{"conversations": [{"role": "user", "content": "List every diagnosis description paired with every insurance plan's website."}, {"role": "assistant", "content": "SELECT T1.description, T2.website FROM healthcare.diagnoses AS T1 CROSS JOIN healthcare.insurance_plans AS T2;"}, {"role": "user", "content": "Only include chronic diagnoses and plans whose website ends with '.org'."}, {"role": "assistant", "content": "SELECT T1.description, T2.website FROM healthcare.diagnoses AS T1 CROSS JOIN healthcare.insurance_plans AS T2 WHERE T1.is_chronic = true AND T2.website LIKE '%.org';"}], "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.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.insurance_plans ( plan_id text PRIMARY KEY, plan_name text, insurance_provider text, plan_type text, contact_phone text, website text )\n"}
{"conversations": [{"role": "user", "content": "Show me all securities (security_id, ticker_symbol, security_name) that are traded on the NASDAQ exchange and belong to the 'Technology' sector, along with their last_updated timestamp."}, {"role": "assistant", "content": "SELECT security_id, ticker_symbol, security_name, last_updated FROM financial_services.securities WHERE exchange = 'NASDAQ' AND sector = 'Technology';"}, {"role": "user", "content": "Now modify the query to only include securities updated within the last 30 days and sort them by last_updated in descending order."}, {"role": "assistant", "content": "SELECT security_id, ticker_symbol, security_name, last_updated FROM financial_services.securities WHERE exchange = 'NASDAQ' AND sector = 'Technology' AND last_updated >= CURRENT_DATE - INTERVAL '30 days' ORDER BY last_updated 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 character varying(64) NOT NULL, ticker_symbol character varying(20) NOT NULL UNIQUE, isin_code character varying(12) UNIQUE, cusip_code character varying(9) UNIQUE, security_name text NOT NULL, security_type character varying(50) NOT NULL, exchange character varying(50), currency character varying(3) NOT NULL, issuer_name character varying(255), sector character varying(100), last_updated timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (security_id) )\n"}
{"conversations": [{"role": "user", "content": "Show the full name of each manager and the average commission rate of the agents who report directly to them. Only include managers who have at least one reporting agent."}, {"role": "assistant", "content": "SELECT T2.first_name AS manager_first_name, T2.last_name AS manager_last_name, AVG(T1.commission_rate) AS average_agent_commission_rate FROM insurance.agents AS T1 JOIN insurance.agents AS T2 ON T1.manager_id = T2.agent_id GROUP BY T2.agent_id, T2.first_name, T2.last_name"}, {"role": "user", "content": "Filter the results to only show managers whose average agent commission rate is above 0.12."}, {"role": "assistant", "content": "SELECT T2.first_name AS manager_first_name, T2.last_name AS manager_last_name, AVG(T1.commission_rate) AS average_agent_commission_rate FROM insurance.agents AS T1 JOIN insurance.agents AS T2 ON T1.manager_id = T2.agent_id GROUP BY T2.agent_id, T2.first_name, T2.last_name HAVING AVG(T1.commission_rate) > 0.12"}], "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.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 )\n"}
{"conversations": [{"role": "user", "content": "What is the average ROI for smart money addresses on the Ethereum chain?"}, {"role": "assistant", "content": "SELECT AVG(roi) FROM smart_money_token_performance WHERE chain = 'Ethereum';"}], "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\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 \"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\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"}
{"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": "Show me a list of users who have logged any action. Include their user ID and username."}, {"role": "assistant", "content": "SELECT DISTINCT u.user_id, u.username FROM users u JOIN logs l ON u.user_id = l.user_id;"}, {"role": "user", "content": "For these users, list each unique action type they have performed. Show the username and the action type."}, {"role": "assistant", "content": "SELECT DISTINCT u.username, l.action FROM users u JOIN logs l ON u.user_id = l.user_id;"}, {"role": "user", "content": "Now, for each user who has logged actions, count the total number of log entries they have. Show the username and the count."}, {"role": "assistant", "content": "SELECT u.username, COUNT(l.log_id) FROM users u JOIN logs l ON u.user_id = l.user_id GROUP BY u.username;"}], "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 trading_platform.users ( user_id text PRIMARY KEY, username text, email text, password_hash 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.assets ( asset_id text PRIMARY KEY, name text, symbol text, type text )\nCREATE TABLE trading_platform.dapps ( dapp_id text PRIMARY KEY, name text, description text, url text )\nCREATE TABLE trading_platform.peers ( peer_id text PRIMARY KEY, ip_address text, port int, last_seen timestamp )\nCREATE TABLE trading_platform.metadata ( metadata_id text PRIMARY KEY, asset_id text, key text, value text )\nCREATE TABLE trading_platform.kyc_audit ( kyc_audit_id text PRIMARY KEY, user_id text, status text, reviewed_at timestamp )\nCREATE TABLE trading_platform.logs ( log_id text PRIMARY KEY, user_id text, action text, details text, logged_at timestamp )\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": "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": "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 ERC20 token transfers where the amount is over 5000, including the sender and receiver addresses."}, {"role": "assistant", "content": "SELECT from_address, to_address, amt, tick, tx_hash FROM token_activities WHERE type = 'transfer' AND CAST(amt AS DECIMAL) > 5000;"}, {"role": "user", "content": "Add the token symbol and decimals for each transfer by joining to the latest token price table."}, {"role": "assistant", "content": "SELECT ta.from_address, ta.to_address, ta.amt, ta.tick, ta.tx_hash, tpl.symbol, tpl.decimals FROM token_activities ta JOIN token_prices_latest tpl ON ta.tick = tpl.symbol WHERE ta.type = 'transfer' AND CAST(ta.amt AS DECIMAL) > 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 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 varchar, wallet_address varchar, amount varchar, pk integer )\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_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_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_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_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 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": "What is the current location of train number Acela 2151?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to real-time location data for trains. The database only contains static information such as train ID, model, capacity, and maintenance schedules. For current location updates, please check with the train operator or a tracking service."}], "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 (\n    train_id character varying(64) NOT NULL, -- Unique identifier for the train set\n    train_number character varying(32) NOT NULL, -- Operational number of the train (e.g., 'Acela 2151')\n    model character varying(128), -- Model of the train (e.g., 'Siemens Velaro')\n    manufacturer character varying(128), -- Manufacturer of the train\n    year_manufactured integer, -- Year the train was built\n    capacity integer NOT NULL, -- Total passenger capacity\n    status character varying(32) NOT NULL DEFAULT 'Active', -- e.g., Active, Maintenance, Retired\n    last_maintenance_date date, -- Date of last scheduled maintenance\n    next_maintenance_date date, -- Date of next scheduled maintenance\n    PRIMARY KEY (train_id),\n    UNIQUE (train_number)\n)\n"}
{"conversations": [{"role": "user", "content": "Now, sort the results by the date opened, oldest first, and show only the top 10."}, {"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' ORDER BY date_opened 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 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 tokens that have a 24-hour trading volume greater than $10,000,000 and a negative price change percentage over the last 24 hours. Show the token symbol, chain, total volume, and the 24-hour price change percentage."}, {"role": "assistant", "content": "SELECT token_symbol, chain, total_volume, price_change_percentage_24h FROM token_basic_info WHERE CAST(REPLACE(total_volume, ',', '') AS numeric) > 10000000 AND price_change_percentage_24h < 0"}, {"role": "user", "content": "From those results, filter further to only include tokens with a market cap rank of 100 or better. Order the results by 24-hour trading volume in descending order."}, {"role": "assistant", "content": "SELECT token_symbol, chain, total_volume, price_change_percentage_24h FROM token_basic_info WHERE CAST(REPLACE(total_volume, ',', '') AS numeric) > 10000000 AND price_change_percentage_24h < 0 AND market_cap_rank IS NOT NULL AND market_cap_rank <= 100 ORDER BY CAST(REPLACE(total_volume, ',', '') AS numeric) 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_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"}
{"conversations": [{"role": "user", "content": "List all lawyers who have never had a time entry that was billed, showing lawyer_id, first_name, and last_name."}, {"role": "assistant", "content": "SELECT l.lawyer_id, l.first_name, l.last_name  \nFROM legal_services.lawyers l  \nLEFT JOIN legal_services.time_entries te  \n  ON l.lawyer_id = te.lawyer_id  \n AND te.is_billed = true  \nWHERE te.entry_id IS NULL;"}, {"role": "user", "content": "Actually, I only want lawyers who have at least one time entry overall but none of those entries are billed."}, {"role": "assistant", "content": "SELECT l.lawyer_id, l.first_name, l.last_name  \nFROM legal_services.lawyers l  \nJOIN legal_services.time_entries te ON l.lawyer_id = te.lawyer_id  \nGROUP BY l.lawyer_id, l.first_name, l.last_name  \nHAVING COUNT(te.entry_id) > 0  \n   AND SUM(CASE WHEN te.is_billed = true THEN 1 ELSE 0 END) = 0;"}, {"role": "user", "content": "Now also include the count of unbilled entries and total unbilled hours for each lawyer."}, {"role": "assistant", "content": "SELECT l.lawyer_id,  \n       l.first_name,  \n       l.last_name,  \n       COUNT(te.entry_id) FILTER (WHERE te.is_billed = false) AS unbilled_entries,  \n       SUM(te.hours_spent) FILTER (WHERE te.is_billed = false) AS total_unbilled_hours  \nFROM legal_services.lawyers l  \nJOIN legal_services.time_entries te ON l.lawyer_id = te.lawyer_id  \nGROUP BY l.lawyer_id, l.first_name, l.last_name  \nHAVING COUNT(te.entry_id) > 0  \n   AND SUM(CASE WHEN te.is_billed = true THEN 1 ELSE 0 END) = 0;"}], "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.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.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 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": "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": "For each property, show the most expensive room type by base_rate, including the property name, room type name, and the highest base_rate."}, {"role": "assistant", "content": "SELECT p.property_name,\n       rt.type_name,\n       MAX(rt.base_rate) AS max_base_rate\nFROM hospitality_technology.room_types rt\nJOIN hospitality_technology.properties p\n  ON rt.property_id = p.property_id\nGROUP BY 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 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.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 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.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.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": "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": "Find all smart contracts where the code length is greater than 1000 characters."}, {"role": "assistant", "content": "SELECT contract_id, creator_address, timestamp FROM blockchain.smart_contracts WHERE LENGTH(code) > 1000;"}, {"role": "user", "content": "Now group these by creator_address and show the count of such contracts per creator."}, {"role": "assistant", "content": "SELECT creator_address, COUNT(*) AS long_code_contracts FROM blockchain.smart_contracts WHERE LENGTH(code) > 1000 GROUP BY creator_address;"}, {"role": "user", "content": "Can you order the results by the count in descending order?"}, {"role": "assistant", "content": "SELECT creator_address, COUNT(*) AS long_code_contracts FROM blockchain.smart_contracts WHERE LENGTH(code) > 1000 GROUP BY creator_address ORDER BY long_code_contracts DESC;"}, {"role": "user", "content": "Now show only creators who have more than 3 such contracts."}, {"role": "assistant", "content": "SELECT creator_address, COUNT(*) AS long_code_contracts FROM blockchain.smart_contracts WHERE LENGTH(code) > 1000 GROUP BY creator_address HAVING COUNT(*) > 3 ORDER BY long_code_contracts 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 blockchain.smart_contracts ( contract_id text PRIMARY KEY, creator_address text, code text, timestamp timestamp )\n"}
{"conversations": [{"role": "user", "content": "Get the number of direct reports for each manager, showing manager_id and report_count."}, {"role": "assistant", "content": "SELECT manager_id,\n       COUNT(*) AS report_count\nFROM hospitality_technology.staff\nWHERE manager_id IS NOT NULL\nGROUP BY manager_id;"}, {"role": "user", "content": "Exclude managers who have fewer than 2 direct reports."}, {"role": "assistant", "content": "SELECT manager_id,\n       COUNT(*) AS report_count\nFROM hospitality_technology.staff\nWHERE manager_id IS NOT NULL\nGROUP BY manager_id\nHAVING COUNT(*) >= 2;"}, {"role": "user", "content": "Also include the manager's full name alongside their ID."}, {"role": "assistant", "content": "SELECT m.staff_id AS manager_id,\n       m.first_name || ' ' || m.last_name AS manager_full_name,\n       COUNT(s.staff_id) AS report_count\nFROM hospitality_technology.staff s\nJOIN hospitality_technology.staff m\n  ON s.manager_id = m.staff_id\nGROUP BY m.staff_id, m.first_name, m.last_name\nHAVING COUNT(s.staff_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 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) )\n"}
{"conversations": [{"role": "user", "content": "List pairs of drivers whose license expiry dates fall within 30 days of each other. Show both driver_ids, names, and the two expiry dates."}, {"role": "assistant", "content": "SELECT d1.driver_id AS driver1_id, d1.first_name AS driver1_first, d1.last_name AS driver1_last, d1.license_expiry_date AS expiry1, d2.driver_id AS driver2_id, d2.first_name AS driver2_first, d2.last_name AS driver2_last, d2.license_expiry_date AS expiry2 FROM transportation.drivers d1 JOIN transportation.drivers d2 ON d1.driver_id < d2.driver_id AND ABS((d1.license_expiry_date - d2.license_expiry_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 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 )\n"}
{"conversations": [{"role": "user", "content": "For each patient, show the total number of diagnoses they have received, along with their patient ID and the ID of their latest diagnosis. Join with the diagnoses table."}, {"role": "assistant", "content": "SELECT patient_id, COUNT(diagnosis_id) AS diagnosis_count, MAX(diagnosis_id) AS latest_diagnosis_id\nFROM healthcare.diagnoses\nGROUP BY patient_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 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": "Show me each product_type along with the count of products for that type, but only include types where the average base_premium exceeds 500. Order the results by the product count in descending order."}, {"role": "assistant", "content": "SELECT product_type,\n       COUNT(*) AS product_count\nFROM insurance.insurance_products\nGROUP BY product_type\nHAVING AVG(base_premium) > 500\nORDER BY product_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 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": "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": "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 pairs of citizens who share the same email domain."}, {"role": "assistant", "content": "SELECT c1.first_name AS first1,\n       c1.last_name AS last1,\n       c2.first_name AS first2,\n       c2.last_name AS last2,\n       SPLIT_PART(c1.contact_email, '@', 2) AS domain\nFROM government_services.citizens c1\nJOIN government_services.citizens c2\n  ON SPLIT_PART(c1.contact_email, '@', 2) = SPLIT_PART(c2.contact_email, '@', 2)\n AND c1.citizen_id < c2.citizen_id\nWHERE c1.contact_email IS NOT NULL\n  AND c2.contact_email 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 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 the medication_name and manufacturer for all medications where the description is null or an empty string."}, {"role": "assistant", "content": "SELECT medication_name, manufacturer FROM healthcare.medications WHERE description IS NULL OR description = '';"}, {"role": "user", "content": "Now, refine the query to only include medications whose ndc_code starts with '5'."}, {"role": "assistant", "content": "SELECT medication_name, manufacturer FROM healthcare.medications WHERE (description IS NULL OR description = '') AND ndc_code LIKE '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 healthcare.patients (\n    patient_id character varying(64) NOT NULL,  -- unique identifier for the patient\n    first_name character varying(100) NOT NULL, -- patient's first name\n    last_name character varying(100) NOT NULL, -- patient's last name\n    date_of_birth date NOT NULL, -- patient's date of birth\n    gender character varying(10), -- patient's gender (e.g., Male, Female, Other)\n    address text, -- patient's home address\n    phone_number character varying(20), -- patient's phone number\n    email character varying(128) UNIQUE, -- patient's email address\n    emergency_contact_name character varying(200), -- name of emergency contact\n    emergency_contact_phone character varying(20), -- phone number of emergency contact\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 (patient_id)\n)\nCREATE TABLE healthcare.doctors (\n    doctor_id character varying(64) NOT NULL,  -- unique identifier for the doctor\n    first_name character varying(100) NOT NULL, -- doctor's first name\n    last_name character varying(100) NOT NULL, -- doctor's last name\n    specialty character varying(100) NOT NULL, -- doctor's medical specialty\n    license_number character varying(50) UNIQUE NOT NULL, -- doctor's medical license number\n    phone_number character varying(20), -- doctor's contact phone\n    email character varying(128) UNIQUE, -- doctor's contact email\n    hospital_affiliation_id character varying(64), -- FK to hospitals table (optional)\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 (doctor_id)\n)\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.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 (\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 (\n    prescription_id character varying(64) NOT NULL, -- unique identifier for the prescription\n    record_id character varying(64) NOT NULL, -- FK linking to the medical record where it was prescribed\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    doctor_id character varying(64) NOT NULL, -- FK to prescribing doctor\n    medication_id character varying(64) NOT NULL, -- FK to medications table\n    dosage character varying(100) NOT NULL, -- e.g., '100mg', '1 tablet'\n    frequency character varying(100) NOT NULL, -- e.g., 'Once daily', 'Twice a day with meals'\n    route character varying(50), -- e.g., 'Oral', 'Topical', 'Intravenous'\n    start_date date NOT NULL, -- date prescription begins\n    end_date date, -- date prescription ends (if applicable)\n    quantity_dispensed numeric(10,2), -- amount dispensed (e.g., number of tablets)\n    refills_allowed integer NOT NULL DEFAULT 0, -- number of allowed refills\n    prescription_date timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (prescription_id)\n)\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 (\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": "Which developers have created games that include at least one item of rarity 'Legendary'? Show the developer_id and the item_name."}, {"role": "assistant", "content": "SELECT d.developer_id, igi.item_name\nFROM gaming_technology.developers d\nJOIN gaming_technology.in_game_items igi ON d.developer_id = igi.game_id /* This assumes developer_id = game_id; adjust join logic as needed */\nWHERE igi.rarity = 'Legendary';"}, {"role": "user", "content": "I think the join is wrong, it should match developers to games and then in_game_items to games. Please revise the SQL."}, {"role": "assistant", "content": "-- Assuming the existence of a 'games' table with columns (game_id, developer_id)\nSELECT d.developer_id, igi.item_name\nFROM gaming_technology.developers d\nJOIN gaming_technology.games g ON d.developer_id = g.developer_id\nJOIN gaming_technology.in_game_items igi ON g.game_id = igi.game_id\nWHERE igi.rarity = 'Legendary';"}, {"role": "user", "content": "You can only use the given tables. Is it possible to get a list of developers who have legendary items in their games with the available schema?"}, {"role": "assistant", "content": "-- Based on the given schema alone (without a games table), it's not possible to relate developers to in_game_items directly since there is no relationship between developer_id and game_id in the available tables."}, {"role": "user", "content": "Okay, then just list all 'Legendary' rarity in-game items, including their item_id, item_name, and cost_amount."}, {"role": "assistant", "content": "SELECT item_id, item_name, cost_amount\nFROM gaming_technology.in_game_items\nWHERE rarity = 'Legendary';"}], "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 )\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 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 (\n    item_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the item definition\n    game_id uuid NOT NULL, -- FK linking to the game this item belongs to\n    item_name character varying(150) NOT NULL, -- name of the item\n    item_type character varying(50) NOT NULL, -- type (e.g., Cosmetic, Consumable, Weapon, Armor)\n    description text, -- description of the item\n    rarity character varying(30), -- item rarity (e.g., Common, Rare, Epic, Legendary)\n    cost_currency character varying(10), -- currency code if purchasable (e.g., USD, EUR, GOLD)\n    cost_amount numeric(12, 2), -- price if purchasable\n    attributes jsonb, -- flexible field for item stats or properties\n    PRIMARY KEY (item_id)\n    -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id)\n)\nCREATE TABLE gaming_technology.player_inventory ( inventory_id.uuid, player_id.uuid, item_id.uuid, quantity.integer, acquired_at.timestamptz, instance_data.jsonb )\n"}
{"conversations": [{"role": "user", "content": "Show me all active managers along with their property IDs and the number of staff members they supervise, ordered by the number of supervised staff in descending order."}, {"role": "assistant", "content": "SELECT s.staff_id, s.property_id, s.first_name, s.last_name, COUNT(s2.staff_id) AS supervised_staff_count FROM hospitality_technology.staff s LEFT JOIN hospitality_technology.staff s2 ON s.staff_id = s2.manager_id WHERE s.position = 'Manager' AND s.is_active = true GROUP BY s.staff_id, s.property_id, s.first_name, s.last_name ORDER BY supervised_staff_count DESC;"}, {"role": "user", "content": "Now, include only managers who supervise at least 3 staff members and show their email addresses as well."}, {"role": "assistant", "content": "SELECT s.staff_id, s.property_id, s.first_name, s.last_name, s.work_email, COUNT(s2.staff_id) AS supervised_staff_count FROM hospitality_technology.staff s LEFT JOIN hospitality_technology.staff s2 ON s.staff_id = s2.manager_id WHERE s.position = 'Manager' AND s.is_active = true GROUP BY s.staff_id, s.property_id, s.first_name, s.last_name, s.work_email HAVING COUNT(s2.staff_id) >= 3 ORDER BY supervised_staff_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.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)\n"}
