for the comment\n    post_id character varying(64) NOT NULL, -- identifier of the post being commented on (FK to posts.post_id)\n    user_id character varying(64) NOT NULL, -- identifier of the user who made the comment (FK to users.user_id)\n    parent_comment_id character varying(64), -- identifier of the parent comment if it's a reply (FK to comments.comment_id)\n    content text NOT NULL, -- textual content of the comment\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of comment creation\n    updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last comment edit\n    PRIMARY KEY (comment_id)\n)\nCREATE TABLE social_media.likes (\n    like_id character varying(64) NOT NULL, -- unique identifier for the like\n    user_id character varying(64) NOT NULL, -- identifier of the user who liked (FK to users.user_id)\n    post_id character varying(64), -- identifier of the post being liked (FK to posts.post_id, nullable)\n    comment_id character varying(64), -- identifier of the comment being liked (FK to comments.comment_id, nullable)\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of when the like occurred\n    PRIMARY KEY (like_id),\n    CONSTRAINT unique_user_like UNIQUE (user_id, post_id, comment_id), -- prevent duplicate likes\n    CONSTRAINT check_like_target CHECK (post_id IS NOT NULL OR comment_id IS NOT NULL) -- ensure it likes something\n)\nCREATE TABLE social_media.follows (\n    follow_id character varying(64) NOT NULL, -- unique identifier for the follow relationship\n    follower_user_id character varying(64) NOT NULL, -- identifier of the user who is following (FK to users.user_id)\n    following_user_id character varying(64) NOT NULL, -- identifier of the user being followed (FK to users.user_id)\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of when the follow started\n    PRIMARY KEY (follow_id),\n    CONSTRAINT unique_follow UNIQUE (follower_user_id, following_user_id) -- prevent duplicate follows\n)\nCREATE TABLE social_media.hashtags (\n    hashtag_id character varying(64) NOT NULL, -- unique identifier for the hashtag\n    tag_name character varying(100) NOT NULL UNIQUE, -- the actual hashtag text (without '#')\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when the hashtag was first used\n    PRIMARY KEY (hashtag_id)\n)\nCREATE TABLE social_media.post_hashtags (\n    post_hashtag_id character varying(64) NOT NULL, -- unique identifier for the post-hashtag link\n    post_id character varying(64) NOT NULL, -- identifier of the post (FK to posts.post_id)\n    hashtag_id character varying(64) NOT NULL, -- identifier of the hashtag (FK to hashtags.hashtag_id)\n    PRIMARY KEY (post_hashtag_id),\n    CONSTRAINT unique_post_hashtag UNIQUE (post_id, hashtag_id) -- prevent duplicate tags on a post\n)\nCREATE TABLE social_media.messages (\n    message_id character varying(64) NOT NULL, -- unique identifier for the message\n    conversation_id character varying(64) NOT NULL, -- identifier for the conversation thread (FK to conversations.conversation_id)\n    sender_user_id character varying(64) NOT NULL, -- identifier of the sender (FK to users.user_id)\n    content text, -- textual content of the message\n    media_url text, -- URL to attached media (image/video)\n    media_type character varying(20), -- type of media ('image', 'video', null)\n    sent_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when message was sent\n    read_at timestamp, -- timestamp when message was read by recipient(s)\n    PRIMARY KEY (message_id)\n)\nCREATE TABLE social_media.conversations (\n    conversation_id character varying(64) NOT NULL, -- unique identifier for the conversation\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when conversation was initiated\n    last_message_at timestamp, -- timestamp of the last message in the conversation\n    is_group_chat boolean NOT NULL DEFAULT false, -- indicates if it's a group chat or direct message\n    group_name character varying(100), -- name of the group chat (if applicable)\n    PRIMARY KEY (conversation_id)\n)\nCREATE TABLE social_media.conversation_participants (\n    participant_id character varying(64) NOT NULL, -- unique identifier for the participant entry\n    conversation_id character varying(64) NOT NULL, -- identifier of the conversation (FK to conversations.conversation_id)\n    user_id character varying(64) NOT NULL, -- identifier of the user in the conversation (FK to users.user_id)\n    joined_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when user joined the conversation\n    last_read_at timestamp, -- timestamp indicating up to when the user has read messages\n    PRIMARY KEY (participant_id),\n    CONSTRAINT unique_user_conversation UNIQUE (conversation_id, user_id) -- prevent user being added multiple times\n)\nCREATE TABLE social_media.notifications (\n    notification_id character varying(64) NOT NULL, -- unique identifier for the notification\n    recipient_user_id character varying(64) NOT NULL, -- user receiving the notification (FK to users.user_id)\n    sender_user_id character varying(64), -- user triggering the notification (FK to users.user_id, can be null for system notifications)\n    notification_type character varying(30) NOT NULL, -- type of notification ('like', 'comment', 'follow', 'mention', 'message')\n    target_entity_id character varying(64), -- ID of the related entity (post_id, comment_id, user_id, conversation_id)\n    target_entity_type character varying(20), -- type of the related entity ('post', 'comment', 'user', 'conversation')\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp notification was created\n    read_at timestamp, -- timestamp notification was marked as read\n    PRIMARY KEY (notification_id)\n)\nCREATE TABLE social_media.user_settings (\n    setting_id character varying(64) NOT NULL, -- unique identifier for the setting entry\n    user_id character varying(64) NOT NULL UNIQUE, -- user the settings belong to (FK to users.user_id)\n    theme character varying(20) DEFAULT 'light', -- UI theme ('light', 'dark')\n    email_notifications_enabled boolean DEFAULT true, -- enable/disable email notifications\n    push_notifications_enabled boolean DEFAULT true, -- enable/disable push notifications\n    private_profile boolean DEFAULT false, -- is the user profile private\n    updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last setting change\n    PRIMARY KEY (setting_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Get the average overall review rating for each property. Return property_name and avg_rating."}, {"role": "assistant", "content": "SELECT pr.property_name, AVG(r.rating_overall) AS avg_rating\nFROM hospitality_technology.reviews r\nJOIN hospitality_technology.properties pr ON r.property_id = pr.property_id\nGROUP BY pr.property_name;"}, {"role": "user", "content": "Filter to only include properties with an average overall rating above 4.0."}, {"role": "assistant", "content": "SELECT pr.property_name, AVG(r.rating_overall) AS avg_rating\nFROM hospitality_technology.reviews r\nJOIN hospitality_technology.properties pr ON r.property_id = pr.property_id\nGROUP BY pr.property_name\nHAVING AVG(r.rating_overall) > 4.0;"}, {"role": "user", "content": "Additionally, include the total number of reviews per property and order the results by avg_rating descending."}, {"role": "assistant", "content": "SELECT pr.property_name,\n       AVG(r.rating_overall) AS avg_rating,\n       COUNT(r.review_id) AS review_count\nFROM hospitality_technology.reviews r\nJOIN hospitality_technology.properties pr ON r.property_id = pr.property_id\nGROUP BY pr.property_name\nHAVING AVG(r.rating_overall) > 4.0\nORDER BY avg_rating DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.properties (\n    property_id character varying(64) NOT NULL,  -- unique identifier for the property (hotel, resort, etc.)\n    property_name character varying(255) NOT NULL, -- name of the property\n    address_line1 character varying(255) NOT NULL, -- primary address line\n    address_line2 character varying(255), -- secondary address line\n    city character varying(100) NOT NULL, -- city\n    state_province character varying(100), -- state or province\n    postal_code character varying(20) NOT NULL, -- zip or postal code\n    country_code character varying(3) NOT NULL, -- ISO country code (e.g., USA, CAN)\n    phone_number character varying(30), -- main contact phone\n    email_address character varying(255), -- main contact email\n    property_type character varying(50) NOT NULL, -- e.g., Hotel, Resort, B&B, Motel\n    star_rating numeric(2,1), -- star rating (e.g., 4.5)\n    timezone character varying(64) NOT NULL, -- IANA timezone ID (e.g., America/New_York)\n    manager_staff_id character varying(64), -- FK to staff table for the general manager\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, -- record creation time\n    updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, -- record last update time\n    PRIMARY KEY (property_id)\n)\nCREATE TABLE hospitality_technology.guests (\n    guest_id character varying(64) NOT NULL,  -- unique identifier for the guest profile\n    first_name character varying(100) NOT NULL, -- guest's first name\n    last_name character varying(100) NOT NULL, -- guest's last name\n    email character varying(255) UNIQUE, -- guest's email address (unique identifier?)\n    phone_number character varying(30), -- guest's phone number\n    date_of_birth date, -- guest's date of birth\n    address_line1 character varying(255), -- guest's home address\n    city character varying(100),\n    state_province character varying(100),\n    postal_code character varying(20),\n    country_code character varying(3),\n    preferences text, -- notes on guest preferences (e.g., allergies, room location)\n    loyalty_member_id character varying(64) UNIQUE, -- FK to loyalty_members table\n    communication_consent boolean DEFAULT true, -- consent for marketing communications\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (guest_id)\n)\nCREATE TABLE hospitality_technology.staff (\n    staff_id character varying(64) NOT NULL,  -- unique identifier for the staff member\n    property_id character varying(64) NOT NULL, -- FK to properties table (primary property)\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    position character varying(100) NOT NULL, -- e.g., Front Desk Agent, Housekeeper, Manager, Concierge\n    work_email character varying(255) UNIQUE, -- staff member's work email\n    work_phone character varying(30),\n    hire_date date NOT NULL,\n    termination_date date, -- date employment ended (if applicable)\n    is_active boolean NOT NULL DEFAULT true, -- currently employed flag\n    access_level integer NOT NULL, -- permission level within systems (e.g., 1=basic, 5=admin)\n    manager_id character varying(64), -- FK to staff table (self-referencing for supervisor)\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (staff_id),\n    FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n    FOREIGN KEY (manager_id) REFERENCES hospitality_technology.staff(staff_id)\n)\nCREATE TABLE hospitality_technology.payments (\n    payment_id character varying(64) NOT NULL,  -- unique identifier for the payment transaction\n    reservation_id character varying(64), -- FK to reservations (if payment is for a stay)\n    guest_id character varying(64) NOT NULL, -- FK to guests (who paid)\n    bill_id character varying(64), -- FK to bills/invoices this payment applies to\n    amount numeric(12,2) NOT NULL, -- amount of the payment\n    currency_code character varying(3) NOT NULL, -- ISO currency code (e.g., USD, EUR)\n    payment_method character varying(50) NOT NULL, -- e.g., CreditCard, Cash, BankTransfer, Points, Voucher\n    card_type character varying(50), -- e.g., Visa, MasterCard, Amex (if CC)\n    card_last_four character varying(4), -- last 4 digits of CC (if CC)\n    transaction_ref character varying(128), -- reference ID from payment gateway or processor\n    payment_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, -- when the payment occurred\n    status character varying(50) NOT NULL, -- e.g., Pending, Succeeded, Failed, Refunded, Disputed\n    staff_id_processed character varying(64), -- FK to staff (who processed the payment)\n    notes text, -- notes about the payment\n    PRIMARY KEY (payment_id),\n    FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id),\n    FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id),\n    FOREIGN KEY (staff_id_processed) REFERENCES hospitality_technology.staff(staff_id)\n)\nCREATE TABLE hospitality_technology.reviews (\n    review_id character varying(64) NOT NULL,  -- unique identifier for the review\n    property_id character varying(64) NOT NULL, -- FK to properties table\n    reservation_id character varying(64) UNIQUE, -- FK to reservations (link review to a specific stay, optional but good)\n    guest_id character varying(64) NOT NULL, -- FK to guests table\n    rating_overall integer, -- overall score (e.g., 1-5 or 1-10)\n    rating_cleanliness integer,\n    rating_service integer,\n    rating_location integer,\n    rating_value integer,\n    comment text, -- guest's written feedback\n    review_source character varying(100), -- e.g., DirectSurvey, TripAdvisor, Google, Booking.com\n    review_date timestamp with time zone NOT NULL DEFAULT current_timestamp, -- when the review was submitted\n    is_public boolean DEFAULT true, -- whether the review is publicly visible\n    staff_response text, -- official response from the property\n    response_staff_id character varying(64), -- FK to staff (who responded)\n    response_date timestamp with time zone, -- when the response was posted\n    PRIMARY KEY (review_id),\n    FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n    FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id),\n    FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id),\n    FOREIGN KEY (response_staff_id) REFERENCES hospitality_technology.staff(staff_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Show me a list of all doctors who have made at least one diagnosis along with the total number of diagnoses they have made."}, {"role": "assistant", "content": "SELECT d.doctor_id, d.first_name, d.last_name, COUNT(di.diagnosis_id) AS diagnosis_count\nFROM healthcare.doctors d\nJOIN healthcare.diagnoses di ON d.doctor_id = di.doctor_id\nGROUP BY d.doctor_id, d.first_name, d.last_name\nHAVING COUNT(di.diagnosis_id) > 0;"}, {"role": "user", "content": "Now, limit the list to doctors with fewer than 10 diagnoses and order them by diagnosis_count ascending."}, {"role": "assistant", "content": "SELECT d.doctor_id, d.first_name, d.last_name, COUNT(di.diagnosis_id) AS diagnosis_count\nFROM healthcare.doctors d\nJOIN healthcare.diagnoses di ON d.doctor_id = di.doctor_id\nGROUP BY d.doctor_id, d.first_name, d.last_name\nHAVING COUNT(di.diagnosis_id) > 0 AND COUNT(di.diagnosis_id) < 10\nORDER BY diagnosis_count ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id.text, first_name.text, last_name.text, date_of_birth.date, gender.text, address.text, phone_number.text, email.text, emergency_contact_name.text, emergency_contact_phone.text, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE healthcare.medical_records (\n    record_id character varying(64) NOT NULL,  -- unique identifier for the medical record entry\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    appointment_id character varying(64) UNIQUE, -- FK to appointments table (can be null if record not tied to specific appt)\n    doctor_id character varying(64) NOT NULL, -- FK to doctors table (doctor creating the record)\n    record_date timestamp with time zone NOT NULL, -- date the record/observation was made\n    chief_complaint text, -- patient's primary reason for visit\n    present_illness_history text, -- detailed history of the current issue\n    past_medical_history text, -- relevant past conditions/surgeries\n    physical_examination_notes text, -- findings from the physical exam\n    assessment text, -- doctor's assessment/diagnosis summary\n    treatment_plan text, -- planned course of action\n    vitals jsonb, -- store vitals like BP, HR, Temp as structured JSON\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (record_id)\n)\nCREATE TABLE healthcare.diagnoses (\n    diagnosis_id character varying(64) NOT NULL, -- unique identifier for the diagnosis entry\n    record_id character varying(64) NOT NULL, -- FK linking to the specific medical record entry\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    doctor_id character varying(64) NOT NULL, -- FK to doctors table (diagnosing doctor)\n    diagnosis_code character varying(20) NOT NULL, -- standard code (e.g., ICD-10)\n    code_type character varying(10) NOT NULL DEFAULT 'ICD-10', -- type of code used\n    description text, -- textual description of the diagnosis\n    diagnosis_date date NOT NULL, -- date the diagnosis was made\n    status character varying(32) NOT NULL, -- e.g., Active, Resolved, Ruled Out\n    is_chronic boolean DEFAULT false, -- flag for chronic conditions\n    PRIMARY KEY (diagnosis_id)\n)\nCREATE TABLE healthcare.medications ( medication_id text, medication_name text, generic_name text, manufacturer text, ndc_code text, description text )\nCREATE TABLE healthcare.prescriptions ( prescription_id text, record_id text, patient_id text, doctor_id text, medication_id text, dosage text, frequency text, route text, start_date date, end_date date, quantity_dispensed numeric, refills_allowed integer, prescription_date timestamp )\nCREATE TABLE healthcare.insurance_plans ( plan_id text, plan_name text, insurance_provider text, plan_type text, contact_phone text, website text )\nCREATE TABLE healthcare.patient_insurance (\n    patient_insurance_id character varying(64) NOT NULL, -- unique identifier for this patient-plan link\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    plan_id character varying(64) NOT NULL, -- FK to insurance_plans table\n    policy_number character varying(100) NOT NULL, -- patient's policy number\n    group_number character varying(100), -- group number, if applicable\n    subscriber_name character varying(200), -- name of the primary policy holder\n    effective_date date NOT NULL, -- date the coverage begins\n    expiration_date date, -- date the coverage ends (if known)\n    is_primary boolean NOT NULL DEFAULT true, -- indicates if this is the primary insurance\n    PRIMARY KEY (patient_insurance_id),\n    UNIQUE (patient_id, plan_id, policy_number) -- ensure a patient doesn't have the same policy twice\n)\n"}
{"conversations": [{"role": "user", "content": "Show me the top 5 ERC20 tokens with the highest total supply on Ethereum, including their names, symbols, and contract addresses."}, {"role": "assistant", "content": "SELECT name, symbol, contract_address FROM token_metas WHERE is_erc20 = 1 ORDER BY CAST(total_supply AS decimal) DESC LIMIT 5;"}, {"role": "user", "content": "Can you join this with the token_prices_latest table to include the current price of each token?"}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address, tpl.price FROM token_metas tm JOIN token_prices_latest tpl ON tm.contract_address = tpl.address WHERE tm.is_erc20 = 1 ORDER BY CAST(tm.total_supply AS decimal) DESC LIMIT 5;"}, {"role": "user", "content": "Now filter these results to only show tokens where the price is greater than $0.10."}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address, tpl.price FROM token_metas tm JOIN token_prices_latest tpl ON tm.contract_address = tpl.address WHERE tm.is_erc20 = 1 AND tpl.price > 0.10 ORDER BY CAST(tm.total_supply AS decimal) DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp timestamp(6) NOT NULL, block_number bigint NOT NULL, transaction_hash varchar NOT NULL, transaction_index bigint NOT NULL, from_address varchar NOT NULL, contract_address varchar NOT NULL, symbol varchar NOT NULL, total_supply varchar NOT NULL, name varchar NOT NULL, decimals bigint NOT NULL, is_erc20 integer NOT NULL, is_erc721 integer NOT NULL, is_erc1155 integer NOT NULL, is_proxy integer NOT NULL, extra_info varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE erc20_balances ( block_number bigint, contract_address varchar, wallet_address varchar, amount varchar, pk varchar )\nCREATE TABLE nft_holder_historical ( block_number.bigint, contract_address.text, wallet_address.text, token_id.text, contract_type.text, amount.text, pk.integer )\nCREATE TABLE sui_coins_metadata ( object_id varchar NOT NULL, coin_type varchar NOT NULL, status varchar NOT NULL, decimals bigint NOT NULL, description varchar NOT NULL, icon_url varchar NOT NULL, symbol varchar NOT NULL, name varchar NOT NULL )\nCREATE TABLE sui_nfts ( object_id text, status text, collection_type text, package_id text, previous_transaction text, display text, owner text, name text )\nCREATE TABLE nft_collections ( blockchain.text, contract_address.text, name.text, symbol.text, deploy_block_number.bigint, deploy_block_time.bigint, erc_type.text, owner.text, traits.text, description.text, slug.text, media_info.text, image_url.text, banner_image_url.text, updated_at.bigint, banner.text, token_count.bigint, floor_price.text, floor_price_symbol.text, floor_price_contract.text, pk.integer )\nCREATE TABLE token_prices_latest (\n    blockchain varchar(36) NOT NULL, -- blockchain fields for the functionType  in contract\n    address varchar(42) NOT NULL, -- address fields for the functionType  in contract\n    decimals bigint NOT NULL, -- decimals fields for the functionType  in contract\n    symbol varchar(36) NOT NULL, -- symbol fields for the functionType  in contract\n    price real NOT NULL, -- price fields for the functionType  in contract\n    timestamp timestamp(6) NOT NULL  -- timestamp fields for the functionType  in contract\n)\nCREATE TABLE token_balances ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply decimal, amount decimal )\nCREATE TABLE token_activities ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\nCREATE TABLE token_balances_bitcoin (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n    tick varchar(255) NOT NULL, -- Ticker: Identifier of the inscription\n    wallet_address varchar(42) NOT NULL, -- Address of owner\n    total_supply varchar NOT NULL, -- Max supply: Set max supply of the inscription\n    amount varchar NOT NULL  -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info_bitcoin (\n    block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n    block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n    tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n    tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n    tick varchar(255) NOT NULL, -- Ticker:  Identifier of the inscription\n    max_supply decimal(38,0) NOT NULL, -- Max supply: Set max supply of the inscription\n    lim decimal(38,0) NOT NULL, -- Mint limit: limit per inscription\n    wlim decimal(38,0) NOT NULL, -- Limit of each address can maximum mint\n    dec integer NOT NULL, -- Decimal for minimum divie\n    creator varchar(42) NOT NULL  -- Address originating the inscription (matches from_address in transactions table)\n)\nCREATE TABLE token_activities_bitcoin (\n    block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n    block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n    tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n    tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n    log_index integer NOT NULL, -- Index of the log within the transaction\n    type varchar(20) NOT NULL, -- Operation: Type of event (deploy, mint, transfer, list)\n    tick varchar(255) NOT NULL, -- Ticker: Identifier of the inscription\n    id varchar(255) NOT NULL, -- Unique identifier of the inscription\n    amt decimal(38,0) NOT NULL, -- Amount to mint: States the amount of the inscription to operation. When operation is mint, has to be less or equal to \"lim\"\n    from_address varchar(62) NOT NULL, -- Address sending the inscription\n    to_address varchar(62) NOT NULL  -- Address receiving the inscription\n)\nCREATE TABLE token_balances_avalanche (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n    tick varchar(20) NOT NULL, -- Ticker: Identifier of the inscription\n    wallet_address varchar(42) NOT NULL, -- Address of owner\n    total_supply decimal(38,0) NOT NULL, -- Max supply: Set max supply of the inscription\n    amount decimal(38,0) NOT NULL  -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar(20) NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL, minted decimal(38,0) NOT NULL, holders decimal(38,0) NOT NULL, txs decimal(38,0) NOT NULL, updated_timestamp timestamp(3) NOT NULL, completed_timestamp timestamp(3) NOT NULL, id varchar(255) NOT NULL )\n"}
{"conversations": [{"role": "user", "content": "Show me all smart contracts created by addresses that have created more than 3 contracts, along with the count of contracts each creator has made."}, {"role": "assistant", "content": "SELECT creator_address, COUNT(*) AS contract_count FROM blockchain.smart_contracts GROUP BY creator_address HAVING COUNT(*) > 3;"}, {"role": "user", "content": "Now filter these results to only show contracts created in the last 6 months."}, {"role": "assistant", "content": "SELECT sc.creator_address, COUNT(*) AS contract_count FROM blockchain.smart_contracts sc WHERE sc.timestamp >= NOW() - INTERVAL '6 months' GROUP BY sc.creator_address HAVING COUNT(*) > 3;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE blockchain.smart_contracts ( contract_id text PRIMARY KEY, creator_address text, code text, timestamp timestamp )\n"}
{"conversations": [{"role": "user", "content": "Find pairs of citizens who share the same gender but registered in different years. Show each citizen's first and last name along with their registration year."}, {"role": "assistant", "content": "SELECT c1.first_name AS first_name_1,\n       c1.last_name  AS last_name_1,\n       EXTRACT(YEAR FROM c1.registration_date) AS reg_year_1,\n       c2.first_name AS first_name_2,\n       c2.last_name  AS last_name_2,\n       EXTRACT(YEAR FROM c2.registration_date) AS reg_year_2\nFROM government_services.citizens c1\nJOIN government_services.citizens c2\n  ON c1.gender = c2.gender\n AND EXTRACT(YEAR FROM c1.registration_date) <> EXTRACT(YEAR FROM c2.registration_date)\n AND c1.citizen_id < c2.citizen_id;"}, {"role": "user", "content": "Exclude any pairs where either citizen is not verified."}, {"role": "assistant", "content": "SELECT c1.first_name AS first_name_1,\n       c1.last_name  AS last_name_1,\n       EXTRACT(YEAR FROM c1.registration_date) AS reg_year_1,\n       c2.first_name AS first_name_2,\n       c2.last_name  AS last_name_2,\n       EXTRACT(YEAR FROM c2.registration_date) AS reg_year_2\nFROM government_services.citizens c1\nJOIN government_services.citizens c2\n  ON c1.gender = c2.gender\n AND EXTRACT(YEAR FROM c1.registration_date) <> EXTRACT(YEAR FROM c2.registration_date)\n AND c1.citizen_id < c2.citizen_id\nWHERE c1.is_verified = TRUE\n  AND c2.is_verified = TRUE;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id text, national_id_number text, first_name text, last_name text, date_of_birth date, gender text, primary_address text, contact_email text, contact_phone text, registration_date timestamp, is_verified boolean )\n"}
{"conversations": [{"role": "user", "content": "List each group conversation with its group name and the number of verified users who have posted in it."}, {"role": "assistant", "content": "SELECT c.conversation_id, c.group_name, COUNT(DISTINCT u.user_id) AS verified_posters\nFROM social_media.conversations c\nJOIN social_media.posts p ON p.location_lat IS NOT NULL -- Simulate posts linked to conversation (since no mapping, using location as a proxy)\nJOIN social_media.users u ON p.user_id = u.user_id AND u.is_verified = true\nWHERE c.is_group_chat = true\nGROUP BY c.conversation_id, c.group_name;"}, {"role": "user", "content": "Actually, only show groups created after May 1, 2024."}, {"role": "assistant", "content": "SELECT c.conversation_id, c.group_name, COUNT(DISTINCT u.user_id) AS verified_posters\nFROM social_media.conversations c\nJOIN social_media.posts p ON p.location_lat IS NOT NULL -- Simulate posts linked to conversation (since no mapping, using location as a proxy)\nJOIN social_media.users u ON p.user_id = u.user_id AND u.is_verified = true\nWHERE c.is_group_chat = true AND c.created_at > '2024-05-01'\nGROUP BY c.conversation_id, c.group_name;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id text, username text, email text, password_hash text, full_name text, profile_picture_url text, bio text, location text, created_at timestamp, updated_at timestamp, is_verified boolean )\nCREATE TABLE social_media.posts ( post_id text, user_id text, content text, media_url text, media_type text, created_at timestamp, updated_at timestamp, visibility text, location_lat numeric, location_lon numeric )\nCREATE TABLE social_media.hashtags ( hashtag_id text PRIMARY KEY, tag_name text, created_at timestamp )\nCREATE TABLE social_media.conversations ( conversation_id.text, created_at.timestamp, last_message_at.timestamp, is_group_chat.boolean, group_name.text )\nCREATE TABLE social_media.user_settings ( setting_id text PRIMARY KEY, user_id text, theme text, email_notifications_enabled bool, push_notifications_enabled bool, private_profile bool, updated_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "For each sector, could you show the sum of volume and the average close price from market_data, including the sector name?"}, {"role": "assistant", "content": "SELECT s.sector, SUM(md.volume) AS total_volume, AVG(md.close_price) AS avg_close_price\nFROM financial_services.securities s\nJOIN financial_services.market_data md ON s.security_id = md.security_id\nGROUP BY s.sector;"}, {"role": "user", "content": "Could you also include the maximum high price for each sector in the result?"}, {"role": "assistant", "content": "SELECT s.sector, SUM(md.volume) AS total_volume, AVG(md.close_price) AS avg_close_price, MAX(md.high_price) AS max_high_price\nFROM financial_services.securities s\nJOIN financial_services.market_data md ON s.security_id = md.security_id\nGROUP BY s.sector;"}, {"role": "user", "content": "Now, only include sectors where the total_volume is at least 1000000, and sort by max_high_price descending."}, {"role": "assistant", "content": "SELECT s.sector, SUM(md.volume) AS total_volume, AVG(md.close_price) AS avg_close_price, MAX(md.high_price) AS max_high_price\nFROM financial_services.securities s\nJOIN financial_services.market_data md ON s.security_id = md.security_id\nGROUP BY s.sector\nHAVING SUM(md.volume) >= 1000000\nORDER BY max_high_price DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.securities ( security_id.text, ticker_symbol.text, isin_code.text, cusip_code.text, security_name.text, security_type.text, exchange.text, currency.text, issuer_name.text, sector.text, last_updated.timestamp )\nCREATE TABLE financial_services.market_data ( data_point_id bigserial NOT NULL, security_id character varying(64) NOT NULL, data_timestamp timestamp NOT NULL, open_price numeric(19, 8), high_price numeric(19, 8), low_price numeric(19, 8), close_price numeric(19, 8) NOT NULL, adjusted_close_price numeric(19, 8), volume bigint, source character varying(50), PRIMARY KEY (data_point_id), UNIQUE (security_id, data_timestamp), FOREIGN KEY (security_id) REFERENCES financial_services.securities(security_id) )\n"}
{"conversations": [{"role": "user", "content": "Find all assets that have metadata with both 'category' and 'subcategory' keys, along with their corresponding values."}, {"role": "assistant", "content": "SELECT m1.asset_id, m1.value as category, m2.value as subcategory FROM trading_platform.metadata m1 JOIN trading_platform.metadata m2 ON m1.asset_id = m2.asset_id WHERE m1.key = 'category' AND m2.key = 'subcategory';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.metadata (\n    metadata_id character varying(64) NOT NULL,  -- unique identifier for the metadata\n    asset_id character varying(64) NOT NULL, -- identifier of the asset the metadata is associated with\n    key character varying(128) NOT NULL, -- key of the metadata\n    value text NOT NULL, -- value of the metadata\n    PRIMARY KEY (metadata_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Find medical records where the assessment mentions the generic name of any medication. Show the record ID, record date, patient ID, and the generic name mentioned."}, {"role": "assistant", "content": "SELECT T1.record_id, T1.record_date, T1.patient_id, T2.generic_name FROM healthcare.medical_records AS T1 JOIN healthcare.medications AS T2 ON T1.assessment LIKE '%' || T2.generic_name || '%' WHERE T2.generic_name IS NOT NULL AND T2.generic_name != ''"}, {"role": "user", "content": "Filter these results to only include records for patient 'pat123' and include the medication name in the output."}, {"role": "assistant", "content": "SELECT T1.record_id, T1.record_date, T1.patient_id, T2.generic_name, T2.medication_name FROM healthcare.medical_records AS T1 JOIN healthcare.medications AS T2 ON T1.assessment LIKE '%' || T2.generic_name || '%' WHERE T2.generic_name IS NOT NULL AND T2.generic_name != '' AND T1.patient_id = 'pat123'"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.medical_records ( record_id text PRIMARY KEY, patient_id text, appointment_id text, doctor_id text, record_date timestamp, chief_complaint text, present_illness_history text, past_medical_history text, physical_examination_notes text, assessment text, treatment_plan text, vitals text, created_at timestamp )\nCREATE TABLE healthcare.medications ( medication_id text PRIMARY KEY, medication_name text, generic_name text, manufacturer text, ndc_code text, description text )\n"}
{"conversations": [{"role": "user", "content": "Find all patients who have insurance plans with group numbers, showing their patient IDs and the count of such plans per patient, ordered by count in descending order."}, {"role": "assistant", "content": "SELECT patient_id, COUNT(*) AS group_plan_count\nFROM healthcare.patient_insurance\nWHERE group_number IS NOT NULL\nGROUP BY patient_id\nORDER BY group_plan_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patient_insurance (\n    patient_insurance_id character varying(64) NOT NULL, -- unique identifier for this patient-plan link\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    plan_id character varying(64) NOT NULL, -- FK to insurance_plans table\n    policy_number character varying(100) NOT NULL, -- patient's policy number\n    group_number character varying(100), -- group number, if applicable\n    subscriber_name character varying(200), -- name of the primary policy holder\n    effective_date date NOT NULL, -- date the coverage begins\n    expiration_date date, -- date the coverage ends (if known)\n    is_primary boolean NOT NULL DEFAULT true, -- indicates if this is the primary insurance\n    PRIMARY KEY (patient_insurance_id),\n    UNIQUE (patient_id, plan_id, policy_number) -- ensure a patient doesn't have the same policy twice\n)\n"}
{"conversations": [{"role": "user", "content": "For each ERC1155 NFT contract on Ethereum, show the `contract_address`, `token_id`, total amount held across all wallets, and number of unique holders."}, {"role": "assistant", "content": "SELECT nh.contract_address,\n       nh.token_id,\n       SUM(CAST(nh.amount AS bigint)) AS total_amount,\n       COUNT(DISTINCT nh.wallet_address) AS holder_count\nFROM nft_holders nh\nJOIN nft_metadata nm\n  ON nh.contract_address = nm.contract_address\n  AND nh.token_id = nm.token_id\nWHERE nm.blockchain = 'Ethereum'\n  AND nm.erc_type = 'ERC1155'\nGROUP BY nh.contract_address, nh.token_id;"}, {"role": "user", "content": "Only include NFTs where the `total_amount` is greater than 1000."}, {"role": "assistant", "content": "SELECT nh.contract_address,\n       nh.token_id,\n       SUM(CAST(nh.amount AS bigint)) AS total_amount,\n       COUNT(DISTINCT nh.wallet_address) AS holder_count\nFROM nft_holders nh\nJOIN nft_metadata nm\n  ON nh.contract_address = nm.contract_address\n  AND nh.token_id = nm.token_id\nWHERE nm.blockchain = 'Ethereum'\n  AND nm.erc_type = 'ERC1155'\nGROUP BY nh.contract_address, nh.token_id\nHAVING SUM(CAST(nh.amount AS bigint)) > 1000;"}, {"role": "user", "content": "Add the NFT `name` from `nft_metadata` in the result."}, {"role": "assistant", "content": "SELECT nh.contract_address,\n       nh.token_id,\n       nm.name,\n       SUM(CAST(nh.amount AS bigint)) AS total_amount,\n       COUNT(DISTINCT nh.wallet_address) AS holder_count\nFROM nft_holders nh\nJOIN nft_metadata nm\n  ON nh.contract_address = nm.contract_address\n  AND nh.token_id = nm.token_id\nWHERE nm.blockchain = 'Ethereum'\n  AND nm.erc_type = 'ERC1155'\nGROUP BY nh.contract_address, nh.token_id, nm.name\nHAVING SUM(CAST(nh.amount AS bigint)) > 1000;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp.timestamp, block_number.bigint, transaction_hash.text, transaction_index.bigint, from_address.text, contract_address.text, symbol.text, total_supply.text, name.text, decimals.bigint, is_erc20.integer, is_erc721.integer, is_erc1155.integer, is_proxy.integer, extra_info.text, pk.integer )\nCREATE TABLE erc1155_approval_for_all (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the transaction\n    transaction_index integer NOT NULL, -- Index of the transaction within the block\n    transaction_hash varchar(66) NOT NULL, -- Transaction hash\n    log_index integer NOT NULL, -- Log index\n    contract_address varchar(42) NOT NULL  -- Event contract address\n)\nCREATE TABLE nft_holders ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, token_id varchar NOT NULL, contract_type varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_coins_metadata (\n    object_id varchar NOT NULL, -- object id of the coin metadata object\n    coin_type varchar NOT NULL, -- coin type, eg. 0x...66::reap_token::REAP_TOKEN\n    status varchar NOT NULL, -- coin status, eg. exists, deleted\n    decimals bigint NOT NULL, -- decimals of the coin\n    description varchar NOT NULL, -- description of the coin\n    icon_url varchar NOT NULL, -- icon url of the coin\n    symbol varchar NOT NULL, -- symbol of the coin\n    name varchar NOT NULL  -- name of the coin\n)\nCREATE TABLE nft_metadata ( blockchain text, contract_address text, token_id text, contract_name text, erc_type text, amount bigint, minter text, owner text, mint_block_number bigint, mint_time bigint, mint_transaction_hash text, mint_price text, token_uri text, metadata text, name text, image_uri text, traits text, updated_at bigint, status text, rarity_score real, rarity_rank integer, unique_attribute_count integer, pk integer )\nCREATE TABLE token_prices ( uuid text, blockchain text, address text, decimals bigint, symbol text, price real, timestamp timestamp )\nCREATE TABLE erc20_approval ( block_number bigint NOT NULL, block_timestamp timestamp(6) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar NOT NULL, log_index integer NOT NULL, contract_address varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_balances ( block_number.bigint, block_timestamp.timestamp, tick.text, wallet_address.text, total_supply.decimal, amount.decimal )\nCREATE TABLE token_info (\n    block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n    block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n    tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n    tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n    tick varchar NOT NULL, -- Token tick\n    max_supply decimal(38,0) NOT NULL, -- Max supply\n    lim decimal(38,0) NOT NULL, -- Limit of each mint\n    wlim decimal(38,0) NOT NULL, -- Limit of each address can maximum mint\n    dec integer NOT NULL, -- Decimal for minimum divie\n    creator varchar(42) NOT NULL  -- Address originating the inscription (matches from_address in transactions table)\n)\nCREATE TABLE mud_holesky_redstone (\n    address varchar NOT NULL, -- address fields for the functionType  in contract\n    table_id varchar NOT NULL, -- table_id fields for the functionType  in contract\n    key_bytes varchar NOT NULL, -- key_bytes fields for the functionType  in contract\n    key0 varchar NOT NULL, -- key0 fields for the functionType  in contract\n    key1 varchar NOT NULL, -- key1 fields for the functionType  in contract\n    static_data varchar NOT NULL, -- static_data fields for the functionType  in contract\n    encoded_lengths varchar NOT NULL, -- encoded_lengths fields for the functionType  in contract\n    dynamic_data varchar NOT NULL, -- dynamic_data fields for the functionType  in contract\n    is_deleted boolean NOT NULL, -- is_deleted fields for the functionType  in contract\n    block_number bigint NOT NULL, -- Block number uniquely identifying the block\n    log_index bigint NOT NULL  -- Index of the log within the transaction\n)\nCREATE TABLE token_info_bitcoin ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, tick.text, max_supply.decimal, lim.decimal, wlim.decimal, dec.integer, creator.text )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_balances_avalanche ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply decimal, amount decimal )\n"}
{"conversations": [{"role": "user", "content": "Show all tokens on the 'Arbitrum' chain from DEX pools that have a 24-hour trading volume between $100,000 and $500,000. Display token symbol, price, and volume_24h."}, {"role": "assistant", "content": "SELECT\n  token_symbol,\n  price,\n  volume_24h\nFROM token_dexpool_info\nWHERE\n  chain = 'Arbitrum' AND volume_24h BETWEEN 100000 AND 500000;"}, {"role": "user", "content": "Include their liquidity and 6-hour price change percentage in the results."}, {"role": "assistant", "content": "SELECT\n  token_symbol,\n  price,\n  volume_24h,\n  liquidity,\n  price_change_percentage_6h\nFROM token_dexpool_info\nWHERE\n  chain = 'Arbitrum' AND volume_24h BETWEEN 100000 AND 500000;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE project_fundraising_record ( id character varying(32) NOT NULL, project_id character varying(32) NOT NULL, project_name character varying(128) NOT NULL, rounds_name character varying(32), investment_value numeric(38,14), investment_date character varying(128), introduction character varying(128), valuation numeric(38,14) )\nCREATE TABLE token_basic_info ( coin_id text, token_name text, token_symbol text, token_address text, chain text, price numeric, price_change_percentage_1h numeric, price_change_percentage_24h numeric, price_change_percentage_7d numeric, highest_price_24h numeric, lowest_price_24h numeric, market_cap numeric, market_cap_rank numeric, market_cap_change_percentage_24h text, total_volume text, narrative text, trend_rank numeric )\n \"CREATE TABLE narrative_info (\",\n    \"narrative character varying(512) NOT NULL, -- the id of narrative\",\n    \"top_3_coins text, -- the top 3 tokens in the narrative\",\n    \"price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour in the narrative\",\n    \"price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours in the narrative\",\n    \"price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days in the narrative\",\n    \"market_cap double precision, -- the market cap of the narrative\",\n    \"volume_24h double precision, -- the trade volume of the narrative\",\n    \"trend_rank bigint, -- the trending rank of the narrative, value 1 expresses the most popular narrative\",\n    \"token_num bigint, -- total token number in the narrative\",\n    \",PRIMARY KEY (narrative));\"\n\nCREATE TABLE token_dexpool_info ( pair_address character varying(512) NOT NULL, -- the id of dexpool token_name character varying(100) NOT NULL, -- the name of the token in the dexpool token_symbol character varying(100) NOT NULL, -- the token's symbol chain text, -- the chain that the dexpool resides price double precision, -- the current price of the token price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour price_change_percentage_6h double precision, -- change in value divided by the absolute price value of the original token price in 6 hours price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours makers_24h double precision, -- the makers of the dex pool in 24 hours volume_24h double precision, -- the trade volume of the dex pool in 24 hours liquidity double precision, -- the liquidity of the dex pool market_cap double precision, -- the market cap of the token trend_rank bigint, -- the rank of token in the dex pool of recent trending, value 1 expresses the most popular token. ,PRIMARY KEY (pair_address, chain) )\n  \"CREATE TABLE cex_token_balance (\",\n    \"snapshot_time character varying(32) NOT NULL,  -- the snapshot time of record, converted from original timestamp\",\n    \"chain character varying(128) NOT NULL, -- the chain that the token resides\",\n    \"address character varying(128) NOT NULL, -- the address that holds the assets, owned by a CEX\",\n    \"exchange character varying(512) NOT NULL, -- a centralized exchange name\",\n    \"token_address character varying(128) NOT NULL, -- token contract address\",\n    \"token_symbol character varying(512), --token symbol\",\n    \"balance numeric(38,10), -- token balance\",\n    \"usd_value numeric(38,14), -- value of the token held in USD\",\n    \"price double precision, --price of the token in USD\",\n    \",PRIMARY KEY (snapshot_time, exchange, address, chain, token_address));\"\n\nCREATE TABLE smart_money_profit ( address character varying(100) NOT NULL, -- the user's address rank INT, -- the rank of the address in trade performance, value 1 expresses the best address. profit numeric(38,6), -- the profit user made in a month roi numeric(38,2), -- the roi of the user in a month realized_ratio numeric(38,2), -- the percentage of the user's realized profit most_profit_token character varying(100), -- the token symbol of the user's most profitable trade last_trade_time character varying(100), -- the last trade time of the user chain character varying(100), -- the chain that the address resides PRIMARY KEY (address, chain) )\nCREATE TABLE smart_money_token_performance ( token_address text, token_symbol text, pnl numeric, net_flow numeric, avg_cost numeric, price numeric, realized_ratio numeric, roi numeric, chain text )\n"}
{"conversations": [{"role": "user", "content": "List all medical record IDs and the record date for records created by doctors specializing in 'Gastroenterology'."}, {"role": "assistant", "content": "SELECT mr.record_id, mr.record_date FROM healthcare.medical_records mr JOIN healthcare.doctors d ON mr.doctor_id = d.doctor_id WHERE d.specialty = 'Gastroenterology';"}, {"role": "user", "content": "Could you also include the patient's first and last name for these records?"}, {"role": "assistant", "content": "SELECT mr.record_id, mr.record_date, p.first_name, p.last_name FROM healthcare.medical_records mr JOIN healthcare.doctors d ON mr.doctor_id = d.doctor_id JOIN healthcare.patients p ON mr.patient_id = p.patient_id WHERE d.specialty = 'Gastroenterology';"}, {"role": "user", "content": "Now, only show records for male patients."}, {"role": "assistant", "content": "SELECT mr.record_id, mr.record_date, p.first_name, p.last_name FROM healthcare.medical_records mr JOIN healthcare.doctors d ON mr.doctor_id = d.doctor_id JOIN healthcare.patients p ON mr.patient_id = p.patient_id WHERE d.specialty = 'Gastroenterology' AND p.gender = 'Male';"}, {"role": "user", "content": "Additionally, restrict the results to medical records that have at least one associated diagnosis with status 'Resolved'."}, {"role": "assistant", "content": "SELECT DISTINCT mr.record_id, mr.record_date, p.first_name, p.last_name FROM healthcare.medical_records mr JOIN healthcare.doctors d ON mr.doctor_id = d.doctor_id JOIN healthcare.patients p ON mr.patient_id = p.patient_id JOIN healthcare.diagnoses diag ON mr.record_id = diag.record_id WHERE d.specialty = 'Gastroenterology' AND p.gender = 'Male' AND diag.status = 'Resolved';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id text, first_name text, last_name text, date_of_birth date, gender text, address text, phone_number text, email text, emergency_contact_name text, emergency_contact_phone text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.doctors ( doctor_id text, first_name text, last_name text, specialty text, license_number text, phone_number text, email text, hospital_affiliation_id text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.medical_records ( record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, appointment_id character varying(64) UNIQUE, doctor_id character varying(64) NOT NULL, record_date timestamp with time zone NOT NULL, chief_complaint text, present_illness_history text, past_medical_history text, physical_examination_notes text, assessment text, treatment_plan text, vitals jsonb, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (record_id) )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id text PRIMARY KEY, record_id text, patient_id text, doctor_id text, diagnosis_code text, code_type text, description text, diagnosis_date date, status text, is_chronic boolean )\nCREATE TABLE healthcare.prescriptions ( prescription_id character varying(64) NOT NULL, record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, doctor_id character varying(64) NOT NULL, medication_id character varying(64) NOT NULL, dosage character varying(100) NOT NULL, frequency character varying(100) NOT NULL, route character varying(50), start_date date NOT NULL, end_date date, quantity_dispensed numeric(10,2), refills_allowed integer NOT NULL DEFAULT 0, prescription_date timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (prescription_id) )\nCREATE TABLE healthcare.insurance_plans ( plan_id character varying(64) NOT NULL, plan_name character varying(200) NOT NULL, insurance_provider character varying(100) NOT NULL, plan_type character varying(50), contact_phone character varying(20), website character varying(255), PRIMARY KEY (plan_id) )\nCREATE TABLE healthcare.patient_insurance (\n    patient_insurance_id character varying(64) NOT NULL, -- unique identifier for this patient-plan link\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    plan_id character varying(64) NOT NULL, -- FK to insurance_plans table\n    policy_number character varying(100) NOT NULL, -- patient's policy number\n    group_number character varying(100), -- group number, if applicable\n    subscriber_name character varying(200), -- name of the primary policy holder\n    effective_date date NOT NULL, -- date the coverage begins\n    expiration_date date, -- date the coverage ends (if known)\n    is_primary boolean NOT NULL DEFAULT true, -- indicates if this is the primary insurance\n    PRIMARY KEY (patient_insurance_id),\n    UNIQUE (patient_id, plan_id, policy_number) -- ensure a patient doesn't have the same policy twice\n)\n"}
{"conversations": [{"role": "user", "content": "What is the ticket price for a journey on train number T4321?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to information about ticket prices for specific trains. The data I have is limited to train details such as model, manufacturer, capacity, and maintenance schedules. For ticket pricing, please consult the ticketing office or the official website."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.trains ( train_id text PRIMARY KEY, train_number text UNIQUE, model text, manufacturer text, year_manufactured int, capacity int, status text, last_maintenance_date date, next_maintenance_date date )\n"}
{"conversations": [{"role": "user", "content": "Show me all reservations with more than 2 adults, along with their property names and room types."}, {"role": "assistant", "content": "SELECT r.reservation_id, p.property_name, rt.room_type_name, r.check_in_date, r.check_out_date, r.num_adults FROM hospitality_technology.reservations r JOIN hospitality_technology.properties p ON r.property_id = p.property_id JOIN hospitality_technology.room_types rt ON r.room_type_id = rt.room_type_id WHERE r.num_adults > 2;"}, {"role": "user", "content": "Now, include only reservations with a total amount over $500 and order them by check-in date."}, {"role": "assistant", "content": "SELECT r.reservation_id, p.property_name, rt.room_type_name, r.check_in_date, r.check_out_date, r.num_adults, r.total_amount FROM hospitality_technology.reservations r JOIN hospitality_technology.properties p ON r.property_id = p.property_id JOIN hospitality_technology.room_types rt ON r.room_type_id = rt.room_type_id WHERE r.num_adults > 2 AND r.total_amount > 500 ORDER BY r.check_in_date;"}, {"role": "user", "content": "The query is missing the guest ID. Can you include that as well?"}, {"role": "assistant", "content": "SELECT r.reservation_id, r.guest_id, p.property_name, rt.room_type_name, r.check_in_date, r.check_out_date, r.num_adults, r.total_amount FROM hospitality_technology.reservations r JOIN hospitality_technology.properties p ON r.property_id = p.property_id JOIN hospitality_technology.room_types rt ON r.room_type_id = rt.room_type_id WHERE r.num_adults > 2 AND r.total_amount > 500 ORDER BY r.check_in_date;"}, {"role": "user", "content": "Actually, I need to see only reservations from properties with a star rating of 4.0 or higher."}, {"role": "assistant", "content": "SELECT r.reservation_id, r.guest_id, p.property_name, rt.room_type_name, r.check_in_date, r.check_out_date, r.num_adults, r.total_amount, p.star_rating FROM hospitality_technology.reservations r JOIN hospitality_technology.properties p ON r.property_id = p.property_id JOIN hospitality_technology.room_types rt ON r.room_type_id = rt.room_type_id WHERE r.num_adults > 2 AND r.total_amount > 500 AND p.star_rating >= 4.0 ORDER BY r.check_in_date;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.properties ( property_id character varying(64) NOT NULL, property_name character varying(255) NOT NULL, address_line1 character varying(255) NOT NULL, address_line2 character varying(255), city character varying(100) NOT NULL, state_province character varying(100), postal_code character varying(20) NOT NULL, country_code character varying(3) NOT NULL, phone_number character varying(30), email_address character varying(255), property_type character varying(50) NOT NULL, star_rating numeric(2,1), timezone character varying(64) NOT NULL, manager_staff_id character varying(64), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (property_id) )\nCREATE TABLE hospitality_technology.rooms ( room_id text PRIMARY KEY, property_id text, room_number text, room_type_id text, floor int, status text, is_smoking boolean, features text, current_condition text, last_cleaned_at timestamp )\nCREATE TABLE hospitality_technology.guests ( guest_id text, first_name text, last_name text, email text, phone_number text, date_of_birth date, address_line1 text, city text, state_province text, postal_code text, country_code text, preferences text, loyalty_member_id text, communication_consent boolean, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.reservations ( reservation_id.text, property_id.text, guest_id.text, room_id.text, room_type_id.text, check_in_date.date, check_out_date.date, actual_check_in_ts.timestamp, actual_check_out_ts.timestamp, num_adults.integer, num_children.integer, status.text, booking_source.text, rate_plan_id.text, total_amount.numeric, amount_paid.numeric, special_requests.text, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE hospitality_technology.staff ( staff_id text, property_id text, first_name text, last_name text, position text, work_email text, work_phone text, hire_date date, termination_date date, is_active boolean, access_level integer, manager_id text, created_at timestamp )\nCREATE TABLE hospitality_technology.services ( service_id text PRIMARY KEY, property_id text, service_name text, description text, category text, price numeric, unit text, is_available boolean, department text )\nCREATE TABLE hospitality_technology.service_orders ( order_id character varying(64) NOT NULL, reservation_id character varying(64), guest_id character varying(64) NOT NULL, service_id character varying(64) NOT NULL, staff_id_ordered character varying(64), staff_id_delivered character varying(64), order_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, delivery_timestamp timestamp with time zone, quantity integer NOT NULL DEFAULT 1, unit_price numeric(10, 2) NOT NULL, total_price numeric(12, 2) NOT NULL, status character varying(50) NOT NULL, notes text, bill_id character varying(64), PRIMARY KEY (order_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (service_id) REFERENCES hospitality_technology.services(service_id), FOREIGN KEY (staff_id_ordered) REFERENCES hospitality_technology.staff(staff_id), FOREIGN KEY (staff_id_delivered) REFERENCES hospitality_technology.staff(staff_id) )\nCREATE TABLE hospitality_technology.payments ( payment_id.text, reservation_id.text, guest_id.text, bill_id.text, amount.numeric, currency_code.text, payment_method.text, card_type.text, card_last_four.text, transaction_ref.text, payment_timestamp.timestamp, status.text, staff_id_processed.text, notes.text )\nCREATE TABLE hospitality_technology.reviews ( review_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, reservation_id character varying(64) UNIQUE, guest_id character varying(64) NOT NULL, rating_overall integer, rating_cleanliness integer, rating_service integer, rating_location integer, rating_value integer, comment text, review_source character varying(100), review_date timestamp with time zone NOT NULL DEFAULT current_timestamp, is_public boolean DEFAULT true, staff_response text, response_staff_id character varying(64), response_date timestamp with time zone, PRIMARY KEY (review_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (response_staff_id) REFERENCES hospitality_technology.staff(staff_id) )\n"}
{"conversations": [{"role": "user", "content": "Provide a count of citizens registered per calendar year."}, {"role": "assistant", "content": "SELECT CAST(EXTRACT(YEAR FROM registration_date) AS INTEGER) AS registration_year, COUNT(*) AS citizen_count FROM government_services.citizens GROUP BY 1 ORDER BY 1;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens (\n    citizen_id character varying(64) NOT NULL,  -- unique identifier for the citizen\n    national_id_number character varying(128) NOT NULL UNIQUE, -- official national identification number\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    date_of_birth date NOT NULL,\n    gender character varying(20),\n    primary_address text NOT NULL, -- full primary residential address\n    contact_email character varying(128) UNIQUE,\n    contact_phone character varying(32),\n    registration_date timestamp NOT NULL, -- when the citizen profile was created\n    is_verified boolean DEFAULT false, -- whether identity has been officially verified\n    PRIMARY KEY (citizen_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List all servers that are currently online and have a player count greater than their average player count across all servers in the same region."}, {"role": "assistant", "content": "SELECT s.server_id, s.server_name, s.region, s.current_players\nFROM gaming_technology.servers s\nJOIN (SELECT region, AVG(current_players) AS avg_players FROM gaming_technology.servers GROUP BY region) r\n  ON s.region = r.region\nWHERE s.status = 'online' AND s.current_players > r.avg_players;"}, {"role": "user", "content": "Can you also include the maximum players of each server in the result?"}, {"role": "assistant", "content": "SELECT s.server_id, s.server_name, s.region, s.current_players, s.max_players\nFROM gaming_technology.servers s\nJOIN (SELECT region, AVG(current_players) AS avg_players FROM gaming_technology.servers GROUP BY region) r\n  ON s.region = r.region\nWHERE s.status = 'online' AND s.current_players > r.avg_players;"}, {"role": "user", "content": "Now only show servers where current_players is at least 75% of max_players."}, {"role": "assistant", "content": "SELECT s.server_id, s.server_name, s.region, s.current_players, s.max_players\nFROM gaming_technology.servers s\nJOIN (SELECT region, AVG(current_players) AS avg_players FROM gaming_technology.servers GROUP BY region) r\n  ON s.region = r.region\nWHERE s.status = 'online'\n  AND s.current_players > r.avg_players\n  AND s.current_players >= 0.75 * s.max_players;"}, {"role": "user", "content": "Please also show the average player count for the region in each row."}, {"role": "assistant", "content": "SELECT s.server_id, s.server_name, s.region, s.current_players, s.max_players, r.avg_players\nFROM gaming_technology.servers s\nJOIN (SELECT region, AVG(current_players) AS avg_players FROM gaming_technology.servers GROUP BY region) r\n  ON s.region = r.region\nWHERE s.status = 'online'\n  AND s.current_players > r.avg_players\n  AND s.current_players >= 0.75 * s.max_players;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.game_sessions ( session_id uuid PRIMARY KEY, player_id uuid, game_id uuid, server_id uuid, start_time timestamptz, end_time timestamptz, duration_seconds int, score int, session_data jsonb )\nCREATE TABLE gaming_technology.servers ( server_id.uuid, game_id.uuid, server_name.text, region.text, ip_address.text, port.integer, current_players.integer, max_players.integer, status.text, last_heartbeat.timestamptz )\nCREATE TABLE gaming_technology.player_achievements ( player_achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), player_id uuid NOT NULL, achievement_id uuid NOT NULL, unlocked_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (player_achievement_id), UNIQUE (player_id, achievement_id) )\nCREATE TABLE gaming_technology.in_game_items ( item_id uuid, game_id uuid, item_name text, item_type text, description text, rarity text, cost_currency text, cost_amount numeric, attributes jsonb )\n"}
{"conversations": [{"role": "user", "content": "List all fuel refueling events with the refueled vehicle's make and model, the fuel type used, and the fueling location ID."}, {"role": "assistant", "content": "SELECT fl.fuel_log_id, fl.log_timestamp, v.make, v.model, fl.fuel_type, fl.quantity, fl.unit, fl.total_cost, fl.location_id\nFROM transportation.fuel_logs fl\nJOIN transportation.vehicles v ON fl.vehicle_id = v.vehicle_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles ( vehicle_id text PRIMARY KEY, license_plate text, vin text, make text, model text, year int, type text, capacity int, fuel_type text, status text, depot_id text, acquisition_date date )\nCREATE TABLE transportation.drivers ( driver_id.text, employee_id.text, first_name.text, last_name.text, license_number.text, license_expiry_date.date, contact_number.text, email.text, hire_date.date, status.text )\nCREATE TABLE transportation.routes ( route_id text, route_number text, description text, origin_location_id text, destination_location_id text, distance_km numeric, estimated_duration_minutes integer, type text )\nCREATE TABLE transportation.trips ( trip_id text, route_id text, vehicle_id text, driver_id text, scheduled_departure timestamp, actual_departure timestamp, scheduled_arrival timestamp, actual_arrival timestamp, origin_location_id text, destination_location_id text, status text, passenger_count integer, cargo_manifest_id text )\nCREATE TABLE transportation.maintenance_logs (\n    log_id character varying(64) NOT NULL,  -- unique identifier for the maintenance record\n    vehicle_id character varying(64) NOT NULL, -- identifier of the vehicle serviced\n    service_date date NOT NULL, -- date the service was performed\n    odometer_reading integer, -- vehicle mileage at time of service\n    service_type character varying(128) NOT NULL, -- type of service (e.g., Oil Change, Tire Rotation, Engine Repair)\n    description text NOT NULL, -- detailed description of work done\n    cost numeric(10, 2), -- cost of the service\n    mechanic_name character varying(128), -- name or ID of the mechanic/shop\n    next_service_due_date date, -- recommended date for next service\n    PRIMARY KEY (log_id)\n)\nCREATE TABLE transportation.fuel_logs (\n    fuel_log_id character varying(64) NOT NULL,  -- unique identifier for the fuel log entry\n    vehicle_id character varying(64) NOT NULL, -- identifier of the vehicle fueled\n    trip_id character varying(64), -- optional: identifier of the trip during which fueling occurred\n    log_timestamp timestamp with time zone NOT NULL, -- time when fueling occurred\n    fuel_type character varying(32) NOT NULL, -- type of fuel added (matches vehicle's fuel type)\n    quantity numeric(10, 3) NOT NULL, -- amount of fuel added (e.g., Liters, Gallons, kWh)\n    unit character varying(16) NOT NULL, -- unit of quantity (e.g., L, gal, kWh)\n    cost_per_unit numeric(8, 4), -- price per unit of fuel\n    total_cost numeric(10, 2) NOT NULL, -- total cost of the fuel purchase\n    odometer_reading integer, -- vehicle mileage at time of fueling\n    location_id character varying(64), -- identifier of the fueling station/location\n    PRIMARY KEY (fuel_log_id)\n)\nCREATE TABLE transportation.bookings ( booking_id character varying(64) NOT NULL, passenger_id character varying(64) NOT NULL, trip_id character varying(64) NOT NULL, seat_number character varying(16), booking_time timestamp with time zone NOT NULL, status character varying(32) NOT NULL, fare numeric(10, 2) NOT NULL, payment_transaction_id character varying(128), special_requests text, PRIMARY KEY (booking_id) )\n"}
{"conversations": [{"role": "user", "content": "List all medical records, showing the record ID, record date, and the full name of the doctor who created the record. Include the patient ID as well."}, {"role": "assistant", "content": "SELECT mr.record_id, mr.record_date, mr.patient_id, d.first_name, d.last_name FROM healthcare.medical_records mr JOIN doctors d ON mr.doctor_id = d.doctor_id;"}, {"role": "user", "content": "Refine this to only include records where the chief_complaint is not null or empty and the doctor's specialty is 'Cardiology'."}, {"role": "assistant", "content": "SELECT mr.record_id, mr.record_date, mr.patient_id, d.first_name, d.last_name FROM healthcare.medical_records mr JOIN doctors d ON mr.doctor_id = d.doctor_id WHERE (mr.chief_complaint IS NOT NULL AND mr.chief_complaint != '') AND d.specialty = 'Cardiology';"}, {"role": "user", "content": "Also, sort the results by record_date in descending order and limit the output to the top 10 records."}, {"role": "assistant", "content": "SELECT mr.record_id, mr.record_date, mr.patient_id, d.first_name, d.last_name FROM healthcare.medical_records mr JOIN doctors d ON mr.doctor_id = d.doctor_id WHERE (mr.chief_complaint IS NOT NULL AND mr.chief_complaint != '') AND d.specialty = 'Cardiology' ORDER BY mr.record_date DESC LIMIT 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.medical_records (\n    record_id character varying(64) NOT NULL,  -- unique identifier for the medical record entry\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    appointment_id character varying(64) UNIQUE, -- FK to appointments table (can be null if record not tied to specific appt)\n    doctor_id character varying(64) NOT NULL, -- FK to doctors table (doctor creating the record)\n    record_date timestamp with time zone NOT NULL, -- date the record/observation was made\n    chief_complaint text, -- patient's primary reason for visit\n    present_illness_history text, -- detailed history of the current issue\n    past_medical_history text, -- relevant past conditions/surgeries\n    physical_examination_notes text, -- findings from the physical exam\n    assessment text, -- doctor's assessment/diagnosis summary\n    treatment_plan text, -- planned course of action\n    vitals jsonb, -- store vitals like BP, HR, Temp as structured JSON\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (record_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Show each contract's address along with the total number of events it has emitted and the total number of transactions sent to it."}, {"role": "assistant", "content": "SELECT\n  c.address,\n  COUNT(e.event_id) AS event_count,\n  COUNT(t.transaction_id) AS tx_count\nFROM web3.contracts c\nLEFT JOIN web3.events e\n  ON c.contract_id = e.contract_id\nLEFT JOIN web3.transactions t\n  ON c.address = t.to_address\nGROUP BY c.address;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.contracts (\n    contract_id character varying(64) NOT NULL,  -- unique identifier for the contract\n    address character varying(128) NOT NULL, -- address of the deployed contract\n    abi text NOT NULL, -- application binary interface of the contract\n    bytecode text NOT NULL, -- bytecode of the contract\n    deployer_address character varying(128) NOT NULL, -- address of the deployer\n    deployed_at timestamp NOT NULL, -- time when the contract was deployed\n    network_id character varying(64) NOT NULL, -- identifier of the network where the contract is deployed\n    status character varying(32) NOT NULL, -- status of the contract (e.g., active, deprecated)\n    PRIMARY KEY (contract_id)\n)\nCREATE TABLE web3.events (\n    event_id character varying(64) NOT NULL,  -- unique identifier for the event\n    contract_id character varying(64) NOT NULL, -- identifier of the contract emitting the event\n    event_name character varying(128) NOT NULL, -- name of the event\n    data text NOT NULL, -- data payload of the event\n    emitted_at timestamp NOT NULL, -- time when the event was emitted\n    transaction_id character varying(64) NOT NULL, -- identifier of the transaction that triggered the event\n    log_index integer NOT NULL, -- index of the event log in the transaction\n    PRIMARY KEY (event_id)\n)\nCREATE TABLE web3.transactions (\n    transaction_id character varying(64) NOT NULL,  -- unique identifier for the transaction\n    from_address character varying(128) NOT NULL, -- address of the sender\n    to_address character varying(128), -- address of the receiver (can be null for contract deployment)\n    value numeric(38,14) NOT NULL, -- value transferred\n    gas_used integer NOT NULL, -- amount of gas used by the transaction\n    gas_price numeric(38,14) NOT NULL, -- price of gas at the time of the transaction\n    block_number integer NOT NULL, -- block number containing the transaction\n    timestamp timestamp NOT NULL, -- time when the transaction was mined\n    input_data text, -- input data of the transaction (can be null)\n    status character varying(32) NOT NULL, -- status of the transaction (e.g., success, failed)\n    nonce integer NOT NULL, -- nonce of the sender at the time of the transaction\n    PRIMARY KEY (transaction_id)\n)\nCREATE TABLE web3.tokens (\n    token_id character varying(64) NOT NULL,  -- unique identifier for the token\n    contract_address character varying(128) NOT NULL, -- address of the token contract\n    token_name character varying(128) NOT NULL, -- name of the token\n    token_symbol character varying(32) NOT NULL, -- symbol of the token\n    decimals integer NOT NULL, -- number of decimals for the token\n    total_supply numeric(38,14) NOT NULL, -- total supply of the token\n    PRIMARY KEY (token_id)\n)\nCREATE TABLE web3.token_transfers (\n    transfer_id character varying(64) NOT NULL,  -- unique identifier for the transfer\n    token_id character varying(64) NOT NULL, -- identifier of the token being transferred\n    from_address character varying(128) NOT NULL, -- address of the sender\n    to_address character varying(128) NOT NULL, -- address of the receiver\n    value numeric(38,14) NOT NULL, -- amount of tokens transferred\n    transaction_id character varying(64) NOT NULL, -- identifier of the transaction containing the transfer\n    log_index integer NOT NULL, -- index of the transfer log in the transaction\n    PRIMARY KEY (transfer_id)\n)\nCREATE TABLE web3.users (\n    user_id character varying(64) NOT NULL,  -- unique identifier for the user\n    username character varying(128) NOT NULL, -- username of the user\n    email character varying(128) NOT NULL, -- email address of the user\n    password_hash text NOT NULL, -- hashed password of the user\n    created_at timestamp NOT NULL, -- time when the user account was created\n    PRIMARY KEY (user_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List the first and last names of employees and the full name of the citizens for whom they have scheduled appointments."}, {"role": "assistant", "content": "SELECT T1.first_name ,  T1.last_name ,  T3.first_name ,  T3.last_name FROM government_services.employees AS T1 JOIN government_services.appointments AS T2 ON T1.employee_id  =  T2.employee_id JOIN government_services.citizens AS T3 ON T2.citizen_id  =  T3.citizen_id"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id text PRIMARY KEY, national_id_number text, first_name text, last_name text, date_of_birth date, gender text, primary_address text, contact_email text, contact_phone text, registration_date timestamp, is_verified boolean )\nCREATE TABLE government_services.agencies ( agency_id text PRIMARY KEY, agency_name text, jurisdiction_level text, primary_contact_email text, main_phone_number text, website_url text, established_date date, parent_agency_id text )\nCREATE TABLE government_services.services ( service_id text PRIMARY KEY, agency_id text, service_name text, description text, category text, eligibility_criteria text, standard_fee numeric, average_processing_time_days int, is_active boolean, online_application_url text )\nCREATE TABLE government_services.applications ( application_id text PRIMARY KEY, citizen_id text, service_id text, submitted_at timestamp, status text, last_updated_at timestamp, assigned_employee_id text, decision_date date, notes text, reference_number text )\nCREATE TABLE government_services.documents ( document_id text PRIMARY KEY, application_id text, citizen_id text, document_type text, file_reference text, upload_timestamp timestamp, expiry_date date, verification_status text, verified_by_employee_id text, verification_timestamp timestamp )\nCREATE TABLE government_services.payments ( payment_id text PRIMARY KEY, application_id text, citizen_id text, service_id text, amount numeric, currency text, payment_method text, payment_provider_reference text, payment_timestamp timestamp, status text, notes text )\nCREATE TABLE government_services.employees ( employee_id text PRIMARY KEY, agency_id text, first_name text, last_name text, job_title text, department text, work_email text, work_phone text, hire_date date, termination_date date, access_level text, manager_employee_id text )\nCREATE TABLE government_services.appointments ( appointment_id text PRIMARY KEY, citizen_id text, employee_id text, location_id text, service_id text, scheduled_start_time timestamp, scheduled_end_time timestamp, purpose text, status text, booking_method text, created_at timestamp, notes text )\nCREATE TABLE government_services.notifications ( notification_id text PRIMARY KEY, citizen_id text, application_id text, message_subject text, message_body text, channel text, sent_at timestamp, status text, related_entity_type text, related_entity_id text )\n"}
{"conversations": [{"role": "user", "content": "Find all pairs of different insurance records that share the same group_number, and show group_number, the patient_insurance_id of both records, and their corresponding patient_ids."}, {"role": "assistant", "content": "SELECT a.group_number,\n       a.patient_insurance_id AS pi_id1,\n       a.patient_id            AS patient1_id,\n       b.patient_insurance_id AS pi_id2,\n       b.patient_id            AS patient2_id\nFROM healthcare.patient_insurance a\nJOIN healthcare.patient_insurance b\n  ON a.group_number = b.group_number\n AND a.patient_insurance_id < b.patient_insurance_id\nWHERE a.group_number IS NOT NULL;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id text, patient_id text, plan_id text, policy_number text, group_number text, subscriber_name text, effective_date date, expiration_date date, is_primary boolean )\n"}
{"conversations": [{"role": "user", "content": "Identify all instances where a vehicle's odometer_reading increased by more than 500 miles between two consecutive fuel log entries."}, {"role": "assistant", "content": "SELECT a.vehicle_id,\n       a.fuel_log_id                         AS previous_log_id,\n       b.fuel_log_id                         AS next_log_id,\n       a.log_timestamp                       AS previous_time,\n       b.log_timestamp                       AS next_time,\n       b.odometer_reading - a.odometer_reading AS mile_increase\nFROM transportation.fuel_logs a\nJOIN transportation.fuel_logs b\n  ON a.vehicle_id = b.vehicle_id\n AND b.log_timestamp = (\n      SELECT MIN(log_timestamp)\n      FROM transportation.fuel_logs\n      WHERE vehicle_id = a.vehicle_id\n        AND log_timestamp > a.log_timestamp\n    )\nWHERE b.odometer_reading - a.odometer_reading > 500;"}, {"role": "user", "content": "Now restrict these increases to those where the time difference between entries is less than 7 days."}, {"role": "assistant", "content": "SELECT a.vehicle_id,\n       a.fuel_log_id                         AS previous_log_id,\n       b.fuel_log_id                         AS next_log_id,\n       a.log_timestamp                       AS previous_time,\n       b.log_timestamp                       AS next_time,\n       b.odometer_reading - a.odometer_reading AS mile_increase,\n       EXTRACT(epoch FROM (b.log_timestamp - a.log_timestamp))/3600 AS hours_diff\nFROM transportation.fuel_logs a\nJOIN transportation.fuel_logs b\n  ON a.vehicle_id = b.vehicle_id\n AND b.log_timestamp = (\n      SELECT MIN(log_timestamp)\n      FROM transportation.fuel_logs\n      WHERE vehicle_id = a.vehicle_id\n        AND log_timestamp > a.log_timestamp\n    )\nWHERE b.odometer_reading - a.odometer_reading > 500\n  AND b.log_timestamp - a.log_timestamp < INTERVAL '7 days';"}, {"role": "user", "content": "Also include both the mile increase and the time difference in hours in the final output columns."}, {"role": "assistant", "content": "SELECT a.vehicle_id,\n       a.fuel_log_id                         AS previous_log_id,\n       b.fuel_log_id                         AS next_log_id,\n       b.odometer_reading - a.odometer_reading AS mile_increase,\n       EXTRACT(epoch FROM (b.log_timestamp - a.log_timestamp))/3600 AS hours_difference\nFROM transportation.fuel_logs a\nJOIN transportation.fuel_logs b\n  ON a.vehicle_id = b.vehicle_id\n AND b.log_timestamp = (\n      SELECT MIN(log_timestamp)\n      FROM transportation.fuel_logs\n      WHERE vehicle_id = a.vehicle_id\n        AND log_timestamp > a.log_timestamp\n    )\nWHERE b.odometer_reading - a.odometer_reading > 500\n  AND b.log_timestamp - a.log_timestamp < INTERVAL '7 days';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.fuel_logs ( fuel_log_id.text, vehicle_id.text, trip_id.text, log_timestamp.timestamp, fuel_type.text, quantity.numeric, unit.text, cost_per_unit.numeric, total_cost.numeric, odometer_reading.integer, location_id.text )\n"}
{"conversations": [{"role": "user", "content": "Give me a breakdown of the number of reviews per day for the last 14 days, including the review_date and review count."}, {"role": "assistant", "content": "SELECT DATE(review_date) AS review_day, COUNT(*) AS review_count\nFROM hospitality_technology.reviews\nWHERE review_date >= CURRENT_DATE - INTERVAL '14 days'\nGROUP BY DATE(review_date)\nORDER BY review_day ASC;"}, {"role": "user", "content": "Add the number of public reviews for each day in a separate column named public_review_count."}, {"role": "assistant", "content": "SELECT DATE(review_date) AS review_day,\n       COUNT(*) AS review_count,\n       SUM(CASE WHEN is_public THEN 1 ELSE 0 END) AS public_review_count\nFROM hospitality_technology.reviews\nWHERE review_date >= CURRENT_DATE - INTERVAL '14 days'\nGROUP BY DATE(review_date)\nORDER BY review_day ASC;"}, {"role": "user", "content": "Now, also include the number of reviews per day with a rating_overall below 3 as a column called low_rating_count."}, {"role": "assistant", "content": "SELECT DATE(review_date) AS review_day,\n       COUNT(*) AS review_count,\n       SUM(CASE WHEN is_public THEN 1 ELSE 0 END) AS public_review_count,\n       SUM(CASE WHEN rating_overall < 3 THEN 1 ELSE 0 END) AS low_rating_count\nFROM hospitality_technology.reviews\nWHERE review_date >= CURRENT_DATE - INTERVAL '14 days'\nGROUP BY DATE(review_date)\nORDER BY review_day ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.reviews ( review_id text, property_id text, reservation_id text, guest_id text, rating_overall integer, rating_cleanliness integer, rating_service integer, rating_location integer, rating_value integer, comment text, review_source text, review_date timestamp, is_public boolean, staff_response text, response_staff_id text, response_date timestamp )\n"}
{"conversations": [{"role": "user", "content": "List the vehicle_id, make, model, and total maintenance cost for each vehicle that has undergone maintenance, ordering by total maintenance cost descending."}, {"role": "assistant", "content": "SELECT m.vehicle_id, v.make, v.model, SUM(m.cost) AS total_maintenance_cost\nFROM transportation.maintenance_logs m\nJOIN transportation.vehicles v ON m.vehicle_id = v.vehicle_id\nGROUP BY m.vehicle_id, v.make, v.model\nORDER BY total_maintenance_cost DESC;"}, {"role": "user", "content": "Now further include the count of maintenance entries per vehicle and only include vehicles with more than 3 maintenance logs."}, {"role": "assistant", "content": "SELECT m.vehicle_id, v.make, v.model, COUNT(*) AS maintenance_count, SUM(m.cost) AS total_maintenance_cost\nFROM transportation.maintenance_logs m\nJOIN transportation.vehicles v ON m.vehicle_id = v.vehicle_id\nGROUP BY m.vehicle_id, v.make, v.model\nHAVING COUNT(*) > 3\nORDER BY total_maintenance_cost DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles ( vehicle_id text PRIMARY KEY, license_plate text, vin text, make text, model text, year int, type text, capacity int, fuel_type text, status text, depot_id text, acquisition_date date )\nCREATE TABLE transportation.drivers ( driver_id text PRIMARY KEY, employee_id text, first_name text, last_name text, license_number text, license_expiry_date date, contact_number text, email text, hire_date date, status text )\nCREATE TABLE transportation.routes ( route_id text PRIMARY KEY, route_number text, description text, origin_location_id text, destination_location_id text, distance_km numeric, estimated_duration_minutes int, type text )\nCREATE TABLE transportation.trips ( trip_id.text, route_id.text, vehicle_id.text, driver_id.text, scheduled_departure.timestamp, actual_departure.timestamp, scheduled_arrival.timestamp, actual_arrival.timestamp, origin_location_id.text, destination_location_id.text, status.text, passenger_count.integer, cargo_manifest_id.text )\nCREATE TABLE transportation.maintenance_logs ( log_id text, vehicle_id text, service_date date, odometer_reading integer, service_type text, description text, cost numeric, mechanic_name text, next_service_due_date date )\nCREATE TABLE transportation.fuel_logs ( fuel_log_id.text, vehicle_id.text, trip_id.text, log_timestamp.timestamp, fuel_type.text, quantity.numeric, unit.text, cost_per_unit.numeric, total_cost.numeric, odometer_reading.integer, location_id.text )\nCREATE TABLE transportation.passengers ( passenger_id text PRIMARY KEY, first_name text, last_name text, email text, phone_number text, date_of_birth date, loyalty_program_id text, created_at timestamp )\nCREATE TABLE transportation.bookings ( booking_id.text, passenger_id.text, trip_id.text, seat_number.text, booking_time.timestamp, status.text, fare.numeric, payment_transaction_id.text, special_requests.text )\n"}
{"conversations": [{"role": "user", "content": "I want a list of game_id and the count of hidden achievements for each game."}, {"role": "assistant", "content": "SELECT game_id, COUNT(*) AS hidden_achievement_count\nFROM gaming_technology.achievements\nWHERE hidden = TRUE\nGROUP BY game_id;"}, {"role": "user", "content": "Now only include games where the hidden_achievement_count is greater than 5."}, {"role": "assistant", "content": "SELECT game_id, COUNT(*) AS hidden_achievement_count\nFROM gaming_technology.achievements\nWHERE hidden = TRUE\nGROUP BY game_id\nHAVING COUNT(*) > 5;"}, {"role": "user", "content": "Also order the results by hidden_achievement_count in descending order."}, {"role": "assistant", "content": "SELECT game_id, COUNT(*) AS hidden_achievement_count\nFROM gaming_technology.achievements\nWHERE hidden = TRUE\nGROUP BY game_id\nHAVING COUNT(*) > 5\nORDER BY hidden_achievement_count DESC;"}, {"role": "user", "content": "Finally, include the average points of those hidden achievements as avg_hidden_points."}, {"role": "assistant", "content": "SELECT game_id,\n       COUNT(*) AS hidden_achievement_count,\n       AVG(points) AS avg_hidden_points\nFROM gaming_technology.achievements\nWHERE hidden = TRUE\nGROUP BY game_id\nHAVING COUNT(*) > 5\nORDER BY hidden_achievement_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.players ( player_id uuid NOT NULL DEFAULT gen_random_uuid(), username character varying(100) NOT NULL UNIQUE, email character varying(255) NOT NULL UNIQUE, password_hash text NOT NULL, registration_date timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, last_login timestamp with time zone, country_code character(2), status character varying(20) NOT NULL DEFAULT 'active', profile_data jsonb, PRIMARY KEY (player_id) )\nCREATE TABLE gaming_technology.games ( game_id uuid PRIMARY KEY, title text, developer_id uuid, publisher_id uuid, genre text, release_date date, description text, platform text, engine text, website text )\nCREATE TABLE gaming_technology.game_sessions ( session_id uuid NOT NULL DEFAULT gen_random_uuid(), player_id uuid NOT NULL, game_id uuid NOT NULL, server_id uuid, start_time timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, end_time timestamp with time zone, duration_seconds integer, score integer, session_data jsonb, PRIMARY KEY (session_id) )\nCREATE TABLE gaming_technology.servers ( server_id uuid PRIMARY KEY, game_id uuid, server_name text, region text, ip_address text, port int, current_players int, max_players int, status text, last_heartbeat timestamptz )\nCREATE TABLE gaming_technology.achievements ( achievement_id.uuid, game_id.uuid, name.text, description.text, icon_url.text, points.integer, hidden.boolean )\nCREATE TABLE gaming_technology.player_achievements ( player_achievement_id uuid PRIMARY KEY, player_id uuid, achievement_id uuid, unlocked_at timestamptz )\nCREATE TABLE gaming_technology.in_game_items ( item_id uuid PRIMARY KEY, game_id uuid, item_name text, item_type text, description text, rarity text, cost_currency text, cost_amount numeric, attributes jsonb )\nCREATE TABLE gaming_technology.player_inventory ( inventory_id uuid PRIMARY KEY, player_id uuid, item_id uuid, quantity int, acquired_at timestamptz, instance_data jsonb )\n"}
{"conversations": [{"role": "user", "content": "List each transaction along with its status and the names of any events that were emitted during that transaction."}, {"role": "assistant", "content": "SELECT tr.transaction_id, tr.status, e.event_name\nFROM web3.transactions tr\nLEFT JOIN web3.events e ON tr.transaction_id = e.transaction_id;"}, {"role": "user", "content": "Only show transactions that had more than one event emitted, and list the number of events for each such transaction."}, {"role": "assistant", "content": "SELECT tr.transaction_id, tr.status, COUNT(e.event_id) AS event_count\nFROM web3.transactions tr\nJOIN web3.events e ON tr.transaction_id = e.transaction_id\nGROUP BY tr.transaction_id, tr.status\nHAVING COUNT(e.event_id) > 1;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.contracts ( contract_id character varying(64) NOT NULL, address character varying(128) NOT NULL, abi text NOT NULL, bytecode text NOT NULL, deployer_address character varying(128) NOT NULL, deployed_at timestamp NOT NULL, network_id character varying(64) NOT NULL, status character varying(32) NOT NULL, PRIMARY KEY (contract_id) )\nCREATE TABLE web3.events ( event_id.text, contract_id.text, event_name.text, data.text, emitted_at.timestamp, transaction_id.text, log_index.integer )\nCREATE TABLE web3.transactions ( transaction_id character varying(64) NOT NULL, from_address character varying(128) NOT NULL, to_address character varying(128), value numeric(38,14) NOT NULL, gas_used integer NOT NULL, gas_price numeric(38,14) NOT NULL, block_number integer NOT NULL, timestamp timestamp NOT NULL, input_data text, status character varying(32) NOT NULL, nonce integer NOT NULL, PRIMARY KEY (transaction_id) )\nCREATE TABLE web3.tokens (\n    token_id character varying(64) NOT NULL,  -- unique identifier for the token\n    contract_address character varying(128) NOT NULL, -- address of the token contract\n    token_name character varying(128) NOT NULL, -- name of the token\n    token_symbol character varying(32) NOT NULL, -- symbol of the token\n    decimals integer NOT NULL, -- number of decimals for the token\n    total_supply numeric(38,14) NOT NULL, -- total supply of the token\n    PRIMARY KEY (token_id)\n)\nCREATE TABLE web3.token_transfers ( transfer_id text PRIMARY KEY, token_id text, from_address text, to_address text, value numeric, transaction_id text, log_index int )\nCREATE TABLE web3.wallets ( wallet_id text, user_id text, address text, private_key text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "What proportion of posts have received at least one like? Return the ratio as a decimal between 0 and 1."}, {"role": "assistant", "content": "SELECT COUNT(DISTINCT CASE WHEN l.post_id IS NOT NULL THEN p.post_id END)::float / COUNT(DISTINCT p.post_id) AS like_ratio\nFROM social_media.posts p\nLEFT JOIN social_media.likes l ON p.post_id = l.post_id;"}, {"role": "user", "content": "Please break down this ratio by media_type, excluding posts without a media_type."}, {"role": "assistant", "content": "SELECT p.media_type,\n       COUNT(DISTINCT CASE WHEN l.post_id IS NOT NULL THEN p.post_id END)::float / COUNT(*) AS like_ratio\nFROM social_media.posts p\nLEFT JOIN social_media.likes l ON p.post_id = l.post_id\nWHERE p.media_type IS NOT NULL\nGROUP BY p.media_type;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.posts ( post_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, content text, media_url text, media_type character varying(20), created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, visibility character varying(20) NOT NULL DEFAULT 'public', location_lat numeric(9,6), location_lon numeric(9,6), PRIMARY KEY (post_id) )\nCREATE TABLE social_media.likes ( like_id text PRIMARY KEY, user_id text, post_id text, comment_id text, created_at timestamp )\nCREATE TABLE social_media.hashtags ( hashtag_id character varying(64) NOT NULL, tag_name character varying(100) NOT NULL UNIQUE, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (hashtag_id) )\nCREATE TABLE social_media.messages (\n    message_id character varying(64) NOT NULL, -- unique identifier for the message\n    conversation_id character varying(64) NOT NULL, -- identifier for the conversation thread (FK to conversations.conversation_id)\n    sender_user_id character varying(64) NOT NULL, -- identifier of the sender (FK to users.user_id)\n    content text, -- textual content of the message\n    media_url text, -- URL to attached media (image/video)\n    media_type character varying(20), -- type of media ('image', 'video', null)\n    sent_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when message was sent\n    read_at timestamp, -- timestamp when message was read by recipient(s)\n    PRIMARY KEY (message_id)\n)\nCREATE TABLE social_media.conversation_participants ( participant_id.text, conversation_id.text, user_id.text, joined_at.timestamp, last_read_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "What is the average age of verified citizens as of today?"}, {"role": "assistant", "content": "SELECT AVG(EXTRACT(YEAR FROM AGE(NOW(), date_of_birth))) AS average_age_verified\nFROM government_services.citizens\nWHERE is_verified = TRUE;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id text PRIMARY KEY, national_id_number text, first_name text, last_name text, date_of_birth date, gender text, primary_address text, contact_email text, contact_phone text, registration_date timestamp, is_verified boolean )\nCREATE TABLE government_services.agencies ( agency_id.text, agency_name.text, jurisdiction_level.text, primary_contact_email.text, main_phone_number.text, website_url.text, established_date.date, parent_agency_id.text )\nCREATE TABLE government_services.services ( service_id text, agency_id text, service_name text, description text, category text, eligibility_criteria text, standard_fee numeric, average_processing_time_days integer, is_active boolean, online_application_url text )\nCREATE TABLE government_services.applications ( application_id.text, citizen_id.text, service_id.text, submitted_at.timestamp, status.text, last_updated_at.timestamp, assigned_employee_id.text, decision_date.date, notes.text, reference_number.text )\nCREATE TABLE government_services.payments ( payment_id character varying(64) NOT NULL, application_id character varying(64), citizen_id character varying(64) NOT NULL, service_id character varying(64), amount numeric(12, 2) NOT NULL, currency character varying(3) NOT NULL DEFAULT 'USD', payment_method character varying(50), payment_provider_reference character varying(128), payment_timestamp timestamp NOT NULL, status character varying(30) NOT NULL, notes text, PRIMARY KEY (payment_id) )\nCREATE TABLE government_services.notifications ( notification_id text PRIMARY KEY, citizen_id text, application_id text, message_subject text, message_body text, channel text, sent_at timestamp, status text, related_entity_type text, related_entity_id text )\n"}
{"conversations": [{"role": "user", "content": "Which patients have insurance policies that are effective between May 1st, 2023 and October 1st, 2023? Show their patient_id, policy_number, and effective_date, and also include the related plan_id."}, {"role": "assistant", "content": "SELECT patient_id, policy_number, effective_date, plan_id FROM healthcare.patient_insurance WHERE effective_date >= '2023-05-01' AND effective_date <= '2023-10-01';"}, {"role": "user", "content": "I only want to see policies that are still primary. Could you adjust the query to add that condition?"}, {"role": "assistant", "content": "SELECT patient_id, policy_number, effective_date, plan_id FROM healthcare.patient_insurance WHERE effective_date >= '2023-05-01' AND effective_date <= '2023-10-01' AND is_primary = true;"}, {"role": "user", "content": "Actually, please also show only entries where the subscriber_name starts with the letter 'A'."}, {"role": "assistant", "content": "SELECT patient_id, policy_number, effective_date, plan_id FROM healthcare.patient_insurance WHERE effective_date >= '2023-05-01' AND effective_date <= '2023-10-01' AND is_primary = true AND subscriber_name LIKE 'A%';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patient_insurance (\n    patient_insurance_id character varying(64) NOT NULL, -- unique identifier for this patient-plan link\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    plan_id character varying(64) NOT NULL, -- FK to insurance_plans table\n    policy_number character varying(100) NOT NULL, -- patient's policy number\n    group_number character varying(100), -- group number, if applicable\n    subscriber_name character varying(200), -- name of the primary policy holder\n    effective_date date NOT NULL, -- date the coverage begins\n    expiration_date date, -- date the coverage ends (if known)\n    is_primary boolean NOT NULL DEFAULT true, -- indicates if this is the primary insurance\n    PRIMARY KEY (patient_insurance_id),\n    UNIQUE (patient_id, plan_id, policy_number) -- ensure a patient doesn't have the same policy twice\n)\n"}
{"conversations": [{"role": "user", "content": "List all case numbers and names, along with the full name of the client associated with each case."}, {"role": "assistant", "content": "SELECT T1.case_number, T1.case_name, T2.first_name, T2.last_name FROM cases AS T1 JOIN clients AS T2 ON T1.client_id = T2.client_id;"}, {"role": "user", "content": "Now, only include cases that were opened after 2023-06-01."}, {"role": "assistant", "content": "SELECT T1.case_number, T1.case_name, T2.first_name, T2.last_name FROM cases AS T1 JOIN clients AS T2 ON T1.client_id = T2.client_id WHERE T1.date_opened > '2023-06-01';"}, {"role": "user", "content": "Please order the results by the client's last name in ascending order."}, {"role": "assistant", "content": "SELECT T1.case_number, T1.case_name, T2.first_name, T2.last_name FROM cases AS T1 JOIN clients AS T2 ON T1.client_id = T2.client_id WHERE T1.date_opened > '2023-06-01' ORDER BY T2.last_name ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.clients ( client_id text PRIMARY KEY, first_name text, last_name text, company_name text, email text UNIQUE, phone text, address text, date_registered timestamp, status text )\nCREATE TABLE legal_services.law_firms ( firm_id text PRIMARY KEY, firm_name text, address text, phone text, website text, founded_date date, managing_partner_id text )\nCREATE TABLE legal_services.cases ( case_id text PRIMARY KEY, case_number text UNIQUE, case_name text, client_id text, lead_lawyer_id text, case_type text, status text, date_opened timestamp, date_closed timestamp, description text, court_jurisdiction text )\nCREATE TABLE legal_services.appointments ( appointment_id text PRIMARY KEY, client_id text, lawyer_id text, case_id text, start_time timestamp, end_time timestamp, location text, subject text, notes text, status text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "For each user, list all the distinct actions they have performed along with the count of each action."}, {"role": "assistant", "content": "SELECT user_id, action, COUNT(*) FROM trading_platform.logs GROUP BY user_id, action ORDER BY user_id, action;"}, {"role": "user", "content": "Now, only show users who have performed more than 5 distinct actions."}, {"role": "assistant", "content": "SELECT user_id FROM trading_platform.logs GROUP BY user_id HAVING COUNT(DISTINCT action) > 5 ORDER BY user_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.logs ( log_id character varying(64) NOT NULL, user_id character varying(64), action character varying(128) NOT NULL, details text NOT NULL, logged_at timestamp NOT NULL, PRIMARY KEY (log_id) )\n"}
{"conversations": [{"role": "user", "content": "Which is the token with the largest difference between its highest and lowest price in the last 24h on each chain, and what is the token's symbol and current price?"}, {"role": "assistant", "content": "SELECT chain, token_symbol, price, (highest_price_24h - lowest_price_24h) AS price_diff_24h\nFROM token_basic_info\nWHERE (chain, highest_price_24h - lowest_price_24h) IN (\n  SELECT chain, MAX(highest_price_24h - lowest_price_24h) AS diff\n  FROM token_basic_info\n  GROUP BY chain\n)\nORDER BY price_diff_24h DESC;"}, {"role": "user", "content": "Could you also include the percentage change over 24 hours for each token in the result?"}, {"role": "assistant", "content": "SELECT chain, token_symbol, price, price_change_percentage_24h, (highest_price_24h - lowest_price_24h) AS price_diff_24h\nFROM token_basic_info\nWHERE (chain, highest_price_24h - lowest_price_24h) IN (\n  SELECT chain, MAX(highest_price_24h - lowest_price_24h) AS diff\n  FROM token_basic_info\n  GROUP BY chain\n)\nORDER BY price_diff_24h DESC;"}, {"role": "user", "content": "I'm only interested in tokens where this price difference exceeds $5. Can you filter for that?"}, {"role": "assistant", "content": "SELECT chain, token_symbol, price, price_change_percentage_24h, (highest_price_24h - lowest_price_24h) AS price_diff_24h\nFROM token_basic_info\nWHERE (chain, highest_price_24h - lowest_price_24h) IN (\n  SELECT chain, MAX(highest_price_24h - lowest_price_24h) AS diff\n  FROM token_basic_info\n  GROUP BY chain\n)\nAND (highest_price_24h - lowest_price_24h) > 5\nORDER BY price_diff_24h DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\n \"CREATE TABLE token_basic_info (\",\n    \"coin_id character varying(100) NOT NULL, -- the id of the token\",\n    \"token_name character varying(100) NOT NULL, -- the token's name\",\n    \"token_symbol character varying(100) NOT NULL, -- the token's symbol\",\n    \"token_address character varying(100) NOT NULL, -- the token's address\",\n    \"chain text, -- the chain that the token resides\",\n    \"price double precision, -- the current price of the token\",\n    \"price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour\",\n    \"price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours\",\n    \"price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days\",\n    \"highest_price_24h double precision, -- the highest price of the token in 24 hours\",\n    \"lowest_price_24h double precision,  -- the lowest price of the token in 24 hours\",\n    \"market_cap double precision, -- the market cap of the token\",\n    \"market_cap_rank bigint, -- the rank of the token market cap in desc\",\n    \"market_cap_change_percentage_24h text, -- the percentage of market cap changes in 24 hours\",\n    \"total_volume text, -- the trade volum of the token both in decentralized exchange(DEX) and centralized exchange(CEX)\",    \n    \"narrative text, -- the category or narrative of the token\",\n    \"trend_rank biging, -- the trending rank of the token, value 1 expresses the most popular token.\",\n    \",PRIMARY KEY (coin_id, chain));\",\n\n"}
{"conversations": [{"role": "user", "content": "Find all in-game items that have a 'mana_cost' attribute in their attributes JSON. Show the item ID, item name, and the value of the 'mana_cost'."}, {"role": "assistant", "content": "SELECT item_id, item_name, attributes ->> 'mana_cost' AS mana_cost FROM gaming_technology.in_game_items WHERE attributes ? 'mana_cost'"}, {"role": "user", "content": "Now, only include items where the 'mana_cost' is greater than 50."}, {"role": "assistant", "content": "SELECT item_id, item_name, attributes ->> 'mana_cost' AS mana_cost FROM gaming_technology.in_game_items WHERE attributes ? 'mana_cost' AND (attributes ->> 'mana_cost')::int > 50"}, {"role": "user", "content": "Add the item's rarity and the title of the game it belongs to in the output."}, {"role": "assistant", "content": "SELECT t1.item_id, t1.item_name, t1.rarity, t2.title, t1.attributes ->> 'mana_cost' AS mana_cost FROM gaming_technology.in_game_items AS t1 JOIN gaming_technology.games AS t2 ON t1.game_id = t2.game_id WHERE t1.attributes ? 'mana_cost' AND (t1.attributes ->> 'mana_cost')::int > 50"}, {"role": "user", "content": "Filter the results to only include items from games in the 'Fantasy' genre."}, {"role": "assistant", "content": "SELECT t1.item_id, t1.item_name, t1.rarity, t2.title, t1.attributes ->> 'mana_cost' AS mana_cost FROM gaming_technology.in_game_items AS t1 JOIN gaming_technology.games AS t2 ON t1.game_id = t2.game_id WHERE t1.attributes ? 'mana_cost' AND (t1.attributes ->> 'mana_cost')::int > 50 AND t2.genre = 'Fantasy'"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.games ( game_id uuid PRIMARY KEY, title text, developer_id uuid, publisher_id uuid, genre text, release_date date, description text, platform text, engine text, website text )\nCREATE TABLE gaming_technology.developers ( developer_id uuid PRIMARY KEY, name text, country text, founded_year int, website text, created_at timestamptz )\nCREATE TABLE gaming_technology.game_sessions ( session_id uuid PRIMARY KEY, player_id uuid, game_id uuid, server_id uuid, start_time timestamptz, end_time timestamptz, duration_seconds int, score int, session_data jsonb )\nCREATE TABLE gaming_technology.servers ( server_id uuid PRIMARY KEY, game_id uuid, server_name text, region text, ip_address text, port int, current_players int, max_players int, status text, last_heartbeat timestamptz )\nCREATE TABLE gaming_technology.achievements ( achievement_id uuid PRIMARY KEY, game_id uuid, name text, description text, icon_url text, points int, hidden boolean )\nCREATE TABLE gaming_technology.player_achievements ( player_achievement_id uuid PRIMARY KEY, player_id uuid, achievement_id uuid, unlocked_at timestamptz )\nCREATE TABLE gaming_technology.in_game_items ( item_id uuid PRIMARY KEY, game_id uuid, item_name text, item_type text, description text, rarity text, cost_currency text, cost_amount numeric, attributes jsonb )\nCREATE TABLE gaming_technology.player_inventory ( inventory_id uuid PRIMARY KEY, player_id uuid, item_id uuid, quantity int, acquired_at timestamptz, instance_data jsonb )\n"}
{"conversations": [{"role": "user", "content": "Show me the object ID, coin type, and balance for all SUI coins where the status is 'active'."}, {"role": "assistant", "content": "SELECT object_id, coin_type, balance FROM sui_coins WHERE status = 'active'"}, {"role": "user", "content": "Also, include the owner address in the result."}, {"role": "assistant", "content": "SELECT object_id, coin_type, balance, owner FROM sui_coins WHERE status = 'active'"}, {"role": "user", "content": "Filter the results to only show coins where the balance is greater than '100000000000'."}, {"role": "assistant", "content": "SELECT object_id, coin_type, balance, owner FROM sui_coins WHERE status = 'active' AND CAST(balance AS NUMERIC) > 100000000000"}, {"role": "user", "content": "Sort the results by balance in descending order and limit the output to 10."}, {"role": "assistant", "content": "SELECT object_id, coin_type, balance, owner FROM sui_coins WHERE status = 'active' AND CAST(balance AS NUMERIC) > 100000000000 ORDER BY CAST(balance AS NUMERIC) DESC LIMIT 10"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp timestamp(6) NOT NULL, block_number bigint NOT NULL, transaction_hash varchar NOT NULL, transaction_index bigint NOT NULL, from_address varchar NOT NULL, contract_address varchar NOT NULL, symbol varchar NOT NULL, total_supply varchar NOT NULL, name varchar NOT NULL, decimals bigint NOT NULL, is_erc20 integer NOT NULL, is_erc721 integer NOT NULL, is_erc1155 integer NOT NULL, is_proxy integer NOT NULL, extra_info varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE erc20_balances_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_holders ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, token_id varchar NOT NULL, contract_type varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE nft_holder_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, token_id varchar NOT NULL, contract_type varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE nft_collections ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, name varchar NOT NULL, symbol varchar NOT NULL, deploy_block_number bigint NOT NULL, deploy_block_time bigint NOT NULL, erc_type varchar NOT NULL, owner varchar NOT NULL, traits varchar NOT NULL, description varchar NOT NULL, slug varchar NOT NULL, media_info varchar NOT NULL, image_url varchar NOT NULL, banner_image_url varchar NOT NULL, updated_at bigint NOT NULL, banner varchar NOT NULL, token_count bigint NOT NULL, floor_price varchar NOT NULL, floor_price_symbol varchar NOT NULL, floor_price_contract varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_prices ( uuid varchar(36) NOT NULL, blockchain varchar(36) NOT NULL, address varchar(42) NOT NULL, decimals bigint NOT NULL, symbol varchar(36) NOT NULL, price real NOT NULL, timestamp timestamp(6) NOT NULL )\nCREATE TABLE token_prices_latest ( blockchain varchar(36) NOT NULL, address varchar(42) NOT NULL, decimals bigint NOT NULL, symbol varchar(36) NOT NULL, price real NOT NULL, timestamp timestamp(6) NOT NULL )\nCREATE TABLE token_info ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE token_activities ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar NOT NULL, tick varchar NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(42) NOT NULL, to_address varchar(42) NOT NULL )\nCREATE TABLE token_balances_bitcoin ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar(255) NOT NULL, wallet_address varchar(42) NOT NULL, total_supply varchar NOT NULL, amount varchar NOT NULL )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar(20) NOT NULL, tick varchar(255) NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(62) NOT NULL, to_address varchar(62) NOT NULL )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar(20) NOT NULL, tick varchar(255) NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(42) NOT NULL, to_address varchar(42) NOT NULL )\nCREATE TABLE token_balances_avalanche ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar(20) NOT NULL, wallet_address varchar(42) NOT NULL, total_supply decimal(38,0) NOT NULL, amount decimal(38,0) NOT NULL )\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar(20) NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL, minted decimal(38,0) NOT NULL, holders decimal(38,0) NOT NULL, txs decimal(38,0) NOT NULL, updated_timestamp timestamp(3) NOT NULL, completed_timestamp timestamp(3) NOT NULL, id varchar(255) NOT NULL )\n"}
{"conversations": [{"role": "user", "content": "What is the total market cap for all tokens listed on the 'Polygon' chain?"}, {"role": "assistant", "content": "SELECT SUM(market_cap) FROM token_dexpool_info WHERE chain = 'Polygon';"}, {"role": "user", "content": "Only sum the market cap for tokens on 'Polygon' that have a 24-hour volume greater than 500000."}, {"role": "assistant", "content": "SELECT SUM(market_cap) FROM token_dexpool_info WHERE chain = 'Polygon' AND volume_24h > 500000;"}, {"role": "user", "content": "Also show the number of unique tokens that meet these criteria."}, {"role": "assistant", "content": "SELECT COUNT(DISTINCT token_symbol), SUM(market_cap) FROM token_dexpool_info WHERE chain = 'Polygon' AND volume_24h > 500000;"}, {"role": "user", "content": "Can you show the total market cap and token count for *each* chain that meets these volume criteria, ordered by total market cap descending?"}, {"role": "assistant", "content": "SELECT chain, COUNT(DISTINCT token_symbol) AS token_count, SUM(market_cap) AS total_market_cap FROM token_dexpool_info WHERE volume_24h > 500000 GROUP BY chain ORDER BY total_market_cap DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_dexpool_info ( pair_address character varying(512) NOT NULL, -- the id of dexpool token_name character varying(100) NOT NULL, -- the name of the token in the dexpool token_symbol character varying(100) NOT NULL, -- the token's symbol chain text, -- the chain that the dexpool resides price double precision, -- the current price of the token price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour price_change_percentage_6h double precision, -- change in value divided by the absolute price value of the original token price in 6 hours price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours makers_24h double precision, -- the makers of the dex pool in 24 hours volume_24h double precision, -- the trade volume of the dex pool in 24 hours liquidity double precision, -- the liquidity of the dex pool market_cap double precision, -- the market cap of the token trend_rank bigint, -- the rank of token in the dex pool of recent trending, value 1 expresses the most popular token. ,PRIMARY KEY (pair_address, chain) )\n"}
{"conversations": [{"role": "user", "content": "Give me the number of patient insurance policies for each plan where the policy is currently active. Return plan_id and policy_count."}, {"role": "assistant", "content": "SELECT\n  plan_id,\n  COUNT(*) AS policy_count\nFROM healthcare.patient_insurance\nWHERE (expiration_date IS NULL OR expiration_date >= CURRENT_DATE)\nGROUP BY plan_id;"}, {"role": "user", "content": "Now, only include plans where the count is greater than 5 and sort by policy_count descending."}, {"role": "assistant", "content": "SELECT\n  plan_id,\n  COUNT(*) AS policy_count\nFROM healthcare.patient_insurance\nWHERE (expiration_date IS NULL OR expiration_date >= CURRENT_DATE)\nGROUP BY plan_id\nHAVING COUNT(*) > 5\nORDER BY policy_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, plan_id character varying(64) NOT NULL, policy_number character varying(100) NOT NULL, group_number character varying(100), subscriber_name character varying(200), effective_date date NOT NULL, expiration_date date, is_primary boolean NOT NULL DEFAULT true, PRIMARY KEY (patient_insurance_id), UNIQUE (patient_id, plan_id, policy_number) )\n"}
{"conversations": [{"role": "user", "content": "List all premium payments made by Bank Transfer where the amount_paid is greater than 5000. Show payment_id, policy_id, customer_id, amount_paid, and payment_date, ordered by amount_paid descending."}, {"role": "assistant", "content": "SELECT payment_id,\n       policy_id,\n       customer_id,\n       amount_paid,\n       payment_date\nFROM insurance.premium_payments\nWHERE payment_method = 'Bank Transfer'\n  AND amount_paid > 5000\nORDER BY amount_paid DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.policies (\n    policy_id character varying(64) NOT NULL, -- unique identifier for the policy\n    customer_id character varying(64) NOT NULL, -- identifier for the policyholder (FK to customers)\n    product_id character varying(64) NOT NULL, -- identifier for the insurance product (FK to insurance_products)\n    agent_id character varying(64), -- identifier for the agent who sold the policy (FK to agents)\n    policy_number character varying(100) NOT NULL UNIQUE, -- customer-facing policy number\n    start_date date NOT NULL, -- date the policy coverage begins\n    end_date date NOT NULL, -- date the policy coverage ends\n    premium_amount numeric(12, 2) NOT NULL, -- total premium for the policy term\n    coverage_limit numeric(15, 2) NOT NULL, -- maximum amount covered\n    deductible numeric(10, 2) NOT NULL, -- amount customer pays before coverage kicks in\n    status character varying(30) NOT NULL, -- e.g., Active, Expired, Cancelled, Pending\n    issued_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the policy was issued\n    cancellation_date date,\n    cancellation_reason text,\n    PRIMARY KEY (policy_id)\n)\nCREATE TABLE insurance.claims (\n    claim_id character varying(64) NOT NULL, -- unique identifier for the claim\n    policy_id character varying(64) NOT NULL, -- identifier of the policy under which the claim is made (FK to policies)\n    customer_id character varying(64) NOT NULL, -- identifier of the customer making the claim (FK to customers)\n    incident_date timestamp NOT NULL, -- date and time of the incident leading to the claim\n    reported_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- date the claim was reported\n    description text NOT NULL, -- detailed description of the incident and claim\n    estimated_loss numeric(15, 2), -- initial estimated cost of the loss\n    status character varying(30) NOT NULL, -- e.g., Filed, Processing, Under Review, Approved, Denied, Settled\n    settlement_amount numeric(15, 2), -- final amount paid out\n    settlement_date date,\n    claim_handler_id character varying(64), -- identifier for the employee handling the claim (FK to employees/adjusters)\n    police_report_number character varying(100),\n    PRIMARY KEY (claim_id)\n)\nCREATE TABLE insurance.insurance_products (\n    product_id character varying(64) NOT NULL, -- unique identifier for the insurance product\n    product_name character varying(150) NOT NULL, -- name of the insurance product (e.g., 'Comprehensive Auto Insurance')\n    product_type character varying(50) NOT NULL, -- category like 'Auto', 'Home', 'Life', 'Health', 'Travel'\n    description text, -- detailed description of the product\n    base_premium numeric(10, 2) NOT NULL, -- starting premium before adjustments\n    coverage_details text, -- details about what is covered (could be JSON or structured text)\n    underwriting_rules text, -- rules used for assessing risk and eligibility\n    is_active boolean NOT NULL DEFAULT true, -- whether the product is currently offered\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n    updated_at timestamp,\n    PRIMARY KEY (product_id)\n)\nCREATE TABLE insurance.agents (\n    agent_id character varying(64) NOT NULL, -- unique identifier for the agent\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    agency_name character varying(150),\n    license_number character varying(100) NOT NULL UNIQUE, -- state insurance license number\n    license_state character varying(50) NOT NULL,\n    contact_email character varying(128) UNIQUE,\n    contact_phone character varying(30),\n    hire_date date,\n    termination_date date,\n    status character varying(20) NOT NULL DEFAULT 'Active', -- e.g., Active, Terminated, On Leave\n    commission_rate numeric(5, 4) NOT NULL DEFAULT 0.05, -- percentage commission\n    manager_id character varying(64), -- identifier for the agent's manager (FK to agents or employees)\n    PRIMARY KEY (agent_id)\n)\nCREATE TABLE insurance.premium_payments (\n    payment_id character varying(64) NOT NULL, -- unique identifier for the payment\n    policy_id character varying(64) NOT NULL, -- identifier of the policy the payment is for (FK to policies)\n    customer_id character varying(64) NOT NULL, -- identifier of the customer making the payment (FK to customers)\n    payment_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- date the payment was received\n    amount_paid numeric(12, 2) NOT NULL, -- amount of the payment\n    payment_method character varying(50), -- e.g., Credit Card, Bank Transfer, Check\n    transaction_reference character varying(128) UNIQUE, -- reference from payment processor\n    due_date date, -- due date for this payment installment\n    payment_period_start date, -- start date of the period this payment covers\n    payment_period_end date, -- end date of the period this payment covers\n    status character varying(30) NOT NULL DEFAULT 'Completed', -- e.g., Completed, Pending, Failed, Refunded\n    PRIMARY KEY (payment_id)\n)\nCREATE TABLE insurance.claim_documents (\n    document_id character varying(64) NOT NULL, -- unique identifier for the document\n    claim_id character varying(64) NOT NULL, -- identifier of the claim this document relates to (FK to claims)\n    document_type character varying(50) NOT NULL, -- e.g., Police Report, Photo, Invoice, Medical Bill\n    file_name character varying(255) NOT NULL, -- original name of the uploaded file\n    file_path character varying(512) NOT NULL, -- storage path (e.g., S3 URL, network path)\n    file_size_bytes integer, -- size of the file in bytes\n    mime_type character varying(100), -- MIME type of the file (e.g., 'image/jpeg', 'application/pdf')\n    uploaded_by character varying(64), -- identifier of the user/system who uploaded (FK to users/customers)\n    uploaded_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- time of upload\n    description text, -- optional description of the document\n    PRIMARY KEY (document_id)\n)\nCREATE TABLE insurance.policy_beneficiaries (\n    beneficiary_id character varying(64) NOT NULL, -- unique identifier for the beneficiary entry\n    policy_id character varying(64) NOT NULL, -- identifier of the life/relevant policy (FK to policies)\n    customer_id character varying(64) NOT NULL, -- identifier of the beneficiary (could be FK to customers or store info directly)\n    first_name character varying(100) NOT NULL, -- beneficiary first name (if not linking to customers table)\n    last_name character varying(100) NOT NULL, -- beneficiary last name\n    relationship character varying(50) NOT NULL, -- relationship to the policyholder (e.g., Spouse, Child, Parent)\n    percentage_share numeric(5, 2) NOT NULL CHECK (percentage_share > 0 AND percentage_share <= 100), -- percentage of payout\n    contact_info text, -- contact details for the beneficiary\n    added_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n    PRIMARY KEY (beneficiary_id),\n    UNIQUE (policy_id, customer_id) -- Ensure a person is listed only once per policy\n)\n"}
{"conversations": [{"role": "user", "content": "For each guest, list reservation_id, guest_id, check_in_date, and the next reservation_id and its check_in_date."}, {"role": "assistant", "content": "SELECT r1.reservation_id,\n       r1.guest_id,\n       r1.check_in_date,\n       r2.reservation_id AS next_reservation_id,\n       r2.check_in_date   AS next_check_in_date\nFROM reservations r1\nLEFT JOIN reservations r2\n  ON r1.guest_id = r2.guest_id\n AND r2.check_in_date = (\n       SELECT MIN(check_in_date)\n       FROM reservations\n       WHERE guest_id = r1.guest_id\n         AND check_in_date > r1.check_in_date\n     );"}, {"role": "user", "content": "Only include guests who have at least two reservations."}, {"role": "assistant", "content": "SELECT r1.reservation_id,\n       r1.guest_id,\n       r1.check_in_date,\n       r2.reservation_id AS next_reservation_id,\n       r2.check_in_date   AS next_check_in_date\nFROM reservations r1\nLEFT JOIN reservations r2\n  ON r1.guest_id = r2.guest_id\n AND r2.check_in_date = (\n       SELECT MIN(check_in_date)\n       FROM reservations\n       WHERE guest_id = r1.guest_id\n         AND check_in_date > r1.check_in_date\n     )\nWHERE r1.guest_id IN (\n  SELECT guest_id\n  FROM reservations\n  GROUP BY guest_id\n  HAVING COUNT(*) >= 2\n);"}, {"role": "user", "content": "Also, only show next reservations that occur within 30 days of the current reservation."}, {"role": "assistant", "content": "SELECT r1.reservation_id,\n       r1.guest_id,\n       r1.check_in_date,\n       r2.reservation_id AS next_reservation_id,\n       r2.check_in_date   AS next_check_in_date\nFROM reservations r1\nLEFT JOIN reservations r2\n  ON r1.guest_id = r2.guest_id\n AND r2.check_in_date = (\n       SELECT MIN(check_in_date)\n       FROM reservations\n       WHERE guest_id = r1.guest_id\n         AND check_in_date > r1.check_in_date\n     )\n   AND r2.check_in_date <= r1.check_in_date + INTERVAL '30 days'\nWHERE r1.guest_id IN (\n  SELECT guest_id\n  FROM reservations\n  GROUP BY guest_id\n  HAVING COUNT(*) >= 2\n);"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.reservations ( reservation_id text, property_id text, guest_id text, room_id text, room_type_id text, check_in_date date, check_out_date date, actual_check_in_ts timestamp, actual_check_out_ts timestamp, num_adults integer, num_children integer, status text, booking_source text, rate_plan_id text, total_amount numeric, amount_paid numeric, special_requests text, created_at timestamp, updated_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show me the top 5 NFT collections with the highest floor price on Ethereum, along with their names and contract addresses."}, {"role": "assistant", "content": "SELECT name, contract_address, floor_price FROM nft_collections WHERE blockchain = 'ethereum' ORDER BY CAST(floor_price AS decimal) DESC LIMIT 5;"}, {"role": "user", "content": "Can you also include the banner image URL and filter to only show ERC721 collections?"}, {"role": "assistant", "content": "SELECT name, contract_address, floor_price, banner_image_url FROM nft_collections WHERE blockchain = 'ethereum' AND erc_type = 'ERC721' ORDER BY CAST(floor_price AS decimal) DESC LIMIT 5;"}, {"role": "user", "content": "I think there's a typo in your query - it should be 'nft_collections' not 'nft_collections'. Also, can you join this with the nft_metadata table to include the average rarity score for these collections?"}, {"role": "assistant", "content": "SELECT nc.name, nc.contract_address, nc.floor_price, nc.banner_image_url, AVG(nm.rarity_score) as avg_rarity_score FROM nft_collections nc JOIN nft_metadata nm ON nc.contract_address = nm.contract_address WHERE nc.blockchain = 'ethereum' AND nc.erc_type = 'ERC721' GROUP BY nc.name, nc.contract_address, nc.floor_price, nc.banner_image_url ORDER BY CAST(nc.floor_price AS decimal) DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE erc1155_approval_for_all (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the transaction\n    transaction_index integer NOT NULL, -- Index of the transaction within the block\n    transaction_hash varchar(66) NOT NULL, -- Transaction hash\n    log_index integer NOT NULL, -- Log index\n    contract_address varchar(42) NOT NULL  -- Event contract address\n)\nCREATE TABLE erc20_balances ( block_number.bigint, contract_address.text, wallet_address.text, amount.text, pk.text )\nCREATE TABLE erc20_balances_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_metadata (\n    blockchain varchar NOT NULL, -- blockchain fields for the functionType  in contract\n    contract_address varchar NOT NULL, -- Contract address(with bloom filter)\n    token_id varchar NOT NULL, -- The number of the token\n    contract_name varchar NOT NULL, -- contract_name fields for the functionType  in contract\n    erc_type varchar NOT NULL, -- The type of token\n    amount bigint NOT NULL, -- amount fields for the functionType  in contract\n    minter varchar NOT NULL, -- minter fields for the functionType  in contract\n    owner varchar NOT NULL, -- owner fields for the functionType  in contract\n    mint_block_number bigint NOT NULL, -- mint_block_number fields for the functionType  in contract\n    mint_time bigint NOT NULL, -- mint_time fields for the functionType  in contract\n    mint_transaction_hash varchar NOT NULL, -- mint_transaction_hash fields for the functionType  in contract\n    mint_price varchar NOT NULL, -- mint_price fields for the functionType  in contract\n    token_uri varchar NOT NULL, -- token_uri fields for the functionType  in contract\n    metadata varchar NOT NULL, -- metadata fields for the functionType  in contract\n    name varchar NOT NULL, -- name fields for the functionType  in contract\n    image_uri varchar NOT NULL, -- image_uri fields for the functionType  in contract\n    traits varchar NOT NULL, -- traits fields for the functionType  in contract\n    updated_at bigint NOT NULL, -- updated_at fields for the functionType  in contract\n    status varchar NOT NULL, -- status fields for the functionType  in contract\n    rarity_score real NOT NULL, -- rarity_score fields for the functionType  in contract\n    rarity_rank integer NOT NULL, -- rarity_rank fields for the functionType  in contract\n    unique_attribute_count integer NOT NULL, -- unique_attribute_count fields for the functionType  in contract\n    pk integer NOT NULL  -- Partition key for the table(floor(mint_time / 1000 / 86400 / 30))\n)\nCREATE TABLE nft_collections ( blockchain.text, contract_address.text, name.text, symbol.text, deploy_block_number.bigint, deploy_block_time.bigint, erc_type.text, owner.text, traits.text, description.text, slug.text, media_info.text, image_url.text, banner_image_url.text, updated_at.bigint, banner.text, token_count.bigint, floor_price.text, floor_price_symbol.text, floor_price_contract.text, pk.integer )\nCREATE TABLE token_prices ( uuid varchar(36) NOT NULL, blockchain varchar(36) NOT NULL, address varchar(42) NOT NULL, decimals bigint NOT NULL, symbol varchar(36) NOT NULL, price real NOT NULL, timestamp timestamp(6) NOT NULL )\nCREATE TABLE erc20_approval ( block_number bigint NOT NULL, block_timestamp timestamp(6) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar NOT NULL, log_index integer NOT NULL, contract_address varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_info ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE mud_holesky_redstone (\n    address varchar NOT NULL, -- address fields for the functionType  in contract\n    table_id varchar NOT NULL, -- table_id fields for the functionType  in contract\n    key_bytes varchar NOT NULL, -- key_bytes fields for the functionType  in contract\n    key0 varchar NOT NULL, -- key0 fields for the functionType  in contract\n    key1 varchar NOT NULL, -- key1 fields for the functionType  in contract\n    static_data varchar NOT NULL, -- static_data fields for the functionType  in contract\n    encoded_lengths varchar NOT NULL, -- encoded_lengths fields for the functionType  in contract\n    dynamic_data varchar NOT NULL, -- dynamic_data fields for the functionType  in contract\n    is_deleted boolean NOT NULL, -- is_deleted fields for the functionType  in contract\n    block_number bigint NOT NULL, -- Block number uniquely identifying the block\n    log_index bigint NOT NULL  -- Index of the log within the transaction\n)\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar )\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id text )\n"}