{"conversations": [{"role": "user", "content": "List the full names and dates of birth for all patients who do not have a phone number on record."}, {"role": "assistant", "content": "SELECT first_name, last_name, date_of_birth FROM healthcare.patients WHERE phone_number IS NULL OR TRIM(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 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.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.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": "Show me wallet addresses that hold more than 1000 of any ERC20 token, along with the token symbol and amount, sorted by amount in descending order."}, {"role": "assistant", "content": "SELECT b.wallet_address, t.symbol, b.amount FROM erc20_balances b JOIN sui_coins_metadata t ON b.contract_address = t.coin_type WHERE CAST(b.amount AS decimal) > 1000 ORDER BY CAST(b.amount AS decimal) DESC;"}, {"role": "user", "content": "Can you also include the current price of each token from the token_prices_latest table?"}, {"role": "assistant", "content": "SELECT b.wallet_address, t.symbol, b.amount, p.price FROM erc20_balances b JOIN sui_coins_metadata t ON b.contract_address = t.coin_type JOIN token_prices_latest p ON b.contract_address = p.address WHERE CAST(b.amount AS decimal) > 1000 ORDER BY CAST(b.amount AS decimal) 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 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_holders ( block_number bigint, contract_address varchar, wallet_address varchar, token_id varchar, contract_type varchar, amount varchar, pk varchar )\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 (\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 token_prices_latest ( blockchain varchar, address varchar, decimals bigint, symbol varchar, price real, timestamp timestamp )\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_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_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 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": "For each user, count how many different conversations they have participated in. Show user_id and conversation_count."}, {"role": "assistant", "content": "SELECT user_id, COUNT(DISTINCT conversation_id) AS conversation_count\nFROM social_media.conversation_participants\nGROUP 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 social_media.follows ( follow_id.text, follower_user_id.text, following_user_id.text, created_at.timestamp )\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": "List all pairs of diagnoses that belong to the same medical record. Show record_id, diagnosis_id from the first entry as diag1_id, and diagnosis_id from the second entry as diag2_id."}, {"role": "assistant", "content": "SELECT d1.record_id,\n       d1.diagnosis_id AS diag1_id,\n       d2.diagnosis_id AS diag2_id\nFROM healthcare.diagnoses d1\nJOIN healthcare.diagnoses d2\n  ON d1.record_id = d2.record_id\n AND d1.diagnosis_id < d2.diagnosis_id;"}, {"role": "user", "content": "Only include pairs where both diagnoses are chronic."}, {"role": "assistant", "content": "SELECT d1.record_id,\n       d1.diagnosis_id AS diag1_id,\n       d2.diagnosis_id AS diag2_id\nFROM healthcare.diagnoses d1\nJOIN healthcare.diagnoses d2\n  ON d1.record_id = d2.record_id\n AND d1.diagnosis_id < d2.diagnosis_id\nWHERE d1.is_chronic = TRUE\n  AND d2.is_chronic = 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.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)\n"}
{"conversations": [{"role": "user", "content": "Show me all events emitted by contracts where the event name contains 'Approval', along with the contract ID and transaction ID, sorted by emitted timestamp in descending order."}, {"role": "assistant", "content": "SELECT event_id, contract_id, event_name, transaction_id, emitted_at FROM web3.events WHERE event_name LIKE '%Approval%' ORDER BY emitted_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 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)\n"}
{"conversations": [{"role": "user", "content": "How many diagnoses does each status have grouped by is_chronic flag?"}, {"role": "assistant", "content": "SELECT is_chronic, status, COUNT(*) AS count FROM healthcare.diagnoses GROUP BY is_chronic, 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 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 )\n"}
{"conversations": [{"role": "user", "content": "List all invoices where amount_paid is less than total_amount."}, {"role": "assistant", "content": "SELECT *\nFROM legal_services.invoices\nWHERE amount_paid < total_amount;"}, {"role": "user", "content": "Only include those with due_date before today."}, {"role": "assistant", "content": "SELECT *\nFROM legal_services.invoices\nWHERE amount_paid < total_amount\n  AND due_date < CURRENT_DATE;"}, {"role": "user", "content": "Now also compute how many days each invoice is overdue as difference between CURRENT_DATE and due_date, and only show those overdue by more than 30 days."}, {"role": "assistant", "content": "SELECT invoice_id,\n       invoice_number,\n       client_id,\n       total_amount,\n       amount_paid,\n       due_date,\n       CURRENT_DATE - due_date AS days_overdue\nFROM legal_services.invoices\nWHERE amount_paid < total_amount\n  AND due_date < CURRENT_DATE\n  AND CURRENT_DATE - due_date > 30;"}, {"role": "user", "content": "Finally, order the result by days_overdue descending."}, {"role": "assistant", "content": "SELECT invoice_id,\n       invoice_number,\n       client_id,\n       total_amount,\n       amount_paid,\n       due_date,\n       CURRENT_DATE - due_date AS days_overdue\nFROM legal_services.invoices\nWHERE amount_paid < total_amount\n  AND due_date < CURRENT_DATE\n  AND CURRENT_DATE - due_date > 30\nORDER BY days_overdue 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.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": "What is the current job satisfaction level or feedback from staff members working at a specific train station?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information on job satisfaction levels or feedback from staff members as this data is not included in the staff 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 train_station_management.staff ( staff_id.text, first_name.text, last_name.text, role.text, primary_station_id.text, employee_number.text, hire_date.date, contact_email.text, contact_phone.text, is_active.boolean )\n"}
{"conversations": [{"role": "user", "content": "I want to find total PNL and average ROI of smart money token performance for each narrative category. Only include narratives with average ROI greater than 0.5."}, {"role": "assistant", "content": "SELECT bi.narrative,\n       SUM(smtp.pnl)       AS total_pnl,\n       AVG(smtp.roi)       AS avg_roi\nFROM smart_money_token_performance AS smtp\nJOIN token_basic_info AS bi\n  ON smtp.token_symbol = bi.token_symbol\nGROUP BY bi.narrative\nHAVING AVG(smtp.roi) > 0.5;"}, {"role": "user", "content": "Exclude narratives with total net_flow below zero and show only the top 3 narratives by total PNL."}, {"role": "assistant", "content": "SELECT bi.narrative,\n       SUM(smtp.pnl)       AS total_pnl,\n       AVG(smtp.roi)       AS avg_roi,\n       SUM(smtp.net_flow)  AS total_net_flow\nFROM smart_money_token_performance AS smtp\nJOIN token_basic_info AS bi\n  ON smtp.token_symbol = bi.token_symbol\nGROUP BY bi.narrative\nHAVING AVG(smtp.roi) > 0.5\n   AND SUM(smtp.net_flow) >= 0\nORDER BY total_pnl 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 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_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 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 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_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": "Show me the top 5 users with the most wallet addresses, along with the count of their wallets."}, {"role": "assistant", "content": "SELECT user_id, COUNT(wallet_id) AS wallet_count FROM blockchain.wallets WHERE user_id IS NOT NULL GROUP BY user_id ORDER BY wallet_count DESC LIMIT 5;"}, {"role": "user", "content": "Now include the earliest created wallet address for each of these top 5 users."}, {"role": "assistant", "content": "Note: The wallets table doesn't have a creation timestamp column. Without this information, we cannot determine the earliest created wallet. Please provide a table with creation timestamps if you need this analysis."}, {"role": "user", "content": "Then just show me these top 5 users with their wallet counts and the first wallet_id alphabetically for each user."}, {"role": "assistant", "content": "SELECT user_id, COUNT(wallet_id) AS wallet_count, MIN(wallet_id) AS first_wallet_id FROM blockchain.wallets WHERE user_id IS NOT NULL GROUP BY user_id ORDER BY wallet_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 blockchain.wallets ( wallet_id text, user_id text, address_id text, private_key text )\n"}
{"conversations": [{"role": "user", "content": "Show me all customers who have missing contact information (either phone number or email is null), along with their state and city."}, {"role": "assistant", "content": "SELECT first_name, last_name, state, city FROM insurance.customers WHERE phone_number IS NULL OR email IS NULL;"}, {"role": "user", "content": "Now filter these to only show customers from Florida or New York who were created in the last 2 years."}, {"role": "assistant", "content": "SELECT first_name, last_name, state, city FROM insurance.customers WHERE (phone_number IS NULL OR email IS NULL) AND state IN ('Florida', 'New York') AND created_at >= CURRENT_DATE - INTERVAL '2 years';"}, {"role": "user", "content": "I also want to see when these customers were last updated (updated_at field)."}, {"role": "assistant", "content": "SELECT first_name, last_name, state, city, updated_at FROM insurance.customers WHERE (phone_number IS NULL OR email IS NULL) AND state IN ('Florida', 'New York') AND created_at >= CURRENT_DATE - INTERVAL '2 years';"}, {"role": "user", "content": "Finally, order the results by state first, then by the most recently updated customers first."}, {"role": "assistant", "content": "SELECT first_name, last_name, state, city, updated_at FROM insurance.customers WHERE (phone_number IS NULL OR email IS NULL) AND state IN ('Florida', 'New York') AND created_at >= CURRENT_DATE - INTERVAL '2 years' ORDER BY state ASC, updated_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 insurance.customers ( customer_id text PRIMARY KEY, 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 )\n"}
{"conversations": [{"role": "user", "content": "Show me the content of all comments that have received at least one like."}, {"role": "assistant", "content": "SELECT DISTINCT T1.content FROM social_media.comments AS T1 JOIN social_media.likes AS T2 ON T1.comment_id = T2.comment_id;"}, {"role": "user", "content": "Also include the creation time of these comments and the user_id of the commenter?"}, {"role": "assistant", "content": "SELECT DISTINCT T1.comment_id, T1.content, T1.created_at, T1.user_id FROM social_media.comments AS T1 JOIN social_media.likes AS T2 ON T1.comment_id = T2.comment_id;"}, {"role": "user", "content": "Only show comments created before '2024-05-01'."}, {"role": "assistant", "content": "SELECT DISTINCT T1.comment_id, T1.content, T1.created_at, T1.user_id FROM social_media.comments AS T1 JOIN social_media.likes AS T2 ON T1.comment_id = T2.comment_id WHERE T1.created_at < '2024-05-01';"}], "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 (\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 ( like_id text, user_id text, post_id text, comment_id text, created_at timestamp )\nCREATE TABLE social_media.conversations ( conversation_id text PRIMARY KEY, created_at timestamp, last_message_at timestamp, is_group_chat bool, group_name text )\n"}
{"conversations": [{"role": "user", "content": "List all medical records created in the last 7 days, including patient_id, doctor_id, and record_date."}, {"role": "assistant", "content": "SELECT patient_id, doctor_id, record_date FROM healthcare.medical_records WHERE created_at >= CURRENT_DATE - INTERVAL '7 days';"}, {"role": "user", "content": "Actually, I only need records where the treatment_plan is not empty."}, {"role": "assistant", "content": "SELECT patient_id, doctor_id, record_date FROM healthcare.medical_records WHERE created_at >= CURRENT_DATE - INTERVAL '7 days' AND treatment_plan IS NOT NULL AND treatment_plan != '';"}, {"role": "user", "content": "Can you also sort them by record_date in descending order?"}, {"role": "assistant", "content": "SELECT patient_id, doctor_id, record_date FROM healthcare.medical_records WHERE created_at >= CURRENT_DATE - INTERVAL '7 days' AND treatment_plan IS NOT NULL AND treatment_plan != '' ORDER BY record_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.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 )\n"}
{"conversations": [{"role": "user", "content": "Can you list the number of citizens registered each month in 2024? Please show the month and the citizen count."}, {"role": "assistant", "content": "SELECT TO_CHAR(registration_date, 'YYYY-MM') AS registration_month, COUNT(*) AS citizen_count FROM government_services.citizens WHERE registration_date >= '2024-01-01' AND registration_date < '2025-01-01' GROUP BY registration_month ORDER BY registration_month;"}, {"role": "user", "content": "Now, can you also show the number of verified citizens for each month?"}, {"role": "assistant", "content": "SELECT TO_CHAR(registration_date, 'YYYY-MM') AS registration_month, COUNT(*) AS citizen_count, SUM(CASE WHEN is_verified = true THEN 1 ELSE 0 END) AS verified_citizen_count FROM government_services.citizens WHERE registration_date >= '2024-01-01' AND registration_date < '2025-01-01' GROUP BY registration_month ORDER BY registration_month;"}, {"role": "user", "content": "I see some months with zero verified citizens, but they still show up. Can you exclude months with zero verified citizens from the result?"}, {"role": "assistant", "content": "SELECT registration_month, citizen_count, verified_citizen_count FROM (SELECT TO_CHAR(registration_date, 'YYYY-MM') AS registration_month, COUNT(*) AS citizen_count, SUM(CASE WHEN is_verified = true THEN 1 ELSE 0 END) AS verified_citizen_count FROM government_services.citizens WHERE registration_date >= '2024-01-01' AND registration_date < '2025-01-01' GROUP BY registration_month) sub WHERE verified_citizen_count > 0 ORDER BY registration_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 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) )\n"}
{"conversations": [{"role": "user", "content": "How many unique tokens are recorded for each chain in the latest snapshot in cex_token_balance?"}, {"role": "assistant", "content": "WITH latest_snapshot AS (\n  SELECT MAX(snapshot_time) AS max_time FROM cex_token_balance\n)\nSELECT \n  chain, \n  COUNT(DISTINCT token_symbol) AS unique_token_count\nFROM cex_token_balance c\nJOIN latest_snapshot l ON c.snapshot_time = l.max_time\nGROUP BY chain\nORDER BY unique_token_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 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 )\n"}
{"conversations": [{"role": "user", "content": "List all active SUI coins with status 'exists' in metadata, showing coin_type, symbol, name, balance, and description."}, {"role": "assistant", "content": "SELECT sc.coin_type, sm.symbol, sm.name, sc.balance, sm.description\nFROM sui_coins sc\nJOIN sui_coins_metadata sm ON sc.coin_type = sm.coin_type\nWHERE sm.status = 'exists';"}, {"role": "user", "content": "Limit to coins where balance > 1000000 and order by balance descending."}, {"role": "assistant", "content": "SELECT sc.coin_type, sm.symbol, sm.name, sc.balance, sm.description\nFROM sui_coins sc\nJOIN sui_coins_metadata sm ON sc.coin_type = sm.coin_type\nWHERE sm.status = 'exists'\n  AND CAST(sc.balance AS numeric) > 1000000\nORDER BY CAST(sc.balance AS numeric) DESC;"}, {"role": "user", "content": "Also include the number of distinct owners per coin_type."}, {"role": "assistant", "content": "SELECT sc.coin_type, sm.symbol, sm.name, sm.description,\n       SUM(CAST(sc.balance AS numeric)) AS total_balance,\n       COUNT(DISTINCT sc.owner) AS owner_count\nFROM sui_coins sc\nJOIN sui_coins_metadata sm ON sc.coin_type = sm.coin_type\nWHERE sm.status = 'exists'\n  AND CAST(sc.balance AS numeric) > 1000000\nGROUP BY sc.coin_type, sm.symbol, sm.name, sm.description\nORDER BY total_balance DESC;"}, {"role": "user", "content": "Only show the top 3 coins by total_balance."}, {"role": "assistant", "content": "SELECT sc.coin_type, sm.symbol, sm.name, sm.description,\n       SUM(CAST(sc.balance AS numeric)) AS total_balance,\n       COUNT(DISTINCT sc.owner) AS owner_count\nFROM sui_coins sc\nJOIN sui_coins_metadata sm ON sc.coin_type = sm.coin_type\nWHERE sm.status = 'exists'\n  AND CAST(sc.balance AS numeric) > 1000000\nGROUP BY sc.coin_type, sm.symbol, sm.name, sm.description\nORDER BY 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 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 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 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_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_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 appointments that are currently scheduled and show their appointment time."}, {"role": "assistant", "content": "SELECT appointment_id, patient_id, doctor_id, appointment_time FROM healthcare.appointments WHERE status = 'Scheduled';"}], "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 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.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": "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": "Can you help me count the total number of active staff members in the database?"}, {"role": "assistant", "content": "db.staff.countDocuments({ is_active: 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\n// db.createCollection('stations')\n// Optional: Add unique index: db.stations.createIndex({ station_id: 1 }, { unique: true })\n{\n  _id: ObjectId(), // Auto-generated MongoDB ID\n  station_id: \"station_xyz\", // String (unique identifier, corresponds to SQL PK)\n  station_name: \"Grand Central Terminal\", // String\n  city: \"New York\", // String\n  state_province: \"NY\", // String\n  country_code: \"USA\", // String\n  address: \"89 E 42nd St, New York, NY 10017\", // String\n  timezone: \"America/New_York\", // String\n  number_of_platforms: 44, // Int32\n  created_at: ISODate(\"2023-01-15T10:00:00Z\"), // Date\n  last_updated_at: ISODate(\"2023-10-28T15:30:00Z\") // Date\n}\n// db.createCollection('trains')\n// Optional: db.trains.createIndex({ train_id: 1 }, { unique: true })\n// Optional: db.trains.createIndex({ train_number: 1 }, { unique: true })\n{\n  _id: ObjectId(),\n  train_id: \"train_789\", // String (unique)\n  train_number: \"Acela 2151\", // String (unique)\n  model: \"Siemens Velaro\", // String\n  manufacturer: \"Siemens\", // String\n  year_manufactured: 2010, // Int32\n  capacity: 304, // Int32\n  status: \"Active\", // String ('Active', 'Maintenance', 'Retired')\n  last_maintenance_date: ISODate(\"2023-09-15\"), // Date (Date part only relevant)\n  next_maintenance_date: ISODate(\"2024-03-15\") // Date (Date part only relevant)\n}\n// db.createCollection('bookings')\n// Optional: db.bookings.createIndex({ booking_id: 1 }, { unique: true })\n// Optional: db.bookings.createIndex({ passenger_id: 1 })\n// Optional: db.bookings.createIndex({ schedule_id: 1 })\n{\n  _id: ObjectId(),\n  booking_id: \"book_zyx\", // String (unique)\n  passenger_id: \"pass_pqr\", // String (references passengers.passenger_id)\n  schedule_id: \"sched_1122\", // String (references schedules.schedule_id)\n  booking_datetime: ISODate(\"2024-04-15T14:30:00Z\"), // Date\n  status: \"Confirmed\", // String ('Confirmed', 'Cancelled', 'Pending')\n  total_price: 150.75, // Decimal128 or Double\n  currency_code: \"USD\", // String\n  special_requests: \"Wheelchair assistance required at origin\" // String\n}\n// db.createCollection('staff')\n// Optional: db.staff.createIndex({ staff_id: 1 }, { unique: true })\n// Optional: db.staff.createIndex({ employee_number: 1 }, { unique: true })\n// Optional: db.staff.createIndex({ contact_email: 1 }, { unique: true, sparse: true })\n{\n  _id: ObjectId(),\n  staff_id: \"staff_mno\", // String (unique)\n  first_name: \"Bob\", // String\n  last_name: \"Jones\", // String\n  role: \"Conductor\", // String\n  primary_station_id: null, // String (references stations.station_id, nullable)\n  employee_number: \"E12345\", // String (unique)\n  hire_date: ISODate(\"2018-06-01\"), // Date\n  contact_email: \"bob.jones@example-rail.com\", // String (unique, sparse)\n  contact_phone: \"+15559876543\", // String\n  is_active: true // Boolean\n}\n"}
{"conversations": [{"role": "user", "content": "For each booking, list the booking_id, fare, and the total quantity of fuel consumed on its associated trip."}, {"role": "assistant", "content": "SELECT b.booking_id,\n       b.fare,\n       SUM(fl.quantity) AS total_fuel_quantity\nFROM transportation.bookings b\nJOIN transportation.fuel_logs fl\n  ON b.trip_id = fl.trip_id\nGROUP BY b.booking_id, b.fare;"}, {"role": "user", "content": "Only include bookings where the total_fuel_quantity > 100 and order the results by total_fuel_quantity DESC."}, {"role": "assistant", "content": "SELECT b.booking_id,\n       b.fare,\n       SUM(fl.quantity) AS total_fuel_quantity\nFROM transportation.bookings b\nJOIN transportation.fuel_logs fl\n  ON b.trip_id = fl.trip_id\nGROUP BY b.booking_id, b.fare\nHAVING SUM(fl.quantity) > 100\nORDER BY total_fuel_quantity 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 (\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.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.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 appointments scheduled in the next 30 days with appointment_id, client_id, case_id, and any invoice_id linked to that case."}, {"role": "assistant", "content": "SELECT\n  a.appointment_id,\n  a.client_id,\n  a.case_id,\n  i.invoice_id\nFROM legal_services.appointments AS a\nLEFT JOIN legal_services.invoices AS i\n  ON a.case_id = i.case_id\nWHERE a.start_time BETWEEN CURRENT_DATE AND CURRENT_DATE + INTERVAL '30 days';"}, {"role": "user", "content": "Change to include only appointments with status 'Scheduled' and invoices that are not fully paid."}, {"role": "assistant", "content": "SELECT\n  a.appointment_id,\n  a.client_id,\n  a.case_id,\n  i.invoice_id\nFROM legal_services.appointments AS a\nLEFT JOIN legal_services.invoices AS i\n  ON a.case_id = i.case_id\nWHERE a.start_time BETWEEN CURRENT_DATE AND CURRENT_DATE + INTERVAL '30 days'\n  AND a.status = 'Scheduled'\n  AND (i.status IS NULL OR i.status <> 'Paid');"}, {"role": "user", "content": "Also include only those where the case_type is 'Corporate'."}, {"role": "assistant", "content": "SELECT\n  a.appointment_id,\n  a.client_id,\n  a.case_id,\n  i.invoice_id\nFROM legal_services.appointments AS a\nJOIN legal_services.cases AS c\n  ON a.case_id = c.case_id\nLEFT JOIN legal_services.invoices AS i\n  ON a.case_id = i.case_id\nWHERE a.start_time BETWEEN CURRENT_DATE AND CURRENT_DATE + INTERVAL '30 days'\n  AND a.status = 'Scheduled'\n  AND (i.status IS NULL OR i.status <> 'Paid')\n  AND c.case_type = 'Corporate';"}, {"role": "user", "content": "Finally, order by start_time ascending and return only the first 10 rows."}, {"role": "assistant", "content": "SELECT\n  a.appointment_id,\n  a.client_id,\n  a.case_id,\n  i.invoice_id\nFROM legal_services.appointments AS a\nJOIN legal_services.cases AS c\n  ON a.case_id = c.case_id\nLEFT JOIN legal_services.invoices AS i\n  ON a.case_id = i.case_id\nWHERE a.start_time BETWEEN CURRENT_DATE AND CURRENT_DATE + INTERVAL '30 days'\n  AND a.status = 'Scheduled'\n  AND (i.status IS NULL OR i.status <> 'Paid')\n  AND c.case_type = 'Corporate'\nORDER BY a.start_time ASC\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 legal_services.law_firms (\n    firm_id character varying(64) NOT NULL,  -- unique identifier for the law firm\n    firm_name character varying(200) NOT NULL, -- official name of the law firm\n    address text NOT NULL, -- primary address of the firm\n    phone character varying(32), -- firm's main phone number\n    website character varying(255), -- firm's website URL\n    founded_date date, -- date the firm was established\n    managing_partner_id character varying(64), -- FK to lawyers table (optional)\n    PRIMARY KEY (firm_id)\n)\nCREATE TABLE legal_services.cases (\n    case_id character varying(64) NOT NULL,  -- unique identifier for the case/matter\n    case_number character varying(100) UNIQUE, -- official case number (court or internal)\n    case_name text NOT NULL, -- descriptive name or title for the case\n    client_id character varying(64) NOT NULL, -- FK to clients table\n    lead_lawyer_id character varying(64) NOT NULL, -- FK to lawyers table (primary lawyer responsible)\n    case_type character varying(100) NOT NULL, -- e.g., Litigation, Corporate, Family Law, IP\n    status character varying(50) NOT NULL, -- e.g., Open, Closed, Pending, On Hold, Appealed\n    date_opened timestamp NOT NULL, -- date the case was formally opened\n    date_closed timestamp, -- date the case was closed (nullable)\n    description text, -- detailed description of the case\n    court_jurisdiction character varying(128), -- court or jurisdiction if applicable\n    PRIMARY KEY (case_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)\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": "I need to find all bookings for a specific schedule with schedule_id 'sched_1122' and include the passenger and ticket details."}, {"role": "assistant", "content": "SMEMBERS schedule:sched_1122:bookings\nHGETALL booking:book_*\nHGETALL passenger:pass_*\nSMEMBERS booking:book_*:tickets\nHGETALL ticket:tkt_*"}, {"role": "user", "content": "Can you filter the tickets to show only those that are not checked in?"}, {"role": "assistant", "content": "SMEMBERS schedule:sched_1122:bookings\nHGETALL booking:book_*\nHGETALL passenger:pass_*\nSMEMBERS booking:book_*:tickets\nHGET ticket:tkt_* is_checked_in\nIF is_checked_in == 0 THEN\nHGETALL ticket:tkt_*\nENDIF"}, {"role": "user", "content": "Can you also include the car details for each ticket?"}, {"role": "assistant", "content": "SMEMBERS schedule:sched_1122:bookings\nHGETALL booking:book_*\nHGETALL passenger:pass_*\nSMEMBERS booking:book_*:tickets\nHGET ticket:tkt_* is_checked_in\nIF is_checked_in == 0 THEN\nHGETALL ticket:tkt_*\nHGET ticket:tkt_* car_id\nHGETALL car:car_*\nENDIF"}], "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// Use Hashes for platform details. Key format: platform:<platform_id>\n// HSET platform:plat_123 platform_id \"plat_123\" station_id \"station_xyz\" platform_number \"1A\" track_number \"T1\" status \"Operational\" length_meters 250.50 accessible 1\n\n// To link platforms to stations (optional):\n// SADD station:station_xyz:platforms platform:plat_123 platform:plat_456\n// Use Hashes for train details. Key format: train:<train_id>\n// HSET train:train_789 train_id \"train_789\" train_number \"Acela 2151\" model \"Siemens Velaro\" ... status \"Active\" ...\n\n// To find train by train_number (optional index):\n// SET train_number:\"Acela 2151\" train:train_789\n// Use Hashes for car details. Key format: car:<car_id>\n// HSET car:car_abc car_id \"car_abc\" train_id \"train_789\" car_number \"C3\" car_type \"Passenger\" class \"Business\" capacity 60 features \"WiFi,Power Outlet\"\n\n// To link cars to trains (optional):\n// SADD train:train_789:cars car:car_abc car:car_def\n// Use Hashes for details. Key format: route_station:<route_station_id>\n// HSET route_station:rs_ne_1 route_station_id \"rs_ne_1\" route_id \"route_ne_corr\" station_id \"station_bos\" sequence_order 1 ...\n\n// To find stops for a route, use a Sorted Set (score by sequence_order):\n// ZADD route:route_ne_corr:stops 1 route_station:rs_ne_1\n// ZADD route:route_ne_corr:stops 2 route_station:rs_ne_2\n// Use Hashes for schedule details. Key format: schedule:<schedule_id>\n// HSET schedule:sched_1122 schedule_id \"sched_1122\" train_id \"train_789\" route_id \"route_ne_corr\" departure_datetime \"2024-05-10T08:00:00-04:00\" ... status \"Scheduled\"\n// Use Hashes for details. Key format: schedule_stop:<stop_id>\n// HSET schedule_stop:stop_sched1122_1 stop_id \"stop_sched1122_1\" schedule_id \"sched_1122\" station_id \"station_bos\" ...\n\n// To find stops for a schedule, use a Sorted Set (score by sequence_order):\n// ZADD schedule:sched_1122:stops 1 schedule_stop:stop_sched1122_1\n// ZADD schedule:sched_1122:stops 2 schedule_stop:stop_sched1122_2\n// Use Hashes for passenger details. Key format: passenger:<passenger_id>\n// HSET passenger:pass_pqr passenger_id \"pass_pqr\" first_name \"Alice\" last_name \"Smith\" email \"alice.smith@example.com\" ...\n\n// To find passenger by email (optional index):\n// SET passenger_email:\"alice.smith@example.com\" passenger:pass_pqr\n// Use Hashes for booking details. Key format: booking:<booking_id>\n// HSET booking:book_zyx booking_id \"book_zyx\" passenger_id \"pass_pqr\" schedule_id \"sched_1122\" ... status \"Confirmed\" ...\n\n// To link bookings to passengers/schedules (optional):\n// SADD passenger:pass_pqr:bookings booking:book_zyx\n// SADD schedule:sched_1122:bookings booking:book_zyx\n// Use Hashes for ticket details. Key format: ticket:<ticket_id>\n// HSET ticket:tkt_1a2b ticket_id \"tkt_1a2b\" booking_id \"book_zyx\" car_id \"car_abc\" seat_number \"12A\" ... is_checked_in 0 ...\n\n// To link tickets to bookings (optional):\n// SADD booking:book_zyx:tickets ticket:tkt_1a2b\n// Use Hashes for staff details. Key format: staff:<staff_id>\n// HSET staff:staff_mno staff_id \"staff_mno\" first_name \"Bob\" ... employee_number \"E12345\" ... is_active 1\n\n// To find staff by employee number (optional index):\n// SET staff_employee_number:\"E12345\" staff:staff_mno\n// Use Hashes for maintenance record details. Key format: maintenance_record:<record_id>\n// HSET maintenance_record:maint_rec_001 record_id \"maint_rec_001\" asset_id \"train_789\" asset_type \"Train\" ... status \"Completed\"\n\n// To link records to assets (optional):\n// SADD train:train_789:maintenance maintenance_record:maint_rec_001\n// SADD platform:plat_123:maintenance maintenance_record:maint_rec_002\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": "Provide every combination of medication name and insurance plan name."}, {"role": "assistant", "content": "SELECT m.medication_name, p.plan_name\nFROM healthcare.medications AS m\nCROSS JOIN healthcare.insurance_plans AS p;"}], "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.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.insurance_plans ( plan_id.text, plan_name.text, insurance_provider.text, plan_type.text, contact_phone.text, website.text )\n"}
{"conversations": [{"role": "user", "content": "List all events with their contract IDs and emitted timestamps, sorted by the most recent events first."}, {"role": "assistant", "content": "SELECT event_id, contract_id, emitted_at FROM web3.events ORDER BY emitted_at DESC;"}, {"role": "user", "content": "Actually, I only want to see events from contracts that start with '0x1234'."}, {"role": "assistant", "content": "SELECT event_id, contract_id, emitted_at FROM web3.events WHERE contract_id LIKE '0x1234%' ORDER BY emitted_at DESC;"}, {"role": "user", "content": "There's a typo in your SQL, it should be 'contract_id' not 'contract_id'. Also, add the event_name to the results."}, {"role": "assistant", "content": "SELECT event_id, contract_id, event_name, emitted_at FROM web3.events WHERE contract_id LIKE '0x1234%' ORDER BY emitted_at DESC;"}, {"role": "user", "content": "Now filter to only show events emitted in the last 24 hours."}, {"role": "assistant", "content": "SELECT event_id, contract_id, event_name, emitted_at FROM web3.events WHERE contract_id LIKE '0x1234%' AND emitted_at >= NOW() - INTERVAL '24 hours' ORDER BY emitted_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 web3.events ( event_id.text, contract_id.text, event_name.text, data.text, emitted_at.timestamp, transaction_id.text, log_index.integer )\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": "Show the total number of customers in each state."}, {"role": "assistant", "content": "SELECT\n  state,\n  COUNT(customer_id)\nFROM insurance.customers\nGROUP BY\n  state;"}], "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.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.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": "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": "For each medication, show the total number of prescriptions where at least one refill was allowed."}, {"role": "assistant", "content": "SELECT medication_id, COUNT(*) AS prescription_count FROM healthcare.prescriptions WHERE refills_allowed > 0 GROUP BY medication_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 healthcare.patients ( patient_id text PRIMARY KEY, 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 PRIMARY KEY, 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 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 )\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.prescriptions ( prescription_id text PRIMARY KEY, 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 int, prescription_date timestamp )\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id text PRIMARY KEY, 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": "Show me all home loans (loan_id, principal_amount, interest_rate) where the current principal balance is more than 75% of the original principal amount, along with the account_id and employee details (first_name, last_name) of the employee who processed the loan application."}, {"role": "assistant", "content": "SELECT l.loan_id, l.principal_amount, l.interest_rate, l.account_id, e.first_name, e.last_name FROM financial_services.loans l JOIN financial_services.employees e ON l.account_id = e.employee_id WHERE l.loan_type = 'Home' AND l.current_principal_balance > (l.principal_amount * 0.75)"}], "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 ( transaction_id.text, account_id.text, related_account_id.text, transaction_type.text, amount.numeric, currency.text, transaction_date.timestamp, effective_date.date, description.text, status.text, reference_number.text )\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.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": "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": "Provide a count of appointments grouped by the booking method."}, {"role": "assistant", "content": "SELECT booking_method, COUNT(*) AS appointment_count FROM government_services.appointments GROUP BY booking_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.documents (\n    document_id character varying(64) NOT NULL, -- unique identifier for the document instance\n    application_id character varying(64), -- FK to applications table (optional, could be linked to citizen directly)\n    citizen_id character varying(64) NOT NULL, -- FK to citizens table\n    document_type character varying(100) NOT NULL, -- e.g., Passport Scan, Proof of Address, Birth Certificate\n    file_reference text NOT NULL, -- reference to the stored file (e.g., S3 URL, internal path)\n    upload_timestamp timestamp NOT NULL,\n    expiry_date date,\n    verification_status character varying(30) DEFAULT 'Pending', -- e.g., Pending, Verified, Rejected\n    verified_by_employee_id character varying(64), -- FK to employees table\n    verification_timestamp timestamp,\n    PRIMARY KEY (document_id)\n)\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 (\n    appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment\n    citizen_id character varying(64) NOT NULL, -- FK to citizens table\n    employee_id character varying(64), -- FK to employees table (optional, if assigned)\n    location_id character varying(64), -- FK to service_locations table (if physical)\n    service_id character varying(64), -- FK to services table (optional, if related to specific service)\n    scheduled_start_time timestamp NOT NULL,\n    scheduled_end_time timestamp,\n    purpose text NOT NULL, -- reason for the appointment\n    status character varying(30) NOT NULL, -- e.g., Scheduled, Completed, Cancelled, No-Show\n    booking_method character varying(50), -- e.g., Online, Phone, In-Person\n    created_at timestamp NOT NULL, -- when the appointment was booked\n    notes text,\n    PRIMARY KEY (appointment_id)\n)\nCREATE TABLE government_services.notifications (\n    notification_id character varying(64) NOT NULL, -- unique identifier for the notification\n    citizen_id character varying(64) NOT NULL, -- FK to citizens table\n    application_id character varying(64), -- FK to applications table (optional)\n    message_subject character varying(255),\n    message_body text NOT NULL,\n    channel character varying(30) NOT NULL, -- e.g., Email, SMS, Portal Message, Mail\n    sent_at timestamp NOT NULL,\n    status character varying(30) NOT NULL, -- e.g., Queued, Sent, Delivered, Failed, Read\n    related_entity_type character varying(50), -- e.g., Application, Appointment, Document Request\n    related_entity_id character varying(64), -- ID of the related entity\n    PRIMARY KEY (notification_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List the reference number and status for applications where the notes contain the keyword 'urgent'."}, {"role": "assistant", "content": "SELECT reference_number, status FROM government_services.applications WHERE notes ILIKE '%urgent%';"}, {"role": "user", "content": "Among those, show only the applications with a status of 'Pending'."}, {"role": "assistant", "content": "SELECT reference_number, status FROM government_services.applications WHERE notes ILIKE '%urgent%' AND status = 'Pending';"}], "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 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) )\n"}
{"conversations": [{"role": "user", "content": "Show me all contracts deployed on the 'ethereum' network along with their deployer addresses and deployment timestamps, sorted by the most recent deployments first."}, {"role": "assistant", "content": "SELECT address, deployer_address, deployed_at FROM web3.contracts WHERE network_id = 'ethereum' ORDER BY deployed_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 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": "For each citizen who has made at least one payment, show the citizen's full name, number of payments, and total amount paid, grouped by currency."}, {"role": "assistant", "content": "SELECT\n  c.first_name || ' ' || c.last_name AS full_name,\n  p.currency,\n  COUNT(*) AS payment_count,\n  SUM(p.amount) AS total_amount\nFROM government_services.citizens c\nJOIN government_services.payments p ON c.citizen_id = p.citizen_id\nGROUP BY full_name, p.currency;"}], "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.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.employees ( employee_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, job_title character varying(150) NOT NULL, department character varying(100), work_email character varying(128) NOT NULL UNIQUE, work_phone character varying(32), hire_date date NOT NULL, termination_date date, access_level character varying(50), manager_employee_id character varying(64), PRIMARY KEY (employee_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) )\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) )\nCREATE TABLE government_services.notifications ( notification_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, application_id character varying(64), message_subject character varying(255), message_body text NOT NULL, channel character varying(30) NOT NULL, sent_at timestamp NOT NULL, status character varying(30) NOT NULL, related_entity_type character varying(50), related_entity_id character varying(64), PRIMARY KEY (notification_id) )\n"}
{"conversations": [{"role": "user", "content": "Count the number of contracts per network and status."}, {"role": "assistant", "content": "SELECT\n  network_id,\n  status,\n  COUNT(*) AS contract_count\nFROM web3.contracts\nGROUP BY network_id, status;"}, {"role": "user", "content": "Actually, please only include statuses with more than 10 contracts."}, {"role": "assistant", "content": "SELECT\n  network_id,\n  status,\n  COUNT(*) AS contract_count\nFROM web3.contracts\nGROUP BY network_id, status\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 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)\n"}
{"conversations": [{"role": "user", "content": "Show me all business center services (category = 'Business Center') along with their property IDs and descriptions, where the service is available."}, {"role": "assistant", "content": "SELECT service_name, property_id, description FROM hospitality_technology.services WHERE category = 'Business Center' AND is_available = true;"}, {"role": "user", "content": "Now, join this with another query to include the property names from the properties table (assuming properties table has property_id and property_name columns)."}, {"role": "assistant", "content": "SELECT s.service_name, s.property_id, s.description, p.property_name FROM hospitality_technology.services s JOIN hospitality_technology.properties p ON s.property_id = p.property_id WHERE s.category = 'Business Center' AND s.is_available = true;"}, {"role": "user", "content": "The query is missing the price information. Can you include that as well?"}, {"role": "assistant", "content": "SELECT s.service_name, s.property_id, s.description, p.property_name, s.price FROM hospitality_technology.services s JOIN hospitality_technology.properties p ON s.property_id = p.property_id WHERE s.category = 'Business Center' AND s.is_available = true;"}, {"role": "user", "content": "Actually, I need to see only services priced per hour (unit = 'Per Hour'), and order them by property name in alphabetical order."}, {"role": "assistant", "content": "SELECT s.service_name, s.property_id, s.description, p.property_name, s.price FROM hospitality_technology.services s JOIN hospitality_technology.properties p ON s.property_id = p.property_id WHERE s.category = 'Business Center' AND s.is_available = true AND s.unit = 'Per Hour' ORDER BY p.property_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 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)\n"}
{"conversations": [{"role": "user", "content": "How many insurance policies have 'Group' in their group_number?"}, {"role": "assistant", "content": "SELECT COUNT(*) FROM healthcare.patient_insurance WHERE group_number ILIKE '%Group%';"}], "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": "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": "Give me each server's name, the region, and the maximum number of players that have been connected at once."}, {"role": "assistant", "content": "SELECT s.server_id, s.server_name, s.region, MAX(s.current_players) AS max_players_seen\nFROM gaming_technology.servers s\nGROUP BY s.server_id, s.server_name, s.region;"}, {"role": "user", "content": "Could you also include the associated game title for each server?"}, {"role": "assistant", "content": "SELECT s.server_id, s.server_name, s.region, g.title AS game_title, MAX(s.current_players) AS max_players_seen\nFROM gaming_technology.servers s\nJOIN gaming_technology.games g ON s.game_id = g.game_id\nGROUP BY s.server_id, s.server_name, s.region, g.title;"}, {"role": "user", "content": "Now, can you show only servers where the max number of players ever connected exceeded 20?"}, {"role": "assistant", "content": "SELECT s.server_id, s.server_name, s.region, g.title AS game_title, MAX(s.current_players) AS max_players_seen\nFROM gaming_technology.servers s\nJOIN gaming_technology.games g ON s.game_id = g.game_id\nGROUP BY s.server_id, s.server_name, s.region, g.title\nHAVING MAX(s.current_players) > 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 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.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 (\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 ( 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 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 me all bookings with a status of 'confirmed' that were made in the last 7 days, including passenger_id and fare."}, {"role": "assistant", "content": "SELECT booking_id, passenger_id, fare FROM transportation.bookings WHERE status = 'confirmed' AND booking_time >= CURRENT_DATE - INTERVAL '7 days';"}, {"role": "user", "content": "Now include only bookings where the fare is greater than $50 and order them by booking_time in descending order."}, {"role": "assistant", "content": "SELECT booking_id, passenger_id, fare FROM transportation.bookings WHERE status = 'confirmed' AND booking_time >= CURRENT_DATE - INTERVAL '7 days' AND fare > 50 ORDER BY booking_time DESC;"}, {"role": "user", "content": "Can you also include the trip_id and filter to only show bookings for trip_id 'TRIP789'?"}, {"role": "assistant", "content": "SELECT booking_id, passenger_id, fare, trip_id FROM transportation.bookings WHERE status = 'confirmed' AND booking_time >= CURRENT_DATE - INTERVAL '7 days' AND fare > 50 AND trip_id = 'TRIP789' ORDER BY booking_time 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.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 all unique claim handler IDs present in the claims table."}, {"role": "assistant", "content": "SELECT DISTINCT claim_handler_id FROM insurance.claims WHERE claim_handler_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 insurance.claims ( claim_id text PRIMARY KEY, 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 )\n"}
{"conversations": [{"role": "user", "content": "Show me all customers who have missing contact information (either phone number or email is null), along with their state and city."}, {"role": "assistant", "content": "SELECT first_name, last_name, state, city FROM insurance.customers WHERE phone_number IS NULL OR email IS NULL;"}, {"role": "user", "content": "Now filter these to only show customers from Florida or New York who were created in the last year."}, {"role": "assistant", "content": "SELECT first_name, last_name, state, city FROM insurance.customers WHERE (phone_number IS NULL OR email IS NULL) AND state IN ('Florida', 'New York') AND created_at >= CURRENT_DATE - INTERVAL '1 year';"}, {"role": "user", "content": "I also want to see when these customers were last updated (updated_at field)."}, {"role": "assistant", "content": "SELECT first_name, last_name, state, city, updated_at FROM insurance.customers WHERE (phone_number IS NULL OR email IS NULL) AND state IN ('Florida', 'New York') AND created_at >= CURRENT_DATE - INTERVAL '1 year';"}, {"role": "user", "content": "Finally, order the results by state first, then by the most recently updated customers first."}, {"role": "assistant", "content": "SELECT first_name, last_name, state, city, updated_at FROM insurance.customers WHERE (phone_number IS NULL OR email IS NULL) AND state IN ('Florida', 'New York') AND created_at >= CURRENT_DATE - INTERVAL '1 year' ORDER BY state, updated_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 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 all active electric vehicles along with their make, model, and license plate, ordered by acquisition date with the newest first."}, {"role": "assistant", "content": "SELECT vehicle_id, make, model, license_plate, acquisition_date FROM transportation.vehicles WHERE status = 'active' AND fuel_type = 'electric' ORDER BY acquisition_date DESC;"}, {"role": "user", "content": "Now include the depot_id for these vehicles and filter to only show vehicles acquired in the last 2 years."}, {"role": "assistant", "content": "SELECT vehicle_id, make, model, license_plate, acquisition_date, depot_id FROM transportation.vehicles WHERE status = 'active' AND fuel_type = 'electric' AND acquisition_date >= CURRENT_DATE - INTERVAL '2 years' ORDER BY acquisition_date DESC;"}, {"role": "user", "content": "Can you also include the vehicle's capacity and order the results by capacity in descending order?"}, {"role": "assistant", "content": "SELECT vehicle_id, make, model, license_plate, acquisition_date, depot_id, capacity FROM transportation.vehicles WHERE status = 'active' AND fuel_type = 'electric' AND acquisition_date >= CURRENT_DATE - INTERVAL '2 years' ORDER 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 character varying(64) NOT NULL, license_plate character varying(32) NOT NULL UNIQUE, vin character varying(17) UNIQUE, make character varying(64) NOT NULL, model character varying(64) NOT NULL, year integer NOT NULL, type character varying(32) NOT NULL, capacity integer, fuel_type character varying(32) NOT NULL, status character varying(32) NOT NULL, depot_id character varying(64), acquisition_date date, PRIMARY KEY (vehicle_id) )\n"}
{"conversations": [{"role": "user", "content": "Find all medical records where the vitals field indicates a heart rate over 100 bpm, along with the associated appointment details and diagnosis description if available."}, {"role": "assistant", "content": "SELECT mr.record_id, mr.patient_id, a.appointment_time, a.doctor_id, a.reason, d.description FROM healthcare.medical_records mr LEFT JOIN healthcare.appointments a ON mr.appointment_id = a.appointment_id LEFT JOIN healthcare.diagnoses d ON mr.record_id = d.record_id WHERE mr.vitals::json->>'heart_rate' > '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 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 ( 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 )\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": "For each transaction, find the next transaction initiated by the same sender. List the original transaction_id, the next transaction_id, the sender address, and the time difference in hours between them."}, {"role": "assistant", "content": "SELECT t1.transaction_id AS original_tx,\n       t2.transaction_id AS next_tx,\n       t1.from_address,\n       EXTRACT(EPOCH FROM (t2.timestamp - t1.timestamp)) / 3600 AS hours_diff\nFROM transactions t1\nJOIN transactions t2\n  ON t1.from_address = t2.from_address\n AND t2.timestamp = (\n       SELECT MIN(timestamp)\n       FROM transactions t3\n       WHERE t3.from_address = t1.from_address\n         AND t3.timestamp > t1.timestamp\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 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 )\n"}