{"conversations": [{"role": "user", "content": "Display the name and type of each location, as well as the earliest and latest maintenance service_date for vehicles assigned to that location (assuming vehicle_id matches location_id)."}, {"role": "assistant", "content": "SELECT l.name, l.type,\n       MIN(m.service_date) AS earliest_service,\n       MAX(m.service_date) AS latest_service\nFROM transportation.locations l\nLEFT JOIN transportation.maintenance_logs m ON l.location_id = m.vehicle_id\nGROUP BY l.location_id, l.name, l.type;"}, {"role": "user", "content": "I got an error because some locations do not have any maintenance logs. Please only show locations that have at least one associated maintenance log."}, {"role": "assistant", "content": "SELECT l.name, l.type,\n       MIN(m.service_date) AS earliest_service,\n       MAX(m.service_date) AS latest_service\nFROM transportation.locations l\nJOIN transportation.maintenance_logs m ON l.location_id = m.vehicle_id\nGROUP BY l.location_id, l.name, l.type;"}, {"role": "user", "content": "Now, include the total cost of all maintenance performed for each location."}, {"role": "assistant", "content": "SELECT l.name, l.type,\n       MIN(m.service_date) AS earliest_service,\n       MAX(m.service_date) AS latest_service,\n       SUM(m.cost) AS total_maintenance_cost\nFROM transportation.locations l\nJOIN transportation.maintenance_logs m ON l.location_id = m.vehicle_id\nGROUP BY l.location_id, l.name, l.type;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.locations ( location_id text PRIMARY KEY, name text, type text, address_line1 text, city text, state_province text, postal_code text, country text, latitude numeric, longitude numeric, timezone text )\nCREATE TABLE transportation.maintenance_logs ( log_id text PRIMARY KEY, vehicle_id text, service_date date, odometer_reading int, service_type text, description text, cost numeric, mechanic_name text, next_service_due_date date )\nCREATE TABLE transportation.passengers ( passenger_id text PRIMARY KEY, first_name text, last_name text, email text, phone_number text, date_of_birth date, loyalty_program_id text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "List all token transfers with values greater than 1000, including the token ID and transaction ID."}, {"role": "assistant", "content": "SELECT transfer_id, token_id, transaction_id, value FROM web3.token_transfers WHERE value > 1000;"}, {"role": "user", "content": "Actually, I also need to see the event names associated with these transactions."}, {"role": "assistant", "content": "SELECT tt.transfer_id, tt.token_id, tt.transaction_id, tt.value, e.event_name FROM web3.token_transfers tt LEFT JOIN web3.events e ON tt.transaction_id = e.transaction_id WHERE tt.value > 1000;"}, {"role": "user", "content": "There's a typo in your SQL, it should be 'token_transfers' not 'token_transfers'. Also, sort the results by value in descending order."}, {"role": "assistant", "content": "SELECT tt.transfer_id, tt.token_id, tt.transaction_id, tt.value, e.event_name FROM web3.token_transfers tt LEFT JOIN web3.events e ON tt.transaction_id = e.transaction_id WHERE tt.value > 1000 ORDER BY tt.value DESC;"}, {"role": "user", "content": "Now filter to only show transfers that have at least one associated event."}, {"role": "assistant", "content": "SELECT tt.transfer_id, tt.token_id, tt.transaction_id, tt.value, e.event_name FROM web3.token_transfers tt JOIN web3.events e ON tt.transaction_id = e.transaction_id WHERE tt.value > 1000 ORDER BY tt.value DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.events ( event_id text PRIMARY KEY, contract_id text, event_name text, data text, emitted_at timestamp, transaction_id text, log_index int )\nCREATE TABLE web3.token_transfers ( transfer_id text PRIMARY KEY, token_id text, from_address text, to_address text, value numeric, transaction_id text, log_index int )\n"}
{"conversations": [{"role": "user", "content": "List the employee's first and last name along with the appointment ID and scheduled start time for all appointments associated with the citizen who has the national ID number 'A123456789'."}, {"role": "assistant", "content": "SELECT e.first_name, e.last_name, a.appointment_id, a.scheduled_start_time\nFROM government_services.appointments a\nJOIN government_services.employees e ON a.employee_id = e.employee_id\nJOIN government_services.citizens c ON a.citizen_id = c.citizen_id\nWHERE c.national_id_number = 'A123456789';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens (\n    citizen_id character varying(64) NOT NULL,  -- unique identifier for the citizen\n    national_id_number character varying(128) NOT NULL UNIQUE, -- official national identification number\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    date_of_birth date NOT NULL,\n    gender character varying(20),\n    primary_address text NOT NULL, -- full primary residential address\n    contact_email character varying(128) UNIQUE,\n    contact_phone character varying(32),\n    registration_date timestamp NOT NULL, -- when the citizen profile was created\n    is_verified boolean DEFAULT false, -- whether identity has been officially verified\n    PRIMARY KEY (citizen_id)\n)\nCREATE TABLE government_services.employees ( employee_id.text, agency_id.text, first_name.text, last_name.text, job_title.text, department.text, work_email.text, work_phone.text, hire_date.date, termination_date.date, access_level.text, manager_employee_id.text )\nCREATE TABLE government_services.appointments ( appointment_id text PRIMARY KEY, citizen_id text, employee_id text, location_id text, service_id text, scheduled_start_time timestamp, scheduled_end_time timestamp, purpose text, status text, booking_method text, created_at timestamp, notes text )\n"}
{"conversations": [{"role": "user", "content": "List all accounts opened in the last 18 months, including the account number, account type, and the full name of the customer."}, {"role": "assistant", "content": "SELECT a.account_number, a.account_type, c.first_name, c.last_name, a.opened_date FROM financial_services.accounts a JOIN financial_services.customers c ON a.customer_id = c.customer_id WHERE a.opened_date >= CURRENT_DATE - INTERVAL '18 months' ORDER BY a.opened_date DESC;"}, {"role": "user", "content": "Additionally, filter this list to only include accounts with a status of 'Open'."}, {"role": "assistant", "content": "SELECT a.account_number, a.account_type, c.first_name, c.last_name, a.opened_date FROM financial_services.accounts a JOIN financial_services.customers c ON a.customer_id = c.customer_id WHERE a.opened_date >= CURRENT_DATE - INTERVAL '18 months' AND a.status = 'Open' ORDER BY a.opened_date DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.accounts (\n    account_id character varying(64) NOT NULL, -- unique identifier for the account\n    customer_id character varying(64) NOT NULL, -- foreign key linking to the customer\n    account_number character varying(128) NOT NULL UNIQUE, -- unique account number visible to customer\n    account_type character varying(50) NOT NULL, -- e.g., Checking, Savings, Investment, Loan, Credit Card\n    balance numeric(19, 4) NOT NULL DEFAULT 0.00, -- current account balance\n    currency character varying(3) NOT NULL, -- currency code (e.g., USD, EUR)\n    opened_date date NOT NULL, -- date the account was opened\n    status character varying(32) NOT NULL, -- e.g., Open, Closed, Frozen\n    interest_rate numeric(5, 4), -- annual interest rate, if applicable\n    last_updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last account update\n    PRIMARY KEY (account_id),\n    FOREIGN KEY (customer_id) REFERENCES financial_services.customers(customer_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List pairs of wallet IDs owned by the same user where the creation dates are more than one year apart. Show the user ID and the wallet IDs of both wallets."}, {"role": "assistant", "content": "SELECT w1.user_id, w1.wallet_id AS wallet_id_1, w2.wallet_id AS wallet_id_2 FROM web3.wallets w1 JOIN web3.wallets w2 ON w1.user_id = w2.user_id AND w2.created_at > w1.created_at + INTERVAL '1 year' ORDER BY w1.user_id, w1.created_at;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.wallets ( wallet_id text PRIMARY KEY, user_id text, address text, private_key text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "For each chain, which token had the highest number of smart money addresses buying it this week? Show the token symbol and narrative too."}, {"role": "assistant", "content": "SELECT chain, token_symbol, narrative, MAX(address_amount) AS max_buyers FROM smart_money_token_inflow WHERE type = 1 AND DATE_TRUNC('week', CURRENT_DATE) = DATE_TRUNC('week', CURRENT_DATE) GROUP BY chain, token_symbol, narrative;"}, {"role": "user", "content": "I got an error, I think the filter for the week may be wrong. Please revise the query so that it only counts buys from the current week."}, {"role": "assistant", "content": "SELECT chain, token_symbol, narrative, address_amount AS buyers FROM smart_money_token_inflow WHERE type = 1 AND EXTRACT(week FROM CURRENT_DATE) = EXTRACT(week FROM CURRENT_DATE) AND EXTRACT(year FROM CURRENT_DATE) = EXTRACT(year FROM CURRENT_DATE) ORDER BY chain, buyers DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE smart_money_token_inflow ( token_address character varying(100) NOT NULL, -- the token's address token_symbol character varying(100), -- the tokens's symbol token_amount numeric(38,2), -- the absolute value of the amount if user bought minus  the amount user sold of this token usd_value numeric(38,2), -- the absolute usd value of the bought token minus sold token avg_price numeric(38,6), -- the average cost price of user spent on this token type int, -- the direction of the trade on this token. 1 means buying, 2 means selling address_amount integer, -- the amount of the user bought this token narrative character varying(100), -- the category or narrative of the token chain character varying(100), -- the chain that the token resides ,PRIMARY KEY (token_address, chain) )\n"}
{"conversations": [{"role": "user", "content": "Show me all room types with a base rate over $200 and max occupancy of at least 4, along with their property IDs and amenities."}, {"role": "assistant", "content": "SELECT room_type_id, property_id, type_name, base_rate, max_occupancy, amenities FROM hospitality_technology.room_types WHERE base_rate > 200 AND max_occupancy >= 4;"}, {"role": "user", "content": "Now, join this with the guests table to show only room types from properties where the guest's country code is 'USA'."}, {"role": "assistant", "content": "SELECT rt.room_type_id, rt.property_id, rt.type_name, rt.base_rate, rt.max_occupancy, rt.amenities FROM hospitality_technology.room_types rt JOIN hospitality_technology.guests g ON rt.property_id = g.property_id WHERE rt.base_rate > 200 AND rt.max_occupancy >= 4 AND g.country_code = 'USA';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.room_types ( room_type_id text PRIMARY KEY, property_id text, type_name text, description text, base_rate numeric, max_occupancy int, bed_type text, area_sqft numeric, amenities text )\nCREATE TABLE hospitality_technology.guests ( guest_id text, first_name text, last_name text, email text, phone_number text, date_of_birth date, address_line1 text, city text, state_province text, postal_code text, country_code text, preferences text, loyalty_member_id text, communication_consent boolean, created_at timestamp, updated_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "I need to list the top 5 ERC20 tokens by total supply, including symbol, contract_address, and name."}, {"role": "assistant", "content": "SELECT tm.contract_address, tm.symbol, tm.name, CAST(tm.total_supply AS DECIMAL) AS total_supply\nFROM token_metas tm\nWHERE tm.is_erc20 = 1\nORDER BY CAST(tm.total_supply AS DECIMAL) DESC\nLIMIT 5;"}, {"role": "user", "content": "Also include the latest USD price for each token from token_prices using the most recent timestamp per token."}, {"role": "assistant", "content": "SELECT tm.contract_address, tm.symbol, tm.name, CAST(tm.total_supply AS DECIMAL) AS total_supply, tp.price\nFROM token_metas tm\nJOIN (\n  SELECT address, price FROM token_prices tp1\n  WHERE tp1.timestamp = (\n    SELECT MAX(tp2.timestamp) FROM token_prices tp2 WHERE tp2.address = tp1.address\n  )\n) tp ON tp.address = tm.contract_address\nWHERE tm.is_erc20 = 1\nORDER BY CAST(tm.total_supply AS DECIMAL) DESC\nLIMIT 5;"}, {"role": "user", "content": "Filter results to only include tokens where the price is greater than 2."}, {"role": "assistant", "content": "SELECT tm.contract_address, tm.symbol, tm.name, CAST(tm.total_supply AS DECIMAL) AS total_supply, tp.price\nFROM token_metas tm\nJOIN (\n  SELECT address, price FROM token_prices tp1\n  WHERE tp1.timestamp = (\n    SELECT MAX(tp2.timestamp) FROM token_prices tp2 WHERE tp2.address = tp1.address\n  )\n) tp ON tp.address = tm.contract_address\nWHERE tm.is_erc20 = 1\n  AND tp.price > 2\nORDER BY CAST(tm.total_supply AS DECIMAL) DESC\nLIMIT 5;"}, {"role": "user", "content": "Order the results by price descending and limit to 5."}, {"role": "assistant", "content": "SELECT tm.contract_address, tm.symbol, tm.name, CAST(tm.total_supply AS DECIMAL) AS total_supply, tp.price\nFROM token_metas tm\nJOIN (\n  SELECT address, price FROM token_prices tp1\n  WHERE tp1.timestamp = (\n    SELECT MAX(tp2.timestamp) FROM token_prices tp2 WHERE tp2.address = tp1.address\n  )\n) tp ON tp.address = tm.contract_address\nWHERE tm.is_erc20 = 1\n  AND tp.price > 2\nORDER BY tp.price DESC\nLIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp.timestamp, block_number.bigint, transaction_hash.text, transaction_index.bigint, from_address.text, contract_address.text, symbol.text, total_supply.text, name.text, decimals.bigint, is_erc20.integer, is_erc721.integer, is_erc1155.integer, is_proxy.integer, extra_info.text, pk.integer )\nCREATE TABLE erc1155_approval_for_all (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the transaction\n    transaction_index integer NOT NULL, -- Index of the transaction within the block\n    transaction_hash varchar(66) NOT NULL, -- Transaction hash\n    log_index integer NOT NULL, -- Log index\n    contract_address varchar(42) NOT NULL  -- Event contract address\n)\nCREATE TABLE erc20_balances ( block_number bigint, contract_address varchar, wallet_address varchar, amount varchar, pk varchar )\nCREATE TABLE nft_holders ( block_number.bigint, contract_address.text, wallet_address.text, token_id.text, contract_type.text, amount.text, pk.text )\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_coins_metadata (\n    object_id varchar NOT NULL, -- object id of the coin metadata object\n    coin_type varchar NOT NULL, -- coin type, eg. 0x...66::reap_token::REAP_TOKEN\n    status varchar NOT NULL, -- coin status, eg. exists, deleted\n    decimals bigint NOT NULL, -- decimals of the coin\n    description varchar NOT NULL, -- description of the coin\n    icon_url varchar NOT NULL, -- icon url of the coin\n    symbol varchar NOT NULL, -- symbol of the coin\n    name varchar NOT NULL  -- name of the coin\n)\nCREATE TABLE nft_collections ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, name varchar NOT NULL, symbol varchar NOT NULL, deploy_block_number bigint NOT NULL, deploy_block_time bigint NOT NULL, erc_type varchar NOT NULL, owner varchar NOT NULL, traits varchar NOT NULL, description varchar NOT NULL, slug varchar NOT NULL, media_info varchar NOT NULL, image_url varchar NOT NULL, banner_image_url varchar NOT NULL, updated_at bigint NOT NULL, banner varchar NOT NULL, token_count bigint NOT NULL, floor_price varchar NOT NULL, floor_price_symbol varchar NOT NULL, floor_price_contract varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_prices ( uuid.text, blockchain.text, address.text, decimals.bigint, symbol.text, price.real, timestamp.timestamp )\nCREATE TABLE erc20_approval ( block_number.bigint, block_timestamp.timestamp, transaction_index.integer, transaction_hash.text, log_index.integer, contract_address.text, pk.integer )\nCREATE TABLE token_balances (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n    tick varchar NOT NULL, -- Token tick\n    wallet_address varchar(42) NOT NULL, -- Address of owner\n    total_supply decimal(38,0) NOT NULL, -- Max supply\n    amount decimal(38,0) NOT NULL  -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE token_activities ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\nCREATE TABLE mud_holesky_redstone ( address text, table_id text, key_bytes text, key0 text, key1 text, static_data text, encoded_lengths text, dynamic_data text, is_deleted boolean, block_number bigint, log_index bigint )\nCREATE TABLE token_balances_bitcoin (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n    tick varchar(255) NOT NULL, -- Ticker: Identifier of the inscription\n    wallet_address varchar(42) NOT NULL, -- Address of owner\n    total_supply varchar NOT NULL, -- Max supply: Set max supply of the inscription\n    amount varchar NOT NULL  -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_balances_avalanche (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n    tick varchar(20) NOT NULL, -- Ticker: Identifier of the inscription\n    wallet_address varchar(42) NOT NULL, -- Address of owner\n    total_supply decimal(38,0) NOT NULL, -- Max supply: Set max supply of the inscription\n    amount decimal(38,0) NOT NULL  -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id varchar )\n"}
{"conversations": [{"role": "user", "content": "Show me the historical balance entries for wallet address '0xabc...' and contract address '0xdef...', including the block number and amount."}, {"role": "assistant", "content": "SELECT block_number, amount FROM erc20_balances_historical WHERE wallet_address = '0xabc...' AND contract_address = '0xdef...'"}, {"role": "user", "content": "For these entries, please also include the token symbol and name by joining with the `token_metas` table."}, {"role": "assistant", "content": "SELECT T1.block_number, T1.amount, T2.symbol, T2.name FROM erc20_balances_historical AS T1 JOIN token_metas AS T2 ON T1.contract_address = T2.contract_address WHERE T1.wallet_address = '0xabc...' AND T1.contract_address = '0xdef...'"}, {"role": "user", "content": "Now, add the latest USD price for this token by joining the `token_prices_latest` table."}, {"role": "assistant", "content": "SELECT T1.block_number, T1.amount, T2.symbol, T2.name, T3.price FROM erc20_balances_historical AS T1 JOIN token_metas AS T2 ON T1.contract_address = T2.contract_address JOIN token_prices_latest AS T3 ON T2.contract_address = T3.address WHERE T1.wallet_address = '0xabc...' AND T1.contract_address = '0xdef...'"}, {"role": "user", "content": "Finally, filter the results to only show historical entries where the latest USD price is greater than 100."}, {"role": "assistant", "content": "SELECT T1.block_number, T1.amount, T2.symbol, T2.name, T3.price FROM erc20_balances_historical AS T1 JOIN token_metas AS T2 ON T1.contract_address = T2.contract_address JOIN token_prices_latest AS T3 ON T2.contract_address = T3.address WHERE T1.wallet_address = '0xabc...' AND T1.contract_address = '0xdef...' AND T3.price > 100"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE erc1155_approval_for_all ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash text, log_index integer, contract_address text )\nCREATE TABLE erc20_balances_historical ( block_number bigint, contract_address text, wallet_address text, amount text, pk integer )\nCREATE TABLE nft_holders ( block_number bigint, contract_address text, wallet_address text, token_id text, contract_type text, amount text, pk text )\nCREATE TABLE nft_holder_historical ( block_number bigint, contract_address text, wallet_address text, token_id text, contract_type text, amount text, pk integer )\nCREATE TABLE sui_coins_metadata ( object_id text, coin_type text, status text, decimals bigint, description text, icon_url text, symbol text, name text )\nCREATE TABLE sui_nfts ( object_id text, status text, collection_type text, package_id text, previous_transaction text, display text, owner text, name text )\nCREATE TABLE nft_metadata ( blockchain text, contract_address text, token_id text, contract_name text, erc_type text, amount bigint, minter text, owner text, mint_block_number bigint, mint_time bigint, mint_transaction_hash text, mint_price text, token_uri text, metadata text, name text, image_uri text, traits text, updated_at bigint, status text, rarity_score real, rarity_rank integer, unique_attribute_count integer, pk integer )\nCREATE TABLE token_prices ( uuid text, blockchain text, address text, decimals bigint, symbol text, price real, timestamp timestamp )\nCREATE TABLE token_prices_latest ( blockchain text, address text, decimals bigint, symbol text, price real, timestamp timestamp )\nCREATE TABLE erc20_approval ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash text, log_index integer, contract_address text, pk integer )\nCREATE TABLE token_balances ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply decimal, amount decimal )\nCREATE TABLE token_info ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text )\nCREATE TABLE token_activities ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE mud_holesky_redstone ( address text, table_id text, key_bytes text, key0 text, key1 text, static_data text, encoded_lengths text, dynamic_data text, is_deleted boolean, block_number bigint, log_index bigint )\nCREATE TABLE token_balances_bitcoin ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply text, amount text )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_balances_avalanche ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply decimal, amount decimal )\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id text )\n"}
{"conversations": [{"role": "user", "content": "List all rooms that have a 'Jacuzzi' feature, including the room_number, property_id, type_name, and base_rate."}, {"role": "assistant", "content": "SELECT r.room_number,\n       r.property_id,\n       rt.type_name,\n       rt.base_rate\nFROM hospitality_technology.rooms AS r\nJOIN hospitality_technology.room_types AS rt\n  ON r.room_type_id = rt.room_type_id\n AND r.property_id = rt.property_id\nWHERE r.features ILIKE '%Jacuzzi%';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.rooms ( room_id.text, property_id.text, room_number.text, room_type_id.text, floor.integer, status.text, is_smoking.boolean, features.text, current_condition.text, last_cleaned_at.timestamp )\nCREATE TABLE hospitality_technology.room_types ( room_type_id.text, property_id.text, type_name.text, description.text, base_rate.numeric, max_occupancy.integer, bed_type.text, area_sqft.numeric, amenities.text )\nCREATE TABLE hospitality_technology.guests ( guest_id.text, first_name.text, last_name.text, email.text, phone_number.text, date_of_birth.date, address_line1.text, city.text, state_province.text, postal_code.text, country_code.text, preferences.text, loyalty_member_id.text, communication_consent.boolean, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE hospitality_technology.staff ( staff_id.text, property_id.text, first_name.text, last_name.text, position.text, work_email.text, work_phone.text, hire_date.date, termination_date.date, is_active.boolean, access_level.integer, manager_id.text, created_at.timestamp )\nCREATE TABLE hospitality_technology.service_orders ( order_id.text, reservation_id.text, guest_id.text, service_id.text, staff_id_ordered.text, staff_id_delivered.text, order_timestamp.timestamp, delivery_timestamp.timestamp, quantity.integer, unit_price.numeric, total_price.numeric, status.text, notes.text, bill_id.text )\nCREATE TABLE hospitality_technology.payments ( payment_id.text, reservation_id.text, guest_id.text, bill_id.text, amount.numeric, currency_code.text, payment_method.text, card_type.text, card_last_four.text, transaction_ref.text, payment_timestamp.timestamp, status.text, staff_id_processed.text, notes.text )\nCREATE TABLE hospitality_technology.reviews ( review_id.text, property_id.text, reservation_id.text, guest_id.text, rating_overall.integer, rating_cleanliness.integer, rating_service.integer, rating_location.integer, rating_value.integer, comment.text, review_source.text, review_date.timestamp, is_public.boolean, staff_response.text, response_staff_id.text, response_date.timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show me all pairs of cases led by the same lawyer, including both case names and the lead lawyer ID."}, {"role": "assistant", "content": "SELECT c1.lead_lawyer_id,\n       c1.case_name AS case_name_1,\n       c2.case_name AS case_name_2\nFROM legal_services.cases c1\nJOIN legal_services.cases c2\n  ON c1.lead_lawyer_id = c2.lead_lawyer_id\n  AND c1.case_id < c2.case_id;"}, {"role": "user", "content": "Actually, only include pairs where the case types are also the same."}, {"role": "assistant", "content": "SELECT c1.lead_lawyer_id,\n       c1.case_name AS case_name_1,\n       c2.case_name AS case_name_2\nFROM legal_services.cases c1\nJOIN legal_services.cases c2\n  ON c1.lead_lawyer_id = c2.lead_lawyer_id\n  AND c1.case_type = c2.case_type\n  AND c1.case_id < c2.case_id;"}, {"role": "user", "content": "Also, show me the earliest opening date between the two cases for each pair."}, {"role": "assistant", "content": "SELECT c1.lead_lawyer_id,\n       c1.case_name AS case_name_1,\n       c2.case_name AS case_name_2,\n       LEAST(c1.date_opened, c2.date_opened) AS earliest_open_date\nFROM legal_services.cases c1\nJOIN legal_services.cases c2\n  ON c1.lead_lawyer_id = c2.lead_lawyer_id\n  AND c1.case_type = c2.case_type\n  AND c1.case_id < c2.case_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.cases ( case_id text, case_number text, case_name text, client_id text, lead_lawyer_id text, case_type text, status text, date_opened timestamp, date_closed timestamp, description text, court_jurisdiction text )\n"}
{"conversations": [{"role": "user", "content": "List all reviews for properties with a star rating of at least 4.5. Include the property_name, review_id, rating_overall, and review_date."}, {"role": "assistant", "content": "SELECT p.property_name, r.review_id, r.rating_overall, r.review_date\nFROM hospitality_technology.reviews r\nJOIN hospitality_technology.properties p ON r.property_id = p.property_id\nWHERE p.star_rating >= 4.5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.properties ( property_id text PRIMARY KEY, property_name text, address_line1 text, address_line2 text, city text, state_province text, postal_code text, country_code text, phone_number text, email_address text, property_type text, star_rating numeric, timezone text, manager_staff_id text, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.room_types ( room_type_id text, property_id text, type_name text, description text, base_rate numeric, max_occupancy integer, bed_type text, area_sqft numeric, amenities text )\nCREATE TABLE hospitality_technology.guests ( guest_id text PRIMARY KEY, first_name text, last_name text, email text, phone_number text, date_of_birth date, address_line1 text, city text, state_province text, postal_code text, country_code text, preferences text, loyalty_member_id text, communication_consent boolean, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.staff ( staff_id text, property_id text, first_name text, last_name text, position text, work_email text, work_phone text, hire_date date, termination_date date, is_active boolean, access_level integer, manager_id text, created_at timestamp )\nCREATE TABLE hospitality_technology.service_orders ( order_id.text, reservation_id.text, guest_id.text, service_id.text, staff_id_ordered.text, staff_id_delivered.text, order_timestamp.timestamp, delivery_timestamp.timestamp, quantity.integer, unit_price.numeric, total_price.numeric, status.text, notes.text, bill_id.text )\nCREATE TABLE hospitality_technology.payments (\n    payment_id character varying(64) NOT NULL,  -- unique identifier for the payment transaction\n    reservation_id character varying(64), -- FK to reservations (if payment is for a stay)\n    guest_id character varying(64) NOT NULL, -- FK to guests (who paid)\n    bill_id character varying(64), -- FK to bills/invoices this payment applies to\n    amount numeric(12,2) NOT NULL, -- amount of the payment\n    currency_code character varying(3) NOT NULL, -- ISO currency code (e.g., USD, EUR)\n    payment_method character varying(50) NOT NULL, -- e.g., CreditCard, Cash, BankTransfer, Points, Voucher\n    card_type character varying(50), -- e.g., Visa, MasterCard, Amex (if CC)\n    card_last_four character varying(4), -- last 4 digits of CC (if CC)\n    transaction_ref character varying(128), -- reference ID from payment gateway or processor\n    payment_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, -- when the payment occurred\n    status character varying(50) NOT NULL, -- e.g., Pending, Succeeded, Failed, Refunded, Disputed\n    staff_id_processed character varying(64), -- FK to staff (who processed the payment)\n    notes text, -- notes about the payment\n    PRIMARY KEY (payment_id),\n    FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id),\n    FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id),\n    FOREIGN KEY (staff_id_processed) REFERENCES hospitality_technology.staff(staff_id)\n)\nCREATE TABLE hospitality_technology.reviews ( review_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, reservation_id character varying(64) UNIQUE, guest_id character varying(64) NOT NULL, rating_overall integer, rating_cleanliness integer, rating_service integer, rating_location integer, rating_value integer, comment text, review_source character varying(100), review_date timestamp with time zone NOT NULL DEFAULT current_timestamp, is_public boolean DEFAULT true, staff_response text, response_staff_id character varying(64), response_date timestamp with time zone, PRIMARY KEY (review_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (response_staff_id) REFERENCES hospitality_technology.staff(staff_id) )\n"}
{"conversations": [{"role": "user", "content": "List all developer names and their founded years, ordered from newest to oldest."}, {"role": "assistant", "content": "SELECT name, founded_year FROM gaming_technology.developers ORDER BY founded_year DESC;"}, {"role": "user", "content": "Show only developers founded after 2015."}, {"role": "assistant", "content": "SELECT name, founded_year FROM gaming_technology.developers WHERE founded_year > 2015 ORDER BY founded_year DESC;"}, {"role": "user", "content": "Can you also include the country of each developer?"}, {"role": "assistant", "content": "SELECT name, country, founded_year FROM gaming_technology.developers WHERE founded_year > 2015 ORDER BY founded_year DESC;"}, {"role": "user", "content": "Only show developers from European countries."}, {"role": "assistant", "content": "SELECT name, country, founded_year FROM gaming_technology.developers WHERE founded_year > 2015 AND country IN ('France','Germany','Spain','Italy','United Kingdom','Netherlands','Sweden','Switzerland','Norway','Finland','Denmark','Belgium','Austria','Ireland','Portugal','Greece','Poland','Hungary','Czech Republic','Romania','Bulgaria','Croatia','Slovakia','Slovenia','Estonia','Latvia','Lithuania','Luxembourg','Iceland','Malta','Cyprus') ORDER BY founded_year DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.developers ( developer_id uuid PRIMARY KEY, name text, country text, founded_year int, website text, created_at timestamptz )\n"}
{"conversations": [{"role": "user", "content": "Show the top 5 properties by average overall review rating."}, {"role": "assistant", "content": "SELECT p.property_name, AVG(r.rating_overall) AS avg_rating\nFROM hospitality_technology.properties p\nJOIN hospitality_technology.reviews r\n  ON p.property_id = r.property_id\nGROUP BY p.property_name\nORDER BY avg_rating DESC\nLIMIT 5;"}, {"role": "user", "content": "Only consider reviews that are publicly visible."}, {"role": "assistant", "content": "SELECT p.property_name, AVG(r.rating_overall) AS avg_rating\nFROM hospitality_technology.properties p\nJOIN hospitality_technology.reviews r\n  ON p.property_id = r.property_id\nWHERE r.is_public = true\nGROUP BY p.property_name\nORDER BY avg_rating DESC\nLIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.properties (\n    property_id character varying(64) NOT NULL,  -- unique identifier for the property (hotel, resort, etc.)\n    property_name character varying(255) NOT NULL, -- name of the property\n    address_line1 character varying(255) NOT NULL, -- primary address line\n    address_line2 character varying(255), -- secondary address line\n    city character varying(100) NOT NULL, -- city\n    state_province character varying(100), -- state or province\n    postal_code character varying(20) NOT NULL, -- zip or postal code\n    country_code character varying(3) NOT NULL, -- ISO country code (e.g., USA, CAN)\n    phone_number character varying(30), -- main contact phone\n    email_address character varying(255), -- main contact email\n    property_type character varying(50) NOT NULL, -- e.g., Hotel, Resort, B&B, Motel\n    star_rating numeric(2,1), -- star rating (e.g., 4.5)\n    timezone character varying(64) NOT NULL, -- IANA timezone ID (e.g., America/New_York)\n    manager_staff_id character varying(64), -- FK to staff table for the general manager\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, -- record creation time\n    updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, -- record last update time\n    PRIMARY KEY (property_id)\n)\nCREATE TABLE hospitality_technology.rooms (\n    room_id character varying(64) NOT NULL,  -- unique identifier for the room\n    property_id character varying(64) NOT NULL, -- FK to properties table\n    room_number character varying(10) NOT NULL, -- room number identifier (e.g., '101', 'Suite 2B')\n    room_type_id character varying(64) NOT NULL, -- FK to room_types table\n    floor integer, -- floor number the room is on\n    status character varying(50) NOT NULL, -- e.g., Available, Occupied, Cleaning, OutOfOrder, Maintenance\n    is_smoking boolean NOT NULL DEFAULT false, -- smoking allowed flag\n    features text, -- description of features (e.g., Balcony, Sea View, Jacuzzi)\n    current_condition text, -- notes on room condition\n    last_cleaned_at timestamp with time zone, -- timestamp of last cleaning\n    PRIMARY KEY (room_id),\n    FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n    FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id)\n)\nCREATE TABLE hospitality_technology.guests (\n    guest_id character varying(64) NOT NULL,  -- unique identifier for the guest profile\n    first_name character varying(100) NOT NULL, -- guest's first name\n    last_name character varying(100) NOT NULL, -- guest's last name\n    email character varying(255) UNIQUE, -- guest's email address (unique identifier?)\n    phone_number character varying(30), -- guest's phone number\n    date_of_birth date, -- guest's date of birth\n    address_line1 character varying(255), -- guest's home address\n    city character varying(100),\n    state_province character varying(100),\n    postal_code character varying(20),\n    country_code character varying(3),\n    preferences text, -- notes on guest preferences (e.g., allergies, room location)\n    loyalty_member_id character varying(64) UNIQUE, -- FK to loyalty_members table\n    communication_consent boolean DEFAULT true, -- consent for marketing communications\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (guest_id)\n)\nCREATE TABLE hospitality_technology.staff (\n    staff_id character varying(64) NOT NULL,  -- unique identifier for the staff member\n    property_id character varying(64) NOT NULL, -- FK to properties table (primary property)\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    position character varying(100) NOT NULL, -- e.g., Front Desk Agent, Housekeeper, Manager, Concierge\n    work_email character varying(255) UNIQUE, -- staff member's work email\n    work_phone character varying(30),\n    hire_date date NOT NULL,\n    termination_date date, -- date employment ended (if applicable)\n    is_active boolean NOT NULL DEFAULT true, -- currently employed flag\n    access_level integer NOT NULL, -- permission level within systems (e.g., 1=basic, 5=admin)\n    manager_id character varying(64), -- FK to staff table (self-referencing for supervisor)\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (staff_id),\n    FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n    FOREIGN KEY (manager_id) REFERENCES hospitality_technology.staff(staff_id)\n)\nCREATE TABLE hospitality_technology.services (\n    service_id character varying(64) NOT NULL, -- unique identifier for a chargeable service\n    property_id character varying(64) NOT NULL, -- FK to properties table\n    service_name character varying(150) NOT NULL, -- e.g., Room Service - Burger, Spa - Massage 60min, Laundry - Shirt\n    description text,\n    category character varying(100), -- e.g., Food & Beverage, Wellness, Business Center, Activities\n    price numeric(10, 2) NOT NULL, -- price per unit/instance\n    unit character varying(30), -- e.g., Per Item, Per Hour, Per Day\n    is_available boolean NOT NULL DEFAULT true, -- is the service currently offered?\n    department character varying(100), -- department responsible (e.g., F&B, Spa, Housekeeping)\n    PRIMARY KEY (service_id),\n    FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id)\n)\nCREATE TABLE hospitality_technology.reviews (\n    review_id character varying(64) NOT NULL,  -- unique identifier for the review\n    property_id character varying(64) NOT NULL, -- FK to properties table\n    reservation_id character varying(64) UNIQUE, -- FK to reservations (link review to a specific stay, optional but good)\n    guest_id character varying(64) NOT NULL, -- FK to guests table\n    rating_overall integer, -- overall score (e.g., 1-5 or 1-10)\n    rating_cleanliness integer,\n    rating_service integer,\n    rating_location integer,\n    rating_value integer,\n    comment text, -- guest's written feedback\n    review_source character varying(100), -- e.g., DirectSurvey, TripAdvisor, Google, Booking.com\n    review_date timestamp with time zone NOT NULL DEFAULT current_timestamp, -- when the review was submitted\n    is_public boolean DEFAULT true, -- whether the review is publicly visible\n    staff_response text, -- official response from the property\n    response_staff_id character varying(64), -- FK to staff (who responded)\n    response_date timestamp with time zone, -- when the response was posted\n    PRIMARY KEY (review_id),\n    FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n    FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id),\n    FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id),\n    FOREIGN KEY (response_staff_id) REFERENCES hospitality_technology.staff(staff_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List all insurance products that have 'auto' in their product type and are currently active, showing their product name and base premium."}, {"role": "assistant", "content": "SELECT product_name, base_premium FROM insurance.insurance_products WHERE product_type LIKE '%auto%' AND is_active = true;"}, {"role": "user", "content": "Now order these results by base premium in descending order and include the coverage details."}, {"role": "assistant", "content": "SELECT product_name, base_premium, coverage_details FROM insurance.insurance_products WHERE product_type LIKE '%auto%' AND is_active = true ORDER BY base_premium DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.claims ( claim_id character varying(64) NOT NULL, policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, incident_date timestamp NOT NULL, reported_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, description text NOT NULL, estimated_loss numeric(15, 2), status character varying(30) NOT NULL, settlement_amount numeric(15, 2), settlement_date date, claim_handler_id character varying(64), police_report_number character varying(100), PRIMARY KEY (claim_id) )\nCREATE TABLE insurance.insurance_products ( product_id character varying(64) NOT NULL, product_name character varying(150) NOT NULL, product_type character varying(50) NOT NULL, description text, base_premium numeric(10, 2) NOT NULL, coverage_details text, underwriting_rules text, is_active boolean NOT NULL DEFAULT true, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, updated_at timestamp, PRIMARY KEY (product_id) )\nCREATE TABLE insurance.policy_beneficiaries ( beneficiary_id character varying(64) NOT NULL, policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, relationship character varying(50) NOT NULL, percentage_share numeric(5, 2) NOT NULL CHECK (percentage_share > 0 AND percentage_share <= 100), contact_info text, added_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (beneficiary_id), UNIQUE (policy_id, customer_id) )\n"}
{"conversations": [{"role": "user", "content": "Compute the total invoiced amount and average payment delay (in days) by status for invoices issued between 2024-01-01 and 2024-06-30."}, {"role": "assistant", "content": "SELECT status,\n       SUM(total_amount) AS total_invoiced,\n       AVG(EXTRACT(day FROM (payment_date::date - issue_date))) AS avg_payment_delay_days\n  FROM legal_services.invoices\n WHERE issue_date BETWEEN '2024-01-01' AND '2024-06-30'\n GROUP BY status;"}, {"role": "user", "content": "Also show the count of invoices per status."}, {"role": "assistant", "content": "SELECT status,\n       SUM(total_amount) AS total_invoiced,\n       AVG(EXTRACT(day FROM (payment_date::date - issue_date))) AS avg_payment_delay_days,\n       COUNT(*) AS invoice_count\n  FROM legal_services.invoices\n WHERE issue_date BETWEEN '2024-01-01' AND '2024-06-30'\n GROUP BY status;"}, {"role": "user", "content": "Exclude statuses where total_invoiced is less than 10000."}, {"role": "assistant", "content": "SELECT status,\n       SUM(total_amount) AS total_invoiced,\n       AVG(EXTRACT(day FROM (payment_date::date - issue_date))) AS avg_payment_delay_days,\n       COUNT(*) AS invoice_count\n  FROM legal_services.invoices\n WHERE issue_date BETWEEN '2024-01-01' AND '2024-06-30'\n GROUP BY status\nHAVING SUM(total_amount) >= 10000;"}, {"role": "user", "content": "Finally, order the results by avg_payment_delay_days ascending."}, {"role": "assistant", "content": "SELECT status,\n       SUM(total_amount) AS total_invoiced,\n       AVG(EXTRACT(day FROM (payment_date::date - issue_date))) AS avg_payment_delay_days,\n       COUNT(*) AS invoice_count\n  FROM legal_services.invoices\n WHERE issue_date BETWEEN '2024-01-01' AND '2024-06-30'\n GROUP BY status\nHAVING SUM(total_amount) >= 10000\n ORDER BY avg_payment_delay_days ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.invoices ( invoice_id text PRIMARY KEY, invoice_number text UNIQUE, client_id text, case_id text, issue_date date, due_date date, total_amount numeric, amount_paid numeric, status text, payment_date timestamp, notes text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "List all clients along with their case_number and case_type for cases that are currently 'Open'."}, {"role": "assistant", "content": "SELECT c.first_name, c.last_name, c.email, cs.case_number, cs.case_type\nFROM legal_services.clients AS c\nJOIN legal_services.cases AS cs\n  ON c.client_id = cs.client_id\nWHERE cs.status = 'Open';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.clients ( client_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, company_name character varying(200), email character varying(128) UNIQUE NOT NULL, phone character varying(32), address text, date_registered timestamp NOT NULL, status character varying(32) NOT NULL, PRIMARY KEY (client_id) )\nCREATE TABLE legal_services.lawyers ( lawyer_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, bar_number character varying(64) UNIQUE NOT NULL, firm_id character varying(64), email character varying(128) UNIQUE NOT NULL, phone character varying(32), specialization text, hire_date timestamp NOT NULL, is_partner boolean DEFAULT false, PRIMARY KEY (lawyer_id) )\nCREATE TABLE legal_services.law_firms ( firm_id character varying(64) NOT NULL, firm_name character varying(200) NOT NULL, address text NOT NULL, phone character varying(32), website character varying(255), founded_date date, managing_partner_id character varying(64), PRIMARY KEY (firm_id) )\nCREATE TABLE legal_services.cases ( case_id character varying(64) NOT NULL, case_number character varying(100) UNIQUE, case_name text NOT NULL, client_id character varying(64) NOT NULL, lead_lawyer_id character varying(64) NOT NULL, case_type character varying(100) NOT NULL, status character varying(50) NOT NULL, date_opened timestamp NOT NULL, date_closed timestamp, description text, court_jurisdiction character varying(128), PRIMARY KEY (case_id) )\nCREATE TABLE legal_services.documents ( document_id character varying(64) NOT NULL, case_id character varying(64) NOT NULL, document_name character varying(255) NOT NULL, document_type character varying(100), storage_path text NOT NULL, uploaded_by_lawyer_id character varying(64), upload_timestamp timestamp NOT NULL, version integer DEFAULT 1, description text, PRIMARY KEY (document_id) )\nCREATE TABLE legal_services.time_entries ( entry_id character varying(64) NOT NULL, case_id character varying(64) NOT NULL, lawyer_id character varying(64) NOT NULL, date_worked date NOT NULL, hours_spent numeric(5, 2) NOT NULL CHECK (hours_spent > 0), billing_rate numeric(10, 2) NOT NULL, description text NOT NULL, is_billable boolean DEFAULT true, is_billed boolean DEFAULT false, invoice_id character varying(64), created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (entry_id) )\nCREATE TABLE legal_services.appointments ( appointment_id character varying(64) NOT NULL, client_id character varying(64) NOT NULL, lawyer_id character varying(64) NOT NULL, case_id character varying(64), start_time timestamp NOT NULL, end_time timestamp NOT NULL, location text, subject character varying(255), notes text, status character varying(50) NOT NULL, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (appointment_id) )\n"}
{"conversations": [{"role": "user", "content": "Show me all claims handled by agent 'AG123' along with their settlement details and policy IDs."}, {"role": "assistant", "content": "SELECT claim_id, policy_id, settlement_amount, settlement_date FROM insurance.claims WHERE claim_handler_id = 'AG123';"}, {"role": "user", "content": "Now filter these to only show claims that were settled for more than $5,000 and include the incident description."}, {"role": "assistant", "content": "SELECT claim_id, policy_id, settlement_amount, settlement_date, description FROM insurance.claims WHERE claim_handler_id = 'AG123' AND settlement_amount > 5000;"}, {"role": "user", "content": "I also want to see how long it took to settle these claims (difference between reported_date and settlement_date in days)."}, {"role": "assistant", "content": "SELECT claim_id, policy_id, settlement_amount, settlement_date, description, EXTRACT(DAY FROM (settlement_date - reported_date)) AS days_to_settle FROM insurance.claims WHERE claim_handler_id = 'AG123' AND settlement_amount > 5000;"}, {"role": "user", "content": "Finally, order the results by the longest settlement time first and include only claims that took more than 30 days to settle."}, {"role": "assistant", "content": "SELECT claim_id, policy_id, settlement_amount, settlement_date, description, EXTRACT(DAY FROM (settlement_date - reported_date)) AS days_to_settle FROM insurance.claims WHERE claim_handler_id = 'AG123' AND settlement_amount > 5000 AND (settlement_date - reported_date) > INTERVAL '30 days' ORDER BY days_to_settle DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.claims ( claim_id character varying(64) NOT NULL, policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, incident_date timestamp NOT NULL, reported_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, description text NOT NULL, estimated_loss numeric(15, 2), status character varying(30) NOT NULL, settlement_amount numeric(15, 2), settlement_date date, claim_handler_id character varying(64), police_report_number character varying(100), PRIMARY KEY (claim_id) )\n"}
{"conversations": [{"role": "user", "content": "Show the invoice number, issue date, total amount, and the client's full name for all invoices, including only those invoices that have not been paid fully."}, {"role": "assistant", "content": "SELECT i.invoice_number, i.issue_date, i.total_amount, c.first_name || ' ' || c.last_name AS client_full_name FROM legal_services.invoices i JOIN legal_services.clients c ON i.client_id = c.client_id WHERE i.amount_paid < i.total_amount;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.clients ( client_id.text, first_name.text, last_name.text, company_name.text, email.text, phone.text, address.text, date_registered.timestamp, status.text )\nCREATE TABLE legal_services.law_firms ( firm_id.text, firm_name.text, address.text, phone.text, website.text, founded_date.date, managing_partner_id.text )\nCREATE TABLE legal_services.documents ( document_id.text, case_id.text, document_name.text, document_type.text, storage_path.text, uploaded_by_lawyer_id.text, upload_timestamp.timestamp, version.integer, description.text )\nCREATE TABLE legal_services.time_entries ( entry_id.text, case_id.text, lawyer_id.text, date_worked.date, hours_spent.numeric, billing_rate.numeric, description.text, is_billable.boolean, is_billed.boolean, invoice_id.text, created_at.timestamp )\nCREATE TABLE legal_services.invoices ( invoice_id.text, invoice_number.text, client_id.text, case_id.text, issue_date.date, due_date.date, total_amount.numeric, amount_paid.numeric, status.text, payment_date.timestamp, notes.text, created_at.timestamp )\nCREATE TABLE legal_services.appointments ( appointment_id.text, client_id.text, lawyer_id.text, case_id.text, start_time.timestamp, end_time.timestamp, location.text, subject.text, notes.text, status.text, created_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show me the top 5 ERC20 tokens with the highest total supply, along with their names and contract addresses, but only include tokens where the price is greater than $0.10."}, {"role": "assistant", "content": "SELECT tm.name, tm.contract_address, tm.total_supply FROM token_metas tm WHERE tm.is_erc20 = 1 ORDER BY CAST(tm.total_supply AS decimal) DESC LIMIT 5;"}, {"role": "user", "content": "I think there's a typo in your query - it should be 'total_supply' not 'total_supply'. Also, can you join this with the token_prices_latest table to include the current price of each token?"}, {"role": "assistant", "content": "SELECT tm.name, tm.contract_address, tm.total_supply, tpl.price FROM token_metas tm JOIN token_prices_latest tpl ON tm.contract_address = tpl.address WHERE tm.is_erc20 = 1 AND tpl.price > 0.10 ORDER BY CAST(tm.total_supply AS decimal) DESC LIMIT 5;"}, {"role": "user", "content": "The token_prices_latest table isn't in the schema. Can you modify the query to use the erc20_balances table instead to show the total balance held across all wallets for each token?"}, {"role": "assistant", "content": "SELECT tm.name, tm.contract_address, tm.total_supply, SUM(CAST(eb.amount AS decimal)) AS total_balance FROM token_metas tm JOIN erc20_balances eb ON tm.contract_address = eb.contract_address WHERE tm.is_erc20 = 1 GROUP BY tm.name, tm.contract_address, tm.total_supply ORDER BY CAST(tm.total_supply AS decimal) DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas (\n    block_timestamp timestamp(6) NOT NULL,  -- Timestamp of the block when token metadata was recorded\n    block_number bigint NOT NULL, -- Block number uniquely identifying the block\n    transaction_hash varchar NOT NULL, -- Hash value of the transaction\n    transaction_index bigint NOT NULL, -- Index of the transaction within the block\n    from_address varchar NOT NULL, -- Address from which the transaction originated\n    contract_address varchar NOT NULL, -- Address of the token contract\n    symbol varchar NOT NULL, -- Symbol of the token\n    total_supply varchar NOT NULL, -- erc20 contract total supply\n    name varchar NOT NULL, -- Name of the token\n    decimals bigint NOT NULL, -- Number of decimal places for the token\n    is_erc20 integer NOT NULL, -- Flag indicating if the token is an ERC-20 token (0 or 1)\n    is_erc721 integer NOT NULL, -- Flag indicating if the token is an ERC-721 token (0 or 1)\n    is_erc1155 integer NOT NULL, -- Flag indicating if the token is an ERC-1155 token (0 or 1)\n    is_proxy integer NOT NULL, -- Flag indicating if the token is a proxy (0 or 1)\n    extra_info varchar NOT NULL, -- Additional information about the token\n    pk integer NOT NULL  -- Partition key for the table(floor(block_number / 5760))\n)\nCREATE TABLE erc1155_approval_for_all (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the transaction\n    transaction_index integer NOT NULL, -- Index of the transaction within the block\n    transaction_hash varchar(66) NOT NULL, -- Transaction hash\n    log_index integer NOT NULL, -- Log index\n    contract_address varchar(42) NOT NULL  -- Event contract address\n)\nCREATE TABLE erc20_balances ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE erc20_balances_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_holders (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    contract_address varchar NOT NULL, -- Event contract address\n    wallet_address varchar NOT NULL, -- The wallet address for the contract(with bloom filter)\n    token_id varchar NOT NULL, -- NFT token id\n    contract_type varchar NOT NULL, -- NFT contract type\n    amount varchar NOT NULL, -- Number of held NFTs\n    pk varchar NOT NULL  -- The last string partition of the contract.\n)\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_nfts ( object_id text, status text, collection_type text, package_id text, previous_transaction text, display text, owner text, name text )\nCREATE TABLE nft_metadata ( blockchain text, contract_address text, token_id text, contract_name text, erc_type text, amount bigint, minter text, owner text, mint_block_number bigint, mint_time bigint, mint_transaction_hash text, mint_price text, token_uri text, metadata text, name text, image_uri text, traits text, updated_at bigint, status text, rarity_score real, rarity_rank integer, unique_attribute_count integer, pk integer )\nCREATE TABLE erc20_approval ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash text, log_index integer, contract_address text, pk integer )\nCREATE TABLE token_info (\n    block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n    block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n    tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n    tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n    tick varchar NOT NULL, -- Token tick\n    max_supply decimal(38,0) NOT NULL, -- Max supply\n    lim decimal(38,0) NOT NULL, -- Limit of each mint\n    wlim decimal(38,0) NOT NULL, -- Limit of each address can maximum mint\n    dec integer NOT NULL, -- Decimal for minimum divie\n    creator varchar(42) NOT NULL  -- Address originating the inscription (matches from_address in transactions table)\n)\nCREATE TABLE token_activities (\n    block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n    block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n    tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n    tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n    log_index integer NOT NULL, -- Index of the log within the transaction\n    type varchar NOT NULL, -- mint | transfer | burn\n    tick varchar NOT NULL, -- Token tick\n    id varchar(255) NOT NULL, -- Unique identifier of the inscription\n    amt decimal(38,0) NOT NULL, -- Mint amount\n    from_address varchar(42) NOT NULL, -- Address sending the inscription (matches from_address in transactions table)\n    to_address varchar(42) NOT NULL  -- Address receiving the inscription (match to_address in transactions table)\n)\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_activities_avalanche ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\n"}