{"conversations": [{"role": "user", "content": "What are the specific tools or equipment used during the maintenance with record_id 'REC456'?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information about the specific tools or equipment used during a maintenance record. The data in the maintenance_records table does not include details about tools or equipment used."}], "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.maintenance_records ( record_id text PRIMARY KEY, asset_id text, asset_type text, maintenance_type text, staff_id text, start_datetime timestamp, end_datetime timestamp, description text, cost numeric, status text )\n"}
{"conversations": [{"role": "user", "content": "Show me all maintenance logs for 'Oil Change' services performed in the last 3 months, including the vehicle ID, service date, and cost."}, {"role": "assistant", "content": "SELECT vehicle_id, service_date, cost FROM transportation.maintenance_logs WHERE service_type = 'Oil Change' AND service_date >= CURRENT_DATE - INTERVAL '3 months';"}, {"role": "user", "content": "Can you also include the mechanic name and filter to only show services that cost more than $100?"}, {"role": "assistant", "content": "SELECT vehicle_id, service_date, cost, mechanic_name FROM transportation.maintenance_logs WHERE service_type = 'Oil Change' AND service_date >= CURRENT_DATE - INTERVAL '3 months' AND cost > 100;"}, {"role": "user", "content": "Now order these results by service date with the most recent first and limit to 10 records."}, {"role": "assistant", "content": "SELECT vehicle_id, service_date, cost, mechanic_name FROM transportation.maintenance_logs WHERE service_type = 'Oil Change' AND service_date >= CURRENT_DATE - INTERVAL '3 months' AND cost > 100 ORDER BY service_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 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)\n"}
{"conversations": [{"role": "user", "content": "What is the history of incidents or accidents that occurred on platform 5 at station GHI?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information about the history of incidents or accidents on platform 5 at station GHI. My data is limited to the structural and operational details of the platforms, such as platform ID, station ID, and status. For incident history, you may need to consult a different database or contact the 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.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": "Find all pairs of transactions that occurred in the same block and were sent to the same address. Show both transaction IDs, the shared recipient address, and the block number."}, {"role": "assistant", "content": "SELECT t1.transaction_id AS tx1,\n       t2.transaction_id AS tx2,\n       t1.to_address,\n       t1.block_number\nFROM transactions t1\nJOIN transactions t2\n  ON t1.to_address = t2.to_address\n AND t1.block_number = t2.block_number\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 ( 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 )\n"}
{"conversations": [{"role": "user", "content": "List all players and the number of distinct games they have grabbed in-game items from, as well as the name of each game."}, {"role": "assistant", "content": "SELECT p.player_id, p.username, g.game_id, g.title, COUNT(DISTINCT pi.item_id) AS distinct_items_acquired\nFROM gaming_technology.players p\nJOIN gaming_technology.player_inventory pi ON p.player_id = pi.player_id\nJOIN gaming_technology.in_game_items i ON pi.item_id = i.item_id\nJOIN gaming_technology.games g ON i.game_id = g.game_id\nGROUP BY p.player_id, p.username, g.game_id, g.title;"}, {"role": "user", "content": "Could you only show players who have grabbed items from more than one game?"}, {"role": "assistant", "content": "SELECT p.player_id, p.username, COUNT(DISTINCT g.game_id) AS games_with_items\nFROM gaming_technology.players p\nJOIN gaming_technology.player_inventory pi ON p.player_id = pi.player_id\nJOIN gaming_technology.in_game_items i ON pi.item_id = i.item_id\nJOIN gaming_technology.games g ON i.game_id = g.game_id\nGROUP BY p.player_id, p.username\nHAVING COUNT(DISTINCT g.game_id) > 1;"}, {"role": "user", "content": "Can you also include the total quantity of all items these players have from each game?"}, {"role": "assistant", "content": "SELECT p.player_id, p.username, g.game_id, g.title, SUM(pi.quantity) AS total_quantity\nFROM gaming_technology.players p\nJOIN gaming_technology.player_inventory pi ON p.player_id = pi.player_id\nJOIN gaming_technology.in_game_items i ON pi.item_id = i.item_id\nJOIN gaming_technology.games g ON i.game_id = g.game_id\nGROUP BY p.player_id, p.username, g.game_id, g.title\nHAVING COUNT(DISTINCT g.game_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 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.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 (\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 ( 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 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": "Can you give me the total number of appointments grouped by status?"}, {"role": "assistant", "content": "SELECT status,\n       COUNT(*) AS total_appointments\nFROM healthcare.appointments\nGROUP BY status;"}, {"role": "user", "content": "Filter the result to show only statuses with more than 50 appointments."}, {"role": "assistant", "content": "SELECT status,\n       COUNT(*) AS total_appointments\nFROM healthcare.appointments\nGROUP BY status\nHAVING COUNT(*) > 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 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": "Show me the top 5 users who have interacted with DApps, along with the count of distinct DApps they interacted with and their wallet addresses."}, {"role": "assistant", "content": "SELECT w.user_id, COUNT(DISTINCT d.dapp_id) AS dapp_count, w.address FROM trading_platform.wallets w JOIN trading_platform.dapps d ON 1=1 GROUP BY w.user_id, w.address ORDER BY dapp_count DESC LIMIT 5;"}, {"role": "user", "content": "This query doesn't properly show DApp interactions. Please modify it to correctly join with a table that records user-DApp interactions."}, {"role": "assistant", "content": "I notice there's no interaction table in the provided schema. Without a table recording user-DApp interactions, I cannot generate this query accurately. Would you like to see users who have wallets and DApps separately instead?"}, {"role": "user", "content": "You're right. Instead, show me users who have wallets but have never interacted with any DApps, along with their wallet addresses."}, {"role": "assistant", "content": "SELECT w.user_id, w.address FROM trading_platform.wallets w WHERE NOT EXISTS (SELECT 1 FROM trading_platform.dapps d WHERE 1=1) GROUP BY w.user_id, w.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 trading_platform.wallets ( wallet_id.text, user_id.text, address.text, private_key.text, created_at.timestamp )\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) )\nCREATE TABLE trading_platform.assets ( asset_id.text, name.text, symbol.text, type.text )\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.metadata ( metadata_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, key character varying(128) NOT NULL, value text NOT NULL, PRIMARY KEY (metadata_id) )\n"}
{"conversations": [{"role": "user", "content": "List the first name, last name, and firm name for all lawyers who are partners."}, {"role": "assistant", "content": "SELECT T1.first_name ,  T1.last_name ,  T2.firm_name FROM legal_services.lawyers AS T1 JOIN law_firms AS T2 ON T1.firm_id  =  T2.firm_id WHERE T1.is_partner  =  TRUE"}, {"role": "user", "content": "Only show partners from law firms founded before 2010."}, {"role": "assistant", "content": "SELECT T1.first_name ,  T1.last_name ,  T2.firm_name FROM legal_services.lawyers AS T1 JOIN law_firms AS T2 ON T1.firm_id  =  T2.firm_id WHERE T1.is_partner  =  TRUE AND T2.founded_date < '2010-01-01'"}, {"role": "user", "content": "Sort the results by firm name and then by the lawyer's last name."}, {"role": "assistant", "content": "SELECT T1.first_name ,  T1.last_name ,  T2.firm_name FROM legal_services.lawyers AS T1 JOIN law_firms AS T2 ON T1.firm_id  =  T2.firm_id WHERE T1.is_partner  =  TRUE AND T2.founded_date < '2010-01-01' ORDER BY T2.firm_name ,  T1.last_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 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": "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": "Find appointments that are longer than 30 minutes."}, {"role": "assistant", "content": "SELECT * FROM legal_services.appointments WHERE end_time IS NOT NULL AND start_time IS NOT NULL AND end_time > start_time + INTERVAL '30 minutes'"}], "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": "Provide the count of diagnoses by status."}, {"role": "assistant", "content": "SELECT status,\n       COUNT(*) AS count\nFROM healthcare.diagnoses\nGROUP BY status;"}, {"role": "user", "content": "Now only include statuses with more than 10 diagnoses."}, {"role": "assistant", "content": "SELECT status,\n       COUNT(*) AS count\nFROM healthcare.diagnoses\nGROUP BY status\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.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)\n"}
{"conversations": [{"role": "user", "content": "List all users whose usernames start with the letter 'B'."}, {"role": "assistant", "content": "SELECT user_id, username, email, created_at FROM trading_platform.users WHERE username LIKE 'B%';"}, {"role": "user", "content": "Can you make it case-insensitive, so usernames starting with either upper or lower case 'b' are included?"}, {"role": "assistant", "content": "SELECT user_id, username, email, created_at FROM trading_platform.users WHERE username ILIKE 'b%';"}, {"role": "user", "content": "Instead of showing all details, just display the usernames in alphabetical order."}, {"role": "assistant", "content": "SELECT username FROM trading_platform.users WHERE username ILIKE 'b%' ORDER BY username ASC;"}, {"role": "user", "content": "Limit the result to only the first 3 usernames."}, {"role": "assistant", "content": "SELECT username FROM trading_platform.users WHERE username ILIKE 'b%' ORDER BY username ASC 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 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)\n"}
{"conversations": [{"role": "user", "content": "List all DApps that have 'wallet' in their description, along with their URLs."}, {"role": "assistant", "content": "SELECT name, url FROM trading_platform.dapps WHERE description LIKE '%wallet%';"}, {"role": "user", "content": "Now show only DApps created in the last year, and include their creation date."}, {"role": "assistant", "content": "SELECT name, url, created_at FROM trading_platform.dapps WHERE description LIKE '%wallet%' AND created_at >= NOW() - INTERVAL '1 year';"}, {"role": "user", "content": "Actually, I want to see the count of such DApps grouped by month of creation."}, {"role": "assistant", "content": "SELECT DATE_TRUNC('month', created_at) AS month, COUNT(*) AS dapp_count FROM trading_platform.dapps WHERE description LIKE '%wallet%' AND created_at >= NOW() - INTERVAL '1 year' GROUP BY month ORDER BY 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 trading_platform.users ( user_id.text, username.text, email.text, password_hash.text, created_at.timestamp )\nCREATE TABLE trading_platform.dapps ( dapp_id.text, name.text, description.text, url.text )\n"}
{"conversations": [{"role": "user", "content": "Show the total trade amount for each account. Include the account_id and account_number."}, {"role": "assistant", "content": "SELECT\n  T1.account_id,\n  T1.account_number,\n  SUM(T2.total_amount) AS total_traded_amount\nFROM financial_services.accounts AS T1\nINNER JOIN financial_services.trades AS T2\n  ON T1.account_id = T2.account_id\nGROUP BY\n  T1.account_id,\n  T1.account_number;"}, {"role": "user", "content": "Only include trades with a status of 'SETTLED'."}, {"role": "assistant", "content": "SELECT\n  T1.account_id,\n  T1.account_number,\n  SUM(T2.total_amount) AS total_traded_amount\nFROM financial_services.accounts AS T1\nINNER JOIN financial_services.trades AS T2\n  ON T1.account_id = T2.account_id\nWHERE\n  T2.status = 'SETTLED'\nGROUP BY\n  T1.account_id,\n  T1.account_number;"}, {"role": "user", "content": "Filter out accounts where the total traded amount for settled trades is less than 5000."}, {"role": "assistant", "content": "SELECT\n  T1.account_id,\n  T1.account_number,\n  SUM(T2.total_amount) AS total_traded_amount\nFROM financial_services.accounts AS T1\nINNER JOIN financial_services.trades AS T2\n  ON T1.account_id = T2.account_id\nWHERE\n  T2.status = 'SETTLED'\nGROUP BY\n  T1.account_id,\n  T1.account_number\nHAVING\n  SUM(T2.total_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 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": "List each employee's first and last name along with the count of active services offered by their agency."}, {"role": "assistant", "content": "SELECT e.first_name, e.last_name, COUNT(s.service_id) AS active_service_count\nFROM government_services.employees e\nJOIN 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;"}, {"role": "user", "content": "Actually, only include employees whose service count is greater than 5."}, {"role": "assistant", "content": "SELECT e.first_name, e.last_name, COUNT(s.service_id) AS active_service_count\nFROM government_services.employees e\nJOIN 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\nHAVING COUNT(s.service_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 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.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 ( service_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, service_name character varying(255) NOT NULL, description text, category character varying(100), eligibility_criteria text, standard_fee numeric(10, 2) DEFAULT 0.00, average_processing_time_days integer, is_active boolean DEFAULT true, online_application_url character varying(255), PRIMARY KEY (service_id) )\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.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.employees ( employee_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, job_title character varying(150) NOT NULL, department character varying(100), work_email character varying(128) NOT NULL UNIQUE, work_phone character varying(32), hire_date date NOT NULL, termination_date date, access_level character varying(50), manager_employee_id character varying(64), PRIMARY KEY (employee_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) )\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) )\nCREATE TABLE government_services.notifications ( notification_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, application_id character varying(64), message_subject character varying(255), message_body text NOT NULL, channel character varying(30) NOT NULL, sent_at timestamp NOT NULL, status character varying(30) NOT NULL, related_entity_type character varying(50), related_entity_id character varying(64), PRIMARY KEY (notification_id) )\n"}
{"conversations": [{"role": "user", "content": "Find all nodes that were last seen in the last 30 days and have port numbers between 8000 and 9000."}, {"role": "assistant", "content": "SELECT node_id, ip_address, port FROM blockchain.nodes WHERE last_seen >= NOW() - INTERVAL '30 days' AND port BETWEEN 8000 AND 9000"}, {"role": "user", "content": "Can you also show the count of transactions sent from wallet addresses that share the same IP as these nodes?"}, {"role": "assistant", "content": "This query isn't possible with the current schema as there's no relationship between nodes IP addresses and wallet addresses."}, {"role": "user", "content": "Then just show me nodes that share the same IP address along with how many nodes share each IP."}, {"role": "assistant", "content": "SELECT ip_address, COUNT(*) as node_count FROM blockchain.nodes GROUP BY ip_address HAVING COUNT(*) > 1"}, {"role": "user", "content": "Now filter this to only show IP addresses with more than 3 nodes and include the earliest and latest last_seen timestamps."}, {"role": "assistant", "content": "SELECT ip_address, COUNT(*) as node_count, MIN(last_seen) as earliest_seen, MAX(last_seen) as latest_seen FROM blockchain.nodes GROUP BY ip_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.transactions ( transaction_id text, block_id text, sender_address text, receiver_address text, amount numeric, timestamp timestamp, signature text )\nCREATE TABLE blockchain.nodes ( node_id text, ip_address text, port integer, last_seen timestamp )\nCREATE TABLE blockchain.wallets ( wallet_id text, user_id text, address_id text, private_key text )\nCREATE TABLE blockchain.smart_contracts ( contract_id text, creator_address text, code text, timestamp timestamp )\n"}
{"conversations": [{"role": "user", "content": "List all passengers along with their ages and loyalty program membership status."}, {"role": "assistant", "content": "SELECT passenger_id, first_name, last_name, date_of_birth, loyalty_program_id, DATE_PART('year', AGE(current_date, date_of_birth)) AS age FROM transportation.passengers ORDER BY last_name, first_name;"}, {"role": "user", "content": "I need to see only passengers who are at least 30 years old."}, {"role": "assistant", "content": "SELECT passenger_id, first_name, last_name, date_of_birth, loyalty_program_id, DATE_PART('year', AGE(current_date, date_of_birth)) AS age FROM transportation.passengers WHERE DATE_PART('year', AGE(current_date, date_of_birth)) >= 30 ORDER BY last_name, first_name;"}, {"role": "user", "content": "Can you also exclude passengers without a registered email address?"}, {"role": "assistant", "content": "SELECT passenger_id, first_name, last_name, date_of_birth, loyalty_program_id, DATE_PART('year', AGE(current_date, date_of_birth)) AS age FROM transportation.passengers WHERE DATE_PART('year', AGE(current_date, date_of_birth)) >= 30 AND email IS NOT NULL ORDER BY last_name, first_name;"}, {"role": "user", "content": "Actually, add their phone number and order by age descending."}, {"role": "assistant", "content": "SELECT passenger_id, first_name, last_name, date_of_birth, loyalty_program_id, email, phone_number, DATE_PART('year', AGE(current_date, date_of_birth)) AS age FROM transportation.passengers WHERE DATE_PART('year', AGE(current_date, date_of_birth)) >= 30 AND email IS NOT NULL ORDER BY age DESC, last_name, first_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 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)\n"}
{"conversations": [{"role": "user", "content": "Show me all time entries from the last 90 days, including the entry description, hours spent, the name of the case, and the name of the client."}, {"role": "assistant", "content": "SELECT T1.description, T1.hours_spent, T2.case_name, T3.first_name, T3.last_name FROM legal_services.time_entries AS T1 JOIN cases AS T2 ON T1.case_id = T2.case_id JOIN clients AS T3 ON T2.client_id = T3.client_id WHERE T1.date_worked >= CURRENT_DATE - INTERVAL '90 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 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)\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": "List each driver along with the driver_id of the driver who was hired immediately after them."}, {"role": "assistant", "content": "SELECT d1.driver_id AS current_driver_id, d2.driver_id AS next_driver_id FROM transportation.drivers d1 LEFT JOIN transportation.drivers d2 ON d2.hire_date = (SELECT MIN(hire_date) FROM transportation.drivers WHERE hire_date > d1.hire_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 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 )\n"}
{"conversations": [{"role": "user", "content": "Show me each patient's full name along with the name of every doctor they've had an appointment with."}, {"role": "assistant", "content": "SELECT p.first_name || ' ' || p.last_name AS patient_full_name, d.first_name || ' ' || d.last_name AS doctor_full_name\nFROM healthcare.appointments a\nJOIN healthcare.patients p ON a.patient_id = p.patient_id\nJOIN healthcare.doctors d ON a.doctor_id = d.doctor_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 healthcare.patients ( patient_id text PRIMARY KEY, 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 PRIMARY KEY, 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 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 )\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 PRIMARY KEY, 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 int, prescription_date timestamp )\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id text PRIMARY KEY, 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 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": "Show me the top 5 narratives by market cap, along with their 24-hour trading volume and 7-day price change percentage."}, {"role": "assistant", "content": "SELECT narrative.text, volume_24h.numeric, price_change_percentage_7d.numeric FROM narrative_info ORDER BY market_cap.numeric DESC LIMIT 5;"}, {"role": "user", "content": "Can you also include the top 3 coins for each of these narratives?"}, {"role": "assistant", "content": "SELECT narrative.text, volume_24h.numeric, price_change_percentage_7d.numeric, top_3_coins.text FROM narrative_info ORDER BY market_cap.numeric 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 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": "Show me all insurance plans that have more than 5 patients enrolled, along with the provider name and count of patients, sorted by patient count in descending order."}, {"role": "assistant", "content": "SELECT i.plan_name, i.insurance_provider, COUNT(p.patient_id) AS patient_count FROM healthcare.insurance_plans i JOIN healthcare.patients p ON i.plan_id = p.primary_insurance_id GROUP BY i.plan_id HAVING COUNT(p.patient_id) > 5 ORDER BY patient_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.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.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.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)\n"}
{"conversations": [{"role": "user", "content": "Find all pairs of overlapping payment periods for the same customer. Return customer_id, first payment_id as payment1_id, second payment_id as payment2_id, and both periods' start and end dates."}, {"role": "assistant", "content": "SELECT p1.customer_id,\n       p1.payment_id AS payment1_id,\n       p2.payment_id AS payment2_id,\n       p1.payment_period_start AS start1,\n       p1.payment_period_end   AS end1,\n       p2.payment_period_start AS start2,\n       p2.payment_period_end   AS end2\nFROM insurance.premium_payments p1\nJOIN insurance.premium_payments p2\n  ON p1.customer_id = p2.customer_id\n AND p1.payment_id < p2.payment_id\n -- periods overlap\n AND p1.payment_period_start <= p2.payment_period_end\n AND p2.payment_period_start <= p1.payment_period_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 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)\n"}
{"conversations": [{"role": "user", "content": "Retrieve the vehicle_id, make, model, and the next_service_due_date for each vehicle based on the most recent maintenance log."}, {"role": "assistant", "content": "SELECT DISTINCT ON (ml.vehicle_id) v.vehicle_id, v.make, v.model, ml.next_service_due_date FROM transportation.maintenance_logs ml JOIN transportation.vehicles v ON v.vehicle_id = ml.vehicle_id ORDER BY ml.vehicle_id, ml.service_date DESC;"}, {"role": "user", "content": "Now, only include vehicles with status 'Active' and whose next_service_due_date is within the next 30 days, ordering by next_service_due_date ascending."}, {"role": "assistant", "content": "SELECT v.vehicle_id, v.make, v.model, ml.next_service_due_date FROM transportation.vehicles v JOIN (SELECT DISTINCT ON (vehicle_id) vehicle_id, next_service_due_date FROM transportation.maintenance_logs ORDER BY vehicle_id, service_date DESC) ml ON v.vehicle_id = ml.vehicle_id WHERE v.status = 'Active' AND ml.next_service_due_date BETWEEN current_date AND current_date + INTERVAL '30 days' ORDER BY ml.next_service_due_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 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": "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": "Could you list each game title along with its developer's name and the total number of servers hosting it?"}, {"role": "assistant", "content": "SELECT g.title, d.name AS developer_name, COUNT(s.server_id) AS server_count\nFROM gaming_technology.games g\nLEFT JOIN gaming_technology.developers d ON g.developer_id = d.developer_id\nLEFT JOIN gaming_technology.servers s ON g.game_id = s.game_id\nGROUP BY g.title, d.name;"}, {"role": "user", "content": "Actually, please include only servers with status = 'online' and exclude games with zero online servers."}, {"role": "assistant", "content": "SELECT g.title, d.name AS developer_name, COUNT(s.server_id) AS server_count\nFROM gaming_technology.games g\nJOIN gaming_technology.developers d ON g.developer_id = d.developer_id\nJOIN gaming_technology.servers s ON g.game_id = s.game_id\nWHERE s.status = 'online'\nGROUP BY g.title, d.name;"}, {"role": "user", "content": "I want to see only developers based in 'USA'."}, {"role": "assistant", "content": "SELECT g.title, d.name AS developer_name, COUNT(s.server_id) AS server_count\nFROM gaming_technology.games g\nJOIN gaming_technology.developers d ON g.developer_id = d.developer_id\nJOIN gaming_technology.servers s ON g.game_id = s.game_id AND s.status = 'online'\nWHERE d.country = 'USA'\nGROUP BY g.title, d.name;"}, {"role": "user", "content": "Finally, sort the results by server_count in descending order."}, {"role": "assistant", "content": "SELECT g.title, d.name AS developer_name, COUNT(s.server_id) AS server_count\nFROM gaming_technology.games g\nJOIN gaming_technology.developers d ON g.developer_id = d.developer_id\nJOIN gaming_technology.servers s ON g.game_id = s.game_id AND s.status = 'online'\nWHERE d.country = 'USA'\nGROUP BY g.title, d.name\nORDER BY server_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.games ( game_id uuid, 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, name text, country text, founded_year integer, website text, created_at timestamp with time zone )\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 timestamp with time zone )\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 timestamp with time zone )\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 )\nCREATE TABLE gaming_technology.player_inventory ( inventory_id uuid, player_id uuid, item_id uuid, quantity integer, acquired_at timestamp with time zone, instance_data jsonb )\n"}
{"conversations": [{"role": "user", "content": "Show me all policies that expired in the last 60 days, along with their product IDs and premium amounts."}, {"role": "assistant", "content": "SELECT policy_id, product_id, premium_amount FROM insurance.policies WHERE status = 'expired' AND end_date >= CURRENT_DATE - INTERVAL '60 days' AND end_date <= CURRENT_DATE;"}, {"role": "user", "content": "Now include only policies that had a deductible of $1000 or more."}, {"role": "assistant", "content": "SELECT policy_id, product_id, premium_amount, deductible FROM insurance.policies WHERE status = 'expired' AND end_date >= CURRENT_DATE - INTERVAL '60 days' AND end_date <= CURRENT_DATE AND deductible >= 1000;"}, {"role": "user", "content": "I also want to see the count of such expired policies per product ID."}, {"role": "assistant", "content": "SELECT product_id, COUNT(*) as policy_count FROM insurance.policies WHERE status = 'expired' AND end_date >= CURRENT_DATE - INTERVAL '60 days' AND end_date <= CURRENT_DATE AND deductible >= 1000 GROUP BY product_id ORDER BY policy_count DESC;"}, {"role": "user", "content": "Finally, show me the average premium amount for these expired high-deductible policies grouped by product ID."}, {"role": "assistant", "content": "SELECT product_id, AVG(premium_amount) as avg_premium FROM insurance.policies WHERE status = 'expired' AND end_date >= CURRENT_DATE - INTERVAL '60 days' AND end_date <= CURRENT_DATE AND deductible >= 1000 GROUP BY product_id ORDER BY avg_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.policies ( policy_id text PRIMARY KEY, 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": "List all insurance products that have a base premium greater than 1000 and are currently active, showing product name, type, and base premium."}, {"role": "assistant", "content": "SELECT product_name, product_type, base_premium FROM insurance.insurance_products WHERE base_premium > 1000 AND is_active = TRUE"}, {"role": "user", "content": "Now, find policies associated with these products that were issued in 2024, showing the policy number and its premium amount."}, {"role": "assistant", "content": "SELECT p.policy_number, p.premium_amount FROM insurance.policies AS p JOIN insurance.insurance_products AS ip ON p.product_id = ip.product_id WHERE ip.base_premium > 1000 AND ip.is_active = TRUE AND date_part('year', p.issued_at) = 2024"}], "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 users have non-empty full_name and bio fields? Return only the count."}, {"role": "assistant", "content": "SELECT COUNT(*)\nFROM social_media.users\nWHERE full_name IS NOT NULL\n  AND full_name <> ''\n  AND bio IS NOT NULL\n  AND bio <> '';"}], "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 )\n"}
{"conversations": [{"role": "user", "content": "For each player, count the total number of achievements they've unlocked."}, {"role": "assistant", "content": "SELECT player_id,\n       COUNT(*) AS total_achievements\nFROM gaming_technology.player_achievements\nGROUP BY player_id;"}, {"role": "user", "content": "Exclude players with fewer than 10 achievements."}, {"role": "assistant", "content": "SELECT player_id,\n       COUNT(*) AS total_achievements\nFROM gaming_technology.player_achievements\nGROUP BY player_id\nHAVING COUNT(*) >= 10;"}, {"role": "user", "content": "Additionally, provide the month when they achieved their 10th achievement. Show player_id, total_achievements, and the month of the 10th unlock."}, {"role": "assistant", "content": "WITH ranked AS (\n  SELECT player_id,\n         unlocked_at,\n         ROW_NUMBER() OVER (PARTITION BY player_id ORDER BY unlocked_at) AS rn\n  FROM gaming_technology.player_achievements\n),\ncounts AS (\n  SELECT player_id,\n         COUNT(*) AS total_achievements\n  FROM gaming_technology.player_achievements\n  GROUP BY player_id\n  HAVING COUNT(*) >= 10\n)\nSELECT c.player_id,\n       c.total_achievements,\n       EXTRACT(MONTH FROM r.unlocked_at) AS tenth_achievement_month\nFROM counts c\nJOIN ranked r\n  ON c.player_id = r.player_id\n AND r.rn = 10;"}, {"role": "user", "content": "Finally, order by total_achievements descending."}, {"role": "assistant", "content": "WITH ranked AS (\n  SELECT player_id,\n         unlocked_at,\n         ROW_NUMBER() OVER (PARTITION BY player_id ORDER BY unlocked_at) AS rn\n  FROM gaming_technology.player_achievements\n),\ncounts AS (\n  SELECT player_id,\n         COUNT(*) AS total_achievements\n  FROM gaming_technology.player_achievements\n  GROUP BY player_id\n  HAVING COUNT(*) >= 10\n)\nSELECT c.player_id,\n       c.total_achievements,\n       EXTRACT(MONTH FROM r.unlocked_at) AS tenth_achievement_month\nFROM counts c\nJOIN ranked r\n  ON c.player_id = r.player_id\n AND r.rn = 10\nORDER BY c.total_achievements 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.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": "Find all pairs of tokens that have the same contract_address but different token_symbols. Show both token_ids, each token's symbol, and the shared contract_address."}, {"role": "assistant", "content": "SELECT t1.token_id AS token_id_1, t2.token_id AS token_id_2, t1.token_symbol AS symbol_1, t2.token_symbol AS symbol_2, t1.contract_address FROM web3.tokens t1 JOIN web3.tokens t2 ON t1.contract_address = t2.contract_address AND t1.token_id < t2.token_id AND t1.token_symbol <> t2.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.tokens ( token_id text PRIMARY KEY, contract_address text, token_name text, token_symbol text, decimals int, total_supply numeric )\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 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": "Can you also include the symbol and decimals for these tokens?"}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address, tm.total_supply, tm.decimals 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": "Now filter these results to only show tokens with decimals equal to 18."}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address, tm.total_supply, tm.decimals 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 AND tm.decimals = 18 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 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_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_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": "List all insurance plans along with their provider, plan type, and the contact phone number. Also, for each plan, show how many doctors have their hospital affiliation ID matching the plan ID."}, {"role": "assistant", "content": "SELECT ip.plan_id, ip.plan_name, ip.insurance_provider, ip.plan_type, ip.contact_phone, COUNT(d.doctor_id) FROM healthcare.insurance_plans ip LEFT JOIN healthcare.doctors d ON ip.plan_id = d.hospital_affiliation_id GROUP BY ip.plan_id, ip.plan_name, ip.insurance_provider, ip.plan_type, ip.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 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, 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.insurance_plans ( plan_id text, plan_name text, insurance_provider text, plan_type text, contact_phone text, website text )\n"}
{"conversations": [{"role": "user", "content": "List all users who have never followed anyone, showing their username, full name, email, and account creation date."}, {"role": "assistant", "content": "SELECT u.username,\n       u.full_name,\n       u.email,\n       u.created_at\nFROM social_media.users AS u\nLEFT JOIN social_media.follows AS f\n  ON u.user_id = f.follower_user_id\nWHERE f.follow_id IS 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, 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 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.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.likes ( like_id text PRIMARY KEY, user_id text, post_id text, comment_id text, created_at timestamp )\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 ( 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.post_hashtags ( post_hashtag_id text PRIMARY KEY, 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.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": "How many documents were uploaded in the year 2023?"}, {"role": "assistant", "content": "SELECT count(*) FROM government_services.documents WHERE date_part('year', upload_timestamp) = 2023;"}], "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": "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": "Could you show me each employee's full name along with their manager's full name?"}, {"role": "assistant", "content": "SELECT e.employee_id,\n       e.first_name || ' ' || e.last_name AS employee_name,\n       m.employee_id AS manager_id,\n       m.first_name || ' ' || m.last_name AS manager_name\nFROM government_services.employees e\nLEFT JOIN government_services.employees m ON e.manager_employee_id = m.employee_id;"}, {"role": "user", "content": "Actually, only include employees who were hired after January 1, 2020."}, {"role": "assistant", "content": "SELECT e.employee_id,\n       e.first_name || ' ' || e.last_name AS employee_name,\n       m.employee_id AS manager_id,\n       m.first_name || ' ' || m.last_name AS manager_name\nFROM government_services.employees e\nLEFT JOIN government_services.employees m ON e.manager_employee_id = m.employee_id\nWHERE e.hire_date > '2020-01-01';"}], "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 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)\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": "How many employees work in each department? List the department name and the count."}, {"role": "assistant", "content": "SELECT department, COUNT(*) FROM government_services.employees GROUP BY department"}, {"role": "user", "content": "Only show departments with more than 5 employees."}, {"role": "assistant", "content": "SELECT department, COUNT(*) FROM government_services.employees GROUP BY department HAVING COUNT(*) > 5"}, {"role": "user", "content": "For these departments, also list the job titles present."}, {"role": "assistant", "content": "SELECT department, COUNT(*), STRING_AGG(DISTINCT job_title, ', ') FROM government_services.employees GROUP BY department HAVING COUNT(*) > 5"}, {"role": "user", "content": "Add the total number of employees hired in 2023 for each of these departments."}, {"role": "assistant", "content": "SELECT department, COUNT(*), STRING_AGG(DISTINCT job_title, ', '), SUM(CASE WHEN EXTRACT(YEAR FROM hire_date) = 2023 THEN 1 ELSE 0 END) AS employees_hired_in_2023 FROM government_services.employees GROUP BY department 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 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.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 (\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.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 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) )\nCREATE TABLE government_services.appointments ( appointment_id.text, 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": "Retrieve each agent's ID, full name, and the count of 'Pending' policies they have sold with a premium_amount greater than 2000. Order the results by the policy count descending."}, {"role": "assistant", "content": "SELECT a.agent_id,\n       a.first_name || ' ' || a.last_name AS agent_name,\n       COUNT(p.policy_id) AS pending_policy_count\nFROM insurance.agents a\nJOIN insurance.policies p ON a.agent_id = p.agent_id\nWHERE p.status = 'Pending'\n  AND p.premium_amount > 2000\nGROUP BY a.agent_id, agent_name\nORDER BY pending_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 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 (\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.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": "What is the average ROI and average realized_ratio for each chain?"}, {"role": "assistant", "content": "SELECT chain,\n       AVG(roi) AS avg_roi,\n       AVG(realized_ratio) AS avg_realized_ratio\nFROM smart_money_token_performance\nGROUP BY chain;"}, {"role": "user", "content": "Now filter to only include chains where average ROI is above 0.5."}, {"role": "assistant", "content": "WITH stats AS (\n  SELECT chain,\n         AVG(roi) AS avg_roi,\n         AVG(realized_ratio) AS avg_realized_ratio\n  FROM smart_money_token_performance\n  GROUP BY chain\n)\nSELECT chain, avg_roi, avg_realized_ratio\nFROM stats\nWHERE avg_roi > 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 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 claim IDs that have both an 'Accident Report' and a 'Damage Assessment' document, and show the earliest upload timestamp for each type."}, {"role": "assistant", "content": "SELECT a.claim_id,\n       MIN(a.uploaded_at) AS accident_report_date,\n       MIN(d.uploaded_at) AS damage_assessment_date\nFROM insurance.claim_documents AS a\nJOIN insurance.claim_documents AS d\n  ON a.claim_id = d.claim_id\nWHERE a.document_type = 'Accident Report'\n  AND d.document_type = 'Damage Assessment'\nGROUP BY a.claim_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 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": "For each player, show the timestamp of their first achievement unlock. Include player_id and the timestamp."}, {"role": "assistant", "content": "SELECT player_id, MIN(unlocked_at) as first_unlock_at FROM gaming_technology.player_achievements GROUP BY player_id ORDER BY first_unlock_at;"}, {"role": "user", "content": "For each player, show the timestamp of their second earliest achievement unlock, if they have at least two. Include player_id and the timestamp."}, {"role": "assistant", "content": "WITH RankedUnlocks AS ( SELECT player_id, unlocked_at, ROW_NUMBER() OVER(PARTITION BY player_id ORDER BY unlocked_at) as rn FROM gaming_technology.player_achievements ) SELECT player_id, unlocked_at as second_unlock_at FROM RankedUnlocks WHERE rn = 2 ORDER BY player_id, second_unlock_at;"}, {"role": "user", "content": "List the player_id for players who unlocked their second achievement within 10 minutes of their first."}, {"role": "assistant", "content": "WITH PlayerFirstUnlock AS ( SELECT player_id, MIN(unlocked_at) as first_unlock_at FROM gaming_technology.player_achievements GROUP BY player_id ), RankedUnlocks AS ( SELECT player_id, unlocked_at, ROW_NUMBER() OVER(PARTITION BY player_id ORDER BY unlocked_at) as rn FROM gaming_technology.player_achievements ) SELECT pfu.player_id FROM PlayerFirstUnlock pfu JOIN RankedUnlocks ru ON pfu.player_id = ru.player_id WHERE ru.rn = 2 AND ru.unlocked_at <= pfu.first_unlock_at + INTERVAL '10 minute' ORDER BY pfu.player_id;"}, {"role": "user", "content": "For the players identified in the previous query (those whose second unlock was within 10 minutes of the first), list the achievement_id of their first and second unlocks."}, {"role": "assistant", "content": "WITH PlayerFirstUnlock AS ( SELECT player_id, MIN(unlocked_at) as first_unlock_at FROM gaming_technology.player_achievements GROUP BY player_id ), RankedUnlocks AS ( SELECT player_id, achievement_id, unlocked_at, ROW_NUMBER() OVER(PARTITION BY player_id ORDER BY unlocked_at) as rn FROM gaming_technology.player_achievements ), PlayersWithFastSecondUnlock AS ( SELECT pfu.player_id FROM PlayerFirstUnlock pfu JOIN RankedUnlocks ru ON pfu.player_id = ru.player_id WHERE ru.rn = 2 AND ru.unlocked_at <= pfu.first_unlock_at + INTERVAL '10 minute' ) SELECT pfl.player_id, ru_first.achievement_id as first_achievement_id, ru_second.achievement_id as second_achievement_id FROM PlayersWithFastSecondUnlock pfl JOIN RankedUnlocks ru_first ON pfl.player_id = ru_first.player_id AND ru_first.rn = 1 JOIN RankedUnlocks ru_second ON pfl.player_id = ru_second.player_id AND ru_second.rn = 2 ORDER BY pfl.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.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": "List each citizen's first and last name along with the number of applications they have submitted, only include those with at least 3 applications."}, {"role": "assistant", "content": "SELECT c.first_name, c.last_name, COUNT(a.application_id) AS application_count\nFROM government_services.citizens c\nJOIN government_services.applications a ON c.citizen_id = a.citizen_id\nGROUP BY c.first_name, c.last_name\nHAVING COUNT(a.application_id) >= 3;"}, {"role": "user", "content": "Now also show the average standard fee of the services those applications are associated with."}, {"role": "assistant", "content": "SELECT c.first_name, c.last_name, COUNT(a.application_id) AS application_count, AVG(s.standard_fee) AS avg_service_fee\nFROM government_services.citizens c\nJOIN government_services.applications a ON c.citizen_id = a.citizen_id\nJOIN government_services.services s ON a.service_id = s.service_id\nGROUP BY c.first_name, c.last_name\nHAVING COUNT(a.application_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.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.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.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.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 )\nCREATE TABLE government_services.appointments ( appointment_id.text, 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 the block ID, timestamp, and difficulty for all blocks created before '2024-01-01', ordered by timestamp in descending order."}, {"role": "assistant", "content": "SELECT block_id, timestamp, difficulty FROM blockchain.blocks WHERE timestamp < '2024-01-01' ORDER BY timestamp DESC;"}, {"role": "user", "content": "Now, filter those results to only show blocks with a difficulty between 8000 and 12000."}, {"role": "assistant", "content": "SELECT block_id, timestamp, difficulty FROM blockchain.blocks WHERE timestamp < '2024-01-01' AND difficulty BETWEEN 8000 AND 12000 ORDER BY timestamp 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 blockchain.blocks ( block_id.text, previous_block_id.text, timestamp.timestamp, nonce.integer, merkle_root.text, difficulty.integer )\nCREATE TABLE blockchain.wallets ( wallet_id.text, user_id.text, address_id.text, private_key.text )\nCREATE TABLE blockchain.smart_contracts ( contract_id.text, creator_address.text, code.text, timestamp.timestamp )\n"}
{"conversations": [{"role": "user", "content": "For each claim handler, count the number of documents uploaded for the claims they handled. Return claim_handler_id and document_count."}, {"role": "assistant", "content": "SELECT c.claim_handler_id,\n       COUNT(d.document_id) AS document_count\nFROM insurance.claims AS c\nJOIN insurance.claim_documents AS d\n  ON c.claim_id = d.claim_id\nGROUP BY c.claim_handler_id;"}, {"role": "user", "content": "Now restrict to handlers who have uploaded more than 10 documents."}, {"role": "assistant", "content": "SELECT c.claim_handler_id,\n       COUNT(d.document_id) AS document_count\nFROM insurance.claims AS c\nJOIN insurance.claim_documents AS d\n  ON c.claim_id = d.claim_id\nGROUP BY c.claim_handler_id\nHAVING COUNT(d.document_id) > 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 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.premium_payments ( payment_id character varying(64) NOT NULL, policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, payment_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, amount_paid numeric(12, 2) NOT NULL, payment_method character varying(50), transaction_reference character varying(128) UNIQUE, due_date date, payment_period_start date, payment_period_end date, status character varying(30) NOT NULL DEFAULT 'Completed', PRIMARY KEY (payment_id) )\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": "List the names of employees and the agency they work for who have scheduled at least one appointment. Show the employee's first name, last name, and agency_id."}, {"role": "assistant", "content": "SELECT DISTINCT e.first_name, e.last_name, e.agency_id\nFROM government_services.employees e\nJOIN government_services.appointments a ON e.employee_id = a.employee_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.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 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.appointments ( appointment_id text, 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, 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 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": "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": "How many distinct ports have been used by peers in the system?"}, {"role": "assistant", "content": "SELECT COUNT(DISTINCT port) AS distinct_port_count\nFROM trading_platform.peers;"}], "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 (\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 ( order_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, wallet_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, order_type character varying(32) NOT NULL, quantity numeric(38,14) NOT NULL, price numeric(38,14) NOT NULL, status character varying(32) NOT NULL, created_at timestamp NOT NULL, PRIMARY KEY (order_id) )\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 ( dapp_id.text, name.text, description.text, url.text )\nCREATE TABLE trading_platform.peers ( peer_id character varying(64) NOT NULL, ip_address character varying(15) NOT NULL, port integer NOT NULL, last_seen timestamp NOT NULL, PRIMARY KEY (peer_id) )\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 ( kyc_audit_id.text, user_id.text, status.text, reviewed_at.timestamp )\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)\nCREATE TABLE trading_platform.notifications ( notification_id.text, user_id.text, message.text, sent_at.timestamp, read_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": "Could you list all pairs of developers that are based in the same country and share the same website domain?"}, {"role": "assistant", "content": "SELECT\n  d1.name AS developer1_name,\n  d2.name AS developer2_name,\n  d1.country,\n  d1.website\nFROM\n  gaming_technology.developers AS d1\nJOIN\n  gaming_technology.developers AS d2 ON d1.country = d2.country\n  AND d1.website = d2.website\n  AND d1.developer_id < d2.developer_id\nWHERE\n  d1.country IS NOT NULL\n  AND d1.website IS NOT NULL AND d1.website != '';"}], "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 (\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)\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": "For each route that originates from a location of type 'Port', list the route number, the name of the origin location, and the total distance accumulated from all completed trips on this route."}, {"role": "assistant", "content": "SELECT\n  r.route_number,\n  l_origin.name AS origin_location_name,\n  SUM(t.distance_km) AS total_accumulated_distance\nFROM transportation.routes AS r\nJOIN transportation.locations AS l_origin\n  ON r.origin_location_id = l_origin.location_id\nJOIN transportation.trips AS t\n  ON r.route_id = t.route_id\nWHERE\n  l_origin.type = 'Port' AND t.status = 'Completed'\nGROUP BY\n  r.route_id,\n  r.route_number,\n  l_origin.name;"}, {"role": "user", "content": "Now, only include routes where the accumulated distance is greater than 5000 kilometers and order the results by accumulated distance descending."}, {"role": "assistant", "content": "SELECT\n  r.route_number,\n  l_origin.name AS origin_location_name,\n  SUM(t.distance_km) AS total_accumulated_distance\nFROM transportation.routes AS r\nJOIN transportation.locations AS l_origin\n  ON r.origin_location_id = l_origin.location_id\nJOIN transportation.trips AS t\n  ON r.route_id = t.route_id\nWHERE\n  l_origin.type = 'Port' AND t.status = 'Completed'\nGROUP BY\n  r.route_id,\n  r.route_number,\n  l_origin.name\nHAVING\n  SUM(t.distance_km) > 5000\nORDER BY\n  total_accumulated_distance DESC;"}, {"role": "user", "content": "Also include the number of completed trips for each of these routes and filter further to only show routes that have had more than 5 completed trips."}, {"role": "assistant", "content": "SELECT\n  r.route_number,\n  l_origin.name AS origin_location_name,\n  SUM(t.distance_km) AS total_accumulated_distance,\n  COUNT(t.trip_id) AS completed_trip_count\nFROM transportation.routes AS r\nJOIN transportation.locations AS l_origin\n  ON r.origin_location_id = l_origin.location_id\nJOIN transportation.trips AS t\n  ON r.route_id = t.route_id\nWHERE\n  l_origin.type = 'Port' AND t.status = 'Completed'\nGROUP BY\n  r.route_id,\n  r.route_number,\n  l_origin.name\nHAVING\n  SUM(t.distance_km) > 5000 AND COUNT(t.trip_id) > 5\nORDER BY\n  total_accumulated_distance 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.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": "Count the number of registered citizens by gender."}, {"role": "assistant", "content": "SELECT\n  gender,\n  COUNT(*) AS citizen_count\nFROM government_services.citizens\nGROUP 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 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.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.employees ( employee_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, job_title character varying(150) NOT NULL, department character varying(100), work_email character varying(128) NOT NULL UNIQUE, work_phone character varying(32), hire_date date NOT NULL, termination_date date, access_level character varying(50), manager_employee_id character varying(64), PRIMARY KEY (employee_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) )\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) )\nCREATE TABLE government_services.notifications ( notification_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, application_id character varying(64), message_subject character varying(255), message_body text NOT NULL, channel character varying(30) NOT NULL, sent_at timestamp NOT NULL, status character varying(30) NOT NULL, related_entity_type character varying(50), related_entity_id character varying(64), PRIMARY KEY (notification_id) )\n"}