{"conversations": [{"role": "user", "content": "What is the average trade price for each asset for trades executed between '2024-05-01' and '2024-05-31'?"}, {"role": "assistant", "content": "SELECT\n  asset_id,\n  AVG(price) AS avg_price\nFROM trading_platform.trades\nWHERE traded_at >= '2024-05-01' AND traded_at < '2024-06-01'\nGROUP BY asset_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.trades (\n    trade_id character varying(64) NOT NULL,  -- unique identifier for the trade\n    order_id character varying(64) NOT NULL, -- identifier of the order that led to the trade\n    buyer_id character varying(64) NOT NULL, -- identifier of the buyer\n    seller_id character varying(64) NOT NULL, -- identifier of the seller\n    asset_id character varying(64) NOT NULL, -- identifier of the asset being traded\n    quantity numeric(38,14) NOT NULL, -- quantity of the asset in the trade\n    price numeric(38,14) NOT NULL, -- price per unit of the asset\n    traded_at timestamp NOT NULL, -- time when the trade was executed\n    PRIMARY KEY (trade_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List all Sui NFT collections where the owner is not null, including their name and collection_type."}, {"role": "assistant", "content": "SELECT name, collection_type FROM sui_nfts WHERE owner IS NOT NULL;"}, {"role": "user", "content": "Can you also include the display field and filter to only show collections with a package_id starting with '0x'?"}, {"role": "assistant", "content": "SELECT name, collection_type, display FROM sui_nfts WHERE owner IS NOT NULL AND package_id LIKE '0x%';"}, {"role": "user", "content": "Now sort these results by name in ascending order and limit to 10."}, {"role": "assistant", "content": "SELECT name, collection_type, display FROM sui_nfts WHERE owner IS NOT NULL AND package_id LIKE '0x%' ORDER BY name ASC LIMIT 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp timestamp(6) NOT NULL, block_number bigint NOT NULL, transaction_hash varchar NOT NULL, transaction_index bigint NOT NULL, from_address varchar NOT NULL, contract_address varchar NOT NULL, symbol varchar NOT NULL, total_supply varchar NOT NULL, name varchar NOT NULL, decimals bigint NOT NULL, is_erc20 integer NOT NULL, is_erc721 integer NOT NULL, is_erc1155 integer NOT NULL, is_proxy integer NOT NULL, extra_info varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE erc20_balances ( block_number bigint, contract_address varchar, wallet_address varchar, amount varchar, pk varchar )\nCREATE TABLE nft_holder_historical ( block_number.bigint, contract_address.text, wallet_address.text, token_id.text, contract_type.text, amount.text, pk.integer )\nCREATE TABLE sui_coins_metadata ( object_id varchar NOT NULL, coin_type varchar NOT NULL, status varchar NOT NULL, decimals bigint NOT NULL, description varchar NOT NULL, icon_url varchar NOT NULL, symbol varchar NOT NULL, name varchar NOT NULL )\nCREATE TABLE sui_nfts ( object_id text, status text, collection_type text, package_id text, previous_transaction text, display text, owner text, name text )\nCREATE TABLE nft_collections ( blockchain.text, contract_address.text, name.text, symbol.text, deploy_block_number.bigint, deploy_block_time.bigint, erc_type.text, owner.text, traits.text, description.text, slug.text, media_info.text, image_url.text, banner_image_url.text, updated_at.bigint, banner.text, token_count.bigint, floor_price.text, floor_price_symbol.text, floor_price_contract.text, pk.integer )\nCREATE TABLE token_prices_latest (\n    blockchain varchar(36) NOT NULL, -- blockchain fields for the functionType  in contract\n    address varchar(42) NOT NULL, -- address fields for the functionType  in contract\n    decimals bigint NOT NULL, -- decimals fields for the functionType  in contract\n    symbol varchar(36) NOT NULL, -- symbol fields for the functionType  in contract\n    price real NOT NULL, -- price fields for the functionType  in contract\n    timestamp timestamp(6) NOT NULL  -- timestamp fields for the functionType  in contract\n)\nCREATE TABLE token_balances ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply decimal, amount decimal )\nCREATE TABLE token_activities ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\nCREATE TABLE token_balances_bitcoin (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n    tick varchar(255) NOT NULL, -- Ticker: Identifier of the inscription\n    wallet_address varchar(42) NOT NULL, -- Address of owner\n    total_supply varchar NOT NULL, -- Max supply: Set max supply of the inscription\n    amount varchar NOT NULL  -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info_bitcoin (\n    block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n    block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n    tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n    tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n    tick varchar(255) NOT NULL, -- Ticker:  Identifier of the inscription\n    max_supply decimal(38,0) NOT NULL, -- Max supply: Set max supply of the inscription\n    lim decimal(38,0) NOT NULL, -- Mint limit: limit per inscription\n    wlim decimal(38,0) NOT NULL, -- Limit of each address can maximum mint\n    dec integer NOT NULL, -- Decimal for minimum divie\n    creator varchar(42) NOT NULL  -- Address originating the inscription (matches from_address in transactions table)\n)\nCREATE TABLE token_activities_bitcoin (\n    block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n    block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n    tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n    tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n    log_index integer NOT NULL, -- Index of the log within the transaction\n    type varchar(20) NOT NULL, -- Operation: Type of event (deploy, mint, transfer, list)\n    tick varchar(255) NOT NULL, -- Ticker: Identifier of the inscription\n    id varchar(255) NOT NULL, -- Unique identifier of the inscription\n    amt decimal(38,0) NOT NULL, -- Amount to mint: States the amount of the inscription to operation. When operation is mint, has to be less or equal to \"lim\"\n    from_address varchar(62) NOT NULL, -- Address sending the inscription\n    to_address varchar(62) NOT NULL  -- Address receiving the inscription\n)\nCREATE TABLE token_balances_avalanche (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n    tick varchar(20) NOT NULL, -- Ticker: Identifier of the inscription\n    wallet_address varchar(42) NOT NULL, -- Address of owner\n    total_supply decimal(38,0) NOT NULL, -- Max supply: Set max supply of the inscription\n    amount decimal(38,0) NOT NULL  -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar(20) NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL, minted decimal(38,0) NOT NULL, holders decimal(38,0) NOT NULL, txs decimal(38,0) NOT NULL, updated_timestamp timestamp(3) NOT NULL, completed_timestamp timestamp(3) NOT NULL, id varchar(255) NOT NULL )\n"}
{"conversations": [{"role": "user", "content": "Show a list of all game developers with their name and founded year."}, {"role": "assistant", "content": "SELECT\n  name,\n  founded_year\nFROM gaming_technology.developers;"}, {"role": "user", "content": "Please filter the list to only include developers founded in the year 1998."}, {"role": "assistant", "content": "SELECT\n  name,\n  founded_year\nFROM gaming_technology.developers\nWHERE\n  founded_year = 1998;"}, {"role": "user", "content": "Can you also include the number of games each of these developers has released?"}, {"role": "assistant", "content": "SELECT\n  T1.name,\n  T1.founded_year,\n  COUNT(T2.game_id) AS game_count\nFROM gaming_technology.developers AS T1\nLEFT JOIN gaming_technology.games AS T2\n  ON T1.developer_id = T2.developer_id\nWHERE\n  T1.founded_year = 1998\nGROUP BY\n  T1.developer_id,\n  T1.name,\n  T1.founded_year;"}, {"role": "user", "content": "Now, only show the developers who have released exactly 2 games."}, {"role": "assistant", "content": "SELECT\n  T1.name,\n  T1.founded_year,\n  COUNT(T2.game_id) AS game_count\nFROM gaming_technology.developers AS T1\nJOIN gaming_technology.games AS T2\n  ON T1.developer_id = T2.developer_id\nWHERE\n  T1.founded_year = 1998\nGROUP BY\n  T1.developer_id,\n  T1.name,\n  T1.founded_year\nHAVING\n  COUNT(T2.game_id) = 2;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.players (\n    player_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the player\n    username character varying(100) NOT NULL UNIQUE, -- player's chosen display name\n    email character varying(255) NOT NULL UNIQUE, -- player's email address for login/recovery\n    password_hash text NOT NULL, -- securely hashed password\n    registration_date timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the player account was created\n    last_login timestamp with time zone, -- timestamp of the last successful login\n    country_code character(2), -- player's country (ISO 3166-1 alpha-2)\n    status character varying(20) NOT NULL DEFAULT 'active', -- account status (e.g., active, banned, suspended)\n    profile_data jsonb, -- flexible field for avatar url, bio, preferences etc.\n    PRIMARY KEY (player_id)\n)\nCREATE TABLE gaming_technology.games (\n    game_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game\n    title character varying(200) NOT NULL, -- official title of the game\n    developer_id uuid NOT NULL, -- FK linking to the developers table\n    publisher_id uuid, -- FK linking to a potential publishers table (optional)\n    genre character varying(100), -- primary genre (e.g., RPG, FPS, Strategy)\n    release_date date, -- official release date\n    description text, -- short description or synopsis of the game\n    platform character varying(50) NOT NULL, -- primary platform (e.g., PC, PlayStation 5, Xbox Series X, Mobile)\n    engine character varying(100), -- game engine used (e.g., Unreal Engine 5, Unity)\n    website character varying(255), -- official website URL\n    PRIMARY KEY (game_id)\n    -- FOREIGN KEY (developer_id) REFERENCES gaming_technology.developers(developer_id) -- Example FK constraint\n)\nCREATE TABLE gaming_technology.developers (\n    developer_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the developer studio\n    name character varying(150) NOT NULL UNIQUE, -- name of the development studio\n    country character varying(100), -- country where the studio is based\n    founded_year integer, -- year the studio was founded\n    website character varying(255), -- developer's official website\n    created_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP,\n    PRIMARY KEY (developer_id)\n)\nCREATE TABLE gaming_technology.game_sessions (\n    session_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game session\n    player_id uuid NOT NULL, -- FK linking to the players table\n    game_id uuid NOT NULL, -- FK linking to the games table\n    server_id uuid, -- FK linking to the servers table (nullable for single-player)\n    start_time timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the session began\n    end_time timestamp with time zone, -- when the session ended (null if ongoing)\n    duration_seconds integer, -- calculated duration of the session in seconds\n    score integer, -- player's score for the session, if applicable\n    session_data jsonb, -- flexible field for session-specific info (e.g., map played, character used)\n    PRIMARY KEY (session_id)\n    -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n    -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id),\n    -- FOREIGN KEY (server_id) REFERENCES gaming_technology.servers(server_id)\n)\nCREATE TABLE gaming_technology.servers (\n    server_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game server instance\n    game_id uuid NOT NULL, -- FK linking to the game this server hosts\n    server_name character varying(150), -- display name for the server\n    region character varying(50) NOT NULL, -- geographical region (e.g., us-east-1, eu-west-2)\n    ip_address character varying(45), -- IP address (IPv4 or IPv6)\n    port integer, -- network port number\n    current_players integer NOT NULL DEFAULT 0, -- number of players currently connected\n    max_players integer NOT NULL, -- maximum player capacity\n    status character varying(30) NOT NULL DEFAULT 'offline', -- server status (e.g., online, offline, maintenance)\n    last_heartbeat timestamp with time zone, -- last time the server reported its status\n    PRIMARY KEY (server_id)\n    -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id)\n)\nCREATE TABLE gaming_technology.achievements (\n    achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for an achievement definition\n    game_id uuid NOT NULL, -- FK linking to the game the achievement belongs to\n    name character varying(150) NOT NULL, -- name of the achievement\n    description text NOT NULL, -- how to unlock the achievement\n    icon_url character varying(255), -- URL for the achievement's icon\n    points integer DEFAULT 0, -- points awarded for unlocking (optional)\n    hidden boolean DEFAULT false, -- whether the achievement details are hidden until unlocked\n    PRIMARY KEY (achievement_id)\n    -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id)\n)\nCREATE TABLE gaming_technology.player_achievements (\n    player_achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for this unlock instance\n    player_id uuid NOT NULL, -- FK linking to the player who unlocked it\n    achievement_id uuid NOT NULL, -- FK linking to the achievement definition\n    unlocked_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the achievement was unlocked\n    PRIMARY KEY (player_achievement_id),\n    UNIQUE (player_id, achievement_id) -- Ensure a player can only unlock an achievement once\n    -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n    -- FOREIGN KEY (achievement_id) REFERENCES gaming_technology.achievements(achievement_id)\n)\n"}
{"conversations": [{"role": "user", "content": "For each patient, find the next appointment after each one. Return patient_id, appointment_id, next_appointment_id, and the waiting time in minutes between them."}, {"role": "assistant", "content": "SELECT A.patient_id,\n       A.appointment_id AS current_id,\n       B.appointment_id AS next_id,\n       EXTRACT(EPOCH FROM (B.appointment_time - A.appointment_time)) / 60 AS wait_minutes\nFROM healthcare.appointments A\nJOIN healthcare.appointments B\n  ON A.patient_id = B.patient_id\n AND B.appointment_time = (\n       SELECT MIN(appointment_time)\n       FROM healthcare.appointments\n       WHERE patient_id = A.patient_id\n         AND appointment_time > A.appointment_time\n   );"}, {"role": "user", "content": "Now include only the pairs where the waiting time is less than 30 minutes."}, {"role": "assistant", "content": "SELECT A.patient_id,\n       A.appointment_id AS current_id,\n       B.appointment_id AS next_id,\n       EXTRACT(EPOCH FROM (B.appointment_time - A.appointment_time)) / 60 AS wait_minutes\nFROM healthcare.appointments A\nJOIN healthcare.appointments B\n  ON A.patient_id = B.patient_id\n AND B.appointment_time = (\n       SELECT MIN(appointment_time)\n       FROM healthcare.appointments\n       WHERE patient_id = A.patient_id\n         AND appointment_time > A.appointment_time\n   )\nWHERE EXTRACT(EPOCH FROM (B.appointment_time - A.appointment_time)) / 60 < 30;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.appointments ( appointment_id text PRIMARY KEY, patient_id text, doctor_id text, appointment_time timestamp, duration_minutes int, reason text, status text, location_id text, notes text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "I want to see pairs of items from the same game that share the same rarity but are of different types. Show each pair's names and types."}, {"role": "assistant", "content": "SELECT a.game_id,\n       a.item_name AS item1_name,\n       a.item_type AS item1_type,\n       b.item_name AS item2_name,\n       b.item_type AS item2_type\nFROM gaming_technology.in_game_items a\nJOIN gaming_technology.in_game_items b\n  ON a.game_id = b.game_id\n AND a.rarity = b.rarity\n AND a.item_type <> b.item_type\n AND a.item_id < b.item_id;"}, {"role": "user", "content": "Also include cost_currency and cost_amount for each item in the output."}, {"role": "assistant", "content": "SELECT a.game_id,\n       a.item_name AS item1_name,\n       a.item_type AS item1_type,\n       a.cost_currency AS item1_currency,\n       a.cost_amount   AS item1_cost,\n       b.item_name AS item2_name,\n       b.item_type AS item2_type,\n       b.cost_currency AS item2_currency,\n       b.cost_amount   AS item2_cost\nFROM gaming_technology.in_game_items a\nJOIN gaming_technology.in_game_items b\n  ON a.game_id = b.game_id\n AND a.rarity = b.rarity\n AND a.item_type <> b.item_type\n AND a.item_id < b.item_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.in_game_items ( item_id.uuid, game_id.uuid, item_name.text, item_type.text, description.text, rarity.text, cost_currency.text, cost_amount.numeric, attributes.jsonb )\n"}
{"conversations": [{"role": "user", "content": "Which bed types are offered in each property and how many different room types are associated with each bed type?"}, {"role": "assistant", "content": "SELECT property_id, bed_type, COUNT(DISTINCT room_type_id) AS room_type_count FROM hospitality_technology.room_types GROUP BY property_id, bed_type;"}, {"role": "user", "content": "Now, show only bed types that are available for at least 3 different room types within the same property."}, {"role": "assistant", "content": "SELECT property_id, bed_type, COUNT(DISTINCT room_type_id) AS room_type_count FROM hospitality_technology.room_types GROUP BY property_id, bed_type HAVING COUNT(DISTINCT room_type_id) >= 3;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.room_types ( room_type_id text PRIMARY KEY, property_id text, type_name text, description text, base_rate numeric, max_occupancy int, bed_type text, area_sqft numeric, amenities text )\n"}
{"conversations": [{"role": "user", "content": "For each fundraising round in 2022 and 2023, list the round name, the year, the total investment_value, and the count of distinct projects. Also include the average market_cap of associated tokens by matching project_name to token_symbol in token_basic_info."}, {"role": "assistant", "content": "SELECT p.rounds_name,\n  SUBSTRING(p.investment_date FROM 1 FOR 4) AS year,\n  SUM(p.investment_value) AS total_investment,\n  COUNT(DISTINCT p.project_id) AS project_count,\n  AVG(t.market_cap) AS avg_market_cap\nFROM project_fundraising_record p\nJOIN token_basic_info t\n  ON LOWER(p.project_name) = LOWER(t.token_symbol)\nWHERE SUBSTRING(p.investment_date FROM 1 FOR 4) IN ('2022','2023')\nGROUP BY p.rounds_name, SUBSTRING(p.investment_date FROM 1 FOR 4);"}, {"role": "user", "content": "The join returns no rows. Please change the join to match when token_symbol is contained within project_name, case-insensitive."}, {"role": "assistant", "content": "SELECT p.rounds_name,\n  SUBSTRING(p.investment_date FROM 1 FOR 4) AS year,\n  SUM(p.investment_value) AS total_investment,\n  COUNT(DISTINCT p.project_id) AS project_count,\n  AVG(t.market_cap) AS avg_market_cap\nFROM project_fundraising_record p\nJOIN token_basic_info t\n  ON LOWER(p.project_name) LIKE '%' || LOWER(t.token_symbol) || '%'\nWHERE SUBSTRING(p.investment_date FROM 1 FOR 4) IN ('2022','2023')\nGROUP BY p.rounds_name, SUBSTRING(p.investment_date FROM 1 FOR 4);"}, {"role": "user", "content": "Now only include rounds where the total investment_value exceeds 5000000."}, {"role": "assistant", "content": "SELECT p.rounds_name,\n  SUBSTRING(p.investment_date FROM 1 FOR 4) AS year,\n  SUM(p.investment_value) AS total_investment,\n  COUNT(DISTINCT p.project_id) AS project_count,\n  AVG(t.market_cap) AS avg_market_cap\nFROM project_fundraising_record p\nJOIN token_basic_info t\n  ON LOWER(p.project_name) LIKE '%' || LOWER(t.token_symbol) || '%'\nWHERE SUBSTRING(p.investment_date FROM 1 FOR 4) IN ('2022','2023')\nGROUP BY p.rounds_name, SUBSTRING(p.investment_date FROM 1 FOR 4)\nHAVING SUM(p.investment_value) > 5000000;"}, {"role": "user", "content": "Finally, order the results by total_investment descending."}, {"role": "assistant", "content": "SELECT p.rounds_name,\n  SUBSTRING(p.investment_date FROM 1 FOR 4) AS year,\n  SUM(p.investment_value) AS total_investment,\n  COUNT(DISTINCT p.project_id) AS project_count,\n  AVG(t.market_cap) AS avg_market_cap\nFROM project_fundraising_record p\nJOIN token_basic_info t\n  ON LOWER(p.project_name) LIKE '%' || LOWER(t.token_symbol) || '%'\nWHERE SUBSTRING(p.investment_date FROM 1 FOR 4) IN ('2022','2023')\nGROUP BY p.rounds_name, SUBSTRING(p.investment_date FROM 1 FOR 4)\nHAVING SUM(p.investment_value) > 5000000\nORDER BY total_investment DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE project_fundraising_record ( id character varying(32) NOT NULL, project_id character varying(32) NOT NULL, project_name character varying(128) NOT NULL, rounds_name character varying(32), investment_value numeric(38,14), investment_date character varying(128), introduction character varying(128), valuation numeric(38,14) )\nCREATE TABLE token_basic_info ( coin_id text, token_name text, token_symbol text, token_address text, chain text, price numeric, price_change_percentage_1h numeric, price_change_percentage_24h numeric, price_change_percentage_7d numeric, highest_price_24h numeric, lowest_price_24h numeric, market_cap numeric, market_cap_rank numeric, market_cap_change_percentage_24h text, total_volume text, narrative text, trend_rank numeric )\n \"CREATE TABLE narrative_info (\",\n    \"narrative character varying(512) NOT NULL, -- the id of narrative\",\n    \"top_3_coins text, -- the top 3 tokens in the narrative\",\n    \"price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour in the narrative\",\n    \"price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours in the narrative\",\n    \"price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days in the narrative\",\n    \"market_cap double precision, -- the market cap of the narrative\",\n    \"volume_24h double precision, -- the trade volume of the narrative\",\n    \"trend_rank bigint, -- the trending rank of the narrative, value 1 expresses the most popular narrative\",\n    \"token_num bigint, -- total token number in the narrative\",\n    \",PRIMARY KEY (narrative));\"\n\nCREATE TABLE token_dexpool_info ( pair_address character varying(512) NOT NULL, -- the id of dexpool token_name character varying(100) NOT NULL, -- the name of the token in the dexpool token_symbol character varying(100) NOT NULL, -- the token's symbol chain text, -- the chain that the dexpool resides price double precision, -- the current price of the token price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour price_change_percentage_6h double precision, -- change in value divided by the absolute price value of the original token price in 6 hours price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours makers_24h double precision, -- the makers of the dex pool in 24 hours volume_24h double precision, -- the trade volume of the dex pool in 24 hours liquidity double precision, -- the liquidity of the dex pool market_cap double precision, -- the market cap of the token trend_rank bigint, -- the rank of token in the dex pool of recent trending, value 1 expresses the most popular token. ,PRIMARY KEY (pair_address, chain) )\n  \"CREATE TABLE cex_token_balance (\",\n    \"snapshot_time character varying(32) NOT NULL,  -- the snapshot time of record, converted from original timestamp\",\n    \"chain character varying(128) NOT NULL, -- the chain that the token resides\",\n    \"address character varying(128) NOT NULL, -- the address that holds the assets, owned by a CEX\",\n    \"exchange character varying(512) NOT NULL, -- a centralized exchange name\",\n    \"token_address character varying(128) NOT NULL, -- token contract address\",\n    \"token_symbol character varying(512), --token symbol\",\n    \"balance numeric(38,10), -- token balance\",\n    \"usd_value numeric(38,14), -- value of the token held in USD\",\n    \"price double precision, --price of the token in USD\",\n    \",PRIMARY KEY (snapshot_time, exchange, address, chain, token_address));\"\n\nCREATE TABLE smart_money_token_performance ( token_address text, token_symbol text, pnl numeric, net_flow numeric, avg_cost numeric, price numeric, realized_ratio numeric, roi numeric, chain text )\nCREATE TABLE smart_money_token_inflow ( token_address text, token_symbol text, token_amount numeric, usd_value numeric, avg_price numeric, type numeric, address_amount numeric, narrative text, chain text )\n"}
{"conversations": [{"role": "user", "content": "Show me the number of guests for each city they reside in."}, {"role": "assistant", "content": "SELECT city, count(*) AS guest_count FROM hospitality_technology.guests WHERE city IS NOT NULL GROUP BY city;"}, {"role": "user", "content": "Now, only show cities with more than 10 guests and order the results by the guest count in descending order."}, {"role": "assistant", "content": "SELECT city, count(*) AS guest_count FROM hospitality_technology.guests WHERE city IS NOT NULL GROUP BY city HAVING count(*) > 10 ORDER BY guest_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.guests ( guest_id text PRIMARY KEY, first_name text, last_name text, email text, phone_number text, date_of_birth date, address_line1 text, city text, state_province text, postal_code text, country_code text, preferences text, loyalty_member_id text, communication_consent boolean, created_at timestamp, updated_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Count the number of trips for each route type."}, {"role": "assistant", "content": "SELECT R.type, COUNT(T.trip_id) FROM transportation.trips AS T JOIN transportation.routes AS R ON T.route_id = R.route_id GROUP BY R.type;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.routes ( route_id.text, route_number.text, description.text, origin_location_id.text, destination_location_id.text, distance_km.numeric, estimated_duration_minutes.integer, type.text )\nCREATE TABLE transportation.trips ( trip_id.text, route_id.text, vehicle_id.text, driver_id.text, scheduled_departure.timestamp, actual_departure.timestamp, scheduled_arrival.timestamp, actual_arrival.timestamp, origin_location_id.text, destination_location_id.text, status.text, passenger_count.integer, cargo_manifest_id.text )\nCREATE TABLE transportation.passengers ( passenger_id.text, first_name.text, last_name.text, email.text, phone_number.text, date_of_birth.date, loyalty_program_id.text, created_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "For each claim, show the claim ID, incident date, and the number of documents attached to it. Only include claims that have at least 2 documents."}, {"role": "assistant", "content": "SELECT c.claim_id, c.incident_date, COUNT(d.document_id) AS document_count\nFROM insurance.claims c\nJOIN insurance.claim_documents d ON c.claim_id = d.claim_id\nGROUP BY c.claim_id, c.incident_date\nHAVING COUNT(d.document_id) >= 2;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.claims ( claim_id text, policy_id text, customer_id text, incident_date timestamp, reported_date timestamp, description text, estimated_loss numeric, status text, settlement_amount numeric, settlement_date date, claim_handler_id text, police_report_number text )\nCREATE TABLE insurance.claim_documents ( document_id text PRIMARY KEY, claim_id text, document_type text, file_name text, file_path text, file_size_bytes int, mime_type text, uploaded_by text, uploaded_at timestamp, description text )\n"}
{"conversations": [{"role": "user", "content": "What is the total amount of all payments recorded?"}, {"role": "assistant", "content": "SELECT SUM(amount) FROM government_services.payments;"}, {"role": "user", "content": "Now only include payments with status 'Completed'."}, {"role": "assistant", "content": "SELECT SUM(amount) FROM government_services.payments WHERE status = 'Completed';"}, {"role": "user", "content": "Also, only consider payments made in the year 2024."}, {"role": "assistant", "content": "SELECT SUM(amount) FROM government_services.payments WHERE status = 'Completed' AND EXTRACT(YEAR FROM payment_timestamp) = 2024;"}, {"role": "user", "content": "Group the results by payment method and show the total amount for each method for these completed 2024 payments."}, {"role": "assistant", "content": "SELECT payment_method, SUM(amount) FROM government_services.payments WHERE status = 'Completed' AND EXTRACT(YEAR FROM payment_timestamp) = 2024 GROUP BY payment_method;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id text PRIMARY KEY, national_id_number text, first_name text, last_name text, date_of_birth date, gender text, primary_address text, contact_email text, contact_phone text, registration_date timestamp, is_verified boolean )\nCREATE TABLE government_services.services ( service_id text PRIMARY KEY, agency_id text, service_name text, description text, category text, eligibility_criteria text, standard_fee numeric, average_processing_time_days int, is_active boolean, online_application_url text )\nCREATE TABLE government_services.payments ( payment_id text PRIMARY KEY, application_id text, citizen_id text, service_id text, amount numeric, currency text, payment_method text, payment_provider_reference text, payment_timestamp timestamp, status text, notes text )\nCREATE TABLE government_services.service_locations ( location_id text PRIMARY KEY, agency_id text, location_name text, address text, city text, state text, postal_code text, latitude numeric, longitude numeric, operating_hours text, contact_phone text, is_accessible boolean )\nCREATE TABLE government_services.appointments ( appointment_id text PRIMARY KEY, citizen_id text, employee_id text, location_id text, service_id text, scheduled_start_time timestamp, scheduled_end_time timestamp, purpose text, status text, booking_method text, created_at timestamp, notes text )\n"}
{"conversations": [{"role": "user", "content": "List all guests who have communication consent enabled along with their email addresses."}, {"role": "assistant", "content": "SELECT guest_id,\n       first_name || ' ' || last_name AS full_name,\n       email\nFROM guests\nWHERE communication_consent = TRUE;"}, {"role": "user", "content": "Now only include those guests who also have a loyalty_member_id."}, {"role": "assistant", "content": "SELECT guest_id,\n       first_name || ' ' || last_name AS full_name,\n       email,\n       loyalty_member_id\nFROM guests\nWHERE communication_consent = TRUE\n  AND loyalty_member_id IS NOT NULL;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.guests ( guest_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, email character varying(255) UNIQUE, phone_number character varying(30), date_of_birth date, address_line1 character varying(255), city character varying(100), state_province character varying(100), postal_code character varying(20), country_code character varying(3), preferences text, loyalty_member_id character varying(64) UNIQUE, communication_consent boolean DEFAULT true, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (guest_id) )\n"}
{"conversations": [{"role": "user", "content": "List pairs of invoice numbers for the same case, including their issue dates."}, {"role": "assistant", "content": "SELECT T1.invoice_number AS invoice1_number, T2.invoice_number AS invoice2_number, T1.case_id, T1.issue_date AS invoice1_issue_date, T2.issue_date AS invoice2_issue_date FROM legal_services.invoices AS T1 JOIN legal_services.invoices AS T2 ON T1.case_id = T2.case_id AND T1.invoice_id <> T2.invoice_id WHERE T1.case_id IS NOT NULL ORDER BY T1.case_id, invoice1_issue_date, invoice2_issue_date"}, {"role": "user", "content": "Only show pairs where one invoice was issued before the other, and calculate the difference in days between their issue dates."}, {"role": "assistant", "content": "SELECT T1.invoice_number AS earlier_invoice_number, T2.invoice_number AS later_invoice_number, T1.case_id, T1.issue_date AS earlier_issue_date, T2.issue_date AS later_issue_date, DATE_PART('day', T2.issue_date - T1.issue_date) AS days_difference FROM legal_services.invoices AS T1 JOIN legal_services.invoices AS T2 ON T1.case_id = T2.case_id AND T1.invoice_id <> T2.invoice_id WHERE T1.issue_date < T2.issue_date AND T1.case_id IS NOT NULL ORDER BY T1.case_id, earlier_issue_date"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.invoices ( invoice_id text PRIMARY KEY, invoice_number text UNIQUE, client_id text, case_id text, issue_date date, due_date date, total_amount numeric, amount_paid numeric, status text, payment_date timestamp, notes text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show me the token names and their contract addresses where the total supply is greater than 1 million, sorted by total supply in descending order."}, {"role": "assistant", "content": "SELECT token_name, contract_address FROM web3.tokens WHERE total_supply > 1000000 ORDER BY total_supply DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.tokens ( token_id text, contract_address text, token_name text, token_symbol text, decimals integer, total_supply numeric )\n"}
{"conversations": [{"role": "user", "content": "Which service locations do not have a contact phone specified? Show the location_id and location_name."}, {"role": "assistant", "content": "SELECT location_id, location_name\nFROM government_services.service_locations\nWHERE contact_phone IS NULL OR contact_phone = '';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.documents ( document_id character varying(64) NOT NULL, application_id character varying(64), citizen_id character varying(64) NOT NULL, document_type character varying(100) NOT NULL, file_reference text NOT NULL, upload_timestamp timestamp NOT NULL, expiry_date date, verification_status character varying(30) DEFAULT 'Pending', verified_by_employee_id character varying(64), verification_timestamp timestamp, PRIMARY KEY (document_id) )\nCREATE TABLE government_services.service_locations ( location_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, location_name character varying(200), address text NOT NULL, city character varying(100), state character varying(50), postal_code character varying(20), latitude numeric(9, 6), longitude numeric(9, 6), operating_hours text, contact_phone character varying(32), is_accessible boolean, PRIMARY KEY (location_id) )\n"}
{"conversations": [{"role": "user", "content": "Show each service's name along with the total number of appointments scheduled and the number of unique locations these appointments are scheduled at."}, {"role": "assistant", "content": "SELECT s.service_name, COUNT(a.application_id) AS appointment_count, COUNT(DISTINCT ap.location_id) AS unique_location_count\nFROM government_services.services s\nJOIN government_services.applications a ON s.service_id = a.service_id\nJOIN government_services.appointments ap ON a.application_id = ap.application_id\nGROUP BY s.service_name;"}, {"role": "user", "content": "I got an error: relation 'appointments' does not exist."}, {"role": "assistant", "content": "-- The appointments table is not present in the provided schema. If you want to count by another join, perhaps by documents or payments, please specify.\n-- Alternatively, do you want appointment information replaced with application submissions per service and their associated location from service_locations?\nSELECT s.service_name, COUNT(a.application_id) AS application_count, COUNT(DISTINCT sl.location_id) AS unique_location_count\nFROM government_services.services s\nJOIN government_services.applications a ON s.service_id = a.service_id\nJOIN government_services.service_locations sl ON s.agency_id = sl.agency_id\nGROUP BY s.service_name;"}, {"role": "user", "content": "Show only those services where application_count is greater than 50."}, {"role": "assistant", "content": "SELECT s.service_name, COUNT(a.application_id) AS application_count, COUNT(DISTINCT sl.location_id) AS unique_location_count\nFROM government_services.services s\nJOIN government_services.applications a ON s.service_id = a.service_id\nJOIN government_services.service_locations sl ON s.agency_id = sl.agency_id\nGROUP BY s.service_name\nHAVING COUNT(a.application_id) > 50;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens (\n    citizen_id character varying(64) NOT NULL,  -- unique identifier for the citizen\n    national_id_number character varying(128) NOT NULL UNIQUE, -- official national identification number\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    date_of_birth date NOT NULL,\n    gender character varying(20),\n    primary_address text NOT NULL, -- full primary residential address\n    contact_email character varying(128) UNIQUE,\n    contact_phone character varying(32),\n    registration_date timestamp NOT NULL, -- when the citizen profile was created\n    is_verified boolean DEFAULT false, -- whether identity has been officially verified\n    PRIMARY KEY (citizen_id)\n)\nCREATE TABLE government_services.agencies ( agency_id.text, agency_name.text, jurisdiction_level.text, primary_contact_email.text, main_phone_number.text, website_url.text, established_date.date, parent_agency_id.text )\nCREATE TABLE government_services.services ( service_id text PRIMARY KEY, agency_id text, service_name text, description text, category text, eligibility_criteria text, standard_fee numeric, average_processing_time_days int, is_active boolean, online_application_url text )\nCREATE TABLE government_services.applications ( application_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, service_id character varying(64) NOT NULL, submitted_at timestamp NOT NULL, status character varying(50) NOT NULL, last_updated_at timestamp NOT NULL, assigned_employee_id character varying(64), decision_date date, notes text, reference_number character varying(100) UNIQUE, PRIMARY KEY (application_id) )\nCREATE TABLE government_services.documents ( document_id.text, application_id.text, citizen_id.text, document_type.text, file_reference.text, upload_timestamp.timestamp, expiry_date.date, verification_status.text, verified_by_employee_id.text, verification_timestamp.timestamp )\nCREATE TABLE government_services.payments ( payment_id text, application_id text, citizen_id text, service_id text, amount numeric, currency text, payment_method text, payment_provider_reference text, payment_timestamp timestamp, status text, notes text )\nCREATE TABLE government_services.service_locations (\n    location_id character varying(64) NOT NULL, -- unique identifier for the physical location\n    agency_id character varying(64) NOT NULL, -- FK to agencies table\n    location_name character varying(200), -- e.g., Downtown DMV Office\n    address text NOT NULL,\n    city character varying(100),\n    state character varying(50),\n    postal_code character varying(20),\n    latitude numeric(9, 6),\n    longitude numeric(9, 6),\n    operating_hours text, -- description of opening times\n    contact_phone character varying(32),\n    is_accessible boolean, -- accessibility information (e.g., wheelchair access)\n    PRIMARY KEY (location_id)\n)\nCREATE TABLE government_services.notifications ( notification_id text PRIMARY KEY, citizen_id text, application_id text, message_subject text, message_body text, channel text, sent_at timestamp, status text, related_entity_type text, related_entity_id text )\n"}
{"conversations": [{"role": "user", "content": "Show all medical records with the record_id, record_date, the patient's insurance policy_number, and the doctor's ID, for records linked to a currently active insurance policy."}, {"role": "assistant", "content": "SELECT mr.record_id, mr.record_date, pi.policy_number, mr.doctor_id\nFROM healthcare.medical_records mr\nINNER JOIN healthcare.patient_insurance pi ON mr.patient_id = pi.patient_id\nWHERE pi.expiration_date IS NULL OR pi.expiration_date >= CURRENT_DATE;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.appointments ( appointment_id.text, patient_id.text, doctor_id.text, appointment_time.timestamp, duration_minutes.integer, reason.text, status.text, location_id.text, notes.text, created_at.timestamp )\nCREATE TABLE healthcare.medical_records ( record_id.text, patient_id.text, appointment_id.text, doctor_id.text, record_date.timestamp, chief_complaint.text, present_illness_history.text, past_medical_history.text, physical_examination_notes.text, assessment.text, treatment_plan.text, vitals.json, created_at.timestamp )\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id text, patient_id text, plan_id text, policy_number text, group_number text, subscriber_name text, effective_date date, expiration_date date, is_primary boolean )\n"}
{"conversations": [{"role": "user", "content": "Provide a count of loans grouped by their status."}, {"role": "assistant", "content": "SELECT status, COUNT(*) FROM financial_services.loans GROUP BY status"}, {"role": "user", "content": "Additionally, show the total current principal balance for each status."}, {"role": "assistant", "content": "SELECT status, COUNT(*), SUM(current_principal_balance) FROM financial_services.loans GROUP BY status"}, {"role": "user", "content": "Only include statuses where the loan count is greater than 5."}, {"role": "assistant", "content": "SELECT status, COUNT(*), SUM(current_principal_balance) FROM financial_services.loans GROUP BY status HAVING COUNT(*) > 5"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.loans ( loan_id.text, account_id.text, loan_type.text, principal_amount.numeric, current_principal_balance.numeric, interest_rate.numeric, term_months.integer, origination_date.date, maturity_date.date, monthly_payment.numeric, collateral_description.text, status.text )\n"}
{"conversations": [{"role": "user", "content": "List all wallets holding the NFT with contract_address '0xabc123' and token_id '100' and the amount held."}, {"role": "assistant", "content": "SELECT wallet_address, amount\nFROM nft_holders\nWHERE contract_address = '0xabc123'\n  AND token_id = '100';"}, {"role": "user", "content": "Also include the NFT name from nft_metadata by joining on contract_address and token_id."}, {"role": "assistant", "content": "SELECT nh.wallet_address,\n       nh.amount,\n       nm.name\nFROM nft_holders nh\nJOIN nft_metadata nm ON nh.contract_address = nm.contract_address\n                   AND nh.token_id = nm.token_id\nWHERE nh.contract_address = '0xabc123'\n  AND nh.token_id = '100';"}, {"role": "user", "content": "Finally, add the collection name from nft_collections where blockchain is 'Ethereum'."}, {"role": "assistant", "content": "SELECT nh.wallet_address,\n       nh.amount,\n       nm.name,\n       nc.name AS collection_name\nFROM nft_holders nh\nJOIN nft_metadata nm ON nh.contract_address = nm.contract_address\n                   AND nh.token_id = nm.token_id\nJOIN nft_collections nc ON nh.contract_address = nc.contract_address\n                      AND nc.blockchain = 'Ethereum'\nWHERE nh.contract_address = '0xabc123'\n  AND nh.token_id = '100';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE erc1155_approval_for_all ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar(66) NOT NULL, log_index integer NOT NULL, contract_address varchar(42) NOT NULL )\nCREATE TABLE erc20_balances ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE erc20_balances_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_holders ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, token_id varchar NOT NULL, contract_type varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_coins_metadata ( object_id varchar NOT NULL, coin_type varchar NOT NULL, status varchar NOT NULL, decimals bigint NOT NULL, description varchar NOT NULL, icon_url varchar NOT NULL, symbol varchar NOT NULL, name varchar NOT NULL )\nCREATE TABLE sui_nfts ( object_id varchar NOT NULL, status varchar NOT NULL, collection_type varchar NOT NULL, package_id varchar NOT NULL, previous_transaction varchar NOT NULL, display varchar NOT NULL, owner varchar NOT NULL, name varchar NOT NULL )\nCREATE TABLE nft_metadata ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, token_id varchar NOT NULL, contract_name varchar NOT NULL, erc_type varchar NOT NULL, amount bigint NOT NULL, minter varchar NOT NULL, owner varchar NOT NULL, mint_block_number bigint NOT NULL, mint_time bigint NOT NULL, mint_transaction_hash varchar NOT NULL, mint_price varchar NOT NULL, token_uri varchar NOT NULL, metadata varchar NOT NULL, name varchar NOT NULL, image_uri varchar NOT NULL, traits varchar NOT NULL, updated_at bigint NOT NULL, status varchar NOT NULL, rarity_score real NOT NULL, rarity_rank integer NOT NULL, unique_attribute_count integer NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_collections ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, name varchar NOT NULL, symbol varchar NOT NULL, deploy_block_number bigint NOT NULL, deploy_block_time bigint NOT NULL, erc_type varchar NOT NULL, owner varchar NOT NULL, traits varchar NOT NULL, description varchar NOT NULL, slug varchar NOT NULL, media_info varchar NOT NULL, image_url varchar NOT NULL, banner_image_url varchar NOT NULL, updated_at bigint NOT NULL, banner varchar NOT NULL, token_count bigint NOT NULL, floor_price varchar NOT NULL, floor_price_symbol varchar NOT NULL, floor_price_contract varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_prices ( uuid varchar(36) NOT NULL, blockchain varchar(36) NOT NULL, address varchar(42) NOT NULL, decimals bigint NOT NULL, symbol varchar(36) NOT NULL, price real NOT NULL, timestamp timestamp(6) NOT NULL )\nCREATE TABLE token_prices_latest ( blockchain varchar(36) NOT NULL, address varchar(42) NOT NULL, decimals bigint NOT NULL, symbol varchar(36) NOT NULL, price real NOT NULL, timestamp timestamp(6) NOT NULL )\nCREATE TABLE erc20_approval ( block_number bigint NOT NULL, block_timestamp timestamp(6) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar NOT NULL, log_index integer NOT NULL, contract_address varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_balances ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar NOT NULL, wallet_address varchar(42) NOT NULL, total_supply decimal(38,0) NOT NULL, amount decimal(38,0) NOT NULL )\nCREATE TABLE token_info ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE token_activities ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar NOT NULL, tick varchar NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(42) NOT NULL, to_address varchar(42) NOT NULL )\nCREATE TABLE mud_holesky_redstone ( address varchar NOT NULL, table_id varchar NOT NULL, key_bytes varchar NOT NULL, key0 varchar NOT NULL, key1 varchar NOT NULL, static_data varchar NOT NULL, encoded_lengths varchar NOT NULL, dynamic_data varchar NOT NULL, is_deleted boolean NOT NULL, block_number bigint NOT NULL, log_index bigint NOT NULL )\nCREATE TABLE token_balances_bitcoin ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar(255) NOT NULL, wallet_address varchar(42) NOT NULL, total_supply varchar NOT NULL, amount varchar NOT NULL )\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar(255) NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar(20) NOT NULL, tick varchar(255) NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(62) NOT NULL, to_address varchar(62) NOT NULL )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar(20) NOT NULL, tick varchar(255) NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(42) NOT NULL, to_address varchar(42) NOT NULL )\nCREATE TABLE token_balances_avalanche ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar(20) NOT NULL, wallet_address varchar(42) NOT NULL, total_supply decimal(38,0) NOT NULL, amount decimal(38,0) NOT NULL )\n"}
{"conversations": [{"role": "user", "content": "List pairs of smoking and non-smoking rooms on the same floor for each property, showing the property_id, floor, smoking room_number, and non_smoking room_number."}, {"role": "assistant", "content": "SELECT r1.property_id,\n       r1.floor,\n       r1.room_number AS smoking_room,\n       r2.room_number AS non_smoking_room\nFROM hospitality_technology.rooms r1\nJOIN hospitality_technology.rooms r2\n  ON r1.property_id = r2.property_id\n AND r1.floor = r2.floor\n AND r1.is_smoking = TRUE\n AND r2.is_smoking = FALSE;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.rooms ( room_id.text, property_id.text, room_number.text, room_type_id.text, floor.integer, status.text, is_smoking.boolean, features.text, current_condition.text, last_cleaned_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "List the ERC20 tokens (from token_metas) with exactly 6 decimals. Show their symbol, contract_address, and name."}, {"role": "assistant", "content": "SELECT symbol, contract_address, name FROM token_metas WHERE is_erc20 = 1 AND decimals = 6;"}, {"role": "user", "content": "Can you also include the total current supply for each token?"}, {"role": "assistant", "content": "SELECT symbol, contract_address, name, total_supply FROM token_metas WHERE is_erc20 = 1 AND decimals = 6;"}, {"role": "user", "content": "Now, join with token_prices_latest to also include the latest price for each token."}, {"role": "assistant", "content": "SELECT tm.symbol, tm.contract_address, tm.name, tm.total_supply, tpl.price AS latest_price\nFROM token_metas tm\nJOIN token_prices_latest tpl ON tm.contract_address = tpl.address AND tpl.blockchain = 'Ethereum'\nWHERE tm.is_erc20 = 1 AND tm.decimals = 6;"}, {"role": "user", "content": "Only include tokens where the latest price is between 0.5 and 2.0 USD, and limit the result to the top 5 tokens by price descending."}, {"role": "assistant", "content": "SELECT tm.symbol, tm.contract_address, tm.name, tm.total_supply, tpl.price AS latest_price\nFROM token_metas tm\nJOIN token_prices_latest tpl ON tm.contract_address = tpl.address AND tpl.blockchain = 'Ethereum'\nWHERE tm.is_erc20 = 1 AND tm.decimals = 6 AND tpl.price BETWEEN 0.5 AND 2.0\nORDER BY tpl.price DESC\nLIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp.timestamp, block_number.bigint, transaction_hash.text, transaction_index.bigint, from_address.text, contract_address.text, symbol.text, total_supply.text, name.text, decimals.bigint, is_erc20.integer, is_erc721.integer, is_erc1155.integer, is_proxy.integer, extra_info.text, pk.integer )\nCREATE TABLE erc1155_approval_for_all (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the transaction\n    transaction_index integer NOT NULL, -- Index of the transaction within the block\n    transaction_hash varchar(66) NOT NULL, -- Transaction hash\n    log_index integer NOT NULL, -- Log index\n    contract_address varchar(42) NOT NULL  -- Event contract address\n)\nCREATE TABLE erc20_balances ( block_number bigint, contract_address varchar, wallet_address varchar, amount varchar, pk varchar )\nCREATE TABLE erc20_balances_historical ( block_number bigint, contract_address text, wallet_address text, amount text, pk integer )\nCREATE TABLE nft_holders ( block_number.bigint, contract_address.text, wallet_address.text, token_id.text, contract_type.text, amount.text, pk.text )\nCREATE TABLE nft_holder_historical (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    contract_address varchar NOT NULL, -- Event contract address\n    wallet_address varchar NOT NULL, -- The wallet address for the contract(with bloom filter)\n    token_id varchar NOT NULL, -- NFT token id\n    contract_type varchar NOT NULL, -- NFT contract type\n    amount varchar NOT NULL, -- The quantity held in the wallet\n    pk integer NOT NULL  -- Partition key for the table(floor(block_number / 7200))\n)\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_coins_metadata (\n    object_id varchar NOT NULL, -- object id of the coin metadata object\n    coin_type varchar NOT NULL, -- coin type, eg. 0x...66::reap_token::REAP_TOKEN\n    status varchar NOT NULL, -- coin status, eg. exists, deleted\n    decimals bigint NOT NULL, -- decimals of the coin\n    description varchar NOT NULL, -- description of the coin\n    icon_url varchar NOT NULL, -- icon url of the coin\n    symbol varchar NOT NULL, -- symbol of the coin\n    name varchar NOT NULL  -- name of the coin\n)\nCREATE TABLE sui_nfts ( object_id.text, status.text, collection_type.text, package_id.text, previous_transaction.text, display.text, owner.text, name.text )\nCREATE TABLE nft_metadata ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, token_id varchar NOT NULL, contract_name varchar NOT NULL, erc_type varchar NOT NULL, amount bigint NOT NULL, minter varchar NOT NULL, owner varchar NOT NULL, mint_block_number bigint NOT NULL, mint_time bigint NOT NULL, mint_transaction_hash varchar NOT NULL, mint_price varchar NOT NULL, token_uri varchar NOT NULL, metadata varchar NOT NULL, name varchar NOT NULL, image_uri varchar NOT NULL, traits varchar NOT NULL, updated_at bigint NOT NULL, status varchar NOT NULL, rarity_score real NOT NULL, rarity_rank integer NOT NULL, unique_attribute_count integer NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_prices ( uuid.text, blockchain.text, address.text, decimals.bigint, symbol.text, price.real, timestamp.timestamp )\nCREATE TABLE token_prices_latest ( blockchain.text, address.text, decimals.bigint, symbol.text, price.real, timestamp.timestamp )\nCREATE TABLE erc20_approval ( block_number.bigint, block_timestamp.timestamp, transaction_index.integer, transaction_hash.text, log_index.integer, contract_address.text, pk.integer )\nCREATE TABLE token_balances (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n    tick varchar NOT NULL, -- Token tick\n    wallet_address varchar(42) NOT NULL, -- Address of owner\n    total_supply decimal(38,0) NOT NULL, -- Max supply\n    amount decimal(38,0) NOT NULL  -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE token_activities ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\nCREATE TABLE mud_holesky_redstone ( address text, table_id text, key_bytes text, key0 text, key1 text, static_data text, encoded_lengths text, dynamic_data text, is_deleted boolean, block_number bigint, log_index bigint )\nCREATE TABLE token_balances_bitcoin (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n    tick varchar(255) NOT NULL, -- Ticker: Identifier of the inscription\n    wallet_address varchar(42) NOT NULL, -- Address of owner\n    total_supply varchar NOT NULL, -- Max supply: Set max supply of the inscription\n    amount varchar NOT NULL  -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\nCREATE TABLE token_balances_avalanche (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n    tick varchar(20) NOT NULL, -- Ticker: Identifier of the inscription\n    wallet_address varchar(42) NOT NULL, -- Address of owner\n    total_supply decimal(38,0) NOT NULL, -- Max supply: Set max supply of the inscription\n    amount decimal(38,0) NOT NULL  -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id varchar )\n"}
{"conversations": [{"role": "user", "content": "For each customer, provide a summary of their account statuses, showing their full name, account status, and the count of accounts for each status."}, {"role": "assistant", "content": "SELECT c.first_name, c.last_name, a.status, COUNT(a.account_id) AS account_count FROM financial_services.accounts a JOIN financial_services.customers c ON a.customer_id = c.customer_id GROUP BY c.customer_id, c.first_name, c.last_name, a.status ORDER BY c.last_name, c.first_name, a.status;"}, {"role": "user", "content": "Refine this to only include customers who have accounts in at least two different statuses."}, {"role": "assistant", "content": "SELECT c.first_name, c.last_name, a.status, COUNT(a.account_id) AS account_count FROM financial_services.accounts a JOIN financial_services.customers c ON a.customer_id = c.customer_id GROUP BY c.customer_id, c.first_name, c.last_name, a.status HAVING c.customer_id IN ( SELECT customer_id FROM financial_services.accounts GROUP BY customer_id HAVING COUNT(DISTINCT status) >= 2 ) ORDER BY c.last_name, c.first_name, a.status;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.accounts (\n    account_id character varying(64) NOT NULL, -- unique identifier for the account\n    customer_id character varying(64) NOT NULL, -- foreign key linking to the customer\n    account_number character varying(128) NOT NULL UNIQUE, -- unique account number visible to customer\n    account_type character varying(50) NOT NULL, -- e.g., Checking, Savings, Investment, Loan, Credit Card\n    balance numeric(19, 4) NOT NULL DEFAULT 0.00, -- current account balance\n    currency character varying(3) NOT NULL, -- currency code (e.g., USD, EUR)\n    opened_date date NOT NULL, -- date the account was opened\n    status character varying(32) NOT NULL, -- e.g., Open, Closed, Frozen\n    interest_rate numeric(5, 4), -- annual interest rate, if applicable\n    last_updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last account update\n    PRIMARY KEY (account_id),\n    FOREIGN KEY (customer_id) REFERENCES financial_services.customers(customer_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Find all prescriptions for patients who have at least one appointment scheduled in the future. Show the prescription ID, patient ID, medication name, and the earliest future appointment time for that patient."}, {"role": "assistant", "content": "SELECT pr.prescription_id, pr.patient_id, m.medication_name, ( SELECT MIN(ap.appointment_time) FROM healthcare.appointments AS ap WHERE ap.patient_id = p.patient_id AND ap.appointment_time > CURRENT_TIMESTAMP ) AS earliest_future_appointment_time FROM healthcare.prescriptions AS pr JOIN healthcare.patients AS p ON pr.patient_id = p.patient_id JOIN healthcare.medications AS m ON pr.medication_id = m.medication_id WHERE p.patient_id IN ( SELECT patient_id FROM healthcare.appointments WHERE appointment_time > CURRENT_TIMESTAMP );"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.doctors ( doctor_id text, first_name text, last_name text, specialty text, license_number text, phone_number text, email text, hospital_affiliation_id text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.appointments ( appointment_id.text, patient_id.text, doctor_id.text, appointment_time.timestamp, duration_minutes.integer, reason.text, status.text, location_id.text, notes.text, created_at.timestamp )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id text, record_id text, patient_id text, doctor_id text, diagnosis_code text, code_type text, description text, diagnosis_date date, status text, is_chronic boolean )\nCREATE TABLE healthcare.medications (\n    medication_id character varying(64) NOT NULL, -- unique identifier for the medication type\n    medication_name character varying(255) NOT NULL, -- common or brand name\n    generic_name character varying(255), -- generic chemical name\n    manufacturer character varying(100), -- drug manufacturer\n    ndc_code character varying(20) UNIQUE, -- National Drug Code (optional but useful)\n    description text, -- description of the medication\n    PRIMARY KEY (medication_id)\n)\nCREATE TABLE healthcare.prescriptions ( prescription_id text, record_id text, patient_id text, doctor_id text, medication_id text, dosage text, frequency text, route text, start_date date, end_date date, quantity_dispensed numeric, refills_allowed integer, prescription_date timestamp )\nCREATE TABLE healthcare.insurance_plans ( plan_id text, plan_name text, insurance_provider text, plan_type text, contact_phone text, website text )\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id text, patient_id text, plan_id text, policy_number text, group_number text, subscriber_name text, effective_date date, expiration_date date, is_primary boolean )\n"}
{"conversations": [{"role": "user", "content": "List the first name and last name of citizens along with the type and verification status of their documents."}, {"role": "assistant", "content": "SELECT T1.first_name, T1.last_name, T2.document_type, T2.verification_status FROM government_services.citizens AS T1 JOIN government_services.documents AS T2 ON T1.citizen_id = T2.citizen_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id text PRIMARY KEY, national_id_number text, first_name text, last_name text, date_of_birth date, gender text, primary_address text, contact_email text, contact_phone text, registration_date timestamp, is_verified boolean )\nCREATE TABLE government_services.services (\n    service_id character varying(64) NOT NULL, -- unique identifier for the service\n    agency_id character varying(64) NOT NULL, -- FK to agencies table\n    service_name character varying(255) NOT NULL, -- name of the service (e.g., Driver's License Renewal)\n    description text,\n    category character varying(100), -- e.g., Licensing, Benefits, Taxation, Permits\n    eligibility_criteria text, -- description of who is eligible\n    standard_fee numeric(10, 2) DEFAULT 0.00, -- typical fee for the service\n    average_processing_time_days integer, -- estimated processing time\n    is_active boolean DEFAULT true, -- whether the service is currently offered\n    online_application_url character varying(255),\n    PRIMARY KEY (service_id)\n)\nCREATE TABLE government_services.documents ( document_id text PRIMARY KEY, application_id text, citizen_id text, document_type text, file_reference text, upload_timestamp timestamp, expiry_date date, verification_status text, verified_by_employee_id text, verification_timestamp timestamp )\nCREATE TABLE government_services.service_locations (\n    location_id character varying(64) NOT NULL, -- unique identifier for the physical location\n    agency_id character varying(64) NOT NULL, -- FK to agencies table\n    location_name character varying(200), -- e.g., Downtown DMV Office\n    address text NOT NULL,\n    city character varying(100),\n    state character varying(50),\n    postal_code character varying(20),\n    latitude numeric(9, 6),\n    longitude numeric(9, 6),\n    operating_hours text, -- description of opening times\n    contact_phone character varying(32),\n    is_accessible boolean, -- accessibility information (e.g., wheelchair access)\n    PRIMARY KEY (location_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Find all customers who have made a premium payment and list their first name, last name, email, and the total amount they have paid across all their payments."}, {"role": "assistant", "content": "SELECT T1.first_name, T1.last_name, T1.email, SUM(T2.amount_paid) FROM insurance.customers AS T1 JOIN insurance.premium_payments AS T2 ON T1.customer_id = T2.customer_id GROUP BY T1.customer_id, T1.first_name, T1.last_name, T1.email;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.customers ( customer_id.text, first_name.text, last_name.text, date_of_birth.date, ssn_hash.text, address_line1.text, address_line2.text, city.text, state.text, zip_code.text, country.text, phone_number.text, email.text, created_at.timestamp, updated_at.timestamp, status.text )\nCREATE TABLE insurance.premium_payments ( payment_id text PRIMARY KEY, policy_id text, customer_id text, payment_date timestamp, amount_paid numeric, payment_method text, transaction_reference text, due_date date, payment_period_start date, payment_period_end date, status text )\n"}
{"conversations": [{"role": "user", "content": "For each trip, calculate the total fuel quantity consumed and the total fuel cost. Show trip_id, total_quantity, total_cost."}, {"role": "assistant", "content": "SELECT trip_id, SUM(quantity) AS total_quantity, SUM(total_cost) AS total_cost FROM transportation.fuel_logs GROUP BY trip_id;"}, {"role": "user", "content": "Also include the route_number for each trip in the result."}, {"role": "assistant", "content": "SELECT fl.trip_id, r.route_number, SUM(fl.quantity) AS total_quantity, SUM(fl.total_cost) AS total_cost FROM transportation.fuel_logs fl JOIN transportation.trips t ON fl.trip_id = t.trip_id JOIN transportation.routes r ON t.route_id = r.route_id GROUP BY fl.trip_id, r.route_number;"}, {"role": "user", "content": "Now, only include trips where passenger_count is greater than 50 and order by total_cost in descending order."}, {"role": "assistant", "content": "SELECT fl.trip_id, r.route_number, SUM(fl.quantity) AS total_quantity, SUM(fl.total_cost) AS total_cost FROM transportation.fuel_logs fl JOIN transportation.trips t ON fl.trip_id = t.trip_id JOIN transportation.routes r ON t.route_id = r.route_id WHERE t.passenger_count > 50 GROUP BY fl.trip_id, r.route_number ORDER BY total_cost DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles ( vehicle_id text PRIMARY KEY, license_plate text, vin text, make text, model text, year int, type text, capacity int, fuel_type text, status text, depot_id text, acquisition_date date )\nCREATE TABLE transportation.drivers ( driver_id text PRIMARY KEY, employee_id text, first_name text, last_name text, license_number text, license_expiry_date date, contact_number text, email text, hire_date date, status text )\nCREATE TABLE transportation.routes ( route_id text PRIMARY KEY, route_number text, description text, origin_location_id text, destination_location_id text, distance_km numeric, estimated_duration_minutes int, type text )\nCREATE TABLE transportation.trips ( trip_id text PRIMARY KEY, route_id text, vehicle_id text, driver_id text, scheduled_departure timestamp, actual_departure timestamp, scheduled_arrival timestamp, actual_arrival timestamp, origin_location_id text, destination_location_id text, status text, passenger_count int, cargo_manifest_id text )\nCREATE TABLE transportation.locations ( location_id text PRIMARY KEY, name text, type text, address_line1 text, city text, state_province text, postal_code text, country text, latitude numeric, longitude numeric, timezone text )\nCREATE TABLE transportation.maintenance_logs ( log_id text PRIMARY KEY, vehicle_id text, service_date date, odometer_reading int, service_type text, description text, cost numeric, mechanic_name text, next_service_due_date date )\nCREATE TABLE transportation.fuel_logs ( fuel_log_id text PRIMARY KEY, vehicle_id text, trip_id text, log_timestamp timestamp, fuel_type text, quantity numeric, unit text, cost_per_unit numeric, total_cost numeric, odometer_reading int, location_id text )\nCREATE TABLE transportation.bookings ( booking_id text PRIMARY KEY, passenger_id text, trip_id text, seat_number text, booking_time timestamp, status text, fare numeric, payment_transaction_id text, special_requests text )\n"}
{"conversations": [{"role": "user", "content": "List the names of services and the total number of times each service has been ordered. Only include services that have been ordered at least once."}, {"role": "assistant", "content": "SELECT T1.service_name, count(T2.order_id) AS order_count FROM hospitality_technology.services AS T1 JOIN hospitality_technology.service_orders AS T2 ON T1.service_id = T2.service_id GROUP BY T1.service_name;"}, {"role": "user", "content": "Now, filter this list to only show services from the 'Food & Beverage' or 'Activities' categories, and sort by the order count in descending order."}, {"role": "assistant", "content": "SELECT T1.service_name, count(T2.order_id) AS order_count FROM hospitality_technology.services AS T1 JOIN hospitality_technology.service_orders AS T2 ON T1.service_id = T2.service_id WHERE T1.category IN ('Food & Beverage', 'Activities') GROUP BY T1.service_name ORDER BY order_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.properties ( property_id character varying(64) NOT NULL, property_name character varying(255) NOT NULL, address_line1 character varying(255) NOT NULL, address_line2 character varying(255), city character varying(100) NOT NULL, state_province character varying(100), postal_code character varying(20) NOT NULL, country_code character varying(3) NOT NULL, phone_number character varying(30), email_address character varying(255), property_type character varying(50) NOT NULL, star_rating numeric(2,1), timezone character varying(64) NOT NULL, manager_staff_id character varying(64), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (property_id) )\nCREATE TABLE hospitality_technology.rooms ( room_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, room_number character varying(10) NOT NULL, room_type_id character varying(64) NOT NULL, floor integer, status character varying(50) NOT NULL, is_smoking boolean NOT NULL DEFAULT false, features text, current_condition text, last_cleaned_at timestamp with time zone, PRIMARY KEY (room_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id) )\nCREATE TABLE hospitality_technology.room_types ( room_type_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, type_name character varying(100) NOT NULL, description text, base_rate numeric(10, 2) NOT NULL, max_occupancy integer NOT NULL, bed_type character varying(50), area_sqft numeric(8,2), amenities text, PRIMARY KEY (room_type_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id) )\nCREATE TABLE hospitality_technology.guests ( guest_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, email character varying(255) UNIQUE, phone_number character varying(30), date_of_birth date, address_line1 character varying(255), city character varying(100), state_province character varying(100), postal_code character varying(20), country_code character varying(3), preferences text, loyalty_member_id character varying(64) UNIQUE, communication_consent boolean DEFAULT true, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (guest_id) )\nCREATE TABLE hospitality_technology.reservations ( reservation_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, guest_id character varying(64) NOT NULL, room_id character varying(64), room_type_id character varying(64) NOT NULL, check_in_date date NOT NULL, check_out_date date NOT NULL, actual_check_in_ts timestamp with time zone, actual_check_out_ts timestamp with time zone, num_adults integer NOT NULL, num_children integer DEFAULT 0, status character varying(50) NOT NULL, booking_source character varying(100), rate_plan_id character varying(64), total_amount numeric(12, 2), amount_paid numeric(12, 2) DEFAULT 0.00, special_requests text, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (reservation_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (room_id) REFERENCES hospitality_technology.rooms(room_id), FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id) )\nCREATE TABLE hospitality_technology.services ( service_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, service_name character varying(150) NOT NULL, description text, category character varying(100), price numeric(10, 2) NOT NULL, unit character varying(30), is_available boolean NOT NULL DEFAULT true, department character varying(100), PRIMARY KEY (service_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id) )\nCREATE TABLE hospitality_technology.service_orders ( order_id character varying(64) NOT NULL, reservation_id character varying(64), guest_id character varying(64) NOT NULL, service_id character varying(64) NOT NULL, staff_id_ordered character varying(64), staff_id_delivered character varying(64), order_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, delivery_timestamp timestamp with time zone, quantity integer NOT NULL DEFAULT 1, unit_price numeric(10, 2) NOT NULL, total_price numeric(12, 2) NOT NULL, status character varying(50) NOT NULL, notes text, bill_id character varying(64), PRIMARY KEY (order_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (service_id) REFERENCES hospitality_technology.services(service_id), FOREIGN KEY (staff_id_ordered) REFERENCES hospitality_technology.staff(staff_id), FOREIGN KEY (staff_id_delivered) REFERENCES hospitality_technology.staff(staff_id) )\nCREATE TABLE hospitality_technology.payments ( payment_id character varying(64) NOT NULL, reservation_id character varying(64), guest_id character varying(64) NOT NULL, bill_id character varying(64), amount numeric(12,2) NOT NULL, currency_code character varying(3) NOT NULL, payment_method character varying(50) NOT NULL, card_type character varying(50), card_last_four character varying(4), transaction_ref character varying(128), payment_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, status character varying(50) NOT NULL, staff_id_processed character varying(64), notes text, PRIMARY KEY (payment_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (staff_id_processed) REFERENCES hospitality_technology.staff(staff_id) )\nCREATE TABLE hospitality_technology.reviews ( review_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, reservation_id character varying(64) UNIQUE, guest_id character varying(64) NOT NULL, rating_overall integer, rating_cleanliness integer, rating_service integer, rating_location integer, rating_value integer, comment text, review_source character varying(100), review_date timestamp with time zone NOT NULL DEFAULT current_timestamp, is_public boolean DEFAULT true, staff_response text, response_staff_id character varying(64), response_date timestamp with time zone, PRIMARY KEY (review_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (response_staff_id) REFERENCES hospitality_technology.staff(staff_id) )\n"}
{"conversations": [{"role": "user", "content": "Find transactions where the from_address is the same as the to_address (self-transactions) with values greater than 1 ETH (1e18 wei), showing transaction_id and value."}, {"role": "assistant", "content": "SELECT transaction_id, value FROM web3.transactions WHERE from_address = to_address AND value > 1000000000000000000;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.transactions ( transaction_id text PRIMARY KEY, from_address text, to_address text, value numeric, gas_used int, gas_price numeric, block_number int, timestamp timestamp, input_data text, status text, nonce int )\n"}
{"conversations": [{"role": "user", "content": "Show me all active customers from California who were born before 1980, along with their contact information."}, {"role": "assistant", "content": "SELECT first_name, last_name, phone_number, email, address_line1, city, zip_code FROM insurance.customers WHERE state = 'California' AND date_of_birth < '1980-01-01' AND status = 'Active';"}, {"role": "user", "content": "Now filter these results to only show customers who have provided both a phone number and an email address."}, {"role": "assistant", "content": "SELECT first_name, last_name, phone_number, email, address_line1, city, zip_code FROM insurance.customers WHERE state = 'California' AND date_of_birth < '1980-01-01' AND status = 'Active' AND phone_number IS NOT NULL AND email IS NOT NULL;"}, {"role": "user", "content": "I also want to see how long these customers have been in our system (difference between current date and created_at in years)."}, {"role": "assistant", "content": "SELECT first_name, last_name, phone_number, email, address_line1, city, zip_code, EXTRACT(YEAR FROM AGE(CURRENT_DATE, created_at)) AS years_in_system FROM insurance.customers WHERE state = 'California' AND date_of_birth < '1980-01-01' AND status = 'Active' AND phone_number IS NOT NULL AND email IS NOT NULL;"}, {"role": "user", "content": "Finally, order the results by the longest tenure in our system first, then by last name alphabetically."}, {"role": "assistant", "content": "SELECT first_name, last_name, phone_number, email, address_line1, city, zip_code, EXTRACT(YEAR FROM AGE(CURRENT_DATE, created_at)) AS years_in_system FROM insurance.customers WHERE state = 'California' AND date_of_birth < '1980-01-01' AND status = 'Active' AND phone_number IS NOT NULL AND email IS NOT NULL ORDER BY years_in_system DESC, last_name ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.customers (\n    customer_id character varying(64) NOT NULL,  -- unique identifier for the customer\n    first_name character varying(100) NOT NULL, -- customer's first name\n    last_name character varying(100) NOT NULL, -- customer's last name\n    date_of_birth date NOT NULL, -- customer's date of birth\n    ssn_hash character varying(128), -- Hashed social security number (or national ID)\n    address_line1 character varying(255) NOT NULL,\n    address_line2 character varying(255),\n    city character varying(100) NOT NULL,\n    state character varying(50) NOT NULL,\n    zip_code character varying(20) NOT NULL,\n    country character varying(50) NOT NULL DEFAULT 'USA',\n    phone_number character varying(30),\n    email character varying(128) UNIQUE, -- unique email address\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the customer record was created\n    updated_at timestamp, -- when the customer record was last updated\n    status character varying(20) NOT NULL DEFAULT 'Active', -- e.g., Active, Inactive, Prospect\n    PRIMARY KEY (customer_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Show me the total traded volume and the average price per security for trades executed last month."}, {"role": "assistant", "content": "SELECT s.ticker_symbol,\n       SUM(t.quantity) AS total_volume,\n       AVG(t.price_per_unit) AS avg_price\nFROM financial_services.trades t\nJOIN financial_services.securities s ON t.security_id = s.security_id\nWHERE t.trade_timestamp >= date_trunc('month', CURRENT_DATE - INTERVAL '1 month')\n  AND t.trade_timestamp < date_trunc('month', CURRENT_DATE)\nGROUP BY s.ticker_symbol;"}, {"role": "user", "content": "Filter to only include those trades with status 'SETTLED' and execution_venue 'NYSE'."}, {"role": "assistant", "content": "SELECT s.ticker_symbol,\n       SUM(t.quantity) AS total_volume,\n       AVG(t.price_per_unit) AS avg_price\nFROM financial_services.trades t\nJOIN financial_services.securities s ON t.security_id = s.security_id\nWHERE t.trade_timestamp >= date_trunc('month', CURRENT_DATE - INTERVAL '1 month')\n  AND t.trade_timestamp < date_trunc('month', CURRENT_DATE)\n  AND t.status = 'SETTLED'\n  AND t.execution_venue = 'NYSE'\nGROUP BY s.ticker_symbol;"}, {"role": "user", "content": "Now exclude any securities where the summed quantity is less than 1000."}, {"role": "assistant", "content": "SELECT s.ticker_symbol,\n       SUM(t.quantity) AS total_volume,\n       AVG(t.price_per_unit) AS avg_price\nFROM financial_services.trades t\nJOIN financial_services.securities s ON t.security_id = s.security_id\nWHERE t.trade_timestamp >= date_trunc('month', CURRENT_DATE - INTERVAL '1 month')\n  AND t.trade_timestamp < date_trunc('month', CURRENT_DATE)\n  AND t.status = 'SETTLED'\n  AND t.execution_venue = 'NYSE'\nGROUP BY s.ticker_symbol\nHAVING SUM(t.quantity) >= 1000;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.customers ( customer_id text PRIMARY KEY, first_name text, last_name text, date_of_birth date, ssn_hash text, address text, city text, state text, zip_code text, country text, email text, phone_number text, created_at timestamp, status text, risk_profile text )\nCREATE TABLE financial_services.accounts ( account_id text, customer_id text, account_number text, account_type text, balance numeric, currency text, opened_date date, status text, interest_rate numeric, last_updated_at timestamp )\nCREATE TABLE financial_services.securities (\n    security_id character varying(64) NOT NULL, -- unique identifier for the security\n    ticker_symbol character varying(20) NOT NULL UNIQUE, -- stock ticker or fund symbol\n    isin_code character varying(12) UNIQUE, -- International Securities Identification Number\n    cusip_code character varying(9) UNIQUE, -- CUSIP number\n    security_name text NOT NULL, -- full name of the security\n    security_type character varying(50) NOT NULL, -- e.g., Stock, Bond, ETF, Mutual Fund, Option, Future\n    exchange character varying(50), -- primary exchange where traded (e.g., NYSE, NASDAQ)\n    currency character varying(3) NOT NULL, -- currency the security is denominated in\n    issuer_name character varying(255), -- name of the issuing entity\n    sector character varying(100), -- industry sector\n    last_updated timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n    PRIMARY KEY (security_id)\n)\nCREATE TABLE financial_services.trades ( trade_id.text, account_id.text, security_id.text, order_id.text, trade_type.text, quantity.numeric, price_per_unit.numeric, total_amount.numeric, commission.numeric, trade_timestamp.timestamp, settlement_date.date, status.text, execution_venue.text )\nCREATE TABLE financial_services.market_data ( data_point_id bigint, security_id text, data_timestamp timestamp, open_price numeric, high_price numeric, low_price numeric, close_price numeric, adjusted_close_price numeric, volume bigint, source text )\nCREATE TABLE financial_services.employees ( employee_id text, first_name text, last_name text, job_title text, department text, branch_id text, email text, phone_extension text, hire_date date, termination_date date, manager_id text, status text )\nCREATE TABLE financial_services.loans ( loan_id text, account_id text, loan_type text, principal_amount numeric, current_principal_balance numeric, interest_rate numeric, term_months integer, origination_date date, maturity_date date, monthly_payment numeric, collateral_description text, status text )\n"}
{"conversations": [{"role": "user", "content": "For each country code, what is the earliest registration date of a player?"}, {"role": "assistant", "content": "SELECT country_code, MIN(registration_date) AS earliest_reg_date FROM gaming_technology.players GROUP BY country_code;"}, {"role": "user", "content": "Only list countries where the earliest registration occurred before January 1st, 2020."}, {"role": "assistant", "content": "SELECT country_code, MIN(registration_date) AS earliest_reg_date FROM gaming_technology.players GROUP BY country_code HAVING MIN(registration_date) < '2020-01-01';"}, {"role": "user", "content": "Also include the total count of players for each of these countries."}, {"role": "assistant", "content": "SELECT country_code, MIN(registration_date) AS earliest_reg_date, COUNT(player_id) AS total_players FROM gaming_technology.players GROUP BY country_code HAVING MIN(registration_date) < '2020-01-01';"}, {"role": "user", "content": "Sort the results by the earliest registration date in ascending order."}, {"role": "assistant", "content": "SELECT country_code, MIN(registration_date) AS earliest_reg_date, COUNT(player_id) AS total_players FROM gaming_technology.players GROUP BY country_code HAVING MIN(registration_date) < '2020-01-01' ORDER BY earliest_reg_date ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.players ( player_id uuid PRIMARY KEY, username text, email text, password_hash text, registration_date timestamptz, last_login timestamptz, country_code text, status text, profile_data jsonb )\n"}
{"conversations": [{"role": "user", "content": "Count the number of unique locations specified in the users table."}, {"role": "assistant", "content": "SELECT count(DISTINCT location) FROM social_media.users WHERE location IS NOT NULL;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id character varying(64) NOT NULL, username character varying(50) NOT NULL UNIQUE, email character varying(128) NOT NULL UNIQUE, password_hash text NOT NULL, full_name character varying(100), profile_picture_url text, bio text, location character varying(100), created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, is_verified boolean NOT NULL DEFAULT false, PRIMARY KEY (user_id) )\nCREATE TABLE social_media.posts ( post_id.text, user_id.text, content.text, media_url.text, media_type.text, created_at.timestamp, updated_at.timestamp, visibility.text, location_lat.numeric, location_lon.numeric )\nCREATE TABLE social_media.comments ( comment_id text PRIMARY KEY, post_id text, user_id text, parent_comment_id text, content text, created_at timestamp, updated_at timestamp )\nCREATE TABLE social_media.likes ( like_id text PRIMARY KEY, user_id text, post_id text, comment_id text, created_at timestamp )\nCREATE TABLE social_media.conversations ( conversation_id character varying(64) NOT NULL, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, last_message_at timestamp, is_group_chat boolean NOT NULL DEFAULT false, group_name character varying(100), PRIMARY KEY (conversation_id) )\nCREATE TABLE social_media.conversation_participants ( participant_id text PRIMARY KEY, conversation_id text, user_id text, joined_at timestamp, last_read_at timestamp )\nCREATE TABLE social_media.notifications ( notification_id text, recipient_user_id text, sender_user_id text, notification_type text, target_entity_id text, target_entity_type text, created_at timestamp, read_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "List the names of employees and the names of the cities where their agency operates service locations."}, {"role": "assistant", "content": "SELECT e.first_name, e.last_name, sl.city\nFROM government_services.employees e\nJOIN government_services.service_locations sl ON e.agency_id = sl.agency_id;"}, {"role": "user", "content": "Only show employees who work in locations that are accessible."}, {"role": "assistant", "content": "SELECT e.first_name, e.last_name, sl.city\nFROM government_services.employees e\nJOIN government_services.service_locations sl ON e.agency_id = sl.agency_id\nWHERE sl.is_accessible = true;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id text, national_id_number text, first_name text, last_name text, date_of_birth date, gender text, primary_address text, contact_email text, contact_phone text, registration_date timestamp, is_verified boolean )\nCREATE TABLE government_services.payments ( payment_id text, application_id text, citizen_id text, service_id text, amount numeric, currency text, payment_method text, payment_provider_reference text, payment_timestamp timestamp, status text, notes text )\nCREATE TABLE government_services.employees ( employee_id text, agency_id text, first_name text, last_name text, job_title text, department text, work_email text, work_phone text, hire_date date, termination_date date, access_level text, manager_employee_id text )\nCREATE TABLE government_services.service_locations ( location_id text, agency_id text, location_name text, address text, city text, state text, postal_code text, latitude numeric, longitude numeric, operating_hours text, contact_phone text, is_accessible boolean )\n"}
{"conversations": [{"role": "user", "content": "Show me the top 5 NFT collections with the highest token count on Ethereum, along with their names, symbols, and floor prices."}, {"role": "assistant", "content": "SELECT n.name, n.symbol, n.floor_price, n.token_count FROM nft_collections n WHERE n.blockchain = 'ethereum' ORDER BY n.token_count DESC LIMIT 5;"}, {"role": "user", "content": "Now, join this with the nft_metadata table to include the average rarity score for each collection."}, {"role": "assistant", "content": "SELECT n.name, n.symbol, n.floor_price, n.token_count, AVG(m.rarity_score) as avg_rarity_score FROM nft_collections n JOIN nft_metadata m ON n.contract_address = m.contract_address WHERE n.blockchain = 'ethereum' GROUP BY n.name, n.symbol, n.floor_price, n.token_count ORDER BY n.token_count DESC LIMIT 5;"}, {"role": "user", "content": "Can you filter these results to only show collections with an average rarity score greater than 80?"}, {"role": "assistant", "content": "SELECT n.name, n.symbol, n.floor_price, n.token_count, AVG(m.rarity_score) as avg_rarity_score FROM nft_collections n JOIN nft_metadata m ON n.contract_address = m.contract_address WHERE n.blockchain = 'ethereum' GROUP BY n.name, n.symbol, n.floor_price, n.token_count HAVING AVG(m.rarity_score) > 80 ORDER BY n.token_count DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp timestamp, block_number bigint, transaction_hash text, transaction_index bigint, from_address text, contract_address text, symbol text, total_supply text, name text, decimals bigint, is_erc20 integer, is_erc721 integer, is_erc1155 integer, is_proxy integer, extra_info text, pk integer )\nCREATE TABLE erc1155_approval_for_all ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash text, log_index integer, contract_address text )\nCREATE TABLE erc20_balances ( block_number bigint, contract_address text, wallet_address text, amount text, pk text )\nCREATE TABLE sui_coins ( object_id text, status text, coin_type text, balance text, owner text )\nCREATE TABLE sui_coins_metadata ( object_id text, coin_type text, status text, decimals bigint, description text, icon_url text, symbol text, name text )\nCREATE TABLE sui_nfts ( object_id text, status text, collection_type text, package_id text, previous_transaction text, display text, owner text, name text )\nCREATE TABLE nft_metadata ( blockchain text, contract_address text, token_id text, contract_name text, erc_type text, amount bigint, minter text, owner text, mint_block_number bigint, mint_time bigint, mint_transaction_hash text, mint_price text, token_uri text, metadata text, name text, image_uri text, traits text, updated_at bigint, status text, rarity_score real, rarity_rank integer, unique_attribute_count integer, pk integer )\nCREATE TABLE nft_collections ( blockchain text, contract_address text, name text, symbol text, deploy_block_number bigint, deploy_block_time bigint, erc_type text, owner text, traits text, description text, slug text, media_info text, image_url text, banner_image_url text, updated_at bigint, banner text, token_count bigint, floor_price text, floor_price_symbol text, floor_price_contract text, pk integer )\nCREATE TABLE token_prices ( uuid text, blockchain text, address text, decimals bigint, symbol text, price real, timestamp timestamp )\nCREATE TABLE token_prices_latest ( blockchain text, address text, decimals bigint, symbol text, price real, timestamp timestamp )\nCREATE TABLE token_balances ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply decimal, amount decimal )\nCREATE TABLE token_info ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text )\nCREATE TABLE token_activities ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE mud_holesky_redstone ( address text, table_id text, key_bytes text, key0 text, key1 text, static_data text, encoded_lengths text, dynamic_data text, is_deleted boolean, block_number bigint, log_index bigint )\nCREATE TABLE token_balances_bitcoin ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply text, amount text )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_balances_avalanche ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply decimal, amount decimal )\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id text )\n"}
{"conversations": [{"role": "user", "content": "List vehicle_id, make, model, and capacity for all vehicles acquired in 2023."}, {"role": "assistant", "content": "SELECT vehicle_id, make, model, capacity\nFROM transportation.vehicles\nWHERE acquisition_date >= '2023-01-01'\n  AND acquisition_date <= '2023-12-31';"}, {"role": "user", "content": "Now include only vehicles with capacity greater than or equal to 50 and order by capacity descending."}, {"role": "assistant", "content": "SELECT vehicle_id, make, model, capacity\nFROM transportation.vehicles\nWHERE acquisition_date >= '2023-01-01'\n  AND acquisition_date <= '2023-12-31'\n  AND capacity >= 50\nORDER BY capacity DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles ( vehicle_id text, license_plate text, vin text, make text, model text, year integer, type text, capacity integer, fuel_type text, status text, depot_id text, acquisition_date date )\nCREATE TABLE transportation.drivers ( driver_id text, employee_id text, first_name text, last_name text, license_number text, license_expiry_date date, contact_number text, email text, hire_date date, status text )\nCREATE TABLE transportation.routes ( route_id text, route_number text, description text, origin_location_id text, destination_location_id text, distance_km numeric, estimated_duration_minutes integer, type text )\nCREATE TABLE transportation.passengers ( passenger_id text, first_name text, last_name text, email text, phone_number text, date_of_birth date, loyalty_program_id text, created_at timestamp )\nCREATE TABLE transportation.bookings ( booking_id text, passenger_id text, trip_id text, seat_number text, booking_time timestamp, status text, fare numeric, payment_transaction_id text, special_requests text )\n"}
{"conversations": [{"role": "user", "content": "What is the current market price of a Boeing 737 MAX aircraft?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to the current market price of aircraft models. The data I have is limited to technical specifications and general information about aircraft models such as passenger capacity, range, and status. For pricing information, you may need to consult with manufacturers or industry reports."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE manufacturing.aircraft_models (\n    model_id character varying(64) NOT NULL,  -- unique identifier for the aircraft model\n    model_name character varying(128) NOT NULL, -- commercial name of the model (e.g., 737 MAX, A320neo)\n    manufacturer character varying(128) NOT NULL, -- manufacturer name (e.g., Boeing, Airbus)\n    passenger_capacity integer, -- typical passenger capacity\n    max_range_km integer, -- maximum flight range in kilometers\n    engine_type character varying(100), -- type of engines used\n    wingspan_m numeric(6,2), -- wingspan in meters\n    status character varying(50) NOT NULL, -- e.g., 'In Production', 'Development', 'Discontinued'\n    first_flight_date date, -- date of the model's first flight\n    PRIMARY KEY (model_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Show the full names and contact emails of all citizens who have applied for services with a standard fee greater than 100."}, {"role": "assistant", "content": "SELECT c.first_name || ' ' || c.last_name AS full_name, c.contact_email\nFROM government_services.citizens c\nJOIN government_services.services s ON c.citizen_id IS NOT NULL -- Replace with actual application linking table if exists\nWHERE s.standard_fee > 100;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id character varying(64) NOT NULL, national_id_number character varying(128) NOT NULL UNIQUE, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, gender character varying(20), primary_address text NOT NULL, contact_email character varying(128) UNIQUE, contact_phone character varying(32), registration_date timestamp NOT NULL, is_verified boolean DEFAULT false, PRIMARY KEY (citizen_id) )\nCREATE TABLE government_services.services ( service_id.text, agency_id.text, service_name.text, description.text, category.text, eligibility_criteria.text, standard_fee.numeric, average_processing_time_days.integer, is_active.boolean, online_application_url.text )\n"}
{"conversations": [{"role": "user", "content": "Find all policies that were cancelled due to 'Non-payment'. Show the policy number, cancellation date, and premium amount for these policies."}, {"role": "assistant", "content": "SELECT policy_number ,  cancellation_date ,  premium_amount FROM insurance.policies WHERE status = 'Cancelled' AND cancellation_reason = 'Non-payment'"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.policies (\n    policy_id character varying(64) NOT NULL, -- unique identifier for the policy\n    customer_id character varying(64) NOT NULL, -- identifier for the policyholder (FK to customers)\n    product_id character varying(64) NOT NULL, -- identifier for the insurance product (FK to insurance_products)\n    agent_id character varying(64), -- identifier for the agent who sold the policy (FK to agents)\n    policy_number character varying(100) NOT NULL UNIQUE, -- customer-facing policy number\n    start_date date NOT NULL, -- date the policy coverage begins\n    end_date date NOT NULL, -- date the policy coverage ends\n    premium_amount numeric(12, 2) NOT NULL, -- total premium for the policy term\n    coverage_limit numeric(15, 2) NOT NULL, -- maximum amount covered\n    deductible numeric(10, 2) NOT NULL, -- amount customer pays before coverage kicks in\n    status character varying(30) NOT NULL, -- e.g., Active, Expired, Cancelled, Pending\n    issued_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the policy was issued\n    cancellation_date date,\n    cancellation_reason text,\n    PRIMARY KEY (policy_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Find the average score for each player who has participated in game sessions."}, {"role": "assistant", "content": "SELECT player_id, AVG(score) AS avg_score\nFROM gaming_technology.game_sessions\nGROUP BY player_id;"}, {"role": "user", "content": "Now show only players who have also unlocked at least one achievement."}, {"role": "assistant", "content": "SELECT gs.player_id, AVG(gs.score) AS avg_score\nFROM gaming_technology.game_sessions gs\nWHERE gs.player_id IN (\n    SELECT DISTINCT pa.player_id FROM gaming_technology.player_achievements pa\n)\nGROUP BY gs.player_id;"}, {"role": "user", "content": "Can you also include the total number of achievements each player has unlocked?"}, {"role": "assistant", "content": "SELECT gs.player_id, AVG(gs.score) AS avg_score, COUNT(pa.achievement_id) AS total_achievements\nFROM gaming_technology.game_sessions gs\nJOIN gaming_technology.player_achievements pa ON gs.player_id = pa.player_id\nGROUP BY gs.player_id;"}, {"role": "user", "content": "I received duplicate player rows. Can you fix the SQL so the achievement count is correct for each player?"}, {"role": "assistant", "content": "SELECT gs.player_id, AVG(gs.score) AS avg_score, (\n    SELECT COUNT(DISTINCT pa.achievement_id)\n    FROM gaming_technology.player_achievements pa\n    WHERE pa.player_id = gs.player_id\n) AS total_achievements\nFROM gaming_technology.game_sessions gs\nWHERE gs.player_id IN (\n    SELECT DISTINCT player_id FROM gaming_technology.player_achievements\n)\nGROUP BY gs.player_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.game_sessions ( session_id uuid, player_id uuid, game_id uuid, server_id uuid, start_time timestamp with time zone, end_time timestamp with time zone, duration_seconds integer, score integer, session_data jsonb )\nCREATE TABLE gaming_technology.player_achievements ( player_achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), player_id uuid NOT NULL, achievement_id uuid NOT NULL, unlocked_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (player_achievement_id), UNIQUE (player_id, achievement_id) )\n"}
{"conversations": [{"role": "user", "content": "What is the maintenance schedule for platform 3 at station DEF for the next month?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to the maintenance schedule for platforms. The data I have only includes static information about platform details such as ID, station, number, track, status, length, and accessibility. For maintenance schedules, you may need to consult the station management or relevant department."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.platforms ( platform_id text, station_id text, platform_number text, track_number text, status text, length_meters numeric, accessible boolean )\n"}
{"conversations": [{"role": "user", "content": "List all wallet addresses that hold any NFT currently. Show the wallet address and the count of distinct token IDs they hold."}, {"role": "assistant", "content": "SELECT wallet_address, COUNT(DISTINCT token_id) FROM nft_holders GROUP BY wallet_address;"}, {"role": "user", "content": "Filter the list to only include wallets that hold more than 5 unique NFTs."}, {"role": "assistant", "content": "SELECT wallet_address, COUNT(DISTINCT token_id) FROM nft_holders GROUP BY wallet_address HAVING COUNT(DISTINCT token_id) > 5;"}, {"role": "user", "content": "Order the results by the count of unique NFTs held in descending order."}, {"role": "assistant", "content": "SELECT wallet_address, COUNT(DISTINCT token_id) AS unique_nft_count FROM nft_holders GROUP BY wallet_address HAVING COUNT(DISTINCT token_id) > 5 ORDER BY unique_nft_count DESC;"}, {"role": "user", "content": "Limit the output to the top 20 wallets."}, {"role": "assistant", "content": "SELECT wallet_address, COUNT(DISTINCT token_id) AS unique_nft_count FROM nft_holders GROUP BY wallet_address HAVING COUNT(DISTINCT token_id) > 5 ORDER BY unique_nft_count DESC LIMIT 20;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp timestamp(6) NOT NULL, block_number bigint NOT NULL, transaction_hash varchar NOT NULL, transaction_index bigint NOT NULL, from_address varchar NOT NULL, contract_address varchar NOT NULL, symbol varchar NOT NULL, total_supply varchar NOT NULL, name varchar NOT NULL, decimals bigint NOT NULL, is_erc20 integer NOT NULL, is_erc721 integer NOT NULL, is_erc1155 integer NOT NULL, is_proxy integer NOT NULL, extra_info varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE erc1155_approval_for_all ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar(66) NOT NULL, log_index integer NOT NULL, contract_address varchar(42) NOT NULL )\nCREATE TABLE erc20_balances ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE erc20_balances_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_holders ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, token_id varchar NOT NULL, contract_type varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE nft_holder_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, token_id varchar NOT NULL, contract_type varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE sui_coins_metadata ( object_id varchar NOT NULL, coin_type varchar NOT NULL, status varchar NOT NULL, decimals bigint NOT NULL, description varchar NOT NULL, icon_url varchar NOT NULL, symbol varchar NOT NULL, name varchar NOT NULL )\nCREATE TABLE sui_nfts ( object_id varchar NOT NULL, status varchar NOT NULL, collection_type varchar NOT NULL, package_id varchar NOT NULL, previous_transaction varchar NOT NULL, display varchar NOT NULL, owner varchar NOT NULL, name varchar NOT NULL )\nCREATE TABLE nft_collections ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, name varchar NOT NULL, symbol varchar NOT NULL, deploy_block_number bigint NOT NULL, deploy_block_time bigint NOT NULL, erc_type varchar NOT NULL, owner varchar NOT NULL, traits varchar NOT NULL, description varchar NOT NULL, slug varchar NOT NULL, media_info varchar NOT NULL, image_url varchar NOT NULL, banner_image_url varchar NOT NULL, updated_at bigint NOT NULL, banner varchar NOT NULL, token_count bigint NOT NULL, floor_price varchar NOT NULL, floor_price_symbol varchar NOT NULL, floor_price_contract varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_prices ( uuid varchar(36) NOT NULL, blockchain varchar(36) NOT NULL, address varchar(42) NOT NULL, decimals bigint NOT NULL, symbol varchar(36) NOT NULL, price real NOT NULL, timestamp timestamp(6) NOT NULL )\nCREATE TABLE token_prices_latest ( blockchain varchar(36) NOT NULL, address varchar(42) NOT NULL, decimals bigint NOT NULL, symbol varchar(36) NOT NULL, price real NOT NULL, timestamp timestamp(6) NOT NULL )\nCREATE TABLE erc20_approval ( block_number bigint NOT NULL, block_timestamp timestamp(6) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar NOT NULL, log_index integer NOT NULL, contract_address varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_balances ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar NOT NULL, wallet_address varchar(42) NOT NULL, total_supply decimal(38,0) NOT NULL, amount decimal(38,0) NOT NULL )\nCREATE TABLE token_info ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE token_activities ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar NOT NULL, tick varchar NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(42) NOT NULL, to_address varchar(42) NOT NULL )\nCREATE TABLE mud_holesky_redstone ( address varchar NOT NULL, table_id varchar NOT NULL, key_bytes varchar NOT NULL, key0 varchar NOT NULL, key1 varchar NOT NULL, static_data varchar NOT NULL, encoded_lengths varchar NOT NULL, dynamic_data varchar NOT NULL, is_deleted boolean NOT NULL, block_number bigint NOT NULL, log_index bigint NOT NULL )\nCREATE TABLE token_balances_bitcoin ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar(255) NOT NULL, wallet_address varchar(42) NOT NULL, total_supply varchar NOT NULL, amount varchar NOT NULL )\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar(255) NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar(20) NOT NULL, tick varchar(255) NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(62) NOT NULL, to_address varchar(62) NOT NULL )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar(20) NOT NULL, tick varchar(255) NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(42) NOT NULL, to_address varchar(42) NOT NULL )\nCREATE TABLE token_balances_avalanche ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar(20) NOT NULL, wallet_address varchar(42) NOT NULL, total_supply decimal(38,0) NOT NULL, amount decimal(38,0) NOT NULL )\n"}
{"conversations": [{"role": "user", "content": "Show me the top 5 games by number of online servers in European regions. I want the game title and the server count."}, {"role": "assistant", "content": "SELECT g.title, COUNT(s.server_id) AS server_count\nFROM gaming_technology.games g\nJOIN gaming_technology.servers s ON g.game_id = s.game_id\nWHERE s.region ILIKE 'eu%' AND s.status = 'online'\nGROUP BY g.title\nORDER BY server_count DESC\nLIMIT 5;"}, {"role": "user", "content": "Now include only those games whose average current_players per online server exceeds 100."}, {"role": "assistant", "content": "SELECT g.title,\n       COUNT(s.server_id) AS server_count,\n       AVG(s.current_players)::numeric(10,2) AS avg_players\nFROM gaming_technology.games g\nJOIN gaming_technology.servers s ON g.game_id = s.game_id\nWHERE s.region ILIKE 'eu%' AND s.status = 'online'\nGROUP BY g.title\nHAVING AVG(s.current_players) > 100\nORDER BY server_count DESC\nLIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.players ( player_id uuid PRIMARY KEY, username text, email text, password_hash text, registration_date timestamptz, last_login timestamptz, country_code text, status text, profile_data jsonb )\nCREATE TABLE gaming_technology.games ( game_id uuid PRIMARY KEY, title text, developer_id uuid, publisher_id uuid, genre text, release_date date, description text, platform text, engine text, website text )\nCREATE TABLE gaming_technology.servers ( server_id uuid PRIMARY KEY, game_id uuid, server_name text, region text, ip_address text, port int, current_players int, max_players int, status text, last_heartbeat timestamptz )\nCREATE TABLE gaming_technology.achievements ( achievement_id uuid PRIMARY KEY, game_id uuid, name text, description text, icon_url text, points int, hidden boolean )\nCREATE TABLE gaming_technology.player_achievements ( player_achievement_id uuid PRIMARY KEY, player_id uuid, achievement_id uuid, unlocked_at timestamptz )\nCREATE TABLE gaming_technology.in_game_items ( item_id uuid PRIMARY KEY, game_id uuid, item_name text, item_type text, description text, rarity text, cost_currency text, cost_amount numeric, attributes jsonb )\nCREATE TABLE gaming_technology.player_inventory ( inventory_id uuid PRIMARY KEY, player_id uuid, item_id uuid, quantity int, acquired_at timestamptz, instance_data jsonb )\n"}
{"conversations": [{"role": "user", "content": "List all the appointments that overlap in time for the same location, showing both appointment IDs, their start and end times, and the location."}, {"role": "assistant", "content": "SELECT a1.appointment_id AS appointment_id_1, a2.appointment_id AS appointment_id_2,\n       a1.start_time AS start_1, a1.end_time AS end_1,\n       a2.start_time AS start_2, a2.end_time AS end_2,\n       a1.location\nFROM legal_services.appointments a1\nJOIN legal_services.appointments a2\n  ON a1.location = a2.location\n AND a1.appointment_id < a2.appointment_id\n AND a1.start_time < a2.end_time\n AND a2.start_time < a1.end_time;"}, {"role": "user", "content": "Can you narrow this to only show overlapping appointments that are both in 'Scheduled' status?"}, {"role": "assistant", "content": "SELECT a1.appointment_id AS appointment_id_1, a2.appointment_id AS appointment_id_2,\n       a1.start_time AS start_1, a1.end_time AS end_1,\n       a2.start_time AS start_2, a2.end_time AS end_2,\n       a1.location\nFROM legal_services.appointments a1\nJOIN legal_services.appointments a2\n  ON a1.location = a2.location\n AND a1.appointment_id < a2.appointment_id\n AND a1.start_time < a2.end_time\n AND a2.start_time < a1.end_time\nWHERE a1.status = 'Scheduled' AND a2.status = 'Scheduled';"}, {"role": "user", "content": "Also, please only show overlaps that last longer than 10 minutes."}, {"role": "assistant", "content": "SELECT a1.appointment_id AS appointment_id_1, a2.appointment_id AS appointment_id_2,\n       a1.start_time AS start_1, a1.end_time AS end_1,\n       a2.start_time AS start_2, a2.end_time AS end_2,\n       a1.location\nFROM legal_services.appointments a1\nJOIN legal_services.appointments a2\n  ON a1.location = a2.location\n AND a1.appointment_id < a2.appointment_id\n AND a1.start_time < a2.end_time\n AND a2.start_time < a1.end_time\nWHERE a1.status = 'Scheduled' AND a2.status = 'Scheduled'\n  AND EXTRACT(EPOCH FROM (LEAST(a1.end_time, a2.end_time) - GREATEST(a1.start_time, a2.start_time))) > 600;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.appointments ( appointment_id.text, client_id.text, lawyer_id.text, case_id.text, start_time.timestamp, end_time.timestamp, location.text, subject.text, notes.text, status.text, created_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "Find all wallets created by users in the last 7 days along with any tokens that have a total supply greater than 10 million, showing the wallet address and token details."}, {"role": "assistant", "content": "SELECT w.address AS wallet_address, t.token_name, t.token_symbol, t.total_supply, t.contract_address FROM web3.wallets w JOIN web3.tokens t ON t.total_supply > 10000000 WHERE w.created_at >= CURRENT_DATE - INTERVAL '7 days';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.tokens ( token_id character varying(64) NOT NULL, contract_address character varying(128) NOT NULL, token_name character varying(128) NOT NULL, token_symbol character varying(32) NOT NULL, decimals integer NOT NULL, total_supply numeric(38,14) NOT NULL, PRIMARY KEY (token_id) )\nCREATE TABLE web3.wallets ( wallet_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, address character varying(128) NOT NULL, private_key text NOT NULL, created_at timestamp NOT NULL, PRIMARY KEY (wallet_id) )\n"}
{"conversations": [{"role": "user", "content": "I want to identify pairs of bookings that share the same payment_transaction_id, showing both booking IDs and the payment_transaction_id."}, {"role": "assistant", "content": "SELECT b1.booking_id AS booking1, b2.booking_id AS booking2, b1.payment_transaction_id\nFROM transportation.bookings b1\nJOIN transportation.bookings b2\n  ON b1.payment_transaction_id = b2.payment_transaction_id\n  AND b1.booking_id < b2.booking_id;"}, {"role": "user", "content": "Now limit the results to only include pairs where both bookings have a status of 'Completed'."}, {"role": "assistant", "content": "SELECT b1.booking_id AS booking1, b2.booking_id AS booking2, b1.payment_transaction_id\nFROM transportation.bookings b1\nJOIN transportation.bookings b2\n  ON b1.payment_transaction_id = b2.payment_transaction_id\n  AND b1.booking_id < b2.booking_id\nWHERE b1.status = 'Completed'\n  AND b2.status = 'Completed';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.bookings ( booking_id.text, passenger_id.text, trip_id.text, seat_number.text, booking_time.timestamp, status.text, fare.numeric, payment_transaction_id.text, special_requests.text )\n"}
{"conversations": [{"role": "user", "content": "List the first and last name of each citizen along with the city and state of the service location for their agency."}, {"role": "assistant", "content": "SELECT c.first_name, c.last_name, sl.city, sl.state\nFROM government_services.citizens c\nJOIN government_services.payments p ON c.citizen_id = p.citizen_id\nJOIN government_services.employees e ON p.application_id IS NOT NULL AND e.agency_id IS NOT NULL\nJOIN government_services.service_locations sl ON e.agency_id = sl.agency_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id text, national_id_number text, first_name text, last_name text, date_of_birth date, gender text, primary_address text, contact_email text, contact_phone text, registration_date timestamp, is_verified boolean )\nCREATE TABLE government_services.payments ( payment_id text, application_id text, citizen_id text, service_id text, amount numeric, currency text, payment_method text, payment_provider_reference text, payment_timestamp timestamp, status text, notes text )\nCREATE TABLE government_services.employees ( employee_id text, agency_id text, first_name text, last_name text, job_title text, department text, work_email text, work_phone text, hire_date date, termination_date date, access_level text, manager_employee_id text )\nCREATE TABLE government_services.service_locations ( location_id text, agency_id text, location_name text, address text, city text, state text, postal_code text, latitude numeric, longitude numeric, operating_hours text, contact_phone text, is_accessible boolean )\n"}
{"conversations": [{"role": "user", "content": "What are the safety ratings or crash statistics for the Boeing 787 Dreamliner?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to safety ratings or crash statistics for specific aircraft models like the Boeing 787 Dreamliner. My data is limited to the information in the aircraft_models table, which includes details such as model name, manufacturer, passenger capacity, and technical specifications. For safety-related information, I recommend consulting official aviation authorities or safety reports."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE manufacturing.aircraft_models ( model_id text, model_name text, manufacturer text, passenger_capacity integer, max_range_km integer, engine_type text, wingspan_m numeric, status text, first_flight_date date )\n"}
{"conversations": [{"role": "user", "content": "For each vehicle, list its vehicle_id, license_plate, and any older vehicle of the same type (showing older_vehicle_id and older year)."}, {"role": "assistant", "content": "SELECT cur.vehicle_id,\n       cur.license_plate,\n       old.vehicle_id AS older_vehicle_id,\n       old.year       AS older_vehicle_year\nFROM transportation.vehicles cur\nJOIN transportation.vehicles old\n  ON cur.type = old.type\n AND old.year < cur.year\nORDER BY cur.vehicle_id, old.year DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles (\n    vehicle_id character varying(64) NOT NULL,  -- unique identifier for the vehicle\n    license_plate character varying(32) NOT NULL UNIQUE, -- vehicle license plate\n    vin character varying(17) UNIQUE, -- vehicle identification number\n    make character varying(64) NOT NULL, -- manufacturer of the vehicle\n    model character varying(64) NOT NULL, -- model of the vehicle\n    year integer NOT NULL, -- manufacturing year\n    type character varying(32) NOT NULL, -- type of vehicle (e.g., Bus, Train, Truck, Car, Van)\n    capacity integer, -- passenger or cargo capacity\n    fuel_type character varying(32) NOT NULL, -- e.g., Diesel, Gasoline, Electric, Hydrogen\n    status character varying(32) NOT NULL, -- e.g., Active, Maintenance, Decommissioned\n    depot_id character varying(64), -- identifier of the home depot/base\n    acquisition_date date, -- date the vehicle was acquired\n    PRIMARY KEY (vehicle_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Get the number of documents for each case, showing case_id and document count, ordered by count descending."}, {"role": "assistant", "content": "SELECT case_id,\n       COUNT(*) AS document_count\nFROM legal_services.documents\nGROUP BY case_id\nORDER BY document_count DESC;"}, {"role": "user", "content": "Actually, only count documents of type 'Evidence'."}, {"role": "assistant", "content": "SELECT case_id,\n       COUNT(*) AS evidence_count\nFROM legal_services.documents\nWHERE document_type = 'Evidence'\nGROUP BY case_id\nORDER BY evidence_count DESC;"}, {"role": "user", "content": "Also, include the case_name from the cases table."}, {"role": "assistant", "content": "SELECT d.case_id,\n       c.case_name,\n       COUNT(*) AS evidence_count\nFROM legal_services.documents d\nJOIN legal_services.cases c ON d.case_id = c.case_id\nWHERE d.document_type = 'Evidence'\nGROUP BY d.case_id, c.case_name\nORDER BY evidence_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.clients ( client_id text PRIMARY KEY, first_name text, last_name text, company_name text, email text UNIQUE, phone text, address text, date_registered timestamp, status text )\nCREATE TABLE legal_services.cases ( case_id text, case_number text, case_name text, client_id text, lead_lawyer_id text, case_type text, status text, date_opened timestamp, date_closed timestamp, description text, court_jurisdiction text )\nCREATE TABLE legal_services.documents ( document_id.text, case_id.text, document_name.text, document_type.text, storage_path.text, uploaded_by_lawyer_id.text, upload_timestamp.timestamp, version.integer, description.text )\nCREATE TABLE legal_services.time_entries ( entry_id text PRIMARY KEY, case_id text, lawyer_id text, date_worked date, hours_spent numeric, billing_rate numeric, description text, is_billable bool, is_billed bool, invoice_id text, created_at timestamp )\nCREATE TABLE legal_services.invoices ( invoice_id text PRIMARY KEY, invoice_number text UNIQUE, client_id text, case_id text, issue_date date, due_date date, total_amount numeric, amount_paid numeric, status text, payment_date timestamp, notes text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show the plan name and insurance provider for all insurance plans along with the total number of unique patients enrolled in each plan."}, {"role": "assistant", "content": "SELECT ip.plan_name, ip.insurance_provider, COUNT(DISTINCT pi.patient_id) AS enrolled_patient_count\nFROM healthcare.insurance_plans ip\nJOIN healthcare.patients_insurance pi ON ip.plan_id = pi.plan_id\nGROUP BY ip.plan_name, ip.insurance_provider;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id text, first_name text, last_name text, date_of_birth date, gender text, address text, phone_number text, email text, emergency_contact_name text, emergency_contact_phone text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.doctors ( doctor_id text, first_name text, last_name text, specialty text, license_number text, phone_number text, email text, hospital_affiliation_id text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.appointments (\n    appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    doctor_id character varying(64) NOT NULL, -- FK to doctors table\n    appointment_time timestamp with time zone NOT NULL, -- date and time of the appointment\n    duration_minutes integer NOT NULL, -- expected duration in minutes\n    reason text, -- reason for the visit\n    status character varying(32) NOT NULL, -- e.g., Scheduled, Completed, Cancelled, No-show\n    location_id character varying(64), -- FK to a potential locations/clinics table\n    notes text, -- notes related to scheduling\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (appointment_id)\n)\nCREATE TABLE healthcare.medical_records ( record_id text PRIMARY KEY, patient_id text, appointment_id text, doctor_id text, record_date timestamp, chief_complaint text, present_illness_history text, past_medical_history text, physical_examination_notes text, assessment text, treatment_plan text, vitals text, created_at timestamp )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id character varying(64) NOT NULL, record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, doctor_id character varying(64) NOT NULL, diagnosis_code character varying(20) NOT NULL, code_type character varying(10) NOT NULL DEFAULT 'ICD-10', description text, diagnosis_date date NOT NULL, status character varying(32) NOT NULL, is_chronic boolean DEFAULT false, PRIMARY KEY (diagnosis_id) )\nCREATE TABLE healthcare.medications (\n    medication_id character varying(64) NOT NULL, -- unique identifier for the medication type\n    medication_name character varying(255) NOT NULL, -- common or brand name\n    generic_name character varying(255), -- generic chemical name\n    manufacturer character varying(100), -- drug manufacturer\n    ndc_code character varying(20) UNIQUE, -- National Drug Code (optional but useful)\n    description text, -- description of the medication\n    PRIMARY KEY (medication_id)\n)\nCREATE TABLE healthcare.prescriptions ( prescription_id text, record_id text, patient_id text, doctor_id text, medication_id text, dosage text, frequency text, route text, start_date date, end_date date, quantity_dispensed numeric, refills_allowed integer, prescription_date timestamp )\nCREATE TABLE healthcare.insurance_plans ( plan_id.text, plan_name.text, insurance_provider.text, plan_type.text, contact_phone.text, website.text )\n"}
{"conversations": [{"role": "user", "content": "Show me the top 5 NFT collections with the highest floor price on Ethereum, along with their names and contract addresses, but only include collections with more than 5000 tokens."}, {"role": "assistant", "content": "SELECT nc.name, nc.contract_address, nc.floor_price FROM nft_collections nc WHERE nc.blockchain = 'Ethereum' AND nc.token_count > 5000 ORDER BY CAST(nc.floor_price AS decimal) DESC LIMIT 5;"}, {"role": "user", "content": "Can you join this with the nft_metadata table to include the average rarity score for these collections?"}, {"role": "assistant", "content": "SELECT nc.name, nc.contract_address, nc.floor_price, AVG(nm.rarity_score) as avg_rarity_score FROM nft_collections nc JOIN nft_metadata nm ON nc.contract_address = nm.contract_address WHERE nc.blockchain = 'Ethereum' AND nc.token_count > 5000 GROUP BY nc.name, nc.contract_address, nc.floor_price ORDER BY CAST(nc.floor_price AS decimal) DESC LIMIT 5;"}, {"role": "user", "content": "Now filter these results to only show collections with an average rarity score above 75."}, {"role": "assistant", "content": "SELECT nc.name, nc.contract_address, nc.floor_price, AVG(nm.rarity_score) as avg_rarity_score FROM nft_collections nc JOIN nft_metadata nm ON nc.contract_address = nm.contract_address WHERE nc.blockchain = 'Ethereum' AND nc.token_count > 5000 GROUP BY nc.name, nc.contract_address, nc.floor_price HAVING AVG(nm.rarity_score) > 75 ORDER BY CAST(nc.floor_price AS decimal) DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp timestamp(6) NOT NULL, block_number bigint NOT NULL, transaction_hash varchar NOT NULL, transaction_index bigint NOT NULL, from_address varchar NOT NULL, contract_address varchar NOT NULL, symbol varchar NOT NULL, total_supply varchar NOT NULL, name varchar NOT NULL, decimals bigint NOT NULL, is_erc20 integer NOT NULL, is_erc721 integer NOT NULL, is_erc1155 integer NOT NULL, is_proxy integer NOT NULL, extra_info varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE erc1155_approval_for_all ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar(66) NOT NULL, log_index integer NOT NULL, contract_address varchar(42) NOT NULL )\nCREATE TABLE erc20_balances ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE erc20_balances_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_holders ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, token_id varchar NOT NULL, contract_type varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE nft_holder_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, token_id varchar NOT NULL, contract_type varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_coins_metadata ( object_id varchar NOT NULL, coin_type varchar NOT NULL, status varchar NOT NULL, decimals bigint NOT NULL, description varchar NOT NULL, icon_url varchar NOT NULL, symbol varchar NOT NULL, name varchar NOT NULL )\nCREATE TABLE sui_nfts ( object_id varchar NOT NULL, status varchar NOT NULL, collection_type varchar NOT NULL, package_id varchar NOT NULL, previous_transaction varchar NOT NULL, display varchar NOT NULL, owner varchar NOT NULL, name varchar NOT NULL )\nCREATE TABLE nft_metadata ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, token_id varchar NOT NULL, contract_name varchar NOT NULL, erc_type varchar NOT NULL, amount bigint NOT NULL, minter varchar NOT NULL, owner varchar NOT NULL, mint_block_number bigint NOT NULL, mint_time bigint NOT NULL, mint_transaction_hash varchar NOT NULL, mint_price varchar NOT NULL, token_uri varchar NOT NULL, metadata varchar NOT NULL, name varchar NOT NULL, image_uri varchar NOT NULL, traits varchar NOT NULL, updated_at bigint NOT NULL, status varchar NOT NULL, rarity_score real NOT NULL, rarity_rank integer NOT NULL, unique_attribute_count integer NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_collections ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, name varchar NOT NULL, symbol varchar NOT NULL, deploy_block_number bigint NOT NULL, deploy_block_time bigint NOT NULL, erc_type varchar NOT NULL, owner varchar NOT NULL, traits varchar NOT NULL, description varchar NOT NULL, slug varchar NOT NULL, media_info varchar NOT NULL, image_url varchar NOT NULL, banner_image_url varchar NOT NULL, updated_at bigint NOT NULL, banner varchar NOT NULL, token_count bigint NOT NULL, floor_price varchar NOT NULL, floor_price_symbol varchar NOT NULL, floor_price_contract varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_prices ( uuid varchar(36) NOT NULL, blockchain varchar(36) NOT NULL, address varchar(42) NOT NULL, decimals bigint NOT NULL, symbol varchar(36) NOT NULL, price real NOT NULL, timestamp timestamp(6) NOT NULL )\nCREATE TABLE token_prices_latest ( blockchain varchar(36) NOT NULL, address varchar(42) NOT NULL, decimals bigint NOT NULL, symbol varchar(36) NOT NULL, price real NOT NULL, timestamp timestamp(6) NOT NULL )\nCREATE TABLE erc20_approval ( block_number bigint NOT NULL, block_timestamp timestamp(6) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar NOT NULL, log_index integer NOT NULL, contract_address varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_balances ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar NOT NULL, wallet_address varchar(42) NOT NULL, total_supply decimal(38,0) NOT NULL, amount decimal(38,0) NOT NULL )\nCREATE TABLE token_info ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar(255) NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar(20) NOT NULL, tick varchar(255) NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(62) NOT NULL, to_address varchar(62) NOT NULL )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar(20) NOT NULL, tick varchar(255) NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(42) NOT NULL, to_address varchar(42) NOT NULL )\nCREATE TABLE token_balances_avalanche ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar(20) NOT NULL, wallet_address varchar(42) NOT NULL, total_supply decimal(38,0) NOT NULL, amount decimal(38,0) NOT NULL )\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar(20) NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL, minted decimal(38,0) NOT NULL, holders decimal(38,0) NOT NULL, txs decimal(38,0) NOT NULL, updated_timestamp timestamp(3) NOT NULL, completed_timestamp timestamp(3) NOT NULL, id varchar(255) NOT NULL )\n"}