{"conversations": [{"role": "user", "content": "Show all log IDs and service dates for maintenance logs where the next service due date is not recorded."}, {"role": "assistant", "content": "SELECT log_id ,  service_date FROM transportation.maintenance_logs WHERE next_service_due_date IS NULL"}, {"role": "user", "content": "Also, include the vehicle ID and order the results by service date ascending."}, {"role": "assistant", "content": "SELECT log_id ,  service_date ,  vehicle_id FROM transportation.maintenance_logs WHERE next_service_due_date IS NULL ORDER BY service_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 transportation.maintenance_logs ( log_id character varying(64) NOT NULL, vehicle_id character varying(64) NOT NULL, service_date date NOT NULL, odometer_reading integer, service_type character varying(128) NOT NULL, description text NOT NULL, cost numeric(10, 2), mechanic_name character varying(128), next_service_due_date date, PRIMARY KEY (log_id) )\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 all guests with their loyalty_member_id and communication consent status."}, {"role": "assistant", "content": "SELECT guest_id,\n       first_name,\n       last_name,\n       loyalty_member_id,\n       communication_consent\nFROM hospitality_technology.guests;"}, {"role": "user", "content": "Actually, only include guests who have communication_consent = true and a non-null loyalty_member_id."}, {"role": "assistant", "content": "SELECT guest_id,\n       first_name,\n       last_name,\n       loyalty_member_id,\n       communication_consent\nFROM hospitality_technology.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": "Show me all users whose email address contains the word 'test', along with their user IDs and the date they registered."}, {"role": "assistant", "content": "SELECT user_id, username, email, created_at FROM trading_platform.users WHERE email ILIKE '%test%';"}, {"role": "user", "content": "Actually, only include users who registered after January 1, 2024, and sort them by newest registration date first."}, {"role": "assistant", "content": "SELECT user_id, username, email, created_at FROM trading_platform.users WHERE email ILIKE '%test%' AND created_at > '2024-01-01' ORDER BY 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 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)\n"}
{"conversations": [{"role": "user", "content": "For each doctor, show their full name along with all plan names of insurance plans that have a 'contact_phone' beginning with '+44'."}, {"role": "assistant", "content": "SELECT d.first_name, d.last_name, ip.plan_name\nFROM healthcare.doctors d\nCROSS JOIN healthcare.insurance_plans ip\nWHERE ip.contact_phone LIKE '+44%';"}], "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.insurance_plans ( plan_id text, plan_name text, insurance_provider text, plan_type text, contact_phone text, website text )\n"}
{"conversations": [{"role": "user", "content": "Can you show, for each employee, the full name and job title of their direct manager, as well as the employee's department and branch_id?"}, {"role": "assistant", "content": "SELECT e.employee_id, e.first_name AS employee_first_name, e.last_name AS employee_last_name, e.department AS employee_department, e.branch_id AS employee_branch_id, m.first_name AS manager_first_name, m.last_name AS manager_last_name, m.job_title AS manager_job_title\nFROM financial_services.employees e\nLEFT JOIN financial_services.employees m ON e.manager_id = m.employee_id;"}, {"role": "user", "content": "Actually, show only employees who have a manager assigned, and include only those where the manager works at a different branch than the employee."}, {"role": "assistant", "content": "SELECT e.employee_id, e.first_name AS employee_first_name, e.last_name AS employee_last_name, e.department AS employee_department, e.branch_id AS employee_branch_id, m.first_name AS manager_first_name, m.last_name AS manager_last_name, m.job_title AS manager_job_title, m.branch_id AS manager_branch_id\nFROM financial_services.employees e\nINNER JOIN financial_services.employees m ON e.manager_id = m.employee_id\nWHERE e.branch_id IS DISTINCT FROM m.branch_id;"}, {"role": "user", "content": "Now, only include employees who were hired after 2021-01-01."}, {"role": "assistant", "content": "SELECT e.employee_id, e.first_name AS employee_first_name, e.last_name AS employee_last_name, e.department AS employee_department, e.branch_id AS employee_branch_id, m.first_name AS manager_first_name, m.last_name AS manager_last_name, m.job_title AS manager_job_title, m.branch_id AS manager_branch_id\nFROM financial_services.employees e\nINNER JOIN financial_services.employees m ON e.manager_id = m.employee_id\nWHERE e.branch_id IS DISTINCT FROM m.branch_id\n  AND e.hire_date > '2021-01-01';"}], "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 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.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)\nCREATE TABLE financial_services.loans ( loan_id character varying(64) NOT NULL, account_id character varying(64) NOT NULL UNIQUE, loan_type character varying(50) NOT NULL, principal_amount numeric(19, 4) NOT NULL, current_principal_balance numeric(19, 4) NOT NULL, interest_rate numeric(6, 4) NOT NULL, term_months integer NOT NULL, origination_date date NOT NULL, maturity_date date NOT NULL, monthly_payment numeric(12, 4), collateral_description text, status character varying(32) NOT NULL, PRIMARY KEY (loan_id), FOREIGN KEY (account_id) REFERENCES financial_services.accounts(account_id) )\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": "Find the names of service locations where services categorized as 'Licensing' have had appointments scheduled."}, {"role": "assistant", "content": "SELECT DISTINCT T1.location_name FROM service_locations AS T1 JOIN appointments AS T2 ON T1.location_id = T2.location_id JOIN services AS T3 ON T2.service_id = T3.service_id WHERE T3.category = 'Licensing';"}], "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.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.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.appointments (\n    appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment\n    citizen_id character varying(64) NOT NULL, -- FK to citizens table\n    employee_id character varying(64), -- FK to employees table (optional, if assigned)\n    location_id character varying(64), -- FK to service_locations table (if physical)\n    service_id character varying(64), -- FK to services table (optional, if related to specific service)\n    scheduled_start_time timestamp NOT NULL,\n    scheduled_end_time timestamp,\n    purpose text NOT NULL, -- reason for the appointment\n    status character varying(30) NOT NULL, -- e.g., Scheduled, Completed, Cancelled, No-Show\n    booking_method character varying(50), -- e.g., Online, Phone, In-Person\n    created_at timestamp NOT NULL, -- when the appointment was booked\n    notes text,\n    PRIMARY KEY (appointment_id)\n)\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": "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": "Which projects had fundraising rounds in the first quarter of 2022, and what were their investment values and round names?"}, {"role": "assistant", "content": "SELECT project_name, rounds_name, investment_value, investment_date FROM project_fundraising_record WHERE investment_date >= '2022-01-01' AND investment_date < '2022-04-01';"}, {"role": "user", "content": "Add each project's valuation and introduction to the output as well."}, {"role": "assistant", "content": "SELECT project_name, rounds_name, investment_value, investment_date, valuation, introduction FROM project_fundraising_record WHERE investment_date >= '2022-01-01' AND investment_date < '2022-04-01';"}, {"role": "user", "content": "Now, show only those projects where the valuation was at least $200 million."}, {"role": "assistant", "content": "SELECT project_name, rounds_name, investment_value, investment_date, valuation, introduction FROM project_fundraising_record WHERE investment_date >= '2022-01-01' AND investment_date < '2022-04-01' AND valuation >= 200000000;"}, {"role": "user", "content": "Order the results by investment_value descending and limit to the top 5 records."}, {"role": "assistant", "content": "SELECT project_name, rounds_name, investment_value, investment_date, valuation, introduction FROM project_fundraising_record WHERE investment_date >= '2022-01-01' AND investment_date < '2022-04-01' AND valuation >= 200000000 ORDER BY investment_value 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\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": "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": "Which staff members are managing properties, and what are the names and email addresses of those properties?"}, {"role": "assistant", "content": "SELECT s.staff_id, s.first_name, s.last_name, p.property_name, p.email_address FROM hospitality_technology.staff s INNER JOIN hospitality_technology.properties p ON s.staff_id = p.manager_staff_id;"}, {"role": "user", "content": "Only include properties located in the United States and list the staff position as well."}, {"role": "assistant", "content": "SELECT s.staff_id, s.first_name, s.last_name, s.position, p.property_name, p.email_address FROM hospitality_technology.staff s INNER JOIN hospitality_technology.properties p ON s.staff_id = p.manager_staff_id WHERE p.country_code = 'US';"}], "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 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 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 PRIMARY KEY, 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 int, manager_id text, created_at timestamp )\nCREATE TABLE hospitality_technology.payments ( payment_id text PRIMARY KEY, 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 )\n"}
{"conversations": [{"role": "user", "content": "Find the total balance per coin_type for active SUI coins, including coin_type, symbol, name, and SUM(balance) as total_balance. Sort by total_balance descending."}, {"role": "assistant", "content": "SELECT\n  c.coin_type,\n  m.symbol,\n  m.name,\n  SUM(CAST(c.balance AS BIGINT)) AS total_balance\nFROM sui_coins c\nJOIN sui_coins_metadata m\n  ON c.coin_type = m.coin_type\nWHERE c.status = 'active'\n  AND m.status = 'exists'\nGROUP BY c.coin_type, m.symbol, m.name\nORDER BY total_balance DESC;"}, {"role": "user", "content": "Actually, limit to coins where total_balance is above 1000000."}, {"role": "assistant", "content": "SELECT\n  c.coin_type,\n  m.symbol,\n  m.name,\n  SUM(CAST(c.balance AS BIGINT)) AS total_balance\nFROM sui_coins c\nJOIN sui_coins_metadata m\n  ON c.coin_type = m.coin_type\nWHERE c.status = 'active'\n  AND m.status = 'exists'\nGROUP BY c.coin_type, m.symbol, m.name\nHAVING SUM(CAST(c.balance AS BIGINT)) > 1000000\nORDER BY total_balance DESC;"}, {"role": "user", "content": "Also filter metadata where description contains 'Utility'."}, {"role": "assistant", "content": "SELECT\n  c.coin_type,\n  m.symbol,\n  m.name,\n  SUM(CAST(c.balance AS BIGINT)) AS total_balance\nFROM sui_coins c\nJOIN sui_coins_metadata m\n  ON c.coin_type = m.coin_type\nWHERE c.status = 'active'\n  AND m.status = 'exists'\n  AND m.description ILIKE '%Utility%'\nGROUP BY c.coin_type, m.symbol, m.name\nHAVING SUM(CAST(c.balance AS BIGINT)) > 1000000\nORDER BY total_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 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 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 ( 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_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 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 token_balances_bitcoin ( block_number.bigint, block_timestamp.timestamp, tick.text, wallet_address.text, total_supply.text, amount.text )\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.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": "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": "List the full names and email addresses of staff members who have delivered at least one service order in the past 30 days, along with the count of orders they delivered. Sort by count descending."}, {"role": "assistant", "content": "SELECT st.staff_id,\n       st.first_name || ' ' || st.last_name AS full_name,\n       st.work_email,\n       COUNT(so.order_id) AS delivered_count\nFROM hospitality_technology.staff st\nJOIN hospitality_technology.service_orders so\n  ON st.staff_id = so.staff_id_delivered\nWHERE so.status = 'Delivered'\n  AND so.delivery_timestamp >= CURRENT_DATE - INTERVAL '30 days'\nGROUP BY st.staff_id, st.first_name, st.last_name, st.work_email\nORDER BY delivered_count DESC;"}, {"role": "user", "content": "Actually, only include staff who delivered more than 5 orders in that period."}, {"role": "assistant", "content": "SELECT st.staff_id,\n       st.first_name || ' ' || st.last_name AS full_name,\n       st.work_email,\n       COUNT(so.order_id) AS delivered_count\nFROM hospitality_technology.staff st\nJOIN hospitality_technology.service_orders so\n  ON st.staff_id = so.staff_id_delivered\nWHERE so.status = 'Delivered'\n  AND so.delivery_timestamp >= CURRENT_DATE - INTERVAL '30 days'\nGROUP BY st.staff_id, st.first_name, st.last_name, st.work_email\nHAVING COUNT(so.order_id) > 5\nORDER BY delivered_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.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 )\n"}
{"conversations": [{"role": "user", "content": "Show me all in-progress trips with their current locations (origin_location_id) and destinations, along with the scheduled vs actual departure time difference in minutes."}, {"role": "assistant", "content": "SELECT trip_id, origin_location_id, destination_location_id, EXTRACT(EPOCH FROM (actual_departure - scheduled_departure))/60 AS departure_delay_minutes FROM transportation.trips WHERE status = 'In Progress';"}, {"role": "user", "content": "Can you also include the vehicle_id and driver_id, and order by the departure delay in descending order?"}, {"role": "assistant", "content": "SELECT trip_id, vehicle_id, driver_id, origin_location_id, destination_location_id, EXTRACT(EPOCH FROM (actual_departure - scheduled_departure))/60 AS departure_delay_minutes FROM transportation.trips WHERE status = 'In Progress' ORDER BY departure_delay_minutes DESC;"}, {"role": "user", "content": "Now filter to only show trips that have been delayed by more than 30 minutes."}, {"role": "assistant", "content": "SELECT trip_id, vehicle_id, driver_id, origin_location_id, destination_location_id, EXTRACT(EPOCH FROM (actual_departure - scheduled_departure))/60 AS departure_delay_minutes FROM transportation.trips WHERE status = 'In Progress' AND EXTRACT(EPOCH FROM (actual_departure - scheduled_departure))/60 > 30 ORDER BY departure_delay_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.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)\n"}
{"conversations": [{"role": "user", "content": "List all NFT collections where the floor price is greater than 0.5 ETH, including their names and contract addresses."}, {"role": "assistant", "content": "SELECT name, contract_address FROM nft_collections WHERE CAST(floor_price AS decimal) > 0.5 AND floor_price_symbol = 'ETH';"}, {"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, banner_image_url FROM nft_collections WHERE CAST(floor_price AS decimal) > 0.5 AND floor_price_symbol = 'ETH' AND erc_type = 'ERC721';"}, {"role": "user", "content": "Now sort these results by floor price in descending order and limit to the top 10."}, {"role": "assistant", "content": "SELECT name, contract_address, banner_image_url, floor_price FROM nft_collections WHERE CAST(floor_price AS decimal) > 0.5 AND floor_price_symbol = 'ETH' AND erc_type = 'ERC721' ORDER BY CAST(floor_price AS decimal) 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 (\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 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 ( 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.text, coin_type.text, status.text, decimals.bigint, description.text, icon_url.text, symbol.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, 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.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 (\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 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 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 )\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, 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": "Show the property name, star rating, and number of rooms for each property."}, {"role": "assistant", "content": "SELECT p.property_name, p.star_rating, COUNT(r.room_id) AS room_count\nFROM hospitality_technology.properties p\nLEFT JOIN hospitality_technology.rooms r ON p.property_id = r.property_id\nGROUP BY p.property_id, p.property_name, p.star_rating;"}, {"role": "user", "content": "Only include properties that have more than 30 rooms."}, {"role": "assistant", "content": "SELECT p.property_name, p.star_rating, COUNT(r.room_id) AS room_count\nFROM hospitality_technology.properties p\nLEFT JOIN hospitality_technology.rooms r ON p.property_id = r.property_id\nGROUP BY p.property_id, p.property_name, p.star_rating\nHAVING COUNT(r.room_id) > 30;"}, {"role": "user", "content": "Add a column showing the total number of unique room types at each property."}, {"role": "assistant", "content": "SELECT p.property_name, p.star_rating, COUNT(r.room_id) AS room_count, COUNT(DISTINCT rt.room_type_id) AS unique_room_type_count\nFROM hospitality_technology.properties p\nLEFT JOIN hospitality_technology.rooms r ON p.property_id = r.property_id\nLEFT JOIN hospitality_technology.room_types rt ON p.property_id = rt.property_id\nGROUP BY p.property_id, p.property_name, p.star_rating\nHAVING COUNT(r.room_id) > 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 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 (\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 (\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.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.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)\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 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": "For each user, show how many users registered after them. Return the user_id, username, and the count of later registrants."}, {"role": "assistant", "content": "SELECT u1.user_id, u1.username, COUNT(u2.user_id) AS later_user_count FROM web3.users u1 LEFT JOIN web3.users u2 ON u2.created_at > u1.created_at GROUP BY u1.user_id, u1.username ORDER BY u1.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 web3.users ( user_id.text, username.text, email.text, password_hash.text, created_at.timestamp )\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": "Find services that have associated documents with a 'Pending' verification status. Show the service name and the document type name."}, {"role": "assistant", "content": "SELECT DISTINCT s.service_name, dt.document_type_name FROM government_services.services AS s JOIN government_services.applications AS a ON s.service_id = a.service_id JOIN government_services.application_documents AS ad ON a.application_id = ad.application_id JOIN government_services.document_types AS dt ON ad.document_type_id = dt.document_type_id WHERE ad.verification_status = 'Pending';"}], "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": "Count the total number of premium payments made in the year 2024."}, {"role": "assistant", "content": "SELECT COUNT(*) FROM premium_payments WHERE EXTRACT(YEAR FROM payment_date) = 2024"}], "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 PRIMARY KEY, 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 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.agents ( agent_id text PRIMARY KEY, 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.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 game_id, calculate the average points of achievements that have been unlocked at least once."}, {"role": "assistant", "content": "SELECT a.game_id, AVG(a.points) AS average_unlocked_points FROM gaming_technology.achievements a JOIN gaming_technology.player_achievements pa ON a.achievement_id = pa.achievement_id GROUP BY a.game_id;"}, {"role": "user", "content": "Only include games where the average unlocked achievement points is greater than 50."}, {"role": "assistant", "content": "SELECT a.game_id, AVG(a.points) AS average_unlocked_points FROM gaming_technology.achievements a JOIN gaming_technology.player_achievements pa ON a.achievement_id = pa.achievement_id GROUP BY a.game_id HAVING AVG(a.points) > 50;"}, {"role": "user", "content": "Also include the total number of unique players who unlocked achievements in each of these games."}, {"role": "assistant", "content": "SELECT a.game_id, AVG(a.points) AS average_unlocked_points, COUNT(DISTINCT pa.player_id) AS unique_players_unlocked FROM gaming_technology.achievements a JOIN gaming_technology.player_achievements pa ON a.achievement_id = pa.achievement_id GROUP BY a.game_id HAVING AVG(a.points) > 50;"}, {"role": "user", "content": "Order the results by the total number of unique players descending."}, {"role": "assistant", "content": "SELECT a.game_id, AVG(a.points) AS average_unlocked_points, COUNT(DISTINCT pa.player_id) AS unique_players_unlocked FROM gaming_technology.achievements a JOIN gaming_technology.player_achievements pa ON a.achievement_id = pa.achievement_id GROUP BY a.game_id HAVING AVG(a.points) > 50 ORDER BY unique_players_unlocked 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.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.player_inventory ( inventory_id.uuid, player_id.uuid, item_id.uuid, quantity.integer, acquired_at.timestamptz, instance_data.jsonb )\n"}