{"conversations": [{"role": "user", "content": "Show each citizen's first and last notification IDs based on sent_at."}, {"role": "assistant", "content": "WITH bounds AS (\n  SELECT citizen_id,\n         MIN(sent_at) AS first_sent,\n         MAX(sent_at) AS last_sent\n  FROM government_services.notifications\n  GROUP BY citizen_id\n)\nSELECT n1.citizen_id,\n       n1.notification_id AS first_notification_id,\n       n2.notification_id AS last_notification_id\nFROM bounds b\nJOIN government_services.notifications n1\n  ON n1.citizen_id = b.citizen_id\n AND n1.sent_at = b.first_sent\nJOIN government_services.notifications n2\n  ON n2.citizen_id = b.citizen_id\n AND n2.sent_at = b.last_sent;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.notifications ( notification_id text PRIMARY KEY, citizen_id text, application_id text, message_subject text, message_body text, channel text, sent_at timestamp, status text, related_entity_type text, related_entity_id text )\n"}
{"conversations": [{"role": "user", "content": "Show me the top 5 projects by valuation that completed fundraising rounds in the last 12 months, along with their token symbol and price from the token_basic_info table."}, {"role": "assistant", "content": "SELECT pfr.project_name, pfr.valuation, tbi.token_symbol, tbi.price FROM project_fundraising_record pfr LEFT JOIN token_basic_info tbi ON pfr.project_name = tbi.token_name WHERE pfr.investment_date >= DATE_SUB(CURRENT_DATE, INTERVAL 12 MONTH) ORDER BY pfr.valuation DESC LIMIT 5;"}, {"role": "user", "content": "Can you also include the 24-hour trading volume for these projects' tokens and filter to only include projects with valuation over $100 million?"}, {"role": "assistant", "content": "SELECT pfr.project_name, pfr.valuation, tbi.token_symbol, tbi.price, tbi.total_volume FROM project_fundraising_record pfr LEFT JOIN token_basic_info tbi ON pfr.project_name = tbi.token_name WHERE pfr.investment_date >= DATE_SUB(CURRENT_DATE, INTERVAL 12 MONTH) AND pfr.valuation > 100000000 ORDER BY pfr.valuation DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\n \"CREATE TABLE project_fundraising_record (\",\n    \"id character varying(32) NOT NULL,  -- fundraising record id\",\n    \"project_id character varying(32) NOT NULL, -- the invested project's id\",\n    \"project_name character varying(128) NOT NULL, -- name of the invested project\",\n    \"rounds_name character varying(32), -- name of the fundraising round\",\n    \"investment_value numeric(38,14), -- amount of the fundraising in USD\",\n    \"investment_date character varying(128), -- the date of the investment happened\",\n    \"introduction character varying(128), -- the introduction of the invested project\",\n    \"valuation numeric(38,14), -- the valuation of the project in USD when invested\",\n\nCREATE TABLE token_basic_info ( coin_id character varying(100) NOT NULL, -- the id of the token token_name character varying(100) NOT NULL, -- the token's name token_symbol character varying(100) NOT NULL, -- the token's symbol token_address character varying(100) NOT NULL, -- the token's address chain text, -- the chain that the token resides price double precision, -- the current price of the token price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days highest_price_24h double precision, -- the highest price of the token in 24 hours lowest_price_24h double precision,  -- the lowest price of the token in 24 hours market_cap double precision, -- the market cap of the token market_cap_rank bigint, -- the rank of the token market cap in desc market_cap_change_percentage_24h text, -- the percentage of market cap changes in 24 hours total_volume text, -- the trade volum of the token both in decentralized exchange(DEX) and centralized exchange(CEX) narrative text, -- the category or narrative of the token trend_rank biging, -- the trending rank of the token, value 1 expresses the most popular token. ,PRIMARY KEY (coin_id, chain) )\nCREATE TABLE narrative_info ( narrative character varying(512) NOT NULL, -- the id of narrative top_3_coins text, -- the top 3 tokens in the narrative price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour in the narrative price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours in the narrative price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days in the narrative market_cap double precision, -- the market cap of the narrative volume_24h double precision, -- the trade volume of the narrative trend_rank bigint, -- the trending rank of the narrative, value 1 expresses the most popular narrative token_num bigint, -- total token number in the narrative ,PRIMARY KEY (narrative) )\nCREATE TABLE token_dexpool_info ( pair_address character varying(512) NOT NULL, token_name character varying(100) NOT NULL, token_symbol character varying(100) NOT NULL, chain text, price double precision, price_change_percentage_1h double precision, price_change_percentage_6h double precision, price_change_percentage_24h double precision, makers_24h double precision, volume_24h double precision, liquidity double precision, market_cap double precision, trend_rank bigint )\nCREATE TABLE smart_money_profit ( address character varying(100) NOT NULL, rank INT, profit numeric(38,6), roi numeric(38,2), realized_ratio numeric(38,2), most_profit_token character varying(100), last_trade_time character varying(100), chain character varying(100) )\n  \"CREATE TABLE smart_money_token_performance (\",\n    \"token_address character varying(100) NOT NULL, -- the token's address\",\n    \"token_symbol character varying(100), -- the tokens's symbol\",\n    \"pnl numeric(38,2), -- the profit users made on this token\",\n    \"net_flow numeric(38,2), -- the netflow of the token, means the money user spent minus the the money user sold of this token\",\n    \"avg_cost numeric(38,16), -- the average cost price of user spent on this token\",\n    \"price double precision, -- the current price of the token\",\n    \"realized_ratio numeric(10,2), -- the ratio user sold of the token\",\n    \"roi numeric(10,2), -- the roi users made of this token\",\n    \"chain character varying(100), -- the chain that the token resides\",\n    \"PRIMARY KEY (token_address, chain));\",\n\n  \"CREATE TABLE smart_money_token_inflow (\",\n    \"token_address character varying(100) NOT NULL, -- the token's address\",\n    \"token_symbol character varying(100), -- the tokens's symbol\",\n    \"token_amount numeric(38,2), -- the absolute value of the amount if user bought minus  the amount user sold of this token\",\n    \"usd_value numeric(38,2), -- the absolute usd value of the bought token minus sold token\",\n    \"avg_price numeric(38,6), -- the average cost price of user spent on this token\",\n    \"type int, -- the direction of the trade on this token. 1 means buying, 2 means selling\",\n    \"address_amount integer, -- the amount of the user bought this token\",\n    \"narrative character varying(100), -- the category or narrative of the token\",\n    \"chain character varying(100), -- the chain that the token resides\",\n    \",PRIMARY KEY (token_address, chain)\",\n\n"}
{"conversations": [{"role": "user", "content": "Find cases where an address received tokens in one transfer and then sent tokens in another. List the receive transfer_id, the send transfer_id, the address, and both transfer values."}, {"role": "assistant", "content": "SELECT recv.transfer_id AS receive_transfer_id,\n       send.transfer_id AS send_transfer_id,\n       recv.to_address AS address,\n       recv.value       AS received_value,\n       send.value       AS sent_value\nFROM web3.token_transfers recv\nJOIN web3.token_transfers send\n  ON recv.to_address = send.from_address;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.token_transfers (\n    transfer_id character varying(64) NOT NULL,  -- unique identifier for the transfer\n    token_id character varying(64) NOT NULL, -- identifier of the token being transferred\n    from_address character varying(128) NOT NULL, -- address of the sender\n    to_address character varying(128) NOT NULL, -- address of the receiver\n    value numeric(38,14) NOT NULL, -- amount of tokens transferred\n    transaction_id character varying(64) NOT NULL, -- identifier of the transaction containing the transfer\n    log_index integer NOT NULL, -- index of the transfer log in the transaction\n    PRIMARY KEY (transfer_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List all wallets that were created during the hour of the day which saw the highest number of wallet creations. Show the wallet ID, user ID, address, and creation timestamp."}, {"role": "assistant", "content": "WITH HourlyCounts AS (\n    SELECT EXTRACT(HOUR FROM created_at) AS hour, COUNT(*) AS wallet_count\n    FROM web3.wallets\n    GROUP BY 1\n),\nMaxHour AS (\n    SELECT hour\n    FROM HourlyCounts\n    ORDER BY wallet_count DESC\n    LIMIT 1\n)\nSELECT wallet_id, user_id, address, created_at\nFROM web3.wallets\nWHERE EXTRACT(HOUR FROM created_at) = (SELECT hour FROM MaxHour);"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.wallets ( wallet_id text PRIMARY KEY, user_id text, address text, private_key text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show me all documents uploaded by lawyers from law firms located in 'New York'. Include the document name, upload timestamp, the first and last name of the uploading lawyer, and the firm name."}, {"role": "assistant", "content": "SELECT d.document_name, d.upload_timestamp, l.first_name AS lawyer_first_name, l.last_name AS lawyer_last_name, lf.firm_name FROM documents AS d JOIN lawyers AS l ON d.uploaded_by_lawyer_id = l.lawyer_id JOIN law_firms AS lf ON l.firm_id = lf.firm_id WHERE lf.address LIKE '%New York%';"}, {"role": "user", "content": "Okay, but only show documents where the document type is 'Contract'."}, {"role": "assistant", "content": "SELECT d.document_name, d.upload_timestamp, l.first_name AS lawyer_first_name, l.last_name AS lawyer_last_name, lf.firm_name FROM documents AS d JOIN lawyers AS l ON d.uploaded_by_lawyer_id = l.lawyer_id JOIN law_firms AS lf ON l.firm_id = lf.firm_id WHERE lf.address LIKE '%New York%' AND d.document_type = 'Contract';"}, {"role": "user", "content": "Also, sort the results by upload timestamp descending and include the document version."}, {"role": "assistant", "content": "SELECT d.document_name, d.upload_timestamp, d.version, l.first_name AS lawyer_first_name, l.last_name AS lawyer_last_name, lf.firm_name FROM documents AS d JOIN lawyers AS l ON d.uploaded_by_lawyer_id = l.lawyer_id JOIN law_firms AS lf ON l.firm_id = lf.firm_id WHERE lf.address LIKE '%New York%' AND d.document_type = 'Contract' ORDER BY d.upload_timestamp DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.clients ( client_id text PRIMARY KEY, first_name text, last_name text, company_name text, email text UNIQUE, phone text, address text, date_registered timestamp, status text )\nCREATE TABLE legal_services.law_firms ( firm_id text PRIMARY KEY, firm_name text, address text, phone text, website text, founded_date date, managing_partner_id text )\nCREATE TABLE legal_services.documents ( document_id text PRIMARY KEY, case_id text, document_name text, document_type text, storage_path text, uploaded_by_lawyer_id text, upload_timestamp timestamp, version int, description text )\n"}
{"conversations": [{"role": "user", "content": "List the first and last names of employees and the number of services offered by their agency."}, {"role": "assistant", "content": "SELECT e.first_name, e.last_name, COUNT(s.service_id) AS service_count\nFROM government_services.employees e\nLEFT JOIN government_services.services s ON e.agency_id = s.agency_id\nGROUP BY e.employee_id, e.first_name, e.last_name;"}, {"role": "user", "content": "Include only employees whose agency offers more than 3 services."}, {"role": "assistant", "content": "SELECT e.first_name, e.last_name, COUNT(s.service_id) AS service_count\nFROM government_services.employees e\nLEFT JOIN government_services.services s ON e.agency_id = s.agency_id\nGROUP BY e.employee_id, e.first_name, e.last_name\nHAVING COUNT(s.service_id) > 3;"}, {"role": "user", "content": "Add the agency name to the result."}, {"role": "assistant", "content": "SELECT e.first_name, e.last_name, ag.agency_name, COUNT(s.service_id) AS service_count\nFROM government_services.employees e\nJOIN government_services.agencies ag ON e.agency_id = ag.agency_id\nLEFT JOIN government_services.services s ON e.agency_id = s.agency_id\nGROUP BY e.employee_id, e.first_name, e.last_name, ag.agency_name\nHAVING COUNT(s.service_id) > 3;"}, {"role": "user", "content": "Now, only show services that are currently active in the count."}, {"role": "assistant", "content": "SELECT e.first_name, e.last_name, ag.agency_name, COUNT(s.service_id) AS active_service_count\nFROM government_services.employees e\nJOIN government_services.agencies ag ON e.agency_id = ag.agency_id\nLEFT JOIN government_services.services s ON e.agency_id = s.agency_id AND s.is_active = TRUE\nGROUP BY e.employee_id, e.first_name, e.last_name, ag.agency_name\nHAVING COUNT(s.service_id) > 3;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.agencies ( agency_id character varying(64) NOT NULL, agency_name character varying(255) NOT NULL, jurisdiction_level character varying(50) NOT NULL, primary_contact_email character varying(128), main_phone_number character varying(32), website_url character varying(255), established_date date, parent_agency_id character varying(64), PRIMARY KEY (agency_id) )\nCREATE TABLE government_services.services (\n    service_id character varying(64) NOT NULL, -- unique identifier for the service\n    agency_id character varying(64) NOT NULL, -- FK to agencies table\n    service_name character varying(255) NOT NULL, -- name of the service (e.g., Driver's License Renewal)\n    description text,\n    category character varying(100), -- e.g., Licensing, Benefits, Taxation, Permits\n    eligibility_criteria text, -- description of who is eligible\n    standard_fee numeric(10, 2) DEFAULT 0.00, -- typical fee for the service\n    average_processing_time_days integer, -- estimated processing time\n    is_active boolean DEFAULT true, -- whether the service is currently offered\n    online_application_url character varying(255),\n    PRIMARY KEY (service_id)\n)\nCREATE TABLE government_services.applications (\n    application_id character varying(64) NOT NULL, -- unique identifier for the application\n    citizen_id character varying(64) NOT NULL, -- FK to citizens table\n    service_id character varying(64) NOT NULL, -- FK to services table\n    submitted_at timestamp NOT NULL, -- time the application was submitted\n    status character varying(50) NOT NULL, -- e.g., Submitted, Processing, Approved, Rejected, Pending Info\n    last_updated_at timestamp NOT NULL, -- time the status or details last changed\n    assigned_employee_id character varying(64), -- FK to employees table (optional)\n    decision_date date, -- date when a final decision was made\n    notes text, -- internal notes or citizen-provided comments\n    reference_number character varying(100) UNIQUE, -- publicly visible reference number\n    PRIMARY KEY (application_id)\n)\nCREATE TABLE government_services.documents ( document_id text PRIMARY KEY, application_id text, citizen_id text, document_type text, file_reference text, upload_timestamp timestamp, expiry_date date, verification_status text, verified_by_employee_id text, verification_timestamp timestamp )\nCREATE TABLE government_services.employees (\n    employee_id character varying(64) NOT NULL, -- unique identifier for the government employee\n    agency_id character varying(64) NOT NULL, -- FK to agencies table\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    job_title character varying(150) NOT NULL,\n    department character varying(100),\n    work_email character varying(128) NOT NULL UNIQUE,\n    work_phone character varying(32),\n    hire_date date NOT NULL,\n    termination_date date, -- null if currently employed\n    access_level character varying(50), -- Role or permission level\n    manager_employee_id character varying(64), -- FK to self for reporting structure\n    PRIMARY KEY (employee_id)\n)\nCREATE TABLE government_services.appointments ( appointment_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, employee_id character varying(64), location_id character varying(64), service_id character varying(64), scheduled_start_time timestamp NOT NULL, scheduled_end_time timestamp, purpose text NOT NULL, status character varying(30) NOT NULL, booking_method character varying(50), created_at timestamp NOT NULL, notes text, PRIMARY KEY (appointment_id) )\n"}
{"conversations": [{"role": "user", "content": "For the 'DeFi' narrative, what is the average ROI and the total net inflow (usd_value where type=1) from smart money token inflow?"}, {"role": "assistant", "content": "SELECT AVG(sm.roi) AS avg_roi, SUM(smt.usd_value) AS total_net_inflow\nFROM smart_money_token_inflow smt\nJOIN smart_money_profit sm ON smt.chain = sm.chain\nWHERE smt.narrative = 'DeFi' AND smt.type = 1;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_basic_info ( coin_id text, token_name text, token_symbol text, token_address text, chain text, price numeric, price_change_percentage_1h numeric, price_change_percentage_24h numeric, price_change_percentage_7d numeric, highest_price_24h numeric, lowest_price_24h numeric, market_cap numeric, market_cap_rank numeric, market_cap_change_percentage_24h text, total_volume text, narrative text, trend_rank numeric )\nCREATE TABLE narrative_info ( narrative text, top_3_coins text, price_change_percentage_1h numeric, price_change_percentage_24h numeric, price_change_percentage_7d numeric, market_cap numeric, volume_24h numeric, trend_rank numeric, token_num numeric )\nCREATE TABLE cex_token_balance ( snapshot_time text, chain text, address text, exchange text, token_address text, token_symbol text, balance numeric, usd_value numeric, price numeric )\nCREATE TABLE smart_money_profit ( address text, rank numeric, profit numeric, roi numeric, realized_ratio numeric, most_profit_token text, last_trade_time text, chain text )\nCREATE TABLE smart_money_token_inflow ( token_address text, token_symbol text, token_amount numeric, usd_value numeric, avg_price numeric, type numeric, address_amount numeric, narrative text, chain text )\n"}
{"conversations": [{"role": "user", "content": "For each user with at least two wallets, calculate the average time difference in hours between consecutive wallet creations. Return user_id and avg_diff_hours."}, {"role": "assistant", "content": "SELECT user_id, AVG(EXTRACT(EPOCH FROM (created_at - prev_created)) / 3600) AS avg_diff_hours FROM (SELECT user_id, created_at, LAG(created_at) OVER (PARTITION BY user_id ORDER BY created_at) AS prev_created FROM web3.wallets) t WHERE prev_created IS NOT NULL GROUP BY user_id;"}, {"role": "user", "content": "Actually, restrict the results to users whose avg_diff_hours is less than 24 hours and sort by avg_diff_hours ascending."}, {"role": "assistant", "content": "WITH diffs AS (SELECT user_id, EXTRACT(EPOCH FROM (created_at - prev_created)) / 3600 AS diff_hours FROM (SELECT user_id, created_at, LAG(created_at) OVER (PARTITION BY user_id ORDER BY created_at) AS prev_created FROM web3.wallets) sub WHERE prev_created IS NOT NULL) SELECT user_id, AVG(diff_hours) AS avg_diff_hours FROM diffs GROUP BY user_id HAVING AVG(diff_hours) < 24 ORDER BY avg_diff_hours;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.contracts (\n    contract_id character varying(64) NOT NULL,  -- unique identifier for the contract\n    address character varying(128) NOT NULL, -- address of the deployed contract\n    abi text NOT NULL, -- application binary interface of the contract\n    bytecode text NOT NULL, -- bytecode of the contract\n    deployer_address character varying(128) NOT NULL, -- address of the deployer\n    deployed_at timestamp NOT NULL, -- time when the contract was deployed\n    network_id character varying(64) NOT NULL, -- identifier of the network where the contract is deployed\n    status character varying(32) NOT NULL, -- status of the contract (e.g., active, deprecated)\n    PRIMARY KEY (contract_id)\n)\nCREATE TABLE web3.transactions (\n    transaction_id character varying(64) NOT NULL,  -- unique identifier for the transaction\n    from_address character varying(128) NOT NULL, -- address of the sender\n    to_address character varying(128), -- address of the receiver (can be null for contract deployment)\n    value numeric(38,14) NOT NULL, -- value transferred\n    gas_used integer NOT NULL, -- amount of gas used by the transaction\n    gas_price numeric(38,14) NOT NULL, -- price of gas at the time of the transaction\n    block_number integer NOT NULL, -- block number containing the transaction\n    timestamp timestamp NOT NULL, -- time when the transaction was mined\n    input_data text, -- input data of the transaction (can be null)\n    status character varying(32) NOT NULL, -- status of the transaction (e.g., success, failed)\n    nonce integer NOT NULL, -- nonce of the sender at the time of the transaction\n    PRIMARY KEY (transaction_id)\n)\nCREATE TABLE web3.wallets (\n    wallet_id character varying(64) NOT NULL,  -- unique identifier for the wallet\n    user_id character varying(64) NOT NULL, -- identifier of the user owning the wallet\n    address character varying(128) NOT NULL, -- address of the wallet\n    private_key text NOT NULL, -- private key of the wallet\n    created_at timestamp NOT NULL, -- time when the wallet was created\n    PRIMARY KEY (wallet_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List all agents who have been terminated, showing their full name, agency name, and termination date."}, {"role": "assistant", "content": "SELECT first_name, last_name, agency_name, termination_date\nFROM insurance.agents\nWHERE status <> 'Active';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.agents ( agent_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, agency_name character varying(150), license_number character varying(100) NOT NULL UNIQUE, license_state character varying(50) NOT NULL, contact_email character varying(128) UNIQUE, contact_phone character varying(30), hire_date date, termination_date date, status character varying(20) NOT NULL DEFAULT 'Active', commission_rate numeric(5, 4) NOT NULL DEFAULT 0.05, manager_id character varying(64), PRIMARY KEY (agent_id) )\n"}
{"conversations": [{"role": "user", "content": "What is the average number of wallets each user owns?"}, {"role": "assistant", "content": "SELECT\n  AVG(wallet_count) AS avg_wallets_per_user\nFROM (\n  SELECT user_id, COUNT(*) AS wallet_count\n  FROM web3.wallets\n  GROUP BY user_id\n) AS sub;"}, {"role": "user", "content": "Actually, calculate the average only for users who own more than one wallet."}, {"role": "assistant", "content": "SELECT\n  AVG(wallet_count) AS avg_wallets_per_user\nFROM (\n  SELECT user_id, COUNT(*) AS wallet_count\n  FROM web3.wallets\n  GROUP BY user_id\n  HAVING COUNT(*) > 1\n) AS sub;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.wallets ( wallet_id text PRIMARY KEY, user_id text, address text, private_key text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "How many likes were given to comments in June 2024?"}, {"role": "assistant", "content": "SELECT COUNT(*) AS comment_likes_count\nFROM social_media.likes\nWHERE comment_id IS NOT NULL \n  AND DATE_TRUNC('month', created_at) = '2024-06-01';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.comments ( comment_id character varying(64) NOT NULL, post_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, parent_comment_id character varying(64), content text NOT NULL, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (comment_id) )\nCREATE TABLE social_media.likes ( like_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, post_id character varying(64), comment_id character varying(64), created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (like_id), CONSTRAINT unique_user_like UNIQUE (user_id, post_id, comment_id), CONSTRAINT check_like_target CHECK (post_id IS NOT NULL OR comment_id IS NOT NULL) )\nCREATE TABLE social_media.post_hashtags ( post_hashtag_id character varying(64) NOT NULL, post_id character varying(64) NOT NULL, hashtag_id character varying(64) NOT NULL, PRIMARY KEY (post_hashtag_id), CONSTRAINT unique_post_hashtag UNIQUE (post_id, hashtag_id) )\nCREATE TABLE social_media.conversations ( conversation_id character varying(64) NOT NULL, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, last_message_at timestamp, is_group_chat boolean NOT NULL DEFAULT false, group_name character varying(100), PRIMARY KEY (conversation_id) )\nCREATE TABLE social_media.notifications ( notification_id character varying(64) NOT NULL, recipient_user_id character varying(64) NOT NULL, sender_user_id character varying(64), notification_type character varying(30) NOT NULL, target_entity_id character varying(64), target_entity_type character varying(20), created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, read_at timestamp, PRIMARY KEY (notification_id) )\nCREATE TABLE social_media.user_settings ( setting_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL UNIQUE, theme character varying(20) DEFAULT 'light', email_notifications_enabled boolean DEFAULT true, push_notifications_enabled boolean DEFAULT true, private_profile boolean DEFAULT false, updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (setting_id) )\n"}
{"conversations": [{"role": "user", "content": "Provide a count of notifications, separated by whether they have been read or not."}, {"role": "assistant", "content": "SELECT CASE WHEN T1.read_at IS NULL THEN 'Unread' ELSE 'Read' END, count(T1.notification_id) FROM trading_platform.notifications AS T1 GROUP BY CASE WHEN T1.read_at IS NULL THEN 'Unread' ELSE 'Read' END"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.notifications ( notification_id.text, user_id.text, message.text, sent_at.timestamp, read_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show me the average market cap and average 24-hour price change percentage for tokens on each chain."}, {"role": "assistant", "content": "SELECT chain, AVG(market_cap) AS average_market_cap, AVG(price_change_percentage_24h) AS average_price_change_24h FROM token_basic_info GROUP BY chain;"}, {"role": "user", "content": "Now, only show chains where the average market cap is greater than 1,000,000,000."}, {"role": "assistant", "content": "SELECT chain, AVG(market_cap) AS average_market_cap, AVG(price_change_percentage_24h) AS average_price_change_24h FROM token_basic_info GROUP BY chain HAVING AVG(market_cap) > 1000000000;"}, {"role": "user", "content": "Also, order the results by average market cap in descending order."}, {"role": "assistant", "content": "SELECT chain, AVG(market_cap) AS average_market_cap, AVG(price_change_percentage_24h) AS average_price_change_24h FROM token_basic_info GROUP BY chain HAVING AVG(market_cap) > 1000000000 ORDER BY average_market_cap DESC;"}, {"role": "user", "content": "Can you also include the total number of tokens for each of these chains?"}, {"role": "assistant", "content": "SELECT chain, COUNT(*) AS number_of_tokens, AVG(market_cap) AS average_market_cap, AVG(price_change_percentage_24h) AS average_price_change_24h FROM token_basic_info GROUP BY chain HAVING AVG(market_cap) > 1000000000 ORDER BY average_market_cap DESC;"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nCREATE TABLE token_basic_info ( coin_id character varying(100) NOT NULL, token_name character varying(100) NOT NULL, token_symbol character varying(100) NOT NULL, token_address character varying(100) NOT NULL, chain text, price double precision, price_change_percentage_1h double precision, price_change_percentage_24h double precision, price_change_percentage_7d double precision, highest_price_24h double precision, lowest_price_24h double precision, market_cap double precision, market_cap_rank bigint, market_cap_change_percentage_24h text, total_volume text, narrative text, trend_rank bigint )\n"}
{"conversations": [{"role": "user", "content": "List all patients who have a current prescription that was prescribed by a doctor with a specialty of 'Endocrinology'. Show patient full name, prescription ID, medication name, and prescription date."}, {"role": "assistant", "content": "SELECT p.patient_id, p.first_name || ' ' || p.last_name AS full_name, pr.prescription_id, m.medication_name, pr.prescription_date\nFROM healthcare.prescriptions pr\nJOIN healthcare.medications m ON pr.medication_id = m.medication_id\nJOIN healthcare.patients p ON pr.patient_id = p.patient_id\nJOIN healthcare.doctors d ON pr.doctor_id = d.doctor_id\nWHERE d.specialty = 'Endocrinology' AND pr.end_date IS NULL OR pr.end_date > CURRENT_DATE;"}, {"role": "user", "content": "Include prescriptions that ended within the past 7 days as well."}, {"role": "assistant", "content": "SELECT p.patient_id, p.first_name || ' ' || p.last_name AS full_name, pr.prescription_id, m.medication_name, pr.prescription_date\nFROM healthcare.prescriptions pr\nJOIN healthcare.medications m ON pr.medication_id = m.medication_id\nJOIN healthcare.patients p ON pr.patient_id = p.patient_id\nJOIN healthcare.doctors d ON pr.doctor_id = d.doctor_id\nWHERE d.specialty = 'Endocrinology' AND (pr.end_date IS NULL OR pr.end_date > CURRENT_DATE OR pr.end_date >= CURRENT_DATE - INTERVAL '7 days');"}, {"role": "user", "content": "I got an error: relation \"healthcare.patients\" does not exist. Can you fix it using existing tables only?"}, {"role": "assistant", "content": "SELECT pr.patient_id, pr.prescription_id, m.medication_name, pr.prescription_date\nFROM healthcare.prescriptions pr\nJOIN healthcare.medications m ON pr.medication_id = m.medication_id\nJOIN healthcare.doctors d ON pr.doctor_id = d.doctor_id\nWHERE d.specialty = 'Endocrinology' AND (pr.end_date IS NULL OR pr.end_date > CURRENT_DATE OR pr.end_date >= CURRENT_DATE - INTERVAL '7 days');"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.appointments ( appointment_id text, patient_id text, doctor_id text, appointment_time timestamp, duration_minutes integer, reason text, status text, location_id text, notes text, created_at timestamp )\nCREATE TABLE healthcare.medical_records ( record_id text, patient_id text, appointment_id text, doctor_id text, record_date timestamp, chief_complaint text, present_illness_history text, past_medical_history text, physical_examination_notes text, assessment text, treatment_plan text, vitals text, created_at timestamp )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id text, record_id text, patient_id text, doctor_id text, diagnosis_code text, code_type text, description text, diagnosis_date date, status text, is_chronic boolean )\nCREATE TABLE healthcare.medications ( medication_id text, medication_name text, generic_name text, manufacturer text, ndc_code text, description text )\nCREATE TABLE healthcare.prescriptions ( prescription_id text, record_id text, patient_id text, doctor_id text, medication_id text, dosage text, frequency text, route text, start_date date, end_date date, quantity_dispensed numeric, refills_allowed integer, prescription_date timestamp )\nCREATE TABLE healthcare.insurance_plans ( plan_id text, plan_name text, insurance_provider text, plan_type text, contact_phone text, website text )\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id text, patient_id text, plan_id text, policy_number text, group_number text, subscriber_name text, effective_date date, expiration_date date, is_primary boolean )\n"}
{"conversations": [{"role": "user", "content": "I need to find all components associated with a specific supplier. Can you help with that?"}, {"role": "assistant", "content": "HGETALL component:<component_id>\nIF HGET component:<component_id> supplier_id = 'sup:ACME_AERO' THEN INCLUDE"}, {"role": "user", "content": "Can you also show me the material ID for each of these components?"}, {"role": "assistant", "content": "HGETALL component:<component_id>\nIF HGET component:<component_id> supplier_id = 'sup:ACME_AERO' THEN INCLUDE\nHGET component:<component_id> material_id"}, {"role": "user", "content": "What if I want to exclude components with a specific material ID?"}, {"role": "assistant", "content": "HGETALL component:<component_id>\nIF HGET component:<component_id> supplier_id = 'sup:ACME_AERO' THEN INCLUDE\nHGET component:<component_id> material_id\nIF HGET component:<component_id> material_id != 'mat:TI64' THEN INCLUDE"}, {"role": "user", "content": "Can you add the component name to the result as well?"}, {"role": "assistant", "content": "HGETALL component:<component_id>\nIF HGET component:<component_id> supplier_id = 'sup:ACME_AERO' THEN INCLUDE\nHGET component:<component_id> material_id\nIF HGET component:<component_id> material_id != 'mat:TI64' THEN INCLUDE\nHGET component:<component_id> component_name"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nUse Hashes. Key pattern: 'component:<component_id>'. Example: HSET component:LGSTRUT01 part_number \"PN-5521-A\" component_name \"Landing Gear Strut\" material_id \"mat:TI64\" supplier_id \"sup:ACME_AERO\" ... Consider Sets for reverse lookups (e.g., 'material_components:<material_id>' -> Set<component_id>).\n"}
{"conversations": [{"role": "user", "content": "List all invoices that were paid within 7 days of their issue date. Show invoice number, issue date, payment date, and total amount."}, {"role": "assistant", "content": "SELECT invoice_number, issue_date, payment_date, total_amount FROM legal_services.invoices WHERE status = 'Paid' AND payment_date IS NOT NULL AND (payment_date::DATE - issue_date) <= 7;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.lawyers ( lawyer_id.text, first_name.text, last_name.text, bar_number.text, firm_id.text, email.text, phone.text, specialization.text, hire_date.timestamp, is_partner.boolean )\nCREATE TABLE legal_services.invoices ( invoice_id text, invoice_number text, client_id text, case_id text, issue_date date, due_date date, total_amount numeric, amount_paid numeric, status text, payment_date timestamp, notes text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Can you help me retrieve the details of all bookings for a specific route with route_id 'RT789', including the passenger names and the scheduled departure times?"}, {"role": "assistant", "content": "SELECT b.booking_id, p.first_name, p.last_name, s.departure_datetime, b.status, b.total_price\nFROM train_station_management.bookings b\nJOIN train_station_management.passengers p ON b.passenger_id = p.passenger_id\nJOIN train_station_management.schedules s ON b.schedule_id = s.schedule_id\nWHERE s.route_id = 'RT789';"}, {"role": "user", "content": "Can you modify the query to include only bookings with a status of 'Pending'?"}, {"role": "assistant", "content": "SELECT b.booking_id, p.first_name, p.last_name, s.departure_datetime, b.status, b.total_price\nFROM train_station_management.bookings b\nJOIN train_station_management.passengers p ON b.passenger_id = p.passenger_id\nJOIN train_station_management.schedules s ON b.schedule_id = s.schedule_id\nWHERE s.route_id = 'RT789' AND b.status = 'Pending';"}, {"role": "user", "content": "Can you also add the route name and origin station ID to the results?"}, {"role": "assistant", "content": "SELECT b.booking_id, p.first_name, p.last_name, s.departure_datetime, b.status, b.total_price, r.route_name, r.origin_station_id\nFROM train_station_management.bookings b\nJOIN train_station_management.passengers p ON b.passenger_id = p.passenger_id\nJOIN train_station_management.schedules s ON b.schedule_id = s.schedule_id\nJOIN train_station_management.routes r ON s.route_id = r.route_id\nWHERE s.route_id = 'RT789' AND b.status = 'Pending';"}, {"role": "user", "content": "Can you sort the results by departure datetime in descending order?"}, {"role": "assistant", "content": "SELECT b.booking_id, p.first_name, p.last_name, s.departure_datetime, b.status, b.total_price, r.route_name, r.origin_station_id\nFROM train_station_management.bookings b\nJOIN train_station_management.passengers p ON b.passenger_id = p.passenger_id\nJOIN train_station_management.schedules s ON b.schedule_id = s.schedule_id\nJOIN train_station_management.routes r ON s.route_id = r.route_id\nWHERE s.route_id = 'RT789' AND b.status = 'Pending'\nORDER BY s.departure_datetime DESC;"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nCREATE TABLE train_station_management.train_cars (\n    car_id character varying(64) NOT NULL, -- Unique identifier for the train car\n    train_id character varying(64) NOT NULL, -- Foreign key referencing trains\n    car_number character varying(10) NOT NULL, -- Identifier of the car within the train set\n    car_type character varying(64) NOT NULL, -- e.g., Locomotive, Passenger, Sleeper, Dining, Baggage\n    class character varying(32), -- e.g., First, Business, Economy (null for non-passenger cars)\n    capacity integer, -- Passenger capacity of this specific car (null for non-passenger cars)\n    features text, -- Comma-separated list of features (e.g., 'WiFi', 'Power Outlet', 'Accessible Restroom')\n    PRIMARY KEY (car_id),\n    FOREIGN KEY (train_id) REFERENCES train_station_management.trains(train_id)\n)\nCREATE TABLE train_station_management.routes (\n    route_id character varying(64) NOT NULL, -- Unique identifier for the route\n    route_name character varying(128) NOT NULL, -- Name of the route (e.g., 'Northeast Corridor')\n    description text, -- Description of the route\n    origin_station_id character varying(64) NOT NULL, -- Starting station\n    destination_station_id character varying(64) NOT NULL, -- Final station\n    is_active boolean NOT NULL DEFAULT true, -- Is the route currently operational?\n    PRIMARY KEY (route_id),\n    FOREIGN KEY (origin_station_id) REFERENCES train_station_management.stations(station_id),\n    FOREIGN KEY (destination_station_id) REFERENCES train_station_management.stations(station_id)\n)\nCREATE TABLE train_station_management.route_stations (\n    route_station_id character varying(64) NOT NULL, -- Unique ID for this route-station link\n    route_id character varying(64) NOT NULL, -- Foreign key referencing routes\n    station_id character varying(64) NOT NULL, -- Foreign key referencing stations\n    sequence_order integer NOT NULL, -- Order of the station in the route (1 for origin, 2, 3...)\n    distance_from_previous_km numeric(10, 2), -- Distance from the previous station in the sequence\n    typical_stop_duration_minutes integer, -- Typical dwell time at this station\n    PRIMARY KEY (route_station_id),\n    UNIQUE (route_id, station_id),\n    UNIQUE (route_id, sequence_order),\n    FOREIGN KEY (route_id) REFERENCES train_station_management.routes(route_id),\n    FOREIGN KEY (station_id) REFERENCES train_station_management.stations(station_id)\n)\nCREATE TABLE train_station_management.schedules (\n    schedule_id character varying(64) NOT NULL, -- Unique identifier for a specific scheduled trip\n    train_id character varying(64) NOT NULL, -- Foreign key referencing the train used\n    route_id character varying(64) NOT NULL, -- Foreign key referencing the route taken\n    departure_datetime timestamp with time zone NOT NULL, -- Scheduled departure time from origin station\n    arrival_datetime timestamp with time zone NOT NULL, -- Scheduled arrival time at destination station\n    status character varying(32) NOT NULL DEFAULT 'Scheduled', -- e.g., Scheduled, On Time, Delayed, Cancelled, Arrived\n    notes text, -- Any notes regarding this specific trip (e.g., reason for delay)\n    PRIMARY KEY (schedule_id),\n    FOREIGN KEY (train_id) REFERENCES train_station_management.trains(train_id),\n    FOREIGN KEY (route_id) REFERENCES train_station_management.routes(route_id)\n)\nCREATE TABLE train_station_management.passengers (\n    passenger_id character varying(64) NOT NULL, -- Unique identifier for the passenger\n    first_name character varying(100) NOT NULL, -- Passenger's first name\n    last_name character varying(100) NOT NULL, -- Passenger's last name\n    email character varying(128) UNIQUE, -- Passenger's email address\n    phone_number character varying(32) UNIQUE, -- Passenger's phone number\n    date_of_birth date, -- Passenger's date of birth\n    loyalty_program_id character varying(64), -- ID for loyalty program, if applicable\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- When the passenger record was created\n    PRIMARY KEY (passenger_id)\n)\nCREATE TABLE train_station_management.bookings (\n    booking_id character varying(64) NOT NULL, -- Unique identifier for the booking\n    passenger_id character varying(64) NOT NULL, -- Foreign key referencing the passenger\n    schedule_id character varying(64) NOT NULL, -- Foreign key referencing the scheduled trip\n    booking_datetime timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- When the booking was made\n    status character varying(32) NOT NULL DEFAULT 'Confirmed', -- e.g., Confirmed, Cancelled, Pending\n    total_price numeric(12, 2) NOT NULL, -- Total price for all tickets in this booking\n    currency_code character varying(3) NOT NULL DEFAULT 'USD', -- Currency of the price\n    special_requests text, -- Any special requests (e.g., wheelchair assistance)\n    PRIMARY KEY (booking_id),\n    FOREIGN KEY (passenger_id) REFERENCES train_station_management.passengers(passenger_id),\n    FOREIGN KEY (schedule_id) REFERENCES train_station_management.schedules(schedule_id)\n)\nCREATE TABLE train_station_management.staff (\n    staff_id character varying(64) NOT NULL, -- Unique identifier for the staff member\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    role character varying(64) NOT NULL, -- e.g., Station Master, Ticket Agent, Conductor, Engineer, Maintenance Crew\n    primary_station_id character varying(64), -- Base station for the staff member (nullable for mobile staff)\n    employee_number character varying(32) UNIQUE NOT NULL, -- Unique employee identifier\n    hire_date date NOT NULL,\n    contact_email character varying(128) UNIQUE,\n    contact_phone character varying(32),\n    is_active boolean NOT NULL DEFAULT true, -- Is the staff member currently employed?\n    PRIMARY KEY (staff_id),\n    FOREIGN KEY (primary_station_id) REFERENCES train_station_management.stations(station_id)\n)\n"}
{"conversations": [{"role": "user", "content": "For each user with 'approved' KYC status, show their user ID and the total amount in their unspent UTXOs."}, {"role": "assistant", "content": "SELECT T1.user_id, SUM(T2.amount) FROM trading_platform.kyc_audit AS T1 JOIN trading_platform.utxos AS T2 ON T1.user_id = T2.user_id WHERE T1.status = 'approved' AND T2.spent = false GROUP BY T1.user_id;"}, {"role": "user", "content": "Only include users where the total unspent amount is greater than 100."}, {"role": "assistant", "content": "SELECT T1.user_id, SUM(T2.amount) FROM trading_platform.kyc_audit AS T1 JOIN trading_platform.utxos AS T2 ON T1.user_id = T2.user_id WHERE T1.status = 'approved' AND T2.spent = false GROUP BY T1.user_id HAVING SUM(T2.amount) > 100;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.utxos ( utxo_id text, transaction_id text, output_index integer, address text, amount numeric, spent boolean )\nCREATE TABLE trading_platform.dapps ( dapp_id text, name text, description text, url text )\nCREATE TABLE trading_platform.peers ( peer_id text, ip_address text, port integer, last_seen timestamp )\nCREATE TABLE trading_platform.kyc_audit ( kyc_audit_id text, user_id text, status text, reviewed_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "List all ERC20 tokens where the price is greater than $10, including their names, symbols, and contract addresses."}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address FROM token_metas tm JOIN token_prices_latest tpl ON tm.contract_address = tpl.address WHERE tpl.price > 10 AND tm.is_erc20 = 1;"}, {"role": "user", "content": "I think there's an error in your query - it should be 'tpl.price > 10' not 'tpl.price > 10'. Also, can you add the current price to the results?"}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address, tpl.price FROM token_metas tm JOIN token_prices_latest tpl ON tm.contract_address = tpl.address WHERE tpl.price > 10 AND tm.is_erc20 = 1;"}, {"role": "user", "content": "Now sort these results by price in descending order and limit to the top 10."}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address, tpl.price FROM token_metas tm JOIN token_prices_latest tpl ON tm.contract_address = tpl.address WHERE tpl.price > 10 AND tm.is_erc20 = 1 ORDER BY tpl.price DESC LIMIT 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp timestamp, block_number bigint, transaction_hash varchar, transaction_index bigint, from_address varchar, contract_address varchar, symbol varchar, total_supply varchar, name varchar, decimals bigint, is_erc20 integer, is_erc721 integer, is_erc1155 integer, is_proxy integer, extra_info varchar, pk integer )\nCREATE TABLE erc1155_approval_for_all ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash varchar, log_index integer, contract_address varchar )\nCREATE TABLE erc20_balances ( block_number bigint, contract_address varchar, wallet_address varchar, amount varchar, pk varchar )\nCREATE TABLE nft_holders ( block_number bigint, contract_address varchar, wallet_address varchar, token_id varchar, contract_type varchar, amount varchar, pk varchar )\nCREATE TABLE nft_holder_historical ( block_number bigint, contract_address varchar, wallet_address varchar, token_id varchar, contract_type varchar, amount varchar, pk integer )\nCREATE TABLE sui_coins_metadata ( object_id varchar, coin_type varchar, status varchar, decimals bigint, description varchar, icon_url varchar, symbol varchar, name varchar )\nCREATE TABLE nft_metadata ( blockchain varchar, contract_address varchar, token_id varchar, contract_name varchar, erc_type varchar, amount bigint, minter varchar, owner varchar, mint_block_number bigint, mint_time bigint, mint_transaction_hash varchar, mint_price varchar, token_uri varchar, metadata varchar, name varchar, image_uri varchar, traits varchar, updated_at bigint, status varchar, rarity_score real, rarity_rank integer, unique_attribute_count integer, pk integer )\nCREATE TABLE nft_collections ( blockchain varchar, contract_address varchar, name varchar, symbol varchar, deploy_block_number bigint, deploy_block_time bigint, erc_type varchar, owner varchar, traits varchar, description varchar, slug varchar, media_info varchar, image_url varchar, banner_image_url varchar, updated_at bigint, banner varchar, token_count bigint, floor_price varchar, floor_price_symbol varchar, floor_price_contract varchar, pk integer )\nCREATE TABLE token_prices ( uuid varchar, blockchain varchar, address varchar, decimals bigint, symbol varchar, price real, timestamp timestamp )\nCREATE TABLE token_prices_latest ( blockchain varchar, address varchar, decimals bigint, symbol varchar, price real, timestamp timestamp )\nCREATE TABLE erc20_approval ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash varchar, log_index integer, contract_address varchar, pk integer )\nCREATE TABLE token_balances ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply decimal, amount decimal )\nCREATE TABLE token_info ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar )\nCREATE TABLE token_activities ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\nCREATE TABLE mud_holesky_redstone ( address varchar, table_id varchar, key_bytes varchar, key0 varchar, key1 varchar, static_data varchar, encoded_lengths varchar, dynamic_data varchar, is_deleted boolean, block_number bigint, log_index bigint )\nCREATE TABLE token_balances_bitcoin ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply varchar, amount varchar )\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\nCREATE TABLE token_balances_avalanche ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply decimal, amount decimal )\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id varchar )\n"}
{"conversations": [{"role": "user", "content": "List all ERC20 tokens where the price is between $1 and $10, including their names, symbols, and contract addresses."}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address FROM token_metas tm JOIN token_prices_latest tpl ON tm.contract_address = tpl.contract_address WHERE tm.is_erc20 = 1 AND tpl.price BETWEEN 1 AND 10;"}, {"role": "user", "content": "I think there's an error in your query - the token_prices_latest table isn't in the schema. Can you modify it to use the token_balances table instead?"}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address FROM token_metas tm JOIN token_balances tb ON tm.contract_address = tb.wallet_address WHERE tm.is_erc20 = 1 AND CAST(tb.amount AS decimal) BETWEEN 1 AND 10;"}, {"role": "user", "content": "That doesn't seem right either. Let's just get the basic ERC20 token information without price filtering for now."}, {"role": "assistant", "content": "SELECT name, symbol, contract_address FROM token_metas WHERE is_erc20 = 1 LIMIT 100;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp.timestamp, block_number.bigint, transaction_hash.text, transaction_index.bigint, from_address.text, contract_address.text, symbol.text, total_supply.text, name.text, decimals.bigint, is_erc20.integer, is_erc721.integer, is_erc1155.integer, is_proxy.integer, extra_info.text, pk.integer )\nCREATE TABLE erc1155_approval_for_all ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar(66) NOT NULL, log_index integer NOT NULL, contract_address varchar(42) NOT NULL )\nCREATE TABLE erc20_balances ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE erc20_balances_historical ( block_number bigint, contract_address text, wallet_address text, amount text, pk integer )\nCREATE TABLE nft_holders ( block_number bigint, contract_address text, wallet_address text, token_id text, contract_type text, amount text, pk text )\nCREATE TABLE nft_holder_historical ( block_number.bigint, contract_address.text, wallet_address.text, token_id.text, contract_type.text, amount.text, pk.integer )\nCREATE TABLE sui_nfts ( object_id text, status text, collection_type text, package_id text, previous_transaction text, display text, owner text, name text )\nCREATE TABLE nft_collections ( blockchain text, contract_address text, name text, symbol text, deploy_block_number bigint, deploy_block_time bigint, erc_type text, owner text, traits text, description text, slug text, media_info text, image_url text, banner_image_url text, updated_at bigint, banner text, token_count bigint, floor_price text, floor_price_symbol text, floor_price_contract text, pk integer )\nCREATE TABLE erc20_approval ( block_number bigint NOT NULL, block_timestamp timestamp(6) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar NOT NULL, log_index integer NOT NULL, contract_address varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_balances ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply decimal, amount decimal )\nCREATE TABLE token_info (\n    block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n    block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n    tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n    tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n    tick varchar NOT NULL, -- Token tick\n    max_supply decimal(38,0) NOT NULL, -- Max supply\n    lim decimal(38,0) NOT NULL, -- Limit of each mint\n    wlim decimal(38,0) NOT NULL, -- Limit of each address can maximum mint\n    dec integer NOT NULL, -- Decimal for minimum divie\n    creator varchar(42) NOT NULL  -- Address originating the inscription (matches from_address in transactions table)\n)\nCREATE TABLE token_activities ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\nCREATE TABLE mud_holesky_redstone ( address varchar NOT NULL, table_id varchar NOT NULL, key_bytes varchar NOT NULL, key0 varchar NOT NULL, key1 varchar NOT NULL, static_data varchar NOT NULL, encoded_lengths varchar NOT NULL, dynamic_data varchar NOT NULL, is_deleted boolean NOT NULL, block_number bigint NOT NULL, log_index bigint NOT NULL )\nCREATE TABLE token_balances_bitcoin ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply varchar, amount varchar )\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar )\nCREATE TABLE token_activities_avalanche ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\nCREATE TABLE token_balances_avalanche (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n    tick varchar(20) NOT NULL, -- Ticker: Identifier of the inscription\n    wallet_address varchar(42) NOT NULL, -- Address of owner\n    total_supply decimal(38,0) NOT NULL, -- Max supply: Set max supply of the inscription\n    amount decimal(38,0) NOT NULL  -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id varchar )\n"}
{"conversations": [{"role": "user", "content": "List trips where the actual arrival was earlier than the scheduled arrival, including the trip ID, scheduled and actual arrival times, and the vehicle make and model used."}, {"role": "assistant", "content": "SELECT T1.trip_id, T1.scheduled_arrival, T1.actual_arrival, T2.make, T2.model FROM transportation.trips AS T1 JOIN transportation.vehicles AS T2 ON T1.vehicle_id = T2.vehicle_id WHERE T1.actual_arrival IS NOT NULL AND T1.actual_arrival < T1.scheduled_arrival;"}, {"role": "user", "content": "For those early trips, also include the route number and description and sort by the arrival time difference in descending order."}, {"role": "assistant", "content": "SELECT T1.trip_id, T1.scheduled_arrival, T1.actual_arrival, T2.make, T2.model, T3.route_number, T3.description, EXTRACT(EPOCH FROM (T1.scheduled_arrival - T1.actual_arrival)) / 60 AS early_arrival_minutes FROM transportation.trips AS T1 JOIN transportation.vehicles AS T2 ON T1.vehicle_id = T2.vehicle_id LEFT JOIN transportation.routes AS T3 ON T1.route_id = T3.route_id WHERE T1.actual_arrival IS NOT NULL AND T1.actual_arrival < T1.scheduled_arrival ORDER BY early_arrival_minutes DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles (\n    vehicle_id character varying(64) NOT NULL,  -- unique identifier for the vehicle\n    license_plate character varying(32) NOT NULL UNIQUE, -- vehicle license plate\n    vin character varying(17) UNIQUE, -- vehicle identification number\n    make character varying(64) NOT NULL, -- manufacturer of the vehicle\n    model character varying(64) NOT NULL, -- model of the vehicle\n    year integer NOT NULL, -- manufacturing year\n    type character varying(32) NOT NULL, -- type of vehicle (e.g., Bus, Train, Truck, Car, Van)\n    capacity integer, -- passenger or cargo capacity\n    fuel_type character varying(32) NOT NULL, -- e.g., Diesel, Gasoline, Electric, Hydrogen\n    status character varying(32) NOT NULL, -- e.g., Active, Maintenance, Decommissioned\n    depot_id character varying(64), -- identifier of the home depot/base\n    acquisition_date date, -- date the vehicle was acquired\n    PRIMARY KEY (vehicle_id)\n)\nCREATE TABLE transportation.drivers (\n    driver_id character varying(64) NOT NULL,  -- unique identifier for the driver\n    employee_id character varying(64) NOT NULL UNIQUE, -- employee reference number\n    first_name character varying(128) NOT NULL, -- driver's first name\n    last_name character varying(128) NOT NULL, -- driver's last name\n    license_number character varying(64) NOT NULL UNIQUE, -- driving license number\n    license_expiry_date date NOT NULL, -- expiry date of the license\n    contact_number character varying(32), -- phone number\n    email character varying(128) UNIQUE, -- email address\n    hire_date date NOT NULL, -- date the driver was hired\n    status character varying(32) NOT NULL, -- e.g., Active, On Leave, Terminated\n    PRIMARY KEY (driver_id)\n)\nCREATE TABLE transportation.routes (\n    route_id character varying(64) NOT NULL,  -- unique identifier for the route\n    route_number character varying(32) NOT NULL UNIQUE, -- public-facing route number/name\n    description text, -- description of the route\n    origin_location_id character varying(64) NOT NULL, -- identifier of the starting location\n    destination_location_id character varying(64) NOT NULL, -- identifier of the ending location\n    distance_km numeric(10, 2), -- estimated distance in kilometers\n    estimated_duration_minutes integer, -- estimated travel time in minutes\n    type character varying(32) NOT NULL, -- e.g., City Bus, Intercity Train, Cargo Delivery\n    PRIMARY KEY (route_id)\n)\nCREATE TABLE transportation.trips (\n    trip_id character varying(64) NOT NULL,  -- unique identifier for a specific trip instance\n    route_id character varying(64), -- identifier of the route being followed (can be null for ad-hoc trips)\n    vehicle_id character varying(64) NOT NULL, -- identifier of the vehicle used\n    driver_id character varying(64) NOT NULL, -- identifier of the driver operating\n    scheduled_departure timestamp with time zone NOT NULL, -- planned departure time\n    actual_departure timestamp with time zone, -- actual departure time\n    scheduled_arrival timestamp with time zone NOT NULL, -- planned arrival time\n    actual_arrival timestamp with time zone, -- actual arrival time\n    origin_location_id character varying(64) NOT NULL, -- actual starting location (could differ from route origin)\n    destination_location_id character varying(64) NOT NULL, -- actual ending location (could differ from route destination)\n    status character varying(32) NOT NULL, -- e.g., Scheduled, In Progress, Completed, Delayed, Cancelled\n    passenger_count integer, -- number of passengers (if applicable)\n    cargo_manifest_id character varying(64), -- link to cargo details (if applicable)\n    PRIMARY KEY (trip_id)\n)\nCREATE TABLE transportation.fuel_logs (\n    fuel_log_id character varying(64) NOT NULL,  -- unique identifier for the fuel log entry\n    vehicle_id character varying(64) NOT NULL, -- identifier of the vehicle fueled\n    trip_id character varying(64), -- optional: identifier of the trip during which fueling occurred\n    log_timestamp timestamp with time zone NOT NULL, -- time when fueling occurred\n    fuel_type character varying(32) NOT NULL, -- type of fuel added (matches vehicle's fuel type)\n    quantity numeric(10, 3) NOT NULL, -- amount of fuel added (e.g., Liters, Gallons, kWh)\n    unit character varying(16) NOT NULL, -- unit of quantity (e.g., L, gal, kWh)\n    cost_per_unit numeric(8, 4), -- price per unit of fuel\n    total_cost numeric(10, 2) NOT NULL, -- total cost of the fuel purchase\n    odometer_reading integer, -- vehicle mileage at time of fueling\n    location_id character varying(64), -- identifier of the fueling station/location\n    PRIMARY KEY (fuel_log_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Show me the top 3 narratives by trend rank, along with their top 3 tokens and 7-day price change percentage."}, {"role": "assistant", "content": "SELECT ni.narrative, ni.top_3_coins, ni.price_change_percentage_7d FROM narrative_info ni ORDER BY ni.trend_rank ASC LIMIT 3;"}, {"role": "user", "content": "Can you also include the 24-hour trading volume for these narratives?"}, {"role": "assistant", "content": "SELECT ni.narrative, ni.top_3_coins, ni.price_change_percentage_7d, ni.volume_24h FROM narrative_info ni ORDER BY ni.trend_rank ASC LIMIT 3;"}, {"role": "user", "content": "Actually, I only want narratives with a 7-day price change percentage above 10%."}, {"role": "assistant", "content": "SELECT ni.narrative, ni.top_3_coins, ni.price_change_percentage_7d, ni.volume_24h FROM narrative_info ni WHERE ni.price_change_percentage_7d > 10 ORDER BY ni.trend_rank ASC LIMIT 3;"}, {"role": "user", "content": "Now order the results by 24-hour trading volume in descending order."}, {"role": "assistant", "content": "SELECT ni.narrative, ni.top_3_coins, ni.price_change_percentage_7d, ni.volume_24h FROM narrative_info ni WHERE ni.price_change_percentage_7d > 10 ORDER BY ni.volume_24h DESC LIMIT 3;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\n \"CREATE TABLE project_fundraising_record (\",\n    \"id character varying(32) NOT NULL,  -- fundraising record id\",\n    \"project_id character varying(32) NOT NULL, -- the invested project's id\",\n    \"project_name character varying(128) NOT NULL, -- name of the invested project\",\n    \"rounds_name character varying(32), -- name of the fundraising round\",\n    \"investment_value numeric(38,14), -- amount of the fundraising in USD\",\n    \"investment_date character varying(128), -- the date of the investment happened\",\n    \"introduction character varying(128), -- the introduction of the invested project\",\n    \"valuation numeric(38,14), -- the valuation of the project in USD when invested\",\n\nCREATE TABLE token_basic_info ( coin_id character varying(100) NOT NULL, -- the id of the token token_name character varying(100) NOT NULL, -- the token's name token_symbol character varying(100) NOT NULL, -- the token's symbol token_address character varying(100) NOT NULL, -- the token's address chain text, -- the chain that the token resides price double precision, -- the current price of the token price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days highest_price_24h double precision, -- the highest price of the token in 24 hours lowest_price_24h double precision,  -- the lowest price of the token in 24 hours market_cap double precision, -- the market cap of the token market_cap_rank bigint, -- the rank of the token market cap in desc market_cap_change_percentage_24h text, -- the percentage of market cap changes in 24 hours total_volume text, -- the trade volum of the token both in decentralized exchange(DEX) and centralized exchange(CEX) narrative text, -- the category or narrative of the token trend_rank biging, -- the trending rank of the token, value 1 expresses the most popular token. ,PRIMARY KEY (coin_id, chain) )\nCREATE TABLE narrative_info ( narrative character varying(512) NOT NULL, -- the id of narrative top_3_coins text, -- the top 3 tokens in the narrative price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour in the narrative price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours in the narrative price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days in the narrative market_cap double precision, -- the market cap of the narrative volume_24h double precision, -- the trade volume of the narrative trend_rank bigint, -- the trending rank of the narrative, value 1 expresses the most popular narrative token_num bigint, -- total token number in the narrative ,PRIMARY KEY (narrative) )\nCREATE TABLE token_dexpool_info ( pair_address character varying(512) NOT NULL, token_name character varying(100) NOT NULL, token_symbol character varying(100) NOT NULL, chain text, price double precision, price_change_percentage_1h double precision, price_change_percentage_6h double precision, price_change_percentage_24h double precision, makers_24h double precision, volume_24h double precision, liquidity double precision, market_cap double precision, trend_rank bigint )\nCREATE TABLE smart_money_profit ( address character varying(100) NOT NULL, rank INT, profit numeric(38,6), roi numeric(38,2), realized_ratio numeric(38,2), most_profit_token character varying(100), last_trade_time character varying(100), chain character varying(100) )\n  \"CREATE TABLE smart_money_token_performance (\",\n    \"token_address character varying(100) NOT NULL, -- the token's address\",\n    \"token_symbol character varying(100), -- the tokens's symbol\",\n    \"pnl numeric(38,2), -- the profit users made on this token\",\n    \"net_flow numeric(38,2), -- the netflow of the token, means the money user spent minus the the money user sold of this token\",\n    \"avg_cost numeric(38,16), -- the average cost price of user spent on this token\",\n    \"price double precision, -- the current price of the token\",\n    \"realized_ratio numeric(10,2), -- the ratio user sold of the token\",\n    \"roi numeric(10,2), -- the roi users made of this token\",\n    \"chain character varying(100), -- the chain that the token resides\",\n    \"PRIMARY KEY (token_address, chain));\",\n\n  \"CREATE TABLE smart_money_token_inflow (\",\n    \"token_address character varying(100) NOT NULL, -- the token's address\",\n    \"token_symbol character varying(100), -- the tokens's symbol\",\n    \"token_amount numeric(38,2), -- the absolute value of the amount if user bought minus  the amount user sold of this token\",\n    \"usd_value numeric(38,2), -- the absolute usd value of the bought token minus sold token\",\n    \"avg_price numeric(38,6), -- the average cost price of user spent on this token\",\n    \"type int, -- the direction of the trade on this token. 1 means buying, 2 means selling\",\n    \"address_amount integer, -- the amount of the user bought this token\",\n    \"narrative character varying(100), -- the category or narrative of the token\",\n    \"chain character varying(100), -- the chain that the token resides\",\n    \",PRIMARY KEY (token_address, chain)\",\n\n"}