{"conversations": [{"role": "user", "content": "List each wallet that has received tokens of more than one distinct token type. Show wallet_id, address, the number of distinct tokens received as distinct_token_count, and the total received value, ordered by total_received_value descending."}, {"role": "assistant", "content": "SELECT w.wallet_id,\n       w.address,\n       COUNT(DISTINCT t.token_id) AS distinct_token_count,\n       SUM(tt.value)            AS total_received_value\nFROM web3.wallets w\nJOIN web3.token_transfers tt\n  ON w.address = tt.to_address\nJOIN web3.tokens t\n  ON tt.token_id = t.token_id\nGROUP BY w.wallet_id, w.address\nHAVING COUNT(DISTINCT t.token_id) > 1\nORDER BY total_received_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.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.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 tokens with a price below $1 and a 24-hour trading volume over $10 million."}, {"role": "assistant", "content": "SELECT token_name, token_symbol, price, total_volume FROM token_basic_info WHERE price < 1 AND CAST(total_volume AS double precision) > 10000000;"}], "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 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": "Show the IDs and registration dates of all verified citizens who could be eligible for at least one active service. Display the citizen ID and registration date."}, {"role": "assistant", "content": "SELECT DISTINCT c.citizen_id, c.registration_date\nFROM government_services.citizens c\nJOIN government_services.services s ON s.is_active = true\nWHERE c.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 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": "What are the personal contact details of the staff member associated with staff_id 'STAFF789' who worked on a specific maintenance record?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide personal contact details of staff members as this information is not stored in the maintenance_records table and is outside the scope of the available data."}], "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.maintenance_records ( record_id text, asset_id text, asset_type text, maintenance_type text, staff_id text, start_datetime timestamp, end_datetime timestamp, description text, cost numeric, status text )\n"}
{"conversations": [{"role": "user", "content": "Show me all chronic diagnoses along with their descriptions and the patient IDs, sorted by diagnosis date in descending order."}, {"role": "assistant", "content": "SELECT patient_id, description, diagnosis_date FROM healthcare.diagnoses WHERE is_chronic = true ORDER BY diagnosis_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.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 )\n"}
{"conversations": [{"role": "user", "content": "Show me all token names and their contract addresses along with the wallet addresses of users who created wallets in the last 30 days, sorted by wallet creation date."}, {"role": "assistant", "content": "SELECT t.token_name, t.contract_address, w.address AS wallet_address FROM web3.tokens t JOIN web3.wallets w ON 1=1 WHERE w.created_at >= CURRENT_DATE - INTERVAL '30 days' ORDER BY w.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.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": "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": "I need a combined report displaying each customer’s full name, their account number, account balance, and the ticker symbol and security name of every security traded in the same currency as their account."}, {"role": "assistant", "content": "SELECT c.first_name || ' ' || c.last_name AS full_name, a.account_number, a.balance, s.ticker_symbol, s.security_name\nFROM financial_services.customers c\nJOIN financial_services.accounts a ON c.customer_id = a.customer_id\nJOIN financial_services.securities s ON a.currency = s.currency\nORDER BY c.last_name, c.first_name, a.account_number, s.ticker_symbol;"}, {"role": "user", "content": "Add the customer's city and state to the output. Also, show only accounts with a balance greater than 5000."}, {"role": "assistant", "content": "SELECT c.first_name || ' ' || c.last_name AS full_name, c.city, c.state, a.account_number, a.balance, s.ticker_symbol, s.security_name\nFROM financial_services.customers c\nJOIN financial_services.accounts a ON c.customer_id = a.customer_id\nJOIN financial_services.securities s ON a.currency = s.currency\nWHERE a.balance > 5000\nORDER BY c.last_name, c.first_name, a.account_number, s.ticker_symbol;"}, {"role": "user", "content": "I only want customers who have at least one account in EUR currency. Could you update the query accordingly?"}, {"role": "assistant", "content": "SELECT c.first_name || ' ' || c.last_name AS full_name, c.city, c.state, a.account_number, a.balance, s.ticker_symbol, s.security_name\nFROM financial_services.customers c\nJOIN financial_services.accounts a ON c.customer_id = a.customer_id\nJOIN financial_services.securities s ON a.currency = s.currency\nWHERE a.balance > 5000\n  AND c.customer_id IN (SELECT customer_id FROM financial_services.accounts WHERE currency = 'EUR')\nORDER BY c.last_name, c.first_name, a.account_number, s.ticker_symbol;"}, {"role": "user", "content": "Now restrict it to only include securities traded on the 'Euronext' exchange."}, {"role": "assistant", "content": "SELECT c.first_name || ' ' || c.last_name AS full_name, c.city, c.state, a.account_number, a.balance, s.ticker_symbol, s.security_name\nFROM financial_services.customers c\nJOIN financial_services.accounts a ON c.customer_id = a.customer_id\nJOIN financial_services.securities s ON a.currency = s.currency\nWHERE a.balance > 5000\n  AND c.customer_id IN (SELECT customer_id FROM financial_services.accounts WHERE currency = 'EUR')\n  AND s.exchange = 'Euronext'\nORDER BY c.last_name, c.first_name, a.account_number, s.ticker_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 financial_services.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 text NOT NULL, 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, email character varying(128) UNIQUE, phone_number character varying(32), created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, status character varying(32) NOT NULL, risk_profile character varying(50), PRIMARY KEY (customer_id) )\nCREATE TABLE financial_services.accounts ( account_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, account_number character varying(128) NOT NULL UNIQUE, account_type character varying(50) NOT NULL, balance numeric(19, 4) NOT NULL DEFAULT 0.00, currency character varying(3) NOT NULL, opened_date date NOT NULL, status character varying(32) NOT NULL, interest_rate numeric(5, 4), last_updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (account_id), FOREIGN KEY (customer_id) REFERENCES financial_services.customers(customer_id) )\nCREATE TABLE financial_services.securities ( security_id character varying(64) NOT NULL, ticker_symbol character varying(20) NOT NULL UNIQUE, isin_code character varying(12) UNIQUE, cusip_code character varying(9) UNIQUE, security_name text NOT NULL, security_type character varying(50) NOT NULL, exchange character varying(50), currency character varying(3) NOT NULL, issuer_name character varying(255), sector character varying(100), last_updated timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (security_id) )\n"}
{"conversations": [{"role": "user", "content": "Retrieve each passenger's full name, their email, booking status, and the name of the origin location for all bookings."}, {"role": "assistant", "content": "SELECT p.first_name || ' ' || p.last_name AS full_name, p.email, b.status, l.name AS origin_location_name\nFROM transportation.bookings b\nJOIN transportation.passengers p ON b.passenger_id = p.passenger_id\nJOIN transportation.trips t ON b.trip_id = t.trip_id\nJOIN transportation.locations l ON t.origin_location_id = l.location_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.trips ( trip_id character varying(64) NOT NULL, route_id character varying(64), vehicle_id character varying(64) NOT NULL, driver_id character varying(64) NOT NULL, scheduled_departure timestamp with time zone NOT NULL, actual_departure timestamp with time zone, scheduled_arrival timestamp with time zone NOT NULL, actual_arrival timestamp with time zone, origin_location_id character varying(64) NOT NULL, destination_location_id character varying(64) NOT NULL, status character varying(32) NOT NULL, passenger_count integer, cargo_manifest_id character varying(64), PRIMARY KEY (trip_id) )\nCREATE TABLE transportation.locations ( location_id character varying(64) NOT NULL, name character varying(255) NOT NULL, type character varying(64) NOT NULL, address_line1 character varying(255), city character varying(128), state_province character varying(128), postal_code character varying(32), country character varying(64) NOT NULL, latitude numeric(9, 6), longitude numeric(9, 6), timezone character varying(64), PRIMARY KEY (location_id) )\nCREATE TABLE transportation.maintenance_logs ( log_id character varying(64) NOT NULL, vehicle_id character varying(64) NOT NULL, service_date date NOT NULL, odometer_reading integer, service_type character varying(128) NOT NULL, description text NOT NULL, cost numeric(10, 2), mechanic_name character varying(128), next_service_due_date date, PRIMARY KEY (log_id) )\nCREATE TABLE transportation.passengers ( passenger_id character varying(64) NOT NULL, first_name character varying(128) NOT NULL, last_name character varying(128) NOT NULL, email character varying(128) UNIQUE, phone_number character varying(32) UNIQUE, date_of_birth date, loyalty_program_id character varying(64), created_at timestamp with time zone NOT NULL, PRIMARY KEY (passenger_id) )\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": "What is the total estimated_loss and average settlement_amount for all claims with status 'Approved'?"}, {"role": "assistant", "content": "SELECT SUM(estimated_loss) AS total_estimated_loss,\n       AVG(settlement_amount) AS average_settlement\nFROM insurance.claims\nWHERE status = 'Approved';"}], "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 )\n"}
{"conversations": [{"role": "user", "content": "Can you help me fetch the inventory details for components associated with a specific aircraft build, including the batch number, quantity, and warehouse location?"}, {"role": "assistant", "content": "MATCH (ab:AircraftBuild {build_id: 'specific_build_id'})-[:IS_MODEL]->(am:AircraftModel),\n(ib:InventoryBatch)-[:IS_INSTANCE_OF]->(c:Component)\nRETURN ib.inventory_record_id, ib.batch_number, ib.quantity, ib.location_warehouse"}, {"role": "user", "content": "Can you modify this to show only inventory batches received after a specific date, say June 1, 2023?"}, {"role": "assistant", "content": "MATCH (ab:AircraftBuild {build_id: 'specific_build_id'})-[:IS_MODEL]->(am:AircraftModel),\n(ib:InventoryBatch)-[:IS_INSTANCE_OF]->(c:Component)\nWHERE ib.received_date > datetime('2023-06-01')\nRETURN ib.inventory_record_id, ib.batch_number, ib.quantity, ib.location_warehouse"}, {"role": "user", "content": "What if I also want to exclude batches with quantities less than 10?"}, {"role": "assistant", "content": "MATCH (ab:AircraftBuild {build_id: 'specific_build_id'})-[:IS_MODEL]->(am:AircraftModel),\n(ib:InventoryBatch)-[:IS_INSTANCE_OF]->(c:Component)\nWHERE ib.received_date > datetime('2023-06-01') AND ib.quantity >= 10\nRETURN ib.inventory_record_id, ib.batch_number, ib.quantity, ib.location_warehouse"}], "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\nNode Label ':AircraftModel'. Properties: { model_id: String (Constraint: UNIQUE), model_name: String, manufacturer: String, passenger_capacity: Integer, max_range_km: Integer, engine_type: String, wingspan_m: Float, status: String, first_flight_date: Date }. Index on model_id.\nNode Label ':Material'. Properties: { material_id: String (Constraint: UNIQUE), material_name: String, specification: String, description: String, density_kg_m3: Float, tensile_strength_mpa: Integer }. Index on material_id.\nNode Label ':AssemblyLine'. Properties: { line_id: String (Constraint: UNIQUE), line_name: String, location_building: String, location_area: String, capacity_units_per_month: Integer, status: String }. Relationship: (:AssemblyLine)-[:BUILDS_MODEL]->(:AircraftModel {model_id}). Index on line_id.\nNode Label ':AssemblyStep'. Properties: { step_id: String (Constraint: UNIQUE), step_number: Integer, step_name: String, description: String, standard_duration_hours: Float, required_skill_level: String, workstation: String }. Relationship: (:AssemblyLine {line_id})-[:HAS_STEP {sequence: <step_number>}]->(:AssemblyStep). Index on step_id.\nNode Label ':AircraftBuild'. Properties: { build_id: String (Constraint: UNIQUE), serial_number: String (Constraint: UNIQUE), build_start_date: Datetime, estimated_completion_date: Date, actual_completion_date: Datetime, current_status: String, customer_order_id: String }. Relationships: (:AircraftBuild)-[:IS_MODEL]->(:AircraftModel {model_id}), (:AircraftBuild)-[:ASSEMBLED_ON]->(:AssemblyLine {line_id}). Index on build_id, serial_number, current_status.\nNode Label ':Employee'. Properties: { employee_id: String (Constraint: UNIQUE), first_name: String, last_name: String, job_title: String, skill_certifications: String[], hire_date: Date, employment_status: String }. Relationships: (:Employee)-[:ASSIGNED_TO]->(:AssemblyLine {line_id}), (:Employee)-[:REPORTS_TO]->(:Employee {employee_id as supervisor_id}). Index on employee_id.\nNode Label ':InventoryBatch'. Properties: { inventory_record_id: String (Constraint: UNIQUE), quantity: Integer, location_warehouse: String, location_bin: String, received_date: Datetime, expiry_date: Date, batch_number: String, last_updated: Datetime }. Relationship: (:InventoryBatch)-[:IS_INSTANCE_OF]->(:Component {component_id}). Index on inventory_record_id, component_id.\n"}
{"conversations": [{"role": "user", "content": "What is the total number of drivers hired each year? Provide the hire_year and driver_count."}, {"role": "assistant", "content": "SELECT EXTRACT(YEAR FROM hire_date) AS hire_year,\n       COUNT(*)                  AS driver_count\nFROM transportation.drivers\nGROUP BY EXTRACT(YEAR FROM hire_date);"}, {"role": "user", "content": "Now only include years where driver_count > 3 and order the results by driver_count DESC."}, {"role": "assistant", "content": "SELECT hire_year, driver_count\nFROM (\n  SELECT EXTRACT(YEAR FROM hire_date) AS hire_year,\n         COUNT(*)                  AS driver_count\n  FROM transportation.drivers\n  GROUP BY EXTRACT(YEAR FROM hire_date)\n) sub\nWHERE driver_count > 3\nORDER BY driver_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 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 )\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": "Can you provide the total number of cars associated with a specific train with train_id 'train_789'?"}, {"role": "assistant", "content": "SCARD train:train_789:cars"}], "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// Use Hashes for platform details. Key format: platform:<platform_id>\n// HSET platform:plat_123 platform_id \"plat_123\" station_id \"station_xyz\" platform_number \"1A\" track_number \"T1\" status \"Operational\" length_meters 250.50 accessible 1\n\n// To link platforms to stations (optional):\n// SADD station:station_xyz:platforms platform:plat_123 platform:plat_456\n// Use Hashes for train details. Key format: train:<train_id>\n// HSET train:train_789 train_id \"train_789\" train_number \"Acela 2151\" model \"Siemens Velaro\" ... status \"Active\" ...\n\n// To find train by train_number (optional index):\n// SET train_number:\"Acela 2151\" train:train_789\n// Use Hashes for car details. Key format: car:<car_id>\n// HSET car:car_abc car_id \"car_abc\" train_id \"train_789\" car_number \"C3\" car_type \"Passenger\" class \"Business\" capacity 60 features \"WiFi,Power Outlet\"\n\n// To link cars to trains (optional):\n// SADD train:train_789:cars car:car_abc car:car_def\n// Use Hashes for details. Key format: route_station:<route_station_id>\n// HSET route_station:rs_ne_1 route_station_id \"rs_ne_1\" route_id \"route_ne_corr\" station_id \"station_bos\" sequence_order 1 ...\n\n// To find stops for a route, use a Sorted Set (score by sequence_order):\n// ZADD route:route_ne_corr:stops 1 route_station:rs_ne_1\n// ZADD route:route_ne_corr:stops 2 route_station:rs_ne_2\n// Use Hashes for schedule details. Key format: schedule:<schedule_id>\n// HSET schedule:sched_1122 schedule_id \"sched_1122\" train_id \"train_789\" route_id \"route_ne_corr\" departure_datetime \"2024-05-10T08:00:00-04:00\" ... status \"Scheduled\"\n// Use Hashes for details. Key format: schedule_stop:<stop_id>\n// HSET schedule_stop:stop_sched1122_1 stop_id \"stop_sched1122_1\" schedule_id \"sched_1122\" station_id \"station_bos\" ...\n\n// To find stops for a schedule, use a Sorted Set (score by sequence_order):\n// ZADD schedule:sched_1122:stops 1 schedule_stop:stop_sched1122_1\n// ZADD schedule:sched_1122:stops 2 schedule_stop:stop_sched1122_2\n// Use Hashes for passenger details. Key format: passenger:<passenger_id>\n// HSET passenger:pass_pqr passenger_id \"pass_pqr\" first_name \"Alice\" last_name \"Smith\" email \"alice.smith@example.com\" ...\n\n// To find passenger by email (optional index):\n// SET passenger_email:\"alice.smith@example.com\" passenger:pass_pqr\n// Use Hashes for booking details. Key format: booking:<booking_id>\n// HSET booking:book_zyx booking_id \"book_zyx\" passenger_id \"pass_pqr\" schedule_id \"sched_1122\" ... status \"Confirmed\" ...\n\n// To link bookings to passengers/schedules (optional):\n// SADD passenger:pass_pqr:bookings booking:book_zyx\n// SADD schedule:sched_1122:bookings booking:book_zyx\n// Use Hashes for ticket details. Key format: ticket:<ticket_id>\n// HSET ticket:tkt_1a2b ticket_id \"tkt_1a2b\" booking_id \"book_zyx\" car_id \"car_abc\" seat_number \"12A\" ... is_checked_in 0 ...\n\n// To link tickets to bookings (optional):\n// SADD booking:book_zyx:tickets ticket:tkt_1a2b\n// Use Hashes for staff details. Key format: staff:<staff_id>\n// HSET staff:staff_mno staff_id \"staff_mno\" first_name \"Bob\" ... employee_number \"E12345\" ... is_active 1\n\n// To find staff by employee number (optional index):\n// SET staff_employee_number:\"E12345\" staff:staff_mno\n// Use Hashes for maintenance record details. Key format: maintenance_record:<record_id>\n// HSET maintenance_record:maint_rec_001 record_id \"maint_rec_001\" asset_id \"train_789\" asset_type \"Train\" ... status \"Completed\"\n\n// To link records to assets (optional):\n// SADD train:train_789:maintenance maintenance_record:maint_rec_001\n// SADD platform:plat_123:maintenance maintenance_record:maint_rec_002\n"}
{"conversations": [{"role": "user", "content": "Show each asset's symbol and the number of unique addresses that have UTXOs associated with it."}, {"role": "assistant", "content": "SELECT a.symbol, COUNT(DISTINCT u.address) AS unique_addresses\nFROM trading_platform.assets a\nJOIN trading_platform.utxos u ON a.asset_id = u.transaction_id\nGROUP BY a.asset_id, a.symbol;"}, {"role": "user", "content": "Now show only assets with more than 5 unique addresses."}, {"role": "assistant", "content": "SELECT a.symbol, COUNT(DISTINCT u.address) AS unique_addresses\nFROM trading_platform.assets a\nJOIN trading_platform.utxos u ON a.asset_id = u.transaction_id\nGROUP BY a.asset_id, a.symbol\nHAVING COUNT(DISTINCT u.address) > 5;"}, {"role": "user", "content": "Please also include the total amount for each asset in the result."}, {"role": "assistant", "content": "SELECT a.symbol, COUNT(DISTINCT u.address) AS unique_addresses, COALESCE(SUM(u.amount), 0) AS total_amount\nFROM trading_platform.assets a\nJOIN trading_platform.utxos u ON a.asset_id = u.transaction_id\nGROUP BY a.asset_id, a.symbol\nHAVING COUNT(DISTINCT u.address) > 5;"}, {"role": "user", "content": "Order the results by total_amount ascending and limit to the top 3."}, {"role": "assistant", "content": "SELECT a.symbol, COUNT(DISTINCT u.address) AS unique_addresses, COALESCE(SUM(u.amount), 0) AS total_amount\nFROM trading_platform.assets a\nJOIN trading_platform.utxos u ON a.asset_id = u.transaction_id\nGROUP BY a.asset_id, a.symbol\nHAVING COUNT(DISTINCT u.address) > 5\nORDER BY total_amount ASC\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 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.assets ( asset_id text, name text, symbol text, type text )\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.metadata ( metadata_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, key character varying(128) NOT NULL, value text NOT NULL, PRIMARY KEY (metadata_id) )\n"}
{"conversations": [{"role": "user", "content": "What is the reason behind the cost variation for maintenance of asset_id 'ASSET456' over the past year?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information on the reasons behind cost variations for maintenance. The data in the maintenance_records table includes only the cost amount and other basic details of each maintenance record, but it does not contain explanations or factors influencing cost changes."}], "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.maintenance_records ( record_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, asset_type character varying(32) NOT NULL, maintenance_type character varying(128) NOT NULL, staff_id character varying(64), start_datetime timestamp NOT NULL, end_datetime timestamp, description text NOT NULL, cost numeric(12, 2), status character varying(32) NOT NULL DEFAULT 'Completed', PRIMARY KEY (record_id), FOREIGN KEY (staff_id) REFERENCES train_station_management.staff(staff_id) )\n"}
{"conversations": [{"role": "user", "content": "List the full name (first name and last name) of all citizens who have uploaded documents whose expiry date is in the past."}, {"role": "assistant", "content": "SELECT DISTINCT T1.first_name, T1.last_name FROM government_services.citizens AS T1 INNER JOIN government_services.documents AS T2 ON T1.citizen_id = T2.citizen_id WHERE T2.expiry_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 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.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.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": "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": "Provide a count of how many peers were last seen on each distinct day recorded in the system."}, {"role": "assistant", "content": "SELECT DATE(last_seen), COUNT(*) FROM trading_platform.peers GROUP BY DATE(last_seen) ORDER BY DATE(last_seen);"}], "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, username text, email text, password_hash text, created_at timestamp )\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.kyc_audit ( kyc_audit_id text, user_id text, status text, reviewed_at timestamp )\nCREATE TABLE trading_platform.logs ( log_id text, user_id text, action text, details text, logged_at timestamp )\nCREATE TABLE trading_platform.notifications ( notification_id text, user_id text, message text, sent_at timestamp, read_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "For each vehicle, show the vehicle_id, license_plate, date of its most recent trip (actual_arrival), and the odometer_reading at its latest maintenance service."}, {"role": "assistant", "content": "SELECT\n    v.vehicle_id,\n    v.license_plate,\n    (\n        SELECT MAX(t.actual_arrival)\n        FROM transportation.trips t\n        WHERE t.vehicle_id = v.vehicle_id\n    ) AS last_trip_arrival,\n    ml.odometer_reading\nFROM transportation.vehicles v\nLEFT JOIN LATERAL (\n    SELECT odometer_reading\n    FROM transportation.maintenance_logs ml\n    WHERE ml.vehicle_id = v.vehicle_id\n    ORDER BY ml.service_date DESC\n    LIMIT 1\n) ml ON 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 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": "List all patients who have received a prescription with the route 'Topical', showing their ID, first name, and last name."}, {"role": "assistant", "content": "SELECT DISTINCT\n    p.patient_id,\n    p.first_name,\n    p.last_name\nFROM\n    healthcare.patients p\nJOIN\n    healthcare.prescriptions pr ON p.patient_id = pr.patient_id\nWHERE\n    pr.route = 'Topical';"}, {"role": "user", "content": "Only show patients who have received at least 2 such prescriptions."}, {"role": "assistant", "content": "SELECT\n    p.patient_id,\n    p.first_name,\n    p.last_name,\n    COUNT(pr.prescription_id) AS topical_prescription_count\nFROM\n    healthcare.patients p\nJOIN\n    healthcare.prescriptions pr ON p.patient_id = pr.patient_id\nWHERE\n    pr.route = 'Topical'\nGROUP BY\n    p.patient_id, p.first_name, p.last_name\nHAVING\n    COUNT(pr.prescription_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 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.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": "特定の職種の従業員情報を取得したいです。従業員ID、名前、職種、雇用日を表示してください。"}, {"role": "assistant", "content": "db.employees.find(\n    { job_title: '<specific_job_title>' },\n    { employee_id: 1, first_name: 1, last_name: 1, job_title: 1, hire_date: 1, _id: 0 }\n).sort({ hire_date: -1 })"}, {"role": "user", "content": "雇用日が2020年1月1日以降の従業員だけに絞り込むことはできますか？"}, {"role": "assistant", "content": "db.employees.find(\n    { \n        job_title: '<specific_job_title>',\n        hire_date: { $gte: ISODate('2020-01-01') }\n    },\n    { employee_id: 1, first_name: 1, last_name: 1, job_title: 1, hire_date: 1, _id: 0 }\n).sort({ hire_date: -1 })"}, {"role": "user", "content": "雇用ステータスが「Active」の従業員だけをさらに条件に加えられますか？"}, {"role": "assistant", "content": "db.employees.find(\n    { \n        job_title: '<specific_job_title>',\n        hire_date: { $gte: ISODate('2020-01-01') },\n        employment_status: 'Active'\n    },\n    { employee_id: 1, first_name: 1, last_name: 1, job_title: 1, hire_date: 1, _id: 0 }\n).sort({ hire_date: -1 })"}, {"role": "user", "content": "スキル認定情報も結果に含めてください。"}, {"role": "assistant", "content": "db.employees.find(\n    { \n        job_title: '<specific_job_title>',\n        hire_date: { $gte: ISODate('2020-01-01') },\n        employment_status: 'Active'\n    },\n    { employee_id: 1, first_name: 1, last_name: 1, job_title: 1, hire_date: 1, skill_certifications: 1, _id: 0 }\n).sort({ hire_date: -1 })"}], "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\nCollection 'assembly_steps'. Document structure: { _id: <ObjectId (or step_id)>, step_id: String, line_id: String (reference), step_number: NumberInt, step_name: String, description: String, standard_duration_hours: Decimal128, required_skill_level: String, workstation: String }. Required: step_id, line_id, step_number, step_name. Index on line_id, step_number.\nCollection 'employees'. Document structure: { _id: <ObjectId (or employee_id)>, employee_id: String, first_name: String, last_name: String, job_title: String, skill_certifications: [String], hire_date: ISODate, assigned_line_id: String (reference, optional), employment_status: String, supervisor_employee_id: String (reference, optional) }. Required: employee_id, first_name, last_name, job_title, hire_date, employment_status.\n"}