{"conversations": [{"role": "user", "content": "For each case type, calculate the average time to close cases in days, only including cases that have been closed."}, {"role": "assistant", "content": "SELECT case_type,\n       AVG(EXTRACT(EPOCH FROM (date_closed - date_opened)) / 86400) AS avg_close_days\nFROM legal_services.cases\nWHERE status = 'Closed'\n  AND date_closed IS NOT NULL\nGROUP BY case_type;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.cases ( case_id text, case_number text, case_name text, client_id text, lead_lawyer_id text, case_type text, status text, date_opened timestamp, date_closed timestamp, description text, court_jurisdiction text )\n"}
{"conversations": [{"role": "user", "content": "Get a list of room types along with their property name and the count of rooms currently Available for each type."}, {"role": "assistant", "content": "SELECT rt.type_name, p.property_name, COUNT(r.room_id) AS available_rooms_count\nFROM hospitality_technology.room_types rt\nJOIN hospitality_technology.rooms r ON rt.room_type_id = r.room_type_id\n  AND r.status = 'Available'\nJOIN hospitality_technology.properties p ON rt.property_id = p.property_id\nGROUP BY rt.type_name, p.property_name;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.properties ( property_id character varying(64) NOT NULL, property_name character varying(255) NOT NULL, address_line1 character varying(255) NOT NULL, address_line2 character varying(255), city character varying(100) NOT NULL, state_province character varying(100), postal_code character varying(20) NOT NULL, country_code character varying(3) NOT NULL, phone_number character varying(30), email_address character varying(255), property_type character varying(50) NOT NULL, star_rating numeric(2,1), timezone character varying(64) NOT NULL, manager_staff_id character varying(64), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (property_id) )\nCREATE TABLE hospitality_technology.rooms ( room_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, room_number character varying(10) NOT NULL, room_type_id character varying(64) NOT NULL, floor integer, status character varying(50) NOT NULL, is_smoking boolean NOT NULL DEFAULT false, features text, current_condition text, last_cleaned_at timestamp with time zone, PRIMARY KEY (room_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id) )\nCREATE TABLE hospitality_technology.room_types ( room_type_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, type_name character varying(100) NOT NULL, description text, base_rate numeric(10, 2) NOT NULL, max_occupancy integer NOT NULL, bed_type character varying(50), area_sqft numeric(8,2), amenities text, PRIMARY KEY (room_type_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id) )\nCREATE TABLE hospitality_technology.guests ( guest_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, email character varying(255) UNIQUE, phone_number character varying(30), date_of_birth date, address_line1 character varying(255), city character varying(100), state_province character varying(100), postal_code character varying(20), country_code character varying(3), preferences text, loyalty_member_id character varying(64) UNIQUE, communication_consent boolean DEFAULT true, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (guest_id) )\nCREATE TABLE hospitality_technology.reservations ( reservation_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, guest_id character varying(64) NOT NULL, room_id character varying(64), room_type_id character varying(64) NOT NULL, check_in_date date NOT NULL, check_out_date date NOT NULL, actual_check_in_ts timestamp with time zone, actual_check_out_ts timestamp with time zone, num_adults integer NOT NULL, num_children integer DEFAULT 0, status character varying(50) NOT NULL, booking_source character varying(100), rate_plan_id character varying(64), total_amount numeric(12, 2), amount_paid numeric(12, 2) DEFAULT 0.00, special_requests text, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (reservation_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (room_id) REFERENCES hospitality_technology.rooms(room_id), FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id) )\nCREATE TABLE hospitality_technology.staff ( staff_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, position character varying(100) NOT NULL, work_email character varying(255) UNIQUE, work_phone character varying(30), hire_date date NOT NULL, termination_date date, is_active boolean NOT NULL DEFAULT true, access_level integer NOT NULL, manager_id character varying(64), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (staff_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (manager_id) REFERENCES hospitality_technology.staff(staff_id) )\nCREATE TABLE hospitality_technology.services ( service_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, service_name character varying(150) NOT NULL, description text, category character varying(100), price numeric(10, 2) NOT NULL, unit character varying(30), is_available boolean NOT NULL DEFAULT true, department character varying(100), PRIMARY KEY (service_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id) )\nCREATE TABLE hospitality_technology.service_orders ( order_id character varying(64) NOT NULL, reservation_id character varying(64), guest_id character varying(64) NOT NULL, service_id character varying(64) NOT NULL, staff_id_ordered character varying(64), staff_id_delivered character varying(64), order_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, delivery_timestamp timestamp with time zone, quantity integer NOT NULL DEFAULT 1, unit_price numeric(10, 2) NOT NULL, total_price numeric(12, 2) NOT NULL, status character varying(50) NOT NULL, notes text, bill_id character varying(64), PRIMARY KEY (order_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (service_id) REFERENCES hospitality_technology.services(service_id), FOREIGN KEY (staff_id_ordered) REFERENCES hospitality_technology.staff(staff_id), FOREIGN KEY (staff_id_delivered) REFERENCES hospitality_technology.staff(staff_id) )\nCREATE TABLE hospitality_technology.reviews ( review_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, reservation_id character varying(64) UNIQUE, guest_id character varying(64) NOT NULL, rating_overall integer, rating_cleanliness integer, rating_service integer, rating_location integer, rating_value integer, comment text, review_source character varying(100), review_date timestamp with time zone NOT NULL DEFAULT current_timestamp, is_public boolean DEFAULT true, staff_response text, response_staff_id character varying(64), response_date timestamp with time zone, PRIMARY KEY (review_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (response_staff_id) REFERENCES hospitality_technology.staff(staff_id) )\n"}
{"conversations": [{"role": "user", "content": "Retrieve the policy_number, start_date, end_date, premium_amount, and corresponding product_name for policies with a coverage_limit greater than 500000."}, {"role": "assistant", "content": "SELECT p.policy_number, p.start_date, p.end_date, p.premium_amount, ip.product_name\nFROM insurance.policies p\nJOIN insurance.insurance_products ip ON p.product_id = ip.product_id\nWHERE p.coverage_limit > 500000;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.policies ( policy_id text, customer_id text, product_id text, agent_id text, policy_number text, start_date date, end_date date, premium_amount numeric, coverage_limit numeric, deductible numeric, status text, issued_at timestamp, cancellation_date date, cancellation_reason text )\nCREATE TABLE insurance.insurance_products ( product_id text, product_name text, product_type text, description text, base_premium numeric, coverage_details text, underwriting_rules text, is_active boolean, created_at timestamp, updated_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "List all pairs of tokens (show token_id for both) that share the same contract address, excluding pairs where the token_id is the same."}, {"role": "assistant", "content": "SELECT t1.token_id AS token_id1, t2.token_id AS token_id2, t1.contract_address FROM web3.tokens AS t1 JOIN web3.tokens AS t2 ON t1.contract_address = t2.contract_address WHERE t1.token_id < t2.token_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.tokens ( token_id character varying(64) NOT NULL, contract_address character varying(128) NOT NULL, token_name character varying(128) NOT NULL, token_symbol character varying(32) NOT NULL, decimals integer NOT NULL, total_supply numeric(38,14) NOT NULL, PRIMARY KEY (token_id) )\n"}
{"conversations": [{"role": "user", "content": "How many documents are there for each document_type? Show document_type and count ordered by the count in descending order."}, {"role": "assistant", "content": "SELECT document_type,\n       COUNT(*) AS count\nFROM legal_services.documents\nGROUP BY document_type\nORDER BY count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.documents ( document_id.text, case_id.text, document_name.text, document_type.text, storage_path.text, uploaded_by_lawyer_id.text, upload_timestamp.timestamp, version.integer, description.text )\n"}
{"conversations": [{"role": "user", "content": "For each prescription, find the next prescription for the same patient. Return current prescription_id, next_prescription_id, patient_id, and days between start dates."}, {"role": "assistant", "content": "SELECT p1.patient_id,\n       p1.prescription_id AS current_id,\n       p2.prescription_id AS next_id,\n       (p2.start_date - p1.start_date) AS days_between\nFROM healthcare.prescriptions p1\nJOIN healthcare.prescriptions p2\n  ON p1.patient_id = p2.patient_id\n AND p2.start_date = (\n       SELECT MIN(start_date)\n       FROM healthcare.prescriptions p3\n       WHERE p3.patient_id = p1.patient_id\n         AND p3.start_date > p1.start_date\n   );"}, {"role": "user", "content": "Only include pairs where days_between is less than 30 days."}, {"role": "assistant", "content": "SELECT p1.patient_id,\n       p1.prescription_id AS current_id,\n       p2.prescription_id AS next_id,\n       (p2.start_date - p1.start_date) AS days_between\nFROM healthcare.prescriptions p1\nJOIN healthcare.prescriptions p2\n  ON p1.patient_id = p2.patient_id\n AND p2.start_date = (\n       SELECT MIN(start_date)\n       FROM healthcare.prescriptions p3\n       WHERE p3.patient_id = p1.patient_id\n         AND p3.start_date > p1.start_date\n   )\nWHERE (p2.start_date - p1.start_date) < 30;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.prescriptions ( prescription_id.text, record_id.text, patient_id.text, doctor_id.text, medication_id.text, dosage.text, frequency.text, route.text, start_date.date, end_date.date, quantity_dispensed.numeric, refills_allowed.integer, prescription_date.timestamp )\n"}
{"conversations": [{"role": "user", "content": "Find all medical records where the vitals JSON field contains a blood pressure reading with systolic higher than 140, and show the patient_id, record_date, and vitals."}, {"role": "assistant", "content": "SELECT patient_id, record_date, vitals FROM healthcare.medical_records WHERE (vitals->>'blood_pressure_systolic')::integer > 140;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.medical_records (\n    record_id character varying(64) NOT NULL,  -- unique identifier for the medical record entry\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    appointment_id character varying(64) UNIQUE, -- FK to appointments table (can be null if record not tied to specific appt)\n    doctor_id character varying(64) NOT NULL, -- FK to doctors table (doctor creating the record)\n    record_date timestamp with time zone NOT NULL, -- date the record/observation was made\n    chief_complaint text, -- patient's primary reason for visit\n    present_illness_history text, -- detailed history of the current issue\n    past_medical_history text, -- relevant past conditions/surgeries\n    physical_examination_notes text, -- findings from the physical exam\n    assessment text, -- doctor's assessment/diagnosis summary\n    treatment_plan text, -- planned course of action\n    vitals jsonb, -- store vitals like BP, HR, Temp as structured JSON\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (record_id)\n)\n"}
{"conversations": [{"role": "user", "content": "What are the top 5 tokens by 7-day price change percentage? Show token_symbol, token_name, narrative, and chain, ordered by price_change_percentage_7d descending."}, {"role": "assistant", "content": "```sql\nSELECT\n  token_symbol,\n  token_name,\n  narrative,\n  chain\nFROM token_basic_info\nORDER BY price_change_percentage_7d DESC\nLIMIT 5;\n```"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE project_fundraising_record ( id character varying(32) NOT NULL, project_id character varying(32) NOT NULL, project_name character varying(128) NOT NULL, rounds_name character varying(32), investment_value numeric(38,14), investment_date character varying(128), introduction character varying(128), valuation numeric(38,14) )\nCREATE TABLE token_basic_info ( coin_id text, token_name text, token_symbol text, token_address text, chain text, price numeric, price_change_percentage_1h numeric, price_change_percentage_24h numeric, price_change_percentage_7d numeric, highest_price_24h numeric, lowest_price_24h numeric, market_cap numeric, market_cap_rank numeric, market_cap_change_percentage_24h text, total_volume text, narrative text, trend_rank numeric )\n \"CREATE TABLE narrative_info (\",\n    \"narrative character varying(512) NOT NULL, -- the id of narrative\",\n    \"top_3_coins text, -- the top 3 tokens in the narrative\",\n    \"price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour in the narrative\",\n    \"price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours in the narrative\",\n    \"price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days in the narrative\",\n    \"market_cap double precision, -- the market cap of the narrative\",\n    \"volume_24h double precision, -- the trade volume of the narrative\",\n    \"trend_rank bigint, -- the trending rank of the narrative, value 1 expresses the most popular narrative\",\n    \"token_num bigint, -- total token number in the narrative\",\n    \",PRIMARY KEY (narrative));\"\n\n  \"CREATE TABLE cex_token_balance (\",\n    \"snapshot_time character varying(32) NOT NULL,  -- the snapshot time of record, converted from original timestamp\",\n    \"chain character varying(128) NOT NULL, -- the chain that the token resides\",\n    \"address character varying(128) NOT NULL, -- the address that holds the assets, owned by a CEX\",\n    \"exchange character varying(512) NOT NULL, -- a centralized exchange name\",\n    \"token_address character varying(128) NOT NULL, -- token contract address\",\n    \"token_symbol character varying(512), --token symbol\",\n    \"balance numeric(38,10), -- token balance\",\n    \"usd_value numeric(38,14), -- value of the token held in USD\",\n    \"price double precision, --price of the token in USD\",\n    \",PRIMARY KEY (snapshot_time, exchange, address, chain, token_address));\"\n\nCREATE TABLE smart_money_profit ( address character varying(100) NOT NULL, -- the user's address rank INT, -- the rank of the address in trade performance, value 1 expresses the best address. profit numeric(38,6), -- the profit user made in a month roi numeric(38,2), -- the roi of the user in a month realized_ratio numeric(38,2), -- the percentage of the user's realized profit most_profit_token character varying(100), -- the token symbol of the user's most profitable trade last_trade_time character varying(100), -- the last trade time of the user chain character varying(100), -- the chain that the address resides PRIMARY KEY (address, chain) )\nCREATE TABLE smart_money_token_performance ( token_address text, token_symbol text, pnl numeric, net_flow numeric, avg_cost numeric, price numeric, realized_ratio numeric, roi numeric, chain text )\nCREATE TABLE smart_money_token_inflow ( token_address text, token_symbol text, token_amount numeric, usd_value numeric, avg_price numeric, type numeric, address_amount numeric, narrative text, chain text )\n"}
{"conversations": [{"role": "user", "content": "List the latest version of each document (identified by case_id and document_name), showing the version number and its upload_timestamp."}, {"role": "assistant", "content": "SELECT d.case_id,\n       d.document_name,\n       d.version   AS latest_version,\n       d.upload_timestamp\nFROM legal_services.documents d\nJOIN (\n  SELECT case_id, document_name, MAX(version) AS max_version\n  FROM legal_services.documents\n  GROUP BY case_id, document_name\n) m ON d.case_id = m.case_id\n    AND d.document_name = m.document_name\n    AND d.version = m.max_version;"}, {"role": "user", "content": "Actually, I also want to see the upload_timestamp of the previous version for each document."}, {"role": "assistant", "content": "SELECT m.case_id,\n       m.document_name,\n       m.max_version         AS latest_version,\n       d_latest.upload_timestamp  AS latest_timestamp,\n       d_prev.upload_timestamp    AS previous_timestamp\nFROM (\n  SELECT case_id, document_name, MAX(version) AS max_version\n  FROM legal_services.documents\n  GROUP BY case_id, document_name\n) m\nJOIN legal_services.documents d_latest\n  ON d_latest.case_id = m.case_id\n AND d_latest.document_name = m.document_name\n AND d_latest.version = m.max_version\nLEFT JOIN legal_services.documents d_prev\n  ON d_prev.case_id = m.case_id\n AND d_prev.document_name = m.document_name\n AND d_prev.version = m.max_version - 1;"}, {"role": "user", "content": "Also, only include documents whose first version (version = 1) was uploaded in 2024."}, {"role": "assistant", "content": "SELECT m.case_id,\n       m.document_name,\n       m.max_version          AS latest_version,\n       d_latest.upload_timestamp   AS latest_timestamp,\n       d_prev.upload_timestamp     AS previous_timestamp\nFROM (\n  SELECT case_id, document_name, MAX(version) AS max_version\n  FROM legal_services.documents\n  GROUP BY case_id, document_name\n) m\nJOIN legal_services.documents d_first\n  ON d_first.case_id = m.case_id\n AND d_first.document_name = m.document_name\n AND d_first.version = 1\n AND d_first.upload_timestamp >= '2024-01-01'\n AND d_first.upload_timestamp < '2025-01-01'\nJOIN legal_services.documents d_latest\n  ON d_latest.case_id = m.case_id\n AND d_latest.document_name = m.document_name\n AND d_latest.version = m.max_version\nLEFT JOIN legal_services.documents d_prev\n  ON d_prev.case_id = m.case_id\n AND d_prev.document_name = m.document_name\n AND d_prev.version = m.max_version - 1;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.documents ( document_id.text, case_id.text, document_name.text, document_type.text, storage_path.text, uploaded_by_lawyer_id.text, upload_timestamp.timestamp, version.integer, description.text )\n"}
{"conversations": [{"role": "user", "content": "List all appointments scheduled in the next 7 days along with the appointment_id, appointment_time, patient's full name, doctor's full name, and the patient's primary insurance plan_name."}, {"role": "assistant", "content": "SELECT ap.appointment_id,\n       ap.appointment_time,\n       pt.first_name || ' ' || pt.last_name AS patient_name,\n       d.first_name || ' ' || d.last_name AS doctor_name,\n       ip.plan_name\nFROM healthcare.appointments ap\nJOIN healthcare.patients pt ON ap.patient_id = pt.patient_id\nJOIN healthcare.doctors d ON ap.doctor_id = d.doctor_id\nJOIN healthcare.patient_insurance pi ON pt.patient_id = pi.patient_id AND pi.is_primary = TRUE\nJOIN healthcare.insurance_plans ip ON pi.plan_id = ip.plan_id\nWHERE ap.appointment_time BETWEEN CURRENT_DATE AND CURRENT_DATE + INTERVAL '7 days';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id text, first_name text, last_name text, date_of_birth date, gender text, address text, phone_number text, email text, emergency_contact_name text, emergency_contact_phone text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.doctors ( doctor_id text, first_name text, last_name text, specialty text, license_number text, phone_number text, email text, hospital_affiliation_id text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.appointments ( appointment_id.text, patient_id.text, doctor_id.text, appointment_time.timestamp, duration_minutes.integer, reason.text, status.text, location_id.text, notes.text, created_at.timestamp )\nCREATE TABLE healthcare.medications (\n    medication_id character varying(64) NOT NULL, -- unique identifier for the medication type\n    medication_name character varying(255) NOT NULL, -- common or brand name\n    generic_name character varying(255), -- generic chemical name\n    manufacturer character varying(100), -- drug manufacturer\n    ndc_code character varying(20) UNIQUE, -- National Drug Code (optional but useful)\n    description text, -- description of the medication\n    PRIMARY KEY (medication_id)\n)\nCREATE TABLE healthcare.prescriptions ( prescription_id text, record_id text, patient_id text, doctor_id text, medication_id text, dosage text, frequency text, route text, start_date date, end_date date, quantity_dispensed numeric, refills_allowed integer, prescription_date timestamp )\nCREATE TABLE healthcare.insurance_plans ( plan_id text, plan_name text, insurance_provider text, plan_type text, contact_phone text, website text )\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id text, patient_id text, plan_id text, policy_number text, group_number text, subscriber_name text, effective_date date, expiration_date date, is_primary boolean )\n"}
{"conversations": [{"role": "user", "content": "What is the fuel consumption rate of train number T1234?"}, {"role": "assistant", "content": "I'm sorry, but I don't have information on the fuel consumption rate of train number T1234. The data available in the system only includes details such as train ID, model, manufacturer, year manufactured, capacity, status, and maintenance dates."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.trains ( train_id character varying(64) NOT NULL, train_number character varying(32) NOT NULL, model character varying(128), manufacturer character varying(128), year_manufactured integer, capacity integer NOT NULL, status character varying(32) NOT NULL DEFAULT 'Active', last_maintenance_date date, next_maintenance_date date, PRIMARY KEY (train_id), UNIQUE (train_number) )\n"}
{"conversations": [{"role": "user", "content": "What is the maintenance schedule for the platforms at the station with ID 'ST234' for the next month?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to the maintenance schedule for the platforms at any station. The data I have only includes basic station information such as station ID, name, location, and number of platforms. For maintenance schedules, you may need to contact the station management or relevant authorities."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.stations ( station_id text PRIMARY KEY, station_name text, city text, state_province text, country_code text, address text, timezone text, number_of_platforms int, created_at timestamp, last_updated_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show me the count of notifications sent for each channel for applications submitted after January 1, 2024."}, {"role": "assistant", "content": "SELECT n.channel, COUNT(*) AS notification_count\nFROM government_services.notifications n\nJOIN government_services.applications a ON n.application_id = a.application_id\nWHERE a.submitted_at > '2024-01-01'\nGROUP BY n.channel;"}, {"role": "user", "content": "Now, only include channels that have sent more than 10 notifications."}, {"role": "assistant", "content": "SELECT n.channel, COUNT(*) AS notification_count\nFROM government_services.notifications n\nJOIN government_services.applications a ON n.application_id = a.application_id\nWHERE a.submitted_at > '2024-01-01'\nGROUP BY n.channel\nHAVING COUNT(*) > 10;"}, {"role": "user", "content": "Exclude notifications with the status 'Failed'."}, {"role": "assistant", "content": "SELECT n.channel, COUNT(*) AS notification_count\nFROM government_services.notifications n\nJOIN government_services.applications a ON n.application_id = a.application_id\nWHERE a.submitted_at > '2024-01-01' AND n.status != 'Failed'\nGROUP BY n.channel\nHAVING COUNT(*) > 10;"}, {"role": "user", "content": "Show for 2023 instead of 2024."}, {"role": "assistant", "content": "SELECT n.channel, COUNT(*) AS notification_count\nFROM government_services.notifications n\nJOIN government_services.applications a ON n.application_id = a.application_id\nWHERE a.submitted_at >= '2023-01-01' AND a.submitted_at < '2024-01-01' AND n.status != 'Failed'\nGROUP BY n.channel\nHAVING COUNT(*) > 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.applications ( application_id text, citizen_id text, service_id text, submitted_at timestamp, status text, last_updated_at timestamp, assigned_employee_id text, decision_date date, notes text, reference_number text )\nCREATE TABLE government_services.notifications ( notification_id text, citizen_id text, application_id text, message_subject text, message_body text, channel text, sent_at timestamp, status text, related_entity_type text, related_entity_id text )\n"}
{"conversations": [{"role": "user", "content": "What is the average speed of train number T9876 during its last journey?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information on the average speed of train number T9876 during its last journey. The data in the trains table does not include details about travel speed or journey-specific performance metrics."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.trains ( train_id.text, train_number.text, model.text, manufacturer.text, year_manufactured.integer, capacity.integer, status.text, last_maintenance_date.date, next_maintenance_date.date )\n"}
{"conversations": [{"role": "user", "content": "Find guests who have made at least one payment using a 'CreditCard'. List their full name (first and last name) and email address."}, {"role": "assistant", "content": "SELECT DISTINCT T1.first_name, T1.last_name, T1.email FROM hospitality_technology.guests AS T1 JOIN hospitality_technology.payments AS T2 ON T1.guest_id = T2.guest_id WHERE T2.payment_method = 'CreditCard';"}, {"role": "user", "content": "For these guests, also show the total amount they have paid using a 'CreditCard'."}, {"role": "assistant", "content": "SELECT T1.first_name, T1.last_name, T1.email, SUM(T2.amount) AS total_credit_card_amount FROM hospitality_technology.guests AS T1 JOIN hospitality_technology.payments AS T2 ON T1.guest_id = T2.guest_id WHERE T2.payment_method = 'CreditCard' GROUP BY T1.guest_id, T1.first_name, T1.last_name, T1.email;"}, {"role": "user", "content": "Now, only include guests where the total credit card payment exceeds 5000."}, {"role": "assistant", "content": "SELECT T1.first_name, T1.last_name, T1.email, SUM(T2.amount) AS total_credit_card_amount FROM hospitality_technology.guests AS T1 JOIN hospitality_technology.payments AS T2 ON T1.guest_id = T2.guest_id WHERE T2.payment_method = 'CreditCard' GROUP BY T1.guest_id, T1.first_name, T1.last_name, T1.email HAVING SUM(T2.amount) > 5000;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.guests (\n    guest_id character varying(64) NOT NULL,  -- unique identifier for the guest profile\n    first_name character varying(100) NOT NULL, -- guest's first name\n    last_name character varying(100) NOT NULL, -- guest's last name\n    email character varying(255) UNIQUE, -- guest's email address (unique identifier?)\n    phone_number character varying(30), -- guest's phone number\n    date_of_birth date, -- guest's date of birth\n    address_line1 character varying(255), -- guest's home address\n    city character varying(100),\n    state_province character varying(100),\n    postal_code character varying(20),\n    country_code character varying(3),\n    preferences text, -- notes on guest preferences (e.g., allergies, room location)\n    loyalty_member_id character varying(64) UNIQUE, -- FK to loyalty_members table\n    communication_consent boolean DEFAULT true, -- consent for marketing communications\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (guest_id)\n)\nCREATE TABLE hospitality_technology.payments (\n    payment_id character varying(64) NOT NULL,  -- unique identifier for the payment transaction\n    reservation_id character varying(64), -- FK to reservations (if payment is for a stay)\n    guest_id character varying(64) NOT NULL, -- FK to guests (who paid)\n    bill_id character varying(64), -- FK to bills/invoices this payment applies to\n    amount numeric(12,2) NOT NULL, -- amount of the payment\n    currency_code character varying(3) NOT NULL, -- ISO currency code (e.g., USD, EUR)\n    payment_method character varying(50) NOT NULL, -- e.g., CreditCard, Cash, BankTransfer, Points, Voucher\n    card_type character varying(50), -- e.g., Visa, MasterCard, Amex (if CC)\n    card_last_four character varying(4), -- last 4 digits of CC (if CC)\n    transaction_ref character varying(128), -- reference ID from payment gateway or processor\n    payment_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, -- when the payment occurred\n    status character varying(50) NOT NULL, -- e.g., Pending, Succeeded, Failed, Refunded, Disputed\n    staff_id_processed character varying(64), -- FK to staff (who processed the payment)\n    notes text, -- notes about the payment\n    PRIMARY KEY (payment_id),\n    FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id),\n    FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id),\n    FOREIGN KEY (staff_id_processed) REFERENCES hospitality_technology.staff(staff_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Show all service orders with the service_id, guest's full name, and the status of each order."}, {"role": "assistant", "content": "SELECT so.order_id, so.service_id, g.first_name, g.last_name, so.status\nFROM hospitality_technology.service_orders so\nJOIN hospitality_technology.guests g ON so.guest_id = g.guest_id;"}, {"role": "user", "content": "Only display service orders with status 'InProgress' or 'Pending', and sort them by order_timestamp ascending."}, {"role": "assistant", "content": "SELECT so.order_id, so.service_id, g.first_name, g.last_name, so.status\nFROM hospitality_technology.service_orders so\nJOIN hospitality_technology.guests g ON so.guest_id = g.guest_id\nWHERE so.status IN ('InProgress', 'Pending')\nORDER BY so.order_timestamp ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.room_types (\n    room_type_id character varying(64) NOT NULL, -- unique identifier for the room type\n    property_id character varying(64) NOT NULL, -- FK to properties table (type might be property-specific)\n    type_name character varying(100) NOT NULL, -- e.g., Standard King, Deluxe Queen, Executive Suite\n    description text, -- description of the room type\n    base_rate numeric(10, 2) NOT NULL, -- standard price per night\n    max_occupancy integer NOT NULL, -- maximum number of guests\n    bed_type character varying(50), -- e.g., King, Queen, 2 Doubles, Twin\n    area_sqft numeric(8,2), -- size of the room in square feet\n    amenities text, -- comma-separated list or JSON of amenities\n    PRIMARY KEY (room_type_id),\n    FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id)\n)\nCREATE TABLE hospitality_technology.guests ( guest_id text, first_name text, last_name text, email text, phone_number text, date_of_birth date, address_line1 text, city text, state_province text, postal_code text, country_code text, preferences text, loyalty_member_id text, communication_consent boolean, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.service_orders ( order_id character varying(64) NOT NULL, reservation_id character varying(64), guest_id character varying(64) NOT NULL, service_id character varying(64) NOT NULL, staff_id_ordered character varying(64), staff_id_delivered character varying(64), order_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, delivery_timestamp timestamp with time zone, quantity integer NOT NULL DEFAULT 1, unit_price numeric(10, 2) NOT NULL, total_price numeric(12, 2) NOT NULL, status character varying(50) NOT NULL, notes text, bill_id character varying(64), PRIMARY KEY (order_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (service_id) REFERENCES hospitality_technology.services(service_id), FOREIGN KEY (staff_id_ordered) REFERENCES hospitality_technology.staff(staff_id), FOREIGN KEY (staff_id_delivered) REFERENCES hospitality_technology.staff(staff_id) )\nCREATE TABLE hospitality_technology.payments (\n    payment_id character varying(64) NOT NULL,  -- unique identifier for the payment transaction\n    reservation_id character varying(64), -- FK to reservations (if payment is for a stay)\n    guest_id character varying(64) NOT NULL, -- FK to guests (who paid)\n    bill_id character varying(64), -- FK to bills/invoices this payment applies to\n    amount numeric(12,2) NOT NULL, -- amount of the payment\n    currency_code character varying(3) NOT NULL, -- ISO currency code (e.g., USD, EUR)\n    payment_method character varying(50) NOT NULL, -- e.g., CreditCard, Cash, BankTransfer, Points, Voucher\n    card_type character varying(50), -- e.g., Visa, MasterCard, Amex (if CC)\n    card_last_four character varying(4), -- last 4 digits of CC (if CC)\n    transaction_ref character varying(128), -- reference ID from payment gateway or processor\n    payment_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, -- when the payment occurred\n    status character varying(50) NOT NULL, -- e.g., Pending, Succeeded, Failed, Refunded, Disputed\n    staff_id_processed character varying(64), -- FK to staff (who processed the payment)\n    notes text, -- notes about the payment\n    PRIMARY KEY (payment_id),\n    FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id),\n    FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id),\n    FOREIGN KEY (staff_id_processed) REFERENCES hospitality_technology.staff(staff_id)\n)\n"}
{"conversations": [{"role": "user", "content": "I need to find all tickets for a specific route 'RT456' along with the car details and route information."}, {"role": "assistant", "content": "SELECT t.ticket_id, t.seat_number, t.price, tc.car_number, tc.car_type, r.route_name, r.description\nFROM train_station_management.tickets t\nJOIN train_station_management.train_cars tc ON t.car_id = tc.car_id\nJOIN train_station_management.trains tr ON tc.train_id = tr.train_id\nJOIN train_station_management.routes r ON tr.route_id = r.route_id\nWHERE r.route_id = 'RT456';"}, {"role": "user", "content": "Can you filter this to show only tickets that have been checked in?"}, {"role": "assistant", "content": "SELECT t.ticket_id, t.seat_number, t.price, tc.car_number, tc.car_type, r.route_name, r.description\nFROM train_station_management.tickets t\nJOIN train_station_management.train_cars tc ON t.car_id = tc.car_id\nJOIN train_station_management.trains tr ON tc.train_id = tr.train_id\nJOIN train_station_management.routes r ON tr.route_id = r.route_id\nWHERE r.route_id = 'RT456' AND t.is_checked_in = true;"}, {"role": "user", "content": "Can you also add the ticket type to the results?"}, {"role": "assistant", "content": "SELECT t.ticket_id, t.seat_number, t.price, t.ticket_type, tc.car_number, tc.car_type, r.route_name, r.description\nFROM train_station_management.tickets t\nJOIN train_station_management.train_cars tc ON t.car_id = tc.car_id\nJOIN train_station_management.trains tr ON tc.train_id = tr.train_id\nJOIN train_station_management.routes r ON tr.route_id = r.route_id\nWHERE r.route_id = 'RT456' AND t.is_checked_in = true;"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nCREATE TABLE train_station_management.train_cars (\n    car_id character varying(64) NOT NULL, -- Unique identifier for the train car\n    train_id character varying(64) NOT NULL, -- Foreign key referencing trains\n    car_number character varying(10) NOT NULL, -- Identifier of the car within the train set\n    car_type character varying(64) NOT NULL, -- e.g., Locomotive, Passenger, Sleeper, Dining, Baggage\n    class character varying(32), -- e.g., First, Business, Economy (null for non-passenger cars)\n    capacity integer, -- Passenger capacity of this specific car (null for non-passenger cars)\n    features text, -- Comma-separated list of features (e.g., 'WiFi', 'Power Outlet', 'Accessible Restroom')\n    PRIMARY KEY (car_id),\n    FOREIGN KEY (train_id) REFERENCES train_station_management.trains(train_id)\n)\nCREATE TABLE train_station_management.routes (\n    route_id character varying(64) NOT NULL, -- Unique identifier for the route\n    route_name character varying(128) NOT NULL, -- Name of the route (e.g., 'Northeast Corridor')\n    description text, -- Description of the route\n    origin_station_id character varying(64) NOT NULL, -- Starting station\n    destination_station_id character varying(64) NOT NULL, -- Final station\n    is_active boolean NOT NULL DEFAULT true, -- Is the route currently operational?\n    PRIMARY KEY (route_id),\n    FOREIGN KEY (origin_station_id) REFERENCES train_station_management.stations(station_id),\n    FOREIGN KEY (destination_station_id) REFERENCES train_station_management.stations(station_id)\n)\nCREATE TABLE train_station_management.tickets (\n    ticket_id character varying(64) NOT NULL, -- Unique identifier for the ticket\n    booking_id character varying(64) NOT NULL, -- Foreign key referencing the booking\n    car_id character varying(64) NOT NULL, -- Foreign key referencing the train car\n    seat_number character varying(10), -- Assigned seat number (e.g., '12A')\n    ticket_type character varying(32) NOT NULL DEFAULT 'Adult', -- e.g., Adult, Child, Senior, Student\n    price numeric(10, 2) NOT NULL, -- Price of this specific ticket\n    is_checked_in boolean NOT NULL DEFAULT false, -- Has the passenger checked in with this ticket?\n    qr_code_data text, -- Data for generating a QR code for the ticket\n    PRIMARY KEY (ticket_id),\n    FOREIGN KEY (booking_id) REFERENCES train_station_management.bookings(booking_id),\n    FOREIGN KEY (car_id) REFERENCES train_station_management.train_cars(car_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Which customers have policies that expired in the last month? Please show the customer ID, policy number, and expiration date."}, {"role": "assistant", "content": "SELECT c.customer_id, p.policy_number, p.end_date\nFROM insurance.customers c\nJOIN insurance.policies p ON c.customer_id = p.customer_id\nWHERE p.end_date >= (CURRENT_DATE - INTERVAL '1 month') AND p.end_date < CURRENT_DATE;"}, {"role": "user", "content": "Add the customer's email to the results."}, {"role": "assistant", "content": "SELECT c.customer_id, c.email, p.policy_number, p.end_date\nFROM insurance.customers c\nJOIN insurance.policies p ON c.customer_id = p.customer_id\nWHERE p.end_date >= (CURRENT_DATE - INTERVAL '1 month') AND p.end_date < CURRENT_DATE;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.customers ( customer_id text, first_name text, last_name text, date_of_birth date, ssn_hash text, address_line1 text, address_line2 text, city text, state text, zip_code text, country text, phone_number text, email text, created_at timestamp, updated_at timestamp, status text )\nCREATE TABLE insurance.policies ( policy_id text, customer_id text, product_id text, agent_id text, policy_number text, start_date date, end_date date, premium_amount numeric, coverage_limit numeric, deductible numeric, status text, issued_at timestamp, cancellation_date date, cancellation_reason text )\nCREATE TABLE insurance.claims ( claim_id text, policy_id text, customer_id text, incident_date timestamp, reported_date timestamp, description text, estimated_loss numeric, status text, settlement_amount numeric, settlement_date date, claim_handler_id text, police_report_number text )\nCREATE TABLE insurance.insurance_products ( product_id text, product_name text, product_type text, description text, base_premium numeric, coverage_details text, underwriting_rules text, is_active boolean, created_at timestamp, updated_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "List all passengers who have never made a booking, showing their passenger_id, first_name, last_name, and email."}, {"role": "assistant", "content": "SELECT\n    p.passenger_id,\n    p.first_name,\n    p.last_name,\n    p.email\nFROM transportation.passengers p\nLEFT JOIN transportation.bookings b ON p.passenger_id = b.passenger_id\nWHERE b.booking_id IS NULL;"}, {"role": "user", "content": "Actually, please include their phone_number as well."}, {"role": "assistant", "content": "SELECT\n    p.passenger_id,\n    p.first_name,\n    p.last_name,\n    p.email,\n    p.phone_number\nFROM transportation.passengers p\nLEFT JOIN transportation.bookings b ON p.passenger_id = b.passenger_id\nWHERE b.booking_id IS NULL;"}, {"role": "user", "content": "Also, limit to passengers created after '2022-01-01'."}, {"role": "assistant", "content": "SELECT\n    p.passenger_id,\n    p.first_name,\n    p.last_name,\n    p.email,\n    p.phone_number\nFROM transportation.passengers p\nLEFT JOIN transportation.bookings b ON p.passenger_id = b.passenger_id\nWHERE b.booking_id IS NULL\n  AND p.created_at > '2022-01-01';"}, {"role": "user", "content": "Finally, sort the results by last_name in ascending order."}, {"role": "assistant", "content": "SELECT\n    p.passenger_id,\n    p.first_name,\n    p.last_name,\n    p.email,\n    p.phone_number\nFROM transportation.passengers p\nLEFT JOIN transportation.bookings b ON p.passenger_id = b.passenger_id\nWHERE b.booking_id IS NULL\n  AND p.created_at > '2022-01-01'\nORDER BY p.last_name ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles ( vehicle_id text PRIMARY KEY, license_plate text, vin text, make text, model text, year int, type text, capacity int, fuel_type text, status text, depot_id text, acquisition_date date )\nCREATE TABLE transportation.drivers ( driver_id text, employee_id text, first_name text, last_name text, license_number text, license_expiry_date date, contact_number text, email text, hire_date date, status text )\nCREATE TABLE transportation.routes ( route_id text PRIMARY KEY, route_number text, description text, origin_location_id text, destination_location_id text, distance_km numeric, estimated_duration_minutes int, type text )\nCREATE TABLE transportation.trips ( trip_id text PRIMARY KEY, route_id text, vehicle_id text, driver_id text, scheduled_departure timestamp, actual_departure timestamp, scheduled_arrival timestamp, actual_arrival timestamp, origin_location_id text, destination_location_id text, status text, passenger_count int, cargo_manifest_id text )\nCREATE TABLE transportation.locations ( location_id text PRIMARY KEY, name text, type text, address_line1 text, city text, state_province text, postal_code text, country text, latitude numeric, longitude numeric, timezone text )\nCREATE TABLE transportation.maintenance_logs ( log_id.text, vehicle_id.text, service_date.date, odometer_reading.integer, service_type.text, description.text, cost.numeric, mechanic_name.text, next_service_due_date.date )\nCREATE TABLE transportation.passengers (\n    passenger_id character varying(64) NOT NULL,  -- unique identifier for the passenger\n    first_name character varying(128) NOT NULL, -- passenger's first name\n    last_name character varying(128) NOT NULL, -- passenger's last name\n    email character varying(128) UNIQUE, -- email address\n    phone_number character varying(32) UNIQUE, -- phone number\n    date_of_birth date, -- passenger's date of birth\n    loyalty_program_id character varying(64), -- identifier for loyalty program membership\n    created_at timestamp with time zone NOT NULL, -- time when the passenger record was created\n    PRIMARY KEY (passenger_id)\n)\nCREATE TABLE transportation.bookings ( booking_id text, passenger_id text, trip_id text, seat_number text, booking_time timestamp, status text, fare numeric, payment_transaction_id text, special_requests text )\n"}
{"conversations": [{"role": "user", "content": "For each route, show the route number and the total number of trips associated with it."}, {"role": "assistant", "content": "SELECT T2.route_number, count(T1.trip_id) FROM transportation.trips AS T1 JOIN transportation.routes AS T2 ON T1.route_id = T2.route_id GROUP BY T2.route_number"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles ( vehicle_id text PRIMARY KEY, license_plate text, vin text, make text, model text, year int, type text, capacity int, fuel_type text, status text, depot_id text, acquisition_date date )\nCREATE TABLE transportation.drivers ( driver_id text PRIMARY KEY, employee_id text, first_name text, last_name text, license_number text, license_expiry_date date, contact_number text, email text, hire_date date, status text )\nCREATE TABLE transportation.routes ( route_id text PRIMARY KEY, route_number text, description text, origin_location_id text, destination_location_id text, distance_km numeric, estimated_duration_minutes int, type text )\nCREATE TABLE transportation.trips ( trip_id text PRIMARY KEY, route_id text, vehicle_id text, driver_id text, scheduled_departure timestamp, actual_departure timestamp, scheduled_arrival timestamp, actual_arrival timestamp, origin_location_id text, destination_location_id text, status text, passenger_count int, cargo_manifest_id text )\nCREATE TABLE transportation.fuel_logs ( fuel_log_id text PRIMARY KEY, vehicle_id text, trip_id text, log_timestamp timestamp, fuel_type text, quantity numeric, unit text, cost_per_unit numeric, total_cost numeric, odometer_reading int, location_id text )\nCREATE TABLE transportation.passengers ( passenger_id text PRIMARY KEY, first_name text, last_name text, email text, phone_number text, date_of_birth date, loyalty_program_id text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "How many services are defined for each service category?"}, {"role": "assistant", "content": "SELECT category, COUNT(*) AS service_count FROM government_services.services GROUP BY category;"}, {"role": "user", "content": "Only show categories that have more than 15 services listed."}, {"role": "assistant", "content": "SELECT category, COUNT(*) AS service_count FROM government_services.services GROUP BY category HAVING COUNT(*) > 15;"}, {"role": "user", "content": "Could you only count services that are currently marked as active?"}, {"role": "assistant", "content": "SELECT category, COUNT(*) AS service_count FROM government_services.services WHERE is_active = true GROUP BY category HAVING COUNT(*) > 15;"}, {"role": "user", "content": "Also, for these categories, provide the average standard fee for the active services."}, {"role": "assistant", "content": "SELECT category, COUNT(*) AS service_count, AVG(standard_fee) AS average_fee FROM government_services.services WHERE is_active = true GROUP BY category HAVING COUNT(*) > 15;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens (\n    citizen_id character varying(64) NOT NULL,  -- unique identifier for the citizen\n    national_id_number character varying(128) NOT NULL UNIQUE, -- official national identification number\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    date_of_birth date NOT NULL,\n    gender character varying(20),\n    primary_address text NOT NULL, -- full primary residential address\n    contact_email character varying(128) UNIQUE,\n    contact_phone character varying(32),\n    registration_date timestamp NOT NULL, -- when the citizen profile was created\n    is_verified boolean DEFAULT false, -- whether identity has been officially verified\n    PRIMARY KEY (citizen_id)\n)\nCREATE TABLE government_services.agencies ( agency_id character varying(64) NOT NULL, agency_name character varying(255) NOT NULL, jurisdiction_level character varying(50) NOT NULL, primary_contact_email character varying(128), main_phone_number character varying(32), website_url character varying(255), established_date date, parent_agency_id character varying(64), PRIMARY KEY (agency_id) )\nCREATE TABLE government_services.services (\n    service_id character varying(64) NOT NULL, -- unique identifier for the service\n    agency_id character varying(64) NOT NULL, -- FK to agencies table\n    service_name character varying(255) NOT NULL, -- name of the service (e.g., Driver's License Renewal)\n    description text,\n    category character varying(100), -- e.g., Licensing, Benefits, Taxation, Permits\n    eligibility_criteria text, -- description of who is eligible\n    standard_fee numeric(10, 2) DEFAULT 0.00, -- typical fee for the service\n    average_processing_time_days integer, -- estimated processing time\n    is_active boolean DEFAULT true, -- whether the service is currently offered\n    online_application_url character varying(255),\n    PRIMARY KEY (service_id)\n)\nCREATE TABLE government_services.applications (\n    application_id character varying(64) NOT NULL, -- unique identifier for the application\n    citizen_id character varying(64) NOT NULL, -- FK to citizens table\n    service_id character varying(64) NOT NULL, -- FK to services table\n    submitted_at timestamp NOT NULL, -- time the application was submitted\n    status character varying(50) NOT NULL, -- e.g., Submitted, Processing, Approved, Rejected, Pending Info\n    last_updated_at timestamp NOT NULL, -- time the status or details last changed\n    assigned_employee_id character varying(64), -- FK to employees table (optional)\n    decision_date date, -- date when a final decision was made\n    notes text, -- internal notes or citizen-provided comments\n    reference_number character varying(100) UNIQUE, -- publicly visible reference number\n    PRIMARY KEY (application_id)\n)\nCREATE TABLE government_services.documents ( document_id text PRIMARY KEY, application_id text, citizen_id text, document_type text, file_reference text, upload_timestamp timestamp, expiry_date date, verification_status text, verified_by_employee_id text, verification_timestamp timestamp )\nCREATE TABLE government_services.payments ( payment_id text, application_id text, citizen_id text, service_id text, amount numeric, currency text, payment_method text, payment_provider_reference text, payment_timestamp timestamp, status text, notes text )\nCREATE TABLE government_services.employees (\n    employee_id character varying(64) NOT NULL, -- unique identifier for the government employee\n    agency_id character varying(64) NOT NULL, -- FK to agencies table\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    job_title character varying(150) NOT NULL,\n    department character varying(100),\n    work_email character varying(128) NOT NULL UNIQUE,\n    work_phone character varying(32),\n    hire_date date NOT NULL,\n    termination_date date, -- null if currently employed\n    access_level character varying(50), -- Role or permission level\n    manager_employee_id character varying(64), -- FK to self for reporting structure\n    PRIMARY KEY (employee_id)\n)\nCREATE TABLE government_services.appointments ( appointment_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, employee_id character varying(64), location_id character varying(64), service_id character varying(64), scheduled_start_time timestamp NOT NULL, scheduled_end_time timestamp, purpose text NOT NULL, status character varying(30) NOT NULL, booking_method character varying(50), created_at timestamp NOT NULL, notes text, PRIMARY KEY (appointment_id) )\n"}
{"conversations": [{"role": "user", "content": "What is the current address of the employee with ID 'EMP234'?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide the current address of an employee as this information is not stored in the database table."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE manufacturing.employees ( employee_id.text, first_name.text, last_name.text, job_title.text, skill_certifications.text, hire_date.date, assigned_line_id.text, employment_status.text, supervisor_employee_id.text )\n"}
{"conversations": [{"role": "user", "content": "For each patient, calculate the total duration of all their completed appointments. Show the patient ID and the total duration in minutes, sorted by total duration descending."}, {"role": "assistant", "content": "SELECT patient_id, SUM(duration_minutes) AS total_completed_duration FROM healthcare.appointments WHERE status = 'Completed' GROUP BY patient_id ORDER BY total_completed_duration DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.appointments (\n    appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    doctor_id character varying(64) NOT NULL, -- FK to doctors table\n    appointment_time timestamp with time zone NOT NULL, -- date and time of the appointment\n    duration_minutes integer NOT NULL, -- expected duration in minutes\n    reason text, -- reason for the visit\n    status character varying(32) NOT NULL, -- e.g., Scheduled, Completed, Cancelled, No-show\n    location_id character varying(64), -- FK to a potential locations/clinics table\n    notes text, -- notes related to scheduling\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (appointment_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List all insurance products that have no active policies currently."}, {"role": "assistant", "content": "SELECT ip.product_id, ip.product_name, ip.product_type FROM insurance.insurance_products ip LEFT JOIN insurance.policies p ON ip.product_id = p.product_id AND p.status = 'Active' WHERE p.policy_id IS NULL AND ip.is_active = true;"}, {"role": "user", "content": "Now include only products that were created in the last year."}, {"role": "assistant", "content": "SELECT ip.product_id, ip.product_name, ip.product_type FROM insurance.insurance_products ip LEFT JOIN insurance.policies p ON ip.product_id = p.product_id AND p.status = 'Active' WHERE p.policy_id IS NULL AND ip.is_active = true AND ip.created_at >= CURRENT_DATE - INTERVAL '1 year';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.customers ( customer_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, ssn_hash character varying(128), address_line1 character varying(255) NOT NULL, address_line2 character varying(255), city character varying(100) NOT NULL, state character varying(50) NOT NULL, zip_code character varying(20) NOT NULL, country character varying(50) NOT NULL DEFAULT 'USA', phone_number character varying(30), email character varying(128) UNIQUE, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, updated_at timestamp, status character varying(20) NOT NULL DEFAULT 'Active', PRIMARY KEY (customer_id) )\nCREATE TABLE insurance.policies ( policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, product_id character varying(64) NOT NULL, agent_id character varying(64), policy_number character varying(100) NOT NULL UNIQUE, start_date date NOT NULL, end_date date NOT NULL, premium_amount numeric(12, 2) NOT NULL, coverage_limit numeric(15, 2) NOT NULL, deductible numeric(10, 2) NOT NULL, status character varying(30) NOT NULL, issued_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, cancellation_date date, cancellation_reason text, PRIMARY KEY (policy_id) )\nCREATE TABLE insurance.claims ( claim_id character varying(64) NOT NULL, policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, incident_date timestamp NOT NULL, reported_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, description text NOT NULL, estimated_loss numeric(15, 2), status character varying(30) NOT NULL, settlement_amount numeric(15, 2), settlement_date date, claim_handler_id character varying(64), police_report_number character varying(100), PRIMARY KEY (claim_id) )\nCREATE TABLE insurance.insurance_products ( product_id character varying(64) NOT NULL, product_name character varying(150) NOT NULL, product_type character varying(50) NOT NULL, description text, base_premium numeric(10, 2) NOT NULL, coverage_details text, underwriting_rules text, is_active boolean NOT NULL DEFAULT true, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, updated_at timestamp, PRIMARY KEY (product_id) )\nCREATE TABLE insurance.claim_documents ( document_id character varying(64) NOT NULL, claim_id character varying(64) NOT NULL, document_type character varying(50) NOT NULL, file_name character varying(255) NOT NULL, file_path character varying(512) NOT NULL, file_size_bytes integer, mime_type character varying(100), uploaded_by character varying(64), uploaded_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, description text, PRIMARY KEY (document_id) )\n"}
{"conversations": [{"role": "user", "content": "What is the total revenue generated by ticket sales at the station with ID 'ST101' for the past month?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information on the revenue generated by ticket sales as this data is not available in the current database table. The table only contains details about station information such as name, location, and platform count. If you have another question or need assistance with something else related to the station data, I'm happy to help."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.stations ( station_id.text, station_name.text, city.text, state_province.text, country_code.text, address.text, timezone.text, number_of_platforms.integer, created_at.timestamp, last_updated_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "List all users who have deployed contracts, along with their email addresses and the count of contracts they've deployed."}, {"role": "assistant", "content": "SELECT u.user_id, u.email, COUNT(c.contract_id) AS contract_count FROM web3.users u JOIN web3.contracts c ON u.user_id = c.deployer_address GROUP BY u.user_id, u.email;"}, {"role": "user", "content": "Actually, I only want to see users who have deployed more than 3 contracts."}, {"role": "assistant", "content": "SELECT u.user_id, u.email, COUNT(c.contract_id) AS contract_count FROM web3.users u JOIN web3.contracts c ON u.user_id = c.deployer_address GROUP BY u.user_id, u.email HAVING COUNT(c.contract_id) > 3;"}, {"role": "user", "content": "There's an error in your SQL, it should be 'deployer_address' not 'user_id' in the JOIN condition."}, {"role": "assistant", "content": "SELECT u.user_id, u.email, COUNT(c.contract_id) AS contract_count FROM web3.users u JOIN web3.contracts c ON u.user_id = c.deployer_address GROUP BY u.user_id, u.email HAVING COUNT(c.contract_id) > 3;"}, {"role": "user", "content": "Now sort the results by contract_count in descending order."}, {"role": "assistant", "content": "SELECT u.user_id, u.email, COUNT(c.contract_id) AS contract_count FROM web3.users u JOIN web3.contracts c ON u.user_id = c.deployer_address GROUP BY u.user_id, u.email HAVING COUNT(c.contract_id) > 3 ORDER BY contract_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.contracts ( contract_id.text, address.text, abi.text, bytecode.text, deployer_address.text, deployed_at.timestamp, network_id.text, status.text )\nCREATE TABLE web3.transactions ( transaction_id text PRIMARY KEY, from_address text, to_address text, value numeric, gas_used int, gas_price numeric, block_number int, timestamp timestamp, input_data text, status text, nonce int )\nCREATE TABLE web3.users ( user_id character varying(64) NOT NULL, username character varying(128) NOT NULL, email character varying(128) NOT NULL, password_hash text NOT NULL, created_at timestamp NOT NULL, PRIMARY KEY (user_id) )\n"}