{"conversations": [{"role": "user", "content": "Can you help me get the total number of operational platforms across all stations?"}, {"role": "assistant", "content": "db.platforms.countDocuments({ status: 'Operational' });"}], "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// db.createCollection('platforms')\n// Optional: db.platforms.createIndex({ platform_id: 1 }, { unique: true })\n// Optional: db.platforms.createIndex({ station_id: 1 })\n{\n  _id: ObjectId(),\n  platform_id: \"plat_123\", // String (unique)\n  station_id: \"station_xyz\", // String (references stations.station_id)\n  platform_number: \"1A\", // String\n  track_number: \"T1\", // String\n  status: \"Operational\", // String ('Operational', 'Maintenance', 'Closed')\n  length_meters: 250.50, // Decimal128 or Double\n  accessible: true // Boolean\n}\n// db.createCollection('routes')\n// Optional: db.routes.createIndex({ route_id: 1 }, { unique: true })\n{\n  _id: ObjectId(),\n  route_id: \"route_ne_corr\", // String (unique)\n  route_name: \"Northeast Corridor\", // String\n  description: \"High-speed rail linking Boston and Washington D.C.\", // String\n  origin_station_id: \"station_bos\", // String (references stations.station_id)\n  destination_station_id: \"station_was\", // String (references stations.station_id)\n  is_active: true // Boolean\n}\n// db.createCollection('route_stations')\n// Optional: db.route_stations.createIndex({ route_station_id: 1 }, { unique: true })\n// Optional: db.route_stations.createIndex({ route_id: 1, sequence_order: 1 }, { unique: true })\n{\n  _id: ObjectId(),\n  route_station_id: \"rs_ne_1\", // String (unique)\n  route_id: \"route_ne_corr\", // String (references routes.route_id)\n  station_id: \"station_bos\", // String (references stations.station_id)\n  sequence_order: 1, // Int32\n  distance_from_previous_km: null, // Decimal128 or Double (null for first stop)\n  typical_stop_duration_minutes: null // Int32 (null for origin/destination or if no stop)\n}\n// --- OR --- Embed within the Route document:\n// {\n//   _id: ObjectId(), route_id: \"route_ne_corr\", ...,\n//   stations: [\n//     { station_id: \"station_bos\", sequence_order: 1, distance_from_previous_km: null, typical_stop_duration_minutes: null },\n//     { station_id: \"station_pvd\", sequence_order: 2, distance_from_previous_km: 70.5, typical_stop_duration_minutes: 5 },\n//     ...\n//   ]\n// }\n// db.createCollection('schedules')\n// Optional: db.schedules.createIndex({ schedule_id: 1 }, { unique: true })\n// Optional: db.schedules.createIndex({ route_id: 1, departure_datetime: 1 })\n{\n  _id: ObjectId(),\n  schedule_id: \"sched_1122\", // String (unique)\n  train_id: \"train_789\", // String (references trains.train_id)\n  route_id: \"route_ne_corr\", // String (references routes.route_id)\n  departure_datetime: ISODate(\"2024-05-10T08:00:00-04:00\"), // Date (with timezone)\n  arrival_datetime: ISODate(\"2024-05-10T15:30:00-04:00\"), // Date (with timezone)\n  status: \"Scheduled\", // String ('Scheduled', 'On Time', 'Delayed', 'Cancelled', 'Arrived')\n  notes: \"Track work expected near Philadelphia\" // String\n}\n// db.createCollection('schedule_stops')\n// Optional: db.schedule_stops.createIndex({ stop_id: 1 }, { unique: true })\n// Optional: db.schedule_stops.createIndex({ schedule_id: 1, sequence_order: 1 }, { unique: true })\n{\n  _id: ObjectId(),\n  stop_id: \"stop_sched1122_1\", // String (unique)\n  schedule_id: \"sched_1122\", // String (references schedules.schedule_id)\n  station_id: \"station_bos\", // String (references stations.station_id)\n  platform_id: \"plat_bos_3\", // String (references platforms.platform_id, nullable)\n  sequence_order: 1, // Int32\n  scheduled_arrival_time: null, // Date\n  scheduled_departure_time: ISODate(\"2024-05-10T08:00:00-04:00\"), // Date\n  actual_arrival_time: null, // Date\n  actual_departure_time: ISODate(\"2024-05-10T08:01:00-04:00\"), // Date\n  status: \"On Time\" // String\n}\n// --- OR --- Embed within the Schedule document using an array 'stops'\n// db.createCollection('passengers')\n// Optional: db.passengers.createIndex({ passenger_id: 1 }, { unique: true })\n// Optional: db.passengers.createIndex({ email: 1 }, { unique: true, sparse: true })\n// Optional: db.passengers.createIndex({ phone_number: 1 }, { unique: true, sparse: true })\n{\n  _id: ObjectId(),\n  passenger_id: \"pass_pqr\", // String (unique)\n  first_name: \"Alice\", // String\n  last_name: \"Smith\", // String\n  email: \"alice.smith@example.com\", // String (unique, sparse)\n  phone_number: \"+15551234567\", // String (unique, sparse)\n  date_of_birth: ISODate(\"1990-03-20\"), // Date\n  loyalty_program_id: \"LOYALTY123\", // String\n  created_at: ISODate(\"2023-02-01T11:00:00Z\") // Date\n}\n// db.createCollection('staff')\n// Optional: db.staff.createIndex({ staff_id: 1 }, { unique: true })\n// Optional: db.staff.createIndex({ employee_number: 1 }, { unique: true })\n// Optional: db.staff.createIndex({ contact_email: 1 }, { unique: true, sparse: true })\n{\n  _id: ObjectId(),\n  staff_id: \"staff_mno\", // String (unique)\n  first_name: \"Bob\", // String\n  last_name: \"Jones\", // String\n  role: \"Conductor\", // String\n  primary_station_id: null, // String (references stations.station_id, nullable)\n  employee_number: \"E12345\", // String (unique)\n  hire_date: ISODate(\"2018-06-01\"), // Date\n  contact_email: \"bob.jones@example-rail.com\", // String (unique, sparse)\n  contact_phone: \"+15559876543\", // String\n  is_active: true // Boolean\n}\n"}
{"conversations": [{"role": "user", "content": "Which states have the highest number of customers? Provide the top 5 states along with their customer counts, ordered by count descending."}, {"role": "assistant", "content": "SELECT\n  state,\n  COUNT(*) AS customer_count\nFROM insurance.customers\nGROUP BY state\nORDER BY customer_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 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 all properties in California with a star rating above 3.5, along with their room types and base rates."}, {"role": "assistant", "content": "SELECT p.property_name, p.city, p.star_rating, rt.type_name, rt.base_rate FROM hospitality_technology.properties p JOIN hospitality_technology.room_types rt ON p.property_id = rt.property_id WHERE p.state_province = 'California' AND p.star_rating > 3.5;"}, {"role": "user", "content": "Now, filter the results to only include room types with a max occupancy of at least 4 people."}, {"role": "assistant", "content": "SELECT p.property_name, p.city, p.star_rating, rt.type_name, rt.base_rate FROM hospitality_technology.properties p JOIN hospitality_technology.room_types rt ON p.property_id = rt.property_id WHERE p.state_province = 'California' AND p.star_rating > 3.5 AND rt.max_occupancy >= 4;"}], "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 )\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, 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 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 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 plan_id, plan_name, and plan_type for all insurance plans where the insurance_provider is 'Humana'."}, {"role": "assistant", "content": "SELECT\n  plan_id,\n  plan_name,\n  plan_type\nFROM healthcare.insurance_plans\nWHERE\n  insurance_provider = 'Humana';"}], "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.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 (\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 ( 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 PRIMARY KEY, medication_name text, generic_name text, manufacturer text, ndc_code text, description text )\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 (\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)\n"}
{"conversations": [{"role": "user", "content": "For each user, show their user ID and the count of unique wallet addresses they own."}, {"role": "assistant", "content": "SELECT user_id, COUNT(DISTINCT address) FROM wallets GROUP 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.wallets ( wallet_id.text, user_id.text, address.text, private_key.text, created_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "For each trip, show the trip_id, vehicle's license plate, total fuel quantity, and number of fueling events."}, {"role": "assistant", "content": "SELECT t.trip_id, v.license_plate, SUM(f.quantity) AS total_fuel, COUNT(f.fuel_log_id) AS fueling_events FROM transportation.trips t JOIN transportation.fuel_logs f ON t.trip_id = f.trip_id JOIN transportation.vehicles v ON t.vehicle_id = v.vehicle_id GROUP BY t.trip_id, v.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 (\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.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.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.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.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 (\n    booking_id character varying(64) NOT NULL,  -- unique identifier for the booking\n    passenger_id character varying(64) NOT NULL, -- identifier of the passenger making the booking\n    trip_id character varying(64) NOT NULL, -- identifier of the trip being booked\n    seat_number character varying(16), -- assigned seat number (if applicable)\n    booking_time timestamp with time zone NOT NULL, -- time when the booking was made\n    status character varying(32) NOT NULL, -- e.g., Confirmed, Cancelled, Pending Payment\n    fare numeric(10, 2) NOT NULL, -- price paid for the booking\n    payment_transaction_id character varying(128), -- reference to the payment transaction\n    special_requests text, -- any special requests from the passenger\n    PRIMARY KEY (booking_id)\n)\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": "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": "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": "Show me the number of approval-for-all events for each ERC1155 contract in the erc1155_approval_for_all table."}, {"role": "assistant", "content": "SELECT contract_address, COUNT(*) AS approval_count FROM erc1155_approval_for_all GROUP BY contract_address;"}, {"role": "user", "content": "Can you also include the number of unique wallets currently holding NFTs from each ERC1155 contract by joining with nft_holders?"}, {"role": "assistant", "content": "SELECT a.contract_address, COUNT(*) AS approval_count, COUNT(DISTINCT h.wallet_address) AS unique_holder_count FROM erc1155_approval_for_all a LEFT JOIN nft_holders h ON h.contract_address = a.contract_address AND h.contract_type = 'ERC1155' GROUP BY a.contract_address;"}, {"role": "user", "content": "Filter the results to only include contracts where the approval_count is greater than 20 and unique_holder_count is more than 5."}, {"role": "assistant", "content": "SELECT a.contract_address, COUNT(*) AS approval_count, COUNT(DISTINCT h.wallet_address) AS unique_holder_count FROM erc1155_approval_for_all a LEFT JOIN nft_holders h ON h.contract_address = a.contract_address AND h.contract_type = 'ERC1155' GROUP BY a.contract_address HAVING COUNT(*) > 20 AND COUNT(DISTINCT h.wallet_address) > 5;"}, {"role": "user", "content": "Order the results by approval_count descending and limit to the top 5 contracts."}, {"role": "assistant", "content": "SELECT a.contract_address, COUNT(*) AS approval_count, COUNT(DISTINCT h.wallet_address) AS unique_holder_count FROM erc1155_approval_for_all a LEFT JOIN nft_holders h ON h.contract_address = a.contract_address AND h.contract_type = 'ERC1155' GROUP BY a.contract_address HAVING COUNT(*) > 20 AND COUNT(DISTINCT h.wallet_address) > 5 ORDER BY approval_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 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_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_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_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_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 (\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 )\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": "Find the average time it takes for users to read notifications after they are sent."}, {"role": "assistant", "content": "SELECT AVG(EXTRACT(EPOCH FROM (read_at - sent_at))/3600) as avg_hours_to_read FROM trading_platform.notifications WHERE read_at IS NOT NULL;"}, {"role": "user", "content": "Now show me this average broken down by day of the week when the notification was sent."}, {"role": "assistant", "content": "SELECT EXTRACT(DOW FROM sent_at) as day_of_week, AVG(EXTRACT(EPOCH FROM (read_at - sent_at))/3600) as avg_hours_to_read FROM trading_platform.notifications WHERE read_at IS NOT NULL GROUP BY day_of_week ORDER BY day_of_week;"}, {"role": "user", "content": "Can you modify the query to show the day names (Monday-Sunday) instead of numbers?"}, {"role": "assistant", "content": "SELECT CASE EXTRACT(DOW FROM sent_at) WHEN 0 THEN 'Sunday' WHEN 1 THEN 'Monday' WHEN 2 THEN 'Tuesday' WHEN 3 THEN 'Wednesday' WHEN 4 THEN 'Thursday' WHEN 5 THEN 'Friday' WHEN 6 THEN 'Saturday' END as day_of_week, AVG(EXTRACT(EPOCH FROM (read_at - sent_at))/3600) as avg_hours_to_read FROM trading_platform.notifications WHERE read_at IS NOT NULL GROUP BY day_of_week ORDER BY EXTRACT(DOW FROM sent_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 trading_platform.notifications ( notification_id text PRIMARY KEY, user_id text, message text, sent_at timestamp, read_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Find all medical records where the vitals JSON field contains a blood pressure reading higher than 140/90, and show the patient_id, record_date, and vitals."}, {"role": "assistant", "content": "SELECT patient_id, record_date, vitals FROM healthcare.medical_records WHERE (vitals->>'systolic')::int > 140 AND (vitals->>'diastolic')::int > 90;"}], "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, 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 )\n"}
{"conversations": [{"role": "user", "content": "Show the document ID, document type, and upload timestamp for all documents uploaded by citizens who registered after January 1st, 2023."}, {"role": "assistant", "content": "SELECT d.document_id, d.document_type, d.upload_timestamp FROM government_services.documents d JOIN citizens c ON d.citizen_id = c.citizen_id WHERE c.registration_date > '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 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 )\n"}
{"conversations": [{"role": "user", "content": "Show me all time entries, including the case name they are associated with."}, {"role": "assistant", "content": "SELECT T1.*, T2.case_name FROM time_entries AS T1 JOIN cases AS T2 ON T1.case_id = T2.case_id"}, {"role": "user", "content": "Only show me time entries for lawyer with ID 'lawyer_789'."}, {"role": "assistant", "content": "SELECT T1.*, T2.case_name FROM time_entries AS T1 JOIN cases AS T2 ON T1.case_id = T2.case_id WHERE T1.lawyer_id = 'lawyer_789'"}, {"role": "user", "content": "Actually, I only want entries for the date '2024-07-30', and just show the entry description, hours spent, and case name."}, {"role": "assistant", "content": "SELECT T1.description, T1.hours_spent, T2.case_name FROM time_entries AS T1 JOIN cases AS T2 ON T1.case_id = T2.case_id WHERE T1.lawyer_id = 'lawyer_789' AND T1.date_worked = '2024-07-30'"}], "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 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.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.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": "For each event recorded, list its ID, name, and the status and value of the transaction in which it occurred."}, {"role": "assistant", "content": "SELECT E.event_id, E.event_name, E.transaction_id, T.status, T.value FROM web3.events AS E JOIN web3.transactions AS T ON E.transaction_id = T.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.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 ( 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 ( token_id text PRIMARY KEY, contract_address text, token_name text, token_symbol text, decimals int, total_supply numeric )\nCREATE TABLE web3.wallets ( wallet_id text, user_id text, address text, private_key text, created_at timestamp )\nCREATE TABLE web3.users ( user_id text, username text, email text, password_hash text, created_at timestamp )\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 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": "Show me the top 3 tokens by trend rank in the 'NFT' narrative, along with their price and 24-hour trading volume."}, {"role": "assistant", "content": "SELECT token_name, token_symbol, price, total_volume FROM token_basic_info WHERE narrative = 'NFT' ORDER BY trend_rank ASC LIMIT 3;"}, {"role": "user", "content": "Can you also include their 1-hour and 7-day price change percentages?"}, {"role": "assistant", "content": "SELECT token_name, token_symbol, price, total_volume, price_change_percentage_1h, price_change_percentage_7d FROM token_basic_info WHERE narrative = 'NFT' ORDER BY trend_rank ASC LIMIT 3;"}, {"role": "user", "content": "Actually, I only want tokens with positive price changes in both time frames."}, {"role": "assistant", "content": "SELECT token_name, token_symbol, price, total_volume, price_change_percentage_1h, price_change_percentage_7d FROM token_basic_info WHERE narrative = 'NFT' AND price_change_percentage_1h > 0 AND price_change_percentage_7d > 0 ORDER BY trend_rank ASC LIMIT 3;"}, {"role": "user", "content": "Now order the results by 24-hour trading volume instead of trend rank."}, {"role": "assistant", "content": "SELECT token_name, token_symbol, price, total_volume, price_change_percentage_1h, price_change_percentage_7d FROM token_basic_info WHERE narrative = 'NFT' AND price_change_percentage_1h > 0 AND price_change_percentage_7d > 0 ORDER BY total_volume::numeric 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 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": "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": "I want to list all employees who currently manage at least one other employee, showing their full name, email, and the total number of direct reports for each manager."}, {"role": "assistant", "content": "SELECT e.employee_id, e.first_name || ' ' || e.last_name AS manager_full_name, e.email, COUNT(r.employee_id) AS direct_report_count\nFROM financial_services.employees e\nJOIN financial_services.employees r ON e.employee_id = r.manager_id\nWHERE e.status = 'Active'\nGROUP BY e.employee_id, e.first_name, e.last_name, e.email;"}, {"role": "user", "content": "Can you also include the job_title and department of each manager in the result?"}, {"role": "assistant", "content": "SELECT e.employee_id, e.first_name || ' ' || e.last_name AS manager_full_name, e.email, e.job_title, e.department, COUNT(r.employee_id) AS direct_report_count\nFROM financial_services.employees e\nJOIN financial_services.employees r ON e.employee_id = r.manager_id\nWHERE e.status = 'Active'\nGROUP BY e.employee_id, e.first_name, e.last_name, e.email, e.job_title, e.department;"}, {"role": "user", "content": "I noticed some managers don't have any reports—that shouldn't be the case. Only show managers who have at least two direct reports."}, {"role": "assistant", "content": "SELECT e.employee_id, e.first_name || ' ' || e.last_name AS manager_full_name, e.email, e.job_title, e.department, COUNT(r.employee_id) AS direct_report_count\nFROM financial_services.employees e\nJOIN financial_services.employees r ON e.employee_id = r.manager_id\nWHERE e.status = 'Active'\nGROUP BY e.employee_id, e.first_name, e.last_name, e.email, e.job_title, e.department\nHAVING COUNT(r.employee_id) >= 2;"}, {"role": "user", "content": "Please order the output by the number of direct reports in descending order."}, {"role": "assistant", "content": "SELECT e.employee_id, e.first_name || ' ' || e.last_name AS manager_full_name, e.email, e.job_title, e.department, COUNT(r.employee_id) AS direct_report_count\nFROM financial_services.employees e\nJOIN financial_services.employees r ON e.employee_id = r.manager_id\nWHERE e.status = 'Active'\nGROUP BY e.employee_id, e.first_name, e.last_name, e.email, e.job_title, e.department\nHAVING COUNT(r.employee_id) >= 2\nORDER BY direct_report_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.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)\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.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": "List all pairs of locations that are in the same city. Include their names and the city they are in."}, {"role": "assistant", "content": "SELECT\n  l1.name AS location1_name,\n  l2.name AS location2_name,\n  l1.city\nFROM transportation.locations AS l1\nJOIN transportation.locations AS l2\n  ON l1.city = l2.city AND l1.location_id < l2.location_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.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 usernames and the length of their 'bio' field for users whose 'is_verified' status is true."}, {"role": "assistant", "content": "SELECT username, LENGTH(bio) AS bio_length FROM social_media.users WHERE is_verified IS 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 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 )\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": "Find the top 5 employees who have verified the most documents. Display the employee full name and the count of verified documents, ordered by count descending."}, {"role": "assistant", "content": "SELECT e.first_name || ' ' || e.last_name AS full_name,\n       COUNT(*) AS verified_count\nFROM government_services.documents d\nJOIN government_services.employees e\n  ON d.verified_by_employee_id = e.employee_id\nWHERE d.verification_status = 'Verified'\nGROUP BY e.first_name, e.last_name\nORDER BY verified_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 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.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.employees ( employee_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, job_title character varying(150) NOT NULL, department character varying(100), work_email character varying(128) NOT NULL UNIQUE, work_phone character varying(32), hire_date date NOT NULL, termination_date date, access