{"conversations": [{"role": "user", "content": "Show the first name, last name, and position of all staff members who are not currently active."}, {"role": "assistant", "content": "SELECT first_name ,  last_name ,  position FROM hospitality_technology.staff WHERE is_active  =  false"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.properties (\n    property_id character varying(64) NOT NULL,  -- unique identifier for the property (hotel, resort, etc.)\n    property_name character varying(255) NOT NULL, -- name of the property\n    address_line1 character varying(255) NOT NULL, -- primary address line\n    address_line2 character varying(255), -- secondary address line\n    city character varying(100) NOT NULL, -- city\n    state_province character varying(100), -- state or province\n    postal_code character varying(20) NOT NULL, -- zip or postal code\n    country_code character varying(3) NOT NULL, -- ISO country code (e.g., USA, CAN)\n    phone_number character varying(30), -- main contact phone\n    email_address character varying(255), -- main contact email\n    property_type character varying(50) NOT NULL, -- e.g., Hotel, Resort, B&B, Motel\n    star_rating numeric(2,1), -- star rating (e.g., 4.5)\n    timezone character varying(64) NOT NULL, -- IANA timezone ID (e.g., America/New_York)\n    manager_staff_id character varying(64), -- FK to staff table for the general manager\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, -- record creation time\n    updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, -- record last update time\n    PRIMARY KEY (property_id)\n)\nCREATE TABLE hospitality_technology.rooms (\n    room_id character varying(64) NOT NULL,  -- unique identifier for the room\n    property_id character varying(64) NOT NULL, -- FK to properties table\n    room_number character varying(10) NOT NULL, -- room number identifier (e.g., '101', 'Suite 2B')\n    room_type_id character varying(64) NOT NULL, -- FK to room_types table\n    floor integer, -- floor number the room is on\n    status character varying(50) NOT NULL, -- e.g., Available, Occupied, Cleaning, OutOfOrder, Maintenance\n    is_smoking boolean NOT NULL DEFAULT false, -- smoking allowed flag\n    features text, -- description of features (e.g., Balcony, Sea View, Jacuzzi)\n    current_condition text, -- notes on room condition\n    last_cleaned_at timestamp with time zone, -- timestamp of last cleaning\n    PRIMARY KEY (room_id),\n    FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n    FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id)\n)\nCREATE TABLE hospitality_technology.staff (\n    staff_id character varying(64) NOT NULL,  -- unique identifier for the staff member\n    property_id character varying(64) NOT NULL, -- FK to properties table (primary property)\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    position character varying(100) NOT NULL, -- e.g., Front Desk Agent, Housekeeper, Manager, Concierge\n    work_email character varying(255) UNIQUE, -- staff member's work email\n    work_phone character varying(30),\n    hire_date date NOT NULL,\n    termination_date date, -- date employment ended (if applicable)\n    is_active boolean NOT NULL DEFAULT true, -- currently employed flag\n    access_level integer NOT NULL, -- permission level within systems (e.g., 1=basic, 5=admin)\n    manager_id character varying(64), -- FK to staff table (self-referencing for supervisor)\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (staff_id),\n    FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n    FOREIGN KEY (manager_id) REFERENCES hospitality_technology.staff(staff_id)\n)\nCREATE TABLE hospitality_technology.reviews (\n    review_id character varying(64) NOT NULL,  -- unique identifier for the review\n    property_id character varying(64) NOT NULL, -- FK to properties table\n    reservation_id character varying(64) UNIQUE, -- FK to reservations (link review to a specific stay, optional but good)\n    guest_id character varying(64) NOT NULL, -- FK to guests table\n    rating_overall integer, -- overall score (e.g., 1-5 or 1-10)\n    rating_cleanliness integer,\n    rating_service integer,\n    rating_location integer,\n    rating_value integer,\n    comment text, -- guest's written feedback\n    review_source character varying(100), -- e.g., DirectSurvey, TripAdvisor, Google, Booking.com\n    review_date timestamp with time zone NOT NULL DEFAULT current_timestamp, -- when the review was submitted\n    is_public boolean DEFAULT true, -- whether the review is publicly visible\n    staff_response text, -- official response from the property\n    response_staff_id character varying(64), -- FK to staff (who responded)\n    response_date timestamp with time zone, -- when the response was posted\n    PRIMARY KEY (review_id),\n    FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n    FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id),\n    FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id),\n    FOREIGN KEY (response_staff_id) REFERENCES hospitality_technology.staff(staff_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Which NFTs minted in the past 14 days on Ethereum have a rarity_score above 70? For each, show contract address, token ID, name, and minter."}, {"role": "assistant", "content": "SELECT contract_address, token_id, name, minter\nFROM nft_metadata\nWHERE blockchain = 'Ethereum'\n  AND mint_time >= (extract(epoch from now()) - 14*24*60*60)\n  AND rarity_score > 70;"}, {"role": "user", "content": "For these NFTs, can you also include the collection name and symbol by joining with the nft_collections table?"}, {"role": "assistant", "content": "SELECT nm.contract_address, nm.token_id, nm.name, nm.minter, nc.name AS collection_name, nc.symbol\nFROM nft_metadata nm\nJOIN nft_collections nc\n  ON nm.blockchain = nc.blockchain AND nm.contract_address = nc.contract_address\nWHERE nm.blockchain = 'Ethereum'\n  AND nm.mint_time >= (extract(epoch from now()) - 14*24*60*60)\n  AND nm.rarity_score > 70;"}, {"role": "user", "content": "Can you filter only those collections where the erc_type is 'ERC1155'?"}, {"role": "assistant", "content": "SELECT nm.contract_address, nm.token_id, nm.name, nm.minter, nc.name AS collection_name, nc.symbol\nFROM nft_metadata nm\nJOIN nft_collections nc\n  ON nm.blockchain = nc.blockchain AND nm.contract_address = nc.contract_address\nWHERE nm.blockchain = 'Ethereum'\n  AND nm.mint_time >= (extract(epoch from now()) - 14*24*60*60)\n  AND nm.rarity_score > 70\n  AND nc.erc_type = 'ERC1155';"}, {"role": "user", "content": "Now, also include the owner for each NFT, and order the results by rarity_rank ascending."}, {"role": "assistant", "content": "SELECT nm.contract_address, nm.token_id, nm.name, nm.minter, nm.owner, nc.name AS collection_name, nc.symbol\nFROM nft_metadata nm\nJOIN nft_collections nc\n  ON nm.blockchain = nc.blockchain AND nm.contract_address = nc.contract_address\nWHERE nm.blockchain = 'Ethereum'\n  AND nm.mint_time >= (extract(epoch from now()) - 14*24*60*60)\n  AND nm.rarity_score > 70\n  AND nc.erc_type = 'ERC1155'\nORDER BY nm.rarity_rank ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE nft_holders ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, token_id varchar NOT NULL, contract_type varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_coins_metadata (\n    object_id varchar NOT NULL, -- object id of the coin metadata object\n    coin_type varchar NOT NULL, -- coin type, eg. 0x...66::reap_token::REAP_TOKEN\n    status varchar NOT NULL, -- coin status, eg. exists, deleted\n    decimals bigint NOT NULL, -- decimals of the coin\n    description varchar NOT NULL, -- description of the coin\n    icon_url varchar NOT NULL, -- icon url of the coin\n    symbol varchar NOT NULL, -- symbol of the coin\n    name varchar NOT NULL  -- name of the coin\n)\nCREATE TABLE sui_nfts ( object_id text, status text, collection_type text, package_id text, previous_transaction text, display text, owner text, name text )\nCREATE TABLE nft_metadata ( blockchain text, contract_address text, token_id text, contract_name text, erc_type text, amount bigint, minter text, owner text, mint_block_number bigint, mint_time bigint, mint_transaction_hash text, mint_price text, token_uri text, metadata text, name text, image_uri text, traits text, updated_at bigint, status text, rarity_score real, rarity_rank integer, unique_attribute_count integer, pk integer )\nCREATE TABLE nft_collections ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, name varchar NOT NULL, symbol varchar NOT NULL, deploy_block_number bigint NOT NULL, deploy_block_time bigint NOT NULL, erc_type varchar NOT NULL, owner varchar NOT NULL, traits varchar NOT NULL, description varchar NOT NULL, slug varchar NOT NULL, media_info varchar NOT NULL, image_url varchar NOT NULL, banner_image_url varchar NOT NULL, updated_at bigint NOT NULL, banner varchar NOT NULL, token_count bigint NOT NULL, floor_price varchar NOT NULL, floor_price_symbol varchar NOT NULL, floor_price_contract varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_prices ( uuid text, blockchain text, address text, decimals bigint, symbol text, price real, timestamp timestamp )\nCREATE TABLE token_prices_latest (\n    blockchain varchar(36) NOT NULL, -- blockchain fields for the functionType  in contract\n    address varchar(42) NOT NULL, -- address fields for the functionType  in contract\n    decimals bigint NOT NULL, -- decimals fields for the functionType  in contract\n    symbol varchar(36) NOT NULL, -- symbol fields for the functionType  in contract\n    price real NOT NULL, -- price fields for the functionType  in contract\n    timestamp timestamp(6) NOT NULL  -- timestamp fields for the functionType  in contract\n)\nCREATE TABLE erc20_approval ( block_number bigint NOT NULL, block_timestamp timestamp(6) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar NOT NULL, log_index integer NOT NULL, contract_address varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_balances ( block_number.bigint, block_timestamp.timestamp, tick.text, wallet_address.text, total_supply.decimal, amount.decimal )\nCREATE TABLE token_info (\n    block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n    block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n    tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n    tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n    tick varchar NOT NULL, -- Token tick\n    max_supply decimal(38,0) NOT NULL, -- Max supply\n    lim decimal(38,0) NOT NULL, -- Limit of each mint\n    wlim decimal(38,0) NOT NULL, -- Limit of each address can maximum mint\n    dec integer NOT NULL, -- Decimal for minimum divie\n    creator varchar(42) NOT NULL  -- Address originating the inscription (matches from_address in transactions table)\n)\nCREATE TABLE mud_holesky_redstone (\n    address varchar NOT NULL, -- address fields for the functionType  in contract\n    table_id varchar NOT NULL, -- table_id fields for the functionType  in contract\n    key_bytes varchar NOT NULL, -- key_bytes fields for the functionType  in contract\n    key0 varchar NOT NULL, -- key0 fields for the functionType  in contract\n    key1 varchar NOT NULL, -- key1 fields for the functionType  in contract\n    static_data varchar NOT NULL, -- static_data fields for the functionType  in contract\n    encoded_lengths varchar NOT NULL, -- encoded_lengths fields for the functionType  in contract\n    dynamic_data varchar NOT NULL, -- dynamic_data fields for the functionType  in contract\n    is_deleted boolean NOT NULL, -- is_deleted fields for the functionType  in contract\n    block_number bigint NOT NULL, -- Block number uniquely identifying the block\n    log_index bigint NOT NULL  -- Index of the log within the transaction\n)\nCREATE TABLE token_info_bitcoin ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, tick.text, max_supply.decimal, lim.decimal, wlim.decimal, dec.integer, creator.text )\nCREATE TABLE token_activities_avalanche (\n    block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n    block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n    tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n    tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n    log_index integer NOT NULL, -- Index of the log within the transaction\n    type varchar(20) NOT NULL, -- Operation: Type of event (deploy, mint, transfer, list)\n    tick varchar(255) NOT NULL, -- Ticker: Identifier of the inscription\n    id varchar(255) NOT NULL, -- Unique identifier of the inscription\n    amt decimal(38,0) NOT NULL, -- Amount to mint: States the amount of the inscription to operation. When operation is mint, has to be less or equal to \"lim\"\n    from_address varchar(42) NOT NULL, -- Address sending the inscription\n    to_address varchar(42) NOT NULL  -- Address receiving the inscription\n)\nCREATE TABLE token_balances_avalanche ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply decimal, amount decimal )\n"}
{"conversations": [{"role": "user", "content": "For each chain, which centralized exchange holds the largest total USD value in their token balance as of the most recent snapshot?"}, {"role": "assistant", "content": "WITH latest_snapshot AS (\n  SELECT MAX(snapshot_time) AS max_time FROM cex_token_balance\n)\nSELECT c.chain, c.exchange, SUM(c.usd_value) AS total_usd_value\nFROM cex_token_balance c\nJOIN latest_snapshot l ON c.snapshot_time = l.max_time\nGROUP BY c.chain, c.exchange\nQUALIFY ROW_NUMBER() OVER(PARTITION BY c.chain ORDER BY SUM(c.usd_value) DESC) = 1;"}, {"role": "user", "content": "Could you also include the number of distinct tokens each exchange holds in those chains?"}, {"role": "assistant", "content": "WITH latest_snapshot AS (\n  SELECT MAX(snapshot_time) AS max_time FROM cex_token_balance\n),\nexchange_totals AS (\n  SELECT c.chain, c.exchange, SUM(c.usd_value) AS total_usd_value, COUNT(DISTINCT c.token_symbol) AS token_count\n  FROM cex_token_balance c\n  JOIN latest_snapshot l ON c.snapshot_time = l.max_time\n  GROUP BY c.chain, c.exchange\n),\nranked_exchanges AS (\n  SELECT *, ROW_NUMBER() OVER(PARTITION BY chain ORDER BY total_usd_value DESC) AS rn\n  FROM exchange_totals\n)\nSELECT chain, exchange, total_usd_value, token_count\nFROM ranked_exchanges\nWHERE rn = 1;"}, {"role": "user", "content": "I got an error with the QUALIFY clause. Can you rewrite the query using a derived table or CTE instead?"}, {"role": "assistant", "content": "WITH latest_snapshot AS (\n  SELECT MAX(snapshot_time) AS max_time FROM cex_token_balance\n),\nexchange_totals AS (\n  SELECT c.chain, c.exchange, SUM(c.usd_value) AS total_usd_value, COUNT(DISTINCT c.token_symbol) AS token_count\n  FROM cex_token_balance c\n  JOIN latest_snapshot l ON c.snapshot_time = l.max_time\n  GROUP BY c.chain, c.exchange\n),\nmax_values AS (\n  SELECT chain, MAX(total_usd_value) AS max_usd_value\n  FROM exchange_totals\n  GROUP BY chain\n)\nSELECT e.chain, e.exchange, e.total_usd_value, e.token_count\nFROM exchange_totals e\nJOIN max_values m ON e.chain = m.chain AND e.total_usd_value = m.max_usd_value;"}, {"role": "user", "content": "Now, only show exchanges where their usd_value is above $5,000,000."}, {"role": "assistant", "content": "WITH latest_snapshot AS (\n  SELECT MAX(snapshot_time) AS max_time FROM cex_token_balance\n),\nexchange_totals AS (\n  SELECT c.chain, c.exchange, SUM(c.usd_value) AS total_usd_value, COUNT(DISTINCT c.token_symbol) AS token_count\n  FROM cex_token_balance c\n  JOIN latest_snapshot l ON c.snapshot_time = l.max_time\n  GROUP BY c.chain, c.exchange\n),\nmax_values AS (\n  SELECT chain, MAX(total_usd_value) AS max_usd_value\n  FROM exchange_totals\n  GROUP BY chain\n)\nSELECT e.chain, e.exchange, e.total_usd_value, e.token_count\nFROM exchange_totals e\nJOIN max_values m ON e.chain = m.chain AND e.total_usd_value = m.max_usd_value\nWHERE e.total_usd_value > 5000000;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE project_fundraising_record ( id character varying(32) NOT NULL,  -- fundraising record id project_id character varying(32) NOT NULL, -- the invested project's id project_name character varying(128) NOT NULL, -- name of the invested project rounds_name character varying(32), -- name of the fundraising round investment_value numeric(38,14), -- amount of the fundraising in USD investment_date character varying(128), -- the date of the investment happened introduction character varying(128), -- the introduction of the invested project valuation numeric(38,14), -- the valuation of the project in USD when invested )\nCREATE TABLE token_basic_info ( coin_id character varying(100) NOT NULL, -- the id of the token token_name character varying(100) NOT NULL, -- the token's name token_symbol character varying(100) NOT NULL, -- the token's symbol token_address character varying(100) NOT NULL, -- the token's address chain text, -- the chain that the token resides price double precision, -- the current price of the token price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days highest_price_24h double precision, -- the highest price of the token in 24 hours lowest_price_24h double precision,  -- the lowest price of the token in 24 hours market_cap double precision, -- the market cap of the token market_cap_rank bigint, -- the rank of the token market cap in desc market_cap_change_percentage_24h text, -- the percentage of market cap changes in 24 hours total_volume text, -- the trade volum of the token both in decentralized exchange(DEX) and centralized exchange(CEX) narrative text, -- the category or narrative of the token trend_rank biging, -- the trending rank of the token, value 1 expresses the most popular token. ,PRIMARY KEY (coin_id, chain) )\nCREATE TABLE narrative_info ( narrative.text, top_3_coins.text, price_change_percentage_1h.numeric, price_change_percentage_24h.numeric, price_change_percentage_7d.numeric, market_cap.numeric, volume_24h.numeric, trend_rank.numeric, token_num.numeric )\nCREATE TABLE cex_token_balance ( snapshot_time character varying(32) NOT NULL,  -- the snapshot time of record, converted from original timestamp chain character varying(128) NOT NULL, -- the chain that the token resides address character varying(128) NOT NULL, -- the address that holds the assets, owned by a CEX exchange character varying(512) NOT NULL, -- a centralized exchange name token_address character varying(128) NOT NULL, -- token contract address token_symbol character varying(512), --token symbol balance numeric(38,10), -- token balance usd_value numeric(38,14), -- value of the token held in USD price double precision, --price of the token in USD ,PRIMARY KEY (snapshot_time, exchange, address, chain, token_address) )\nCREATE TABLE smart_money_profit ( address text, rank numeric, profit numeric, roi numeric, realized_ratio numeric, most_profit_token text, last_trade_time text, chain text )\n"}
{"conversations": [{"role": "user", "content": "Show me the name and type for all the locations."}, {"role": "assistant", "content": "SELECT name, type FROM transportation.locations"}, {"role": "user", "content": "Now, filter this list to only include locations whose type is either 'Distribution Center' or 'Warehouse'."}, {"role": "assistant", "content": "SELECT name, type FROM transportation.locations WHERE type IN ('Distribution Center', 'Warehouse')"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.locations ( location_id.text, name.text, type.text, address_line1.text, city.text, state_province.text, postal_code.text, country.text, latitude.numeric, longitude.numeric, timezone.text )\n"}
{"conversations": [{"role": "user", "content": "List all customers who have two policies with overlapping coverage periods and show both policy numbers along with the overlap start and end dates."}, {"role": "assistant", "content": "SELECT p1.customer_id, p1.policy_number AS policy_number1, p2.policy_number AS policy_number2, GREATEST(p1.start_date, p2.start_date) AS overlap_start, LEAST(p1.end_date, p2.end_date) AS overlap_end FROM insurance.policies p1 JOIN insurance.policies p2 ON p1.customer_id = p2.customer_id AND p1.policy_id < p2.policy_id WHERE p1.start_date <= p2.end_date AND p2.start_date <= p1.end_date;"}, {"role": "user", "content": "Actually, I only want overlapping policies where both policies are currently active."}, {"role": "assistant", "content": "SELECT p1.customer_id, p1.policy_number AS policy_number1, p2.policy_number AS policy_number2, GREATEST(p1.start_date, p2.start_date) AS overlap_start, LEAST(p1.end_date, p2.end_date) AS overlap_end FROM insurance.policies p1 JOIN insurance.policies p2 ON p1.customer_id = p2.customer_id AND p1.policy_id < p2.policy_id WHERE p1.status = 'active' AND p2.status = 'active' AND p1.start_date <= p2.end_date AND p2.start_date <= p1.end_date;"}, {"role": "user", "content": "Also include the number of days of overlap as overlap_days."}, {"role": "assistant", "content": "SELECT p1.customer_id, p1.policy_number AS policy_number1, p2.policy_number AS policy_number2, GREATEST(p1.start_date, p2.start_date) AS overlap_start, LEAST(p1.end_date, p2.end_date) AS overlap_end, (LEAST(p1.end_date, p2.end_date) - GREATEST(p1.start_date, p2.start_date)) AS overlap_days FROM insurance.policies p1 JOIN insurance.policies p2 ON p1.customer_id = p2.customer_id AND p1.policy_id < p2.policy_id WHERE p1.status = 'active' AND p2.status = 'active' AND p1.start_date <= p2.end_date AND p2.start_date <= p1.end_date;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.policies ( policy_id text, customer_id text, product_id text, agent_id text, policy_number text, start_date date, end_date date, premium_amount numeric, coverage_limit numeric, deductible numeric, status text, issued_at timestamp, cancellation_date date, cancellation_reason text )\n"}
{"conversations": [{"role": "user", "content": "I want to list all insurance plans along with the number of medical records that have a record_date in 2024. Display plan_id, plan_name, and the total medical records."}, {"role": "assistant", "content": "SELECT ip.plan_id, ip.plan_name, COUNT(mr.record_id) AS total_medical_records\nFROM healthcare.insurance_plans ip\nLEFT JOIN healthcare.medical_records mr ON 1=0 -- there is no direct relationship in schema, so no records will be counted\nWHERE mr.record_date >= '2024-01-01' AND mr.record_date < '2025-01-01'\nGROUP BY ip.plan_id, ip.plan_name;"}, {"role": "user", "content": "Since there's no direct relationship, can you adjust it to just show all insurance plans of type 'EPO' with their plan_id and plan_name?"}, {"role": "assistant", "content": "SELECT plan_id, plan_name\nFROM healthcare.insurance_plans\nWHERE plan_type = 'EPO';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.medical_records (\n    record_id character varying(64) NOT NULL,  -- unique identifier for the medical record entry\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    appointment_id character varying(64) UNIQUE, -- FK to appointments table (can be null if record not tied to specific appt)\n    doctor_id character varying(64) NOT NULL, -- FK to doctors table (doctor creating the record)\n    record_date timestamp with time zone NOT NULL, -- date the record/observation was made\n    chief_complaint text, -- patient's primary reason for visit\n    present_illness_history text, -- detailed history of the current issue\n    past_medical_history text, -- relevant past conditions/surgeries\n    physical_examination_notes text, -- findings from the physical exam\n    assessment text, -- doctor's assessment/diagnosis summary\n    treatment_plan text, -- planned course of action\n    vitals jsonb, -- store vitals like BP, HR, Temp as structured JSON\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (record_id)\n)\nCREATE TABLE healthcare.insurance_plans ( plan_id text, plan_name text, insurance_provider text, plan_type text, contact_phone text, website text )\n"}
{"conversations": [{"role": "user", "content": "Show me the notification ID, recipient user ID, and notification type for notifications received by users that user 'user123' is following."}, {"role": "assistant", "content": "SELECT n.notification_id, n.recipient_user_id, n.notification_type FROM social_media.notifications AS n JOIN social_media.follows AS f ON n.recipient_user_id = f.following_user_id WHERE f.follower_user_id = 'user123';"}, {"role": "user", "content": "Filter this list to only include notifications created after '2024-06-01' and also show the notification creation time."}, {"role": "assistant", "content": "SELECT n.notification_id, n.recipient_user_id, n.notification_type, n.created_at FROM social_media.notifications AS n JOIN social_media.follows AS f ON n.recipient_user_id = f.following_user_id WHERE f.follower_user_id = 'user123' AND n.created_at >= '2024-06-01';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.comments ( comment_id.text, post_id.text, user_id.text, parent_comment_id.text, content.text, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE social_media.follows ( follow_id.text, follower_user_id.text, following_user_id.text, created_at.timestamp )\nCREATE TABLE social_media.conversations ( conversation_id.text, created_at.timestamp, last_message_at.timestamp, is_group_chat.boolean, group_name.text )\nCREATE TABLE social_media.notifications ( notification_id.text, recipient_user_id.text, sender_user_id.text, notification_type.text, target_entity_id.text, target_entity_type.text, created_at.timestamp, read_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "能否帮我查询特定路线(route_id 为 'RT001')的所有行程信息，并关联到乘客的联系方式？"}, {"role": "assistant", "content": "SELECT s.schedule_id, s.train_id, s.route_id, s.departure_datetime, s.arrival_datetime, s.status, p.passenger_id, p.first_name, p.last_name, p.phone_number, p.email\nFROM schedules s\nLEFT JOIN passengers p ON s.schedule_id = (SELECT schedule_id FROM bookings WHERE passenger_id = p.passenger_id)\nWHERE s.route_id = 'RT001';"}, {"role": "user", "content": "能否只显示状态为‘On Time’的行程，并按出发时间升序排列？"}, {"role": "assistant", "content": "SELECT s.schedule_id, s.train_id, s.route_id, s.departure_datetime, s.arrival_datetime, s.status, p.passenger_id, p.first_name, p.last_name, p.phone_number, p.email\nFROM schedules s\nLEFT JOIN passengers p ON s.schedule_id = (SELECT schedule_id FROM bookings WHERE passenger_id = p.passenger_id)\nWHERE s.route_id = 'RT001' AND s.status = 'On Time'\nORDER BY s.departure_datetime ASC;"}, {"role": "user", "content": "如果乘客信息为空，能否仍然显示行程信息，并限制结果前10条？"}, {"role": "assistant", "content": "SELECT s.schedule_id, s.train_id, s.route_id, s.departure_datetime, s.arrival_datetime, s.status, p.passenger_id, p.first_name, p.last_name, p.phone_number, p.email\nFROM schedules s\nLEFT JOIN passengers p ON s.schedule_id = (SELECT schedule_id FROM bookings WHERE passenger_id = p.passenger_id)\nWHERE s.route_id = 'RT001' AND s.status = 'On Time'\nORDER BY s.departure_datetime ASC\nLIMIT 10;"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\n// PUT /schedules\n{\n  \"mappings\": {\n    \"properties\": {\n      \"schedule_id\": { \"type\": \"keyword\" },\n      \"train_id\": { \"type\": \"keyword\" }, // References trains index\n      \"route_id\": { \"type\": \"keyword\" }, // References routes index\n      \"departure_datetime\": { \"type\": \"date\" }, // ISO 8601 format recommended\n      \"arrival_datetime\": { \"type\": \"date\" },\n      \"status\": { \"type\": \"keyword\" },\n      \"notes\": { \"type\": \"text\" }\n    }\n  }\n}\n// PUT /passengers\n{\n  \"mappings\": {\n    \"properties\": {\n      \"passenger_id\": { \"type\": \"keyword\" },\n      \"first_name\": { \n        \"type\": \"text\", \n        \"fields\": { \"keyword\": { \"type\": \"keyword\", \"ignore_above\": 100 } }\n      },\n      \"last_name\": { \n        \"type\": \"text\", \n        \"fields\": { \"keyword\": { \"type\": \"keyword\", \"ignore_above\": 100 } }\n       },\n      \"email\": { \"type\": \"keyword\" }, // Often used for exact matches\n      \"phone_number\": { \"type\": \"keyword\" },\n      \"date_of_birth\": { \"type\": \"date\", \"format\": \"yyyy-MM-dd\" },\n      \"loyalty_program_id\": { \"type\": \"keyword\" },\n      \"created_at\": { \"type\": \"date\" }\n    }\n  }\n}\n"}
{"conversations": [{"role": "user", "content": "What is the average daily trading volume for each security_id in the market_data table from the last 30 days?"}, {"role": "assistant", "content": "SELECT security_id, AVG(volume) as avg_daily_volume FROM financial_services.market_data WHERE data_timestamp >= CURRENT_DATE - INTERVAL '30 days' GROUP BY security_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.accounts ( account_id text, customer_id text, account_number text, account_type text, balance numeric, currency text, opened_date date, status text, interest_rate numeric, last_updated_at timestamp )\nCREATE TABLE financial_services.securities ( security_id.text, ticker_symbol.text, isin_code.text, cusip_code.text, security_name.text, security_type.text, exchange.text, currency.text, issuer_name.text, sector.text, last_updated.timestamp )\nCREATE TABLE financial_services.trades ( trade_id text, account_id text, security_id text, order_id text, trade_type text, quantity numeric, price_per_unit numeric, total_amount numeric, commission numeric, trade_timestamp timestamp, settlement_date date, status text, execution_venue text )\nCREATE TABLE financial_services.market_data ( data_point_id.bigint, security_id.text, data_timestamp.timestamp, open_price.numeric, high_price.numeric, low_price.numeric, close_price.numeric, adjusted_close_price.numeric, volume.bigint, source.text )\nCREATE TABLE financial_services.employees ( employee_id text, first_name text, last_name text, job_title text, department text, branch_id text, email text, phone_extension text, hire_date date, termination_date date, manager_id text, status text )\n"}
{"conversations": [{"role": "user", "content": "List all vehicles that use diesel fuel, showing their make, model, and year."}, {"role": "assistant", "content": "SELECT make, model, year FROM transportation.vehicles WHERE fuel_type = 'diesel';"}, {"role": "user", "content": "Now include only vehicles acquired in the last 5 years."}, {"role": "assistant", "content": "SELECT make, model, year FROM transportation.vehicles WHERE fuel_type = 'diesel' AND acquisition_date >= CURRENT_DATE - INTERVAL '5 years';"}, {"role": "user", "content": "Can you also show their status and order the results by year in descending order?"}, {"role": "assistant", "content": "SELECT make, model, year, status FROM transportation.vehicles WHERE fuel_type = 'diesel' AND acquisition_date >= CURRENT_DATE - INTERVAL '5 years' ORDER BY year DESC;"}, {"role": "user", "content": "Actually, I only want to see active vehicles in this list."}, {"role": "assistant", "content": "SELECT make, model, year, status FROM transportation.vehicles WHERE fuel_type = 'diesel' AND acquisition_date >= CURRENT_DATE - INTERVAL '5 years' AND status = 'active' ORDER BY year DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles ( vehicle_id text PRIMARY KEY, license_plate text, vin text, make text, model text, year int, type text, capacity int, fuel_type text, status text, depot_id text, acquisition_date date )\n"}
{"conversations": [{"role": "user", "content": "List the transaction IDs and gas used for transactions where gas used is greater than 500000."}, {"role": "assistant", "content": "SELECT transaction_id, gas_used FROM web3.transactions WHERE gas_used > 500000;"}, {"role": "user", "content": "Order the results by gas used in descending order."}, {"role": "assistant", "content": "SELECT transaction_id, gas_used FROM web3.transactions WHERE gas_used > 500000 ORDER BY gas_used DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.contracts ( contract_id character varying(64) NOT NULL, address character varying(128) NOT NULL, abi text NOT NULL, bytecode text NOT NULL, deployer_address character varying(128) NOT NULL, deployed_at timestamp NOT NULL, network_id character varying(64) NOT NULL, status character varying(32) NOT NULL, PRIMARY KEY (contract_id) )\nCREATE TABLE web3.transactions ( transaction_id character varying(64) NOT NULL, from_address character varying(128) NOT NULL, to_address character varying(128), value numeric(38,14) NOT NULL, gas_used integer NOT NULL, gas_price numeric(38,14) NOT NULL, block_number integer NOT NULL, timestamp timestamp NOT NULL, input_data text, status character varying(32) NOT NULL, nonce integer NOT NULL, PRIMARY KEY (transaction_id) )\nCREATE TABLE web3.users ( user_id text, username text, email text, password_hash text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "List pairs of routes where the destination of one route matches the origin of another route."}, {"role": "assistant", "content": "SELECT r1.route_number AS route_1, r2.route_number AS route_2 FROM transportation.routes r1 JOIN transportation.routes r2 ON r1.destination_location_id = r2.origin_location_id;"}, {"role": "user", "content": "Now restrict to pairs where both routes are of type 'Intercity' and order by the first route_number."}, {"role": "assistant", "content": "SELECT r1.route_number AS route_1, r2.route_number AS route_2 FROM transportation.routes r1 JOIN transportation.routes r2 ON r1.destination_location_id = r2.origin_location_id WHERE r1.type = 'Intercity' AND r2.type = 'Intercity' ORDER BY r1.route_number;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.routes ( route_id text PRIMARY KEY, route_number text, description text, origin_location_id text, destination_location_id text, distance_km numeric, estimated_duration_minutes int, type text )\n"}
{"conversations": [{"role": "user", "content": "List all accounts for customers who have at least one account with a balance over 10000 and another account with a balance under 1000. Show customer_id, account_id, account_type, balance, and currency."}, {"role": "assistant", "content": "SELECT account_id ,  customer_id ,  account_type ,  balance ,  currency FROM financial_services.accounts WHERE customer_id IN ( SELECT T1.customer_id FROM financial_services.accounts AS T1 JOIN financial_services.accounts AS T2 ON T1.customer_id  =  T2.customer_id WHERE T1.balance  >  10000 AND T2.balance  <  1000 )"}, {"role": "user", "content": "Actually, I only want to see the accounts that meet the specific balance criteria (over 10k or under 1k), not all accounts for those customers. And only include accounts where the status is 'Open'."}, {"role": "assistant", "content": "SELECT account_id ,  customer_id ,  account_type ,  balance ,  currency FROM financial_services.accounts WHERE customer_id IN ( SELECT T1.customer_id FROM financial_services.accounts AS T1 JOIN financial_services.accounts AS T2 ON T1.customer_id  =  T2.customer_id WHERE T1.balance  >  10000 AND T2.balance  <  1000 ) AND (balance  >  10000 OR balance  <  1000) AND status  =  'Open'"}, {"role": "user", "content": "Could you also include the opened_date and sort the results by customer_id, then by balance descending?"}, {"role": "assistant", "content": "SELECT account_id ,  customer_id ,  account_type ,  balance ,  currency ,  opened_date FROM financial_services.accounts WHERE customer_id IN ( SELECT T1.customer_id FROM financial_services.accounts AS T1 JOIN financial_services.accounts AS T2 ON T1.customer_id  =  T2.customer_id WHERE T1.balance  >  10000 AND T2.balance  <  1000 ) AND (balance  >  10000 OR balance  <  1000) AND status  =  'Open' ORDER BY customer_id ASC ,  balance DESC"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.accounts ( account_id text, customer_id text, account_number text, account_type text, balance numeric, currency text, opened_date date, status text, interest_rate numeric, last_updated_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "What is the performance review score for employee with ID 'EMP456' for the last quarter?"}, {"role": "assistant", "content": "I'm sorry, but I can't assist with information about performance review scores as this data is not included in the employees table."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE manufacturing.employees ( employee_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, job_title character varying(128) NOT NULL, skill_certifications text, hire_date date NOT NULL, assigned_line_id character varying(64), employment_status character varying(50) NOT NULL, supervisor_employee_id character varying(64), PRIMARY KEY (employee_id) )\n"}
{"conversations": [{"role": "user", "content": "Show a list of all wallet addresses along with the user_id who owns them, sorted by the wallet creation time."}, {"role": "assistant", "content": "SELECT user_id, address FROM web3.wallets ORDER BY created_at;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.wallets (\n    wallet_id character varying(64) NOT NULL,  -- unique identifier for the wallet\n    user_id character varying(64) NOT NULL, -- identifier of the user owning the wallet\n    address character varying(128) NOT NULL, -- address of the wallet\n    private_key text NOT NULL, -- private key of the wallet\n    created_at timestamp NOT NULL, -- time when the wallet was created\n    PRIMARY KEY (wallet_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Show me all room types with a base rate over $200 and max occupancy of at least 4, along with their property IDs and amenities."}, {"role": "assistant", "content": "SELECT room_type_id, property_id, amenities FROM hospitality_technology.room_types WHERE base_rate > 200 AND max_occupancy >= 4;"}, {"role": "user", "content": "Now, join this with the service_orders table to show only room types that have at least 5 service orders."}, {"role": "assistant", "content": "SELECT rt.room_type_id, rt.property_id, rt.amenities FROM hospitality_technology.room_types rt JOIN hospitality_technology.service_orders so ON rt.property_id = so.property_id WHERE rt.base_rate > 200 AND rt.max_occupancy >= 4 GROUP BY rt.room_type_id, rt.property_id, rt.amenities HAVING COUNT(so.order_id) >= 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.room_types ( room_type_id text PRIMARY KEY, property_id text, type_name text, description text, base_rate numeric, max_occupancy int, bed_type text, area_sqft numeric, amenities text )\nCREATE TABLE hospitality_technology.service_orders ( order_id text PRIMARY KEY, reservation_id text, guest_id text, service_id text, staff_id_ordered text, staff_id_delivered text, order_timestamp timestamp, delivery_timestamp timestamp, quantity int, unit_price numeric, total_price numeric, status text, notes text, bill_id text )\n"}
{"conversations": [{"role": "user", "content": "For each asset, I want to know how many orders have the status 'filled', showing the asset symbol."}, {"role": "assistant", "content": "SELECT m.value AS asset_symbol,\n       COUNT(*) AS filled_order_count\nFROM trading_platform.orders o\nJOIN trading_platform.metadata m\n  ON o.asset_id = m.asset_id\n AND m.key = 'symbol'\nWHERE o.status = 'filled'\nGROUP BY m.value;"}, {"role": "user", "content": "Include assets that have zero filled orders, showing filled_order_count as 0."}, {"role": "assistant", "content": "WITH asset_symbols AS (\n  SELECT DISTINCT asset_id,\n         value AS asset_symbol\n  FROM trading_platform.metadata\n  WHERE key = 'symbol'\n)\nSELECT a.asset_symbol,\n       COALESCE(f.filled_order_count, 0) AS filled_order_count\nFROM asset_symbols a\nLEFT JOIN (\n  SELECT asset_id,\n         COUNT(*) AS filled_order_count\n  FROM trading_platform.orders\n  WHERE status = 'filled'\n  GROUP BY asset_id\n) f\n  ON a.asset_id = f.asset_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.users (\n    user_id character varying(64) NOT NULL,  -- unique identifier for the user\n    username character varying(128) NOT NULL, -- username of the user\n    email character varying(128) NOT NULL, -- email address of the user\n    password_hash text NOT NULL, -- hashed password of the user\n    created_at timestamp NOT NULL, -- time when the user account was created\n    PRIMARY KEY (user_id)\n)\nCREATE TABLE trading_platform.orders (\n    order_id character varying(64) NOT NULL,  -- unique identifier for the order\n    user_id character varying(64) NOT NULL, -- identifier of the user placing the order\n    wallet_id character varying(64) NOT NULL, -- identifier of the wallet used for the order\n    asset_id character varying(64) NOT NULL, -- identifier of the asset being traded\n    order_type character varying(32) NOT NULL, -- type of the order (e.g., buy, sell)\n    quantity numeric(38,14) NOT NULL, -- quantity of the asset in the order\n    price numeric(38,14) NOT NULL, -- price per unit of the asset\n    status character varying(32) NOT NULL, -- status of the order (e.g., open, filled, canceled)\n    created_at timestamp NOT NULL, -- time when the order was created\n    PRIMARY KEY (order_id)\n)\nCREATE TABLE trading_platform.dapps (\n    dapp_id character varying(64) NOT NULL,  -- unique identifier for the DApp\n    name character varying(128) NOT NULL, -- name of the DApp\n    description text NOT NULL, -- description of the DApp\n    url character varying(256) NOT NULL, -- URL of the DApp\n    PRIMARY KEY (dapp_id)\n)\nCREATE TABLE trading_platform.peers (\n    peer_id character varying(64) NOT NULL,  -- unique identifier for the peer\n    ip_address character varying(15) NOT NULL, -- IP address of the peer\n    port integer NOT NULL, -- port number of the peer\n    last_seen timestamp NOT NULL, -- last time the peer was active\n    PRIMARY KEY (peer_id)\n)\nCREATE TABLE trading_platform.metadata (\n    metadata_id character varying(64) NOT NULL,  -- unique identifier for the metadata\n    asset_id character varying(64) NOT NULL, -- identifier of the asset the metadata is associated with\n    key character varying(128) NOT NULL, -- key of the metadata\n    value text NOT NULL, -- value of the metadata\n    PRIMARY KEY (metadata_id)\n)\nCREATE TABLE trading_platform.logs (\n    log_id character varying(64) NOT NULL,  -- unique identifier for the log entry\n    user_id character varying(64), -- identifier of the user associated with the log entry\n    action character varying(128) NOT NULL, -- action performed\n    details text NOT NULL, -- details of the action\n    logged_at timestamp NOT NULL, -- time when the log entry was created\n    PRIMARY KEY (log_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List the top 3 tokens by net flow on the Binance chain, including their symbol and average cost."}, {"role": "assistant", "content": "SELECT token_symbol, net_flow, avg_cost FROM smart_money_token_performance WHERE chain = 'Binance' ORDER BY net_flow DESC LIMIT 3;"}, {"role": "user", "content": "Actually, I want to see tokens with a positive net flow and ROI above 20%."}, {"role": "assistant", "content": "SELECT token_symbol, net_flow, avg_cost FROM smart_money_token_performance WHERE chain = 'Binance' AND net_flow > 0 AND roi > 20 ORDER BY net_flow DESC LIMIT 3;"}, {"role": "user", "content": "Can you also include the current price and order by ROI instead?"}, {"role": "assistant", "content": "SELECT token_symbol, net_flow, avg_cost, price FROM smart_money_token_performance WHERE chain = 'Binance' AND net_flow > 0 AND roi > 20 ORDER BY roi DESC LIMIT 3;"}, {"role": "user", "content": "Now filter these results to only include tokens with a price above $1."}, {"role": "assistant", "content": "SELECT token_symbol, net_flow, avg_cost, price FROM smart_money_token_performance WHERE chain = 'Binance' AND net_flow > 0 AND roi > 20 AND price > 1 ORDER BY roi DESC LIMIT 3;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE smart_money_token_performance ( token_address character varying(100) NOT NULL, -- the token's address token_symbol character varying(100), -- the tokens's symbol pnl numeric(38,2), -- the profit users made on this token net_flow numeric(38,2), -- the netflow of the token, means the money user spent minus the the money user sold of this token avg_cost numeric(38,16), -- the average cost price of user spent on this token price double precision, -- the current price of the token realized_ratio numeric(10,2), -- the ratio user sold of the token roi numeric(10,2), -- the roi users made of this token chain character varying(100), -- the chain that the token resides PRIMARY KEY (token_address, chain) )\n"}
{"conversations": [{"role": "user", "content": "Count the number of policies issued in each calendar year, and show the year and the count."}, {"role": "assistant", "content": "SELECT EXTRACT(YEAR FROM issued_at), COUNT(*) FROM insurance.policies WHERE issued_at IS NOT NULL GROUP BY 1 ORDER BY 1;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.customers ( customer_id text, first_name text, last_name text, date_of_birth date, ssn_hash text, address_line1 text, address_line2 text, city text, state text, zip_code text, country text, phone_number text, email text, created_at timestamp, updated_at timestamp, status text )\nCREATE TABLE insurance.policies ( policy_id text, customer_id text, product_id text, agent_id text, policy_number text, start_date date, end_date date, premium_amount numeric, coverage_limit numeric, deductible numeric, status text, issued_at timestamp, cancellation_date date, cancellation_reason text )\nCREATE TABLE insurance.insurance_products ( product_id text, product_name text, product_type text, description text, base_premium numeric, coverage_details text, underwriting_rules text, is_active boolean, created_at timestamp, updated_at timestamp )\nCREATE TABLE insurance.agents ( agent_id text, first_name text, last_name text, agency_name text, license_number text, license_state text, contact_email text, contact_phone text, hire_date date, termination_date date, status text, commission_rate numeric, manager_id text )\nCREATE TABLE insurance.policy_beneficiaries ( beneficiary_id text, policy_id text, customer_id text, first_name text, last_name text, relationship text, percentage_share numeric, contact_info text, added_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "For each game session, list session_id, player_id, and the number of achievements that the player had unlocked before the session start_time."}, {"role": "assistant", "content": "```sql\nSELECT\n  gs.session_id,\n  gs.player_id,\n  COUNT(pa.achievement_id) AS achievements_before_session\nFROM gaming_technology.game_sessions gs\nLEFT JOIN gaming_technology.player_achievements pa\n  ON gs.player_id = pa.player_id\n  AND pa.unlocked_at < gs.start_time\nGROUP BY\n  gs.session_id,\n  gs.player_id;\n```"}, {"role": "user", "content": "Exclude sessions where achievements_before_session is zero."}, {"role": "assistant", "content": "```sql\nSELECT\n  gs.session_id,\n  gs.player_id,\n  COUNT(pa.achievement_id) AS achievements_before_session\nFROM gaming_technology.game_sessions gs\nLEFT JOIN gaming_technology.player_achievements pa\n  ON gs.player_id = pa.player_id\n  AND pa.unlocked_at < gs.start_time\nGROUP BY\n  gs.session_id,\n  gs.player_id\nHAVING\n  COUNT(pa.achievement_id) > 0;\n```"}, {"role": "user", "content": "Finally, order by achievements_before_session descending and limit to the top 10 sessions."}, {"role": "assistant", "content": "```sql\nSELECT\n  gs.session_id,\n  gs.player_id,\n  COUNT(pa.achievement_id) AS achievements_before_session\nFROM gaming_technology.game_sessions gs\nLEFT JOIN gaming_technology.player_achievements pa\n  ON gs.player_id = pa.player_id\n  AND pa.unlocked_at < gs.start_time\nGROUP BY\n  gs.session_id,\n  gs.player_id\nHAVING\n  COUNT(pa.achievement_id) > 0\nORDER BY\n  achievements_before_session DESC\nLIMIT 10;\n```"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.players ( player_id uuid PRIMARY KEY, username text, email text, password_hash text, registration_date timestamptz, last_login timestamptz, country_code text, status text, profile_data jsonb )\nCREATE TABLE gaming_technology.game_sessions ( session_id uuid PRIMARY KEY, player_id uuid, game_id uuid, server_id uuid, start_time timestamptz, end_time timestamptz, duration_seconds int, score int, session_data jsonb )\nCREATE TABLE gaming_technology.servers ( server_id.uuid, game_id.uuid, server_name.text, region.text, ip_address.text, port.integer, current_players.integer, max_players.integer, status.text, last_heartbeat.timestamptz )\nCREATE TABLE gaming_technology.player_achievements ( player_achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), player_id uuid NOT NULL, achievement_id uuid NOT NULL, unlocked_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (player_achievement_id), UNIQUE (player_id, achievement_id) )\nCREATE TABLE gaming_technology.player_inventory ( inventory_id uuid NOT NULL DEFAULT gen_random_uuid(), player_id uuid NOT NULL, item_id uuid NOT NULL, quantity integer NOT NULL DEFAULT 1, acquired_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, instance_data jsonb, PRIMARY KEY (inventory_id) )\n"}
{"conversations": [{"role": "user", "content": "Show the total file size in bytes for all documents uploaded with a MIME type of 'application/pdf'."}, {"role": "assistant", "content": "SELECT SUM(file_size_bytes) FROM insurance.claim_documents WHERE mime_type = 'application/pdf'"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.policies ( policy_id text, customer_id text, product_id text, agent_id text, policy_number text, start_date date, end_date date, premium_amount numeric, coverage_limit numeric, deductible numeric, status text, issued_at timestamp, cancellation_date date, cancellation_reason text )\nCREATE TABLE insurance.insurance_products ( product_id text, product_name text, product_type text, description text, base_premium numeric, coverage_details text, underwriting_rules text, is_active boolean, created_at timestamp, updated_at timestamp )\nCREATE TABLE insurance.claim_documents ( document_id text, claim_id text, document_type text, file_name text, file_path text, file_size_bytes integer, mime_type text, uploaded_by text, uploaded_at timestamp, description text )\n"}
{"conversations": [{"role": "user", "content": "How many messages in total have been sent that do not contain any media attachment?"}, {"role": "assistant", "content": "SELECT COUNT(*) AS non_media_message_count\nFROM social_media.messages\nWHERE media_url IS NULL OR media_url = '';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.messages ( message_id text PRIMARY KEY, conversation_id text, sender_user_id text, content text, media_url text, media_type text, sent_at timestamp, read_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show me the first name, last name, and email address for all passengers who are part of the loyalty program with ID 'Gold'."}, {"role": "assistant", "content": "SELECT first_name ,  last_name ,  email FROM transportation.passengers WHERE loyalty_program_id  =  'Gold'"}, {"role": "user", "content": "Now, narrow this list to only include those passengers whose record was created after January 1, 2023."}, {"role": "assistant", "content": "SELECT first_name ,  last_name ,  email FROM transportation.passengers WHERE loyalty_program_id  =  'Gold' AND created_at  >  '2023-01-01'"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.routes ( route_id text PRIMARY KEY, route_number text, description text, origin_location_id text, destination_location_id text, distance_km numeric, estimated_duration_minutes int, type text )\nCREATE TABLE transportation.maintenance_logs ( log_id.text, vehicle_id.text, service_date.date, odometer_reading.integer, service_type.text, description.text, cost.numeric, mechanic_name.text, next_service_due_date.date )\nCREATE TABLE transportation.fuel_logs ( fuel_log_id text, vehicle_id text, trip_id text, log_timestamp timestamp, fuel_type text, quantity numeric, unit text, cost_per_unit numeric, total_cost numeric, odometer_reading integer, location_id text )\nCREATE TABLE transportation.passengers ( passenger_id text, first_name text, last_name text, email text, phone_number text, date_of_birth date, loyalty_program_id text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show all room types that offer 'WiFi' in their amenities."}, {"role": "assistant", "content": "SELECT room_type_id, property_id, type_name, amenities FROM hospitality_technology.room_types WHERE amenities LIKE '%WiFi%';"}, {"role": "user", "content": "Only include those with a base rate below 100 and return the results sorted by base_rate ascending."}, {"role": "assistant", "content": "SELECT room_type_id, property_id, type_name, amenities, base_rate FROM hospitality_technology.room_types WHERE amenities LIKE '%WiFi%' AND base_rate < 100 ORDER BY base_rate ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.room_types ( room_type_id.text, property_id.text, type_name.text, description.text, base_rate.numeric, max_occupancy.integer, bed_type.text, area_sqft.numeric, amenities.text )\n"}
{"conversations": [{"role": "user", "content": "List all patients who have been prescribed medications with dosage greater than 50mg, along with their medication details and prescribing doctor's name."}, {"role": "assistant", "content": "SELECT p.first_name, p.last_name, pr.dosage, pr.medication_id, pr.frequency, d.first_name AS doctor_first_name, d.last_name AS doctor_last_name FROM healthcare.patients p JOIN healthcare.prescriptions pr ON p.patient_id = pr.patient_id JOIN healthcare.doctors d ON pr.doctor_id = d.doctor_id WHERE pr.dosage LIKE '%50mg%' OR pr.dosage LIKE '%>50%' OR CAST(SUBSTRING(pr.dosage FROM '[0-9]+') AS INTEGER) > 50;"}, {"role": "user", "content": "Actually, I need to see only prescriptions that were issued in the last 3 months."}, {"role": "assistant", "content": "SELECT p.first_name, p.last_name, pr.dosage, pr.medication_id, pr.frequency, d.first_name AS doctor_first_name, d.last_name AS doctor_last_name FROM healthcare.patients p JOIN healthcare.prescriptions pr ON p.patient_id = pr.patient_id JOIN healthcare.doctors d ON pr.doctor_id = d.doctor_id WHERE (pr.dosage LIKE '%50mg%' OR pr.dosage LIKE '%>50%' OR CAST(SUBSTRING(pr.dosage FROM '[0-9]+') AS INTEGER) > 50) AND pr.prescription_date >= CURRENT_DATE - INTERVAL '3 months';"}, {"role": "user", "content": "Can you also include the prescription start date and end date in the results?"}, {"role": "assistant", "content": "SELECT p.first_name, p.last_name, pr.dosage, pr.medication_id, pr.frequency, pr.start_date, pr.end_date, d.first_name AS doctor_first_name, d.last_name AS doctor_last_name FROM healthcare.patients p JOIN healthcare.prescriptions pr ON p.patient_id = pr.patient_id JOIN healthcare.doctors d ON pr.doctor_id = d.doctor_id WHERE (pr.dosage LIKE '%50mg%' OR pr.dosage LIKE '%>50%' OR CAST(SUBSTRING(pr.dosage FROM '[0-9]+') AS INTEGER) > 50) AND pr.prescription_date >= CURRENT_DATE - INTERVAL '3 months';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, gender character varying(10), address text, phone_number character varying(20), email character varying(128) UNIQUE, emergency_contact_name character varying(200), emergency_contact_phone character varying(20), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (patient_id) )\nCREATE TABLE healthcare.doctors ( doctor_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, specialty character varying(100) NOT NULL, license_number character varying(50) UNIQUE NOT NULL, phone_number character varying(20), email character varying(128) UNIQUE, hospital_affiliation_id character varying(64), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (doctor_id) )\nCREATE TABLE healthcare.appointments ( appointment_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, doctor_id character varying(64) NOT NULL, appointment_time timestamp with time zone NOT NULL, duration_minutes integer NOT NULL, reason text, status character varying(32) NOT NULL, location_id character varying(64), notes text, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (appointment_id) )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id character varying(64) NOT NULL, record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, doctor_id character varying(64) NOT NULL, diagnosis_code character varying(20) NOT NULL, code_type character varying(10) NOT NULL DEFAULT 'ICD-10', description text, diagnosis_date date NOT NULL, status character varying(32) NOT NULL, is_chronic boolean DEFAULT false, PRIMARY KEY (diagnosis_id) )\nCREATE TABLE healthcare.prescriptions ( prescription_id character varying(64) NOT NULL, record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, doctor_id character varying(64) NOT NULL, medication_id character varying(64) NOT NULL, dosage character varying(100) NOT NULL, frequency character varying(100) NOT NULL, route character varying(50), start_date date NOT NULL, end_date date, quantity_dispensed numeric(10,2), refills_allowed integer NOT NULL DEFAULT 0, prescription_date timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (prescription_id) )\nCREATE TABLE healthcare.insurance_plans ( plan_id character varying(64) NOT NULL, plan_name character varying(200) NOT NULL, insurance_provider character varying(100) NOT NULL, plan_type character varying(50), contact_phone character varying(20), website character varying(255), PRIMARY KEY (plan_id) )\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, plan_id character varying(64) NOT NULL, policy_number character varying(100) NOT NULL, group_number character varying(100), subscriber_name character varying(200), effective_date date NOT NULL, expiration_date date, is_primary boolean NOT NULL DEFAULT true, PRIMARY KEY (patient_insurance_id), UNIQUE (patient_id, plan_id, policy_number) )\n"}
{"conversations": [{"role": "user", "content": "Show me the content and creation time of comments made on posts authored by the user with ID 'user_X'."}, {"role": "assistant", "content": "SELECT T1.content, T1.created_at FROM social_media.comments AS T1 JOIN social_media.posts AS T2 ON T1.post_id = T2.post_id WHERE T2.user_id = 'user_X';"}, {"role": "user", "content": "Can you also include the username of the user who made each comment?"}, {"role": "assistant", "content": "SELECT T1.content, T1.created_at, T3.username FROM social_media.comments AS T1 JOIN social_media.posts AS T2 ON T1.post_id = T2.post_id JOIN social_media.users AS T3 ON T1.user_id = T3.user_id WHERE T2.user_id = 'user_X';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.comments (\n    comment_id character varying(64) NOT NULL, -- unique identifier for the comment\n    post_id character varying(64) NOT NULL, -- identifier of the post being commented on (FK to posts.post_id)\n    user_id character varying(64) NOT NULL, -- identifier of the user who made the comment (FK to users.user_id)\n    parent_comment_id character varying(64), -- identifier of the parent comment if it's a reply (FK to comments.comment_id)\n    content text NOT NULL, -- textual content of the comment\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of comment creation\n    updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last comment edit\n    PRIMARY KEY (comment_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Show the names and types of all assets whose symbol is exactly 3 characters long."}, {"role": "assistant", "content": "SELECT name, type, symbol FROM trading_platform.assets WHERE LENGTH(symbol) = 3;"}, {"role": "user", "content": "Also, I want to order the results alphabetically by asset name."}, {"role": "assistant", "content": "SELECT name, type, symbol FROM trading_platform.assets WHERE LENGTH(symbol) = 3 ORDER BY name ASC;"}, {"role": "user", "content": "Actually, can you only show assets of type 'token' in the result?"}, {"role": "assistant", "content": "SELECT name, type, symbol FROM trading_platform.assets WHERE LENGTH(symbol) = 3 AND type = 'token' ORDER BY name ASC;"}, {"role": "user", "content": "Now, just return the asset name and symbol for these tokens, sorted by symbol descending."}, {"role": "assistant", "content": "SELECT name, symbol FROM trading_platform.assets WHERE LENGTH(symbol) = 3 AND type = 'token' ORDER BY symbol DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.assets ( asset_id text PRIMARY KEY, name text, symbol text, type text )\n"}
{"conversations": [{"role": "user", "content": "How many documents of each type exist in the system? Show the document type and the count."}, {"role": "assistant", "content": "SELECT document_type, COUNT(*) AS document_count\nFROM legal_services.documents\ngroup BY document_type;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.clients ( client_id text, first_name text, last_name text, company_name text, email text, phone text, address text, date_registered timestamp, status text )\nCREATE TABLE legal_services.law_firms ( firm_id text, firm_name text, address text, phone text, website text, founded_date date, managing_partner_id text )\nCREATE TABLE legal_services.cases ( case_id text, case_number text, case_name text, client_id text, lead_lawyer_id text, case_type text, status text, date_opened timestamp, date_closed timestamp, description text, court_jurisdiction text )\nCREATE TABLE legal_services.documents ( document_id text, case_id text, document_name text, document_type text, storage_path text, uploaded_by_lawyer_id text, upload_timestamp timestamp, version integer, description text )\nCREATE TABLE legal_services.time_entries ( entry_id text, case_id text, lawyer_id text, date_worked date, hours_spent numeric, billing_rate numeric, description text, is_billable boolean, is_billed boolean, invoice_id text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "List for each fuel type the number of unique vehicle models available. Show the fuel_type and the model count."}, {"role": "assistant", "content": "SELECT fuel_type, COUNT(DISTINCT model) AS model_count FROM transportation.vehicles GROUP BY fuel_type ORDER BY fuel_type;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles ( vehicle_id text, license_plate text, vin text, make text, model text, year integer, type text, capacity integer, fuel_type text, status text, depot_id text, acquisition_date date )\n"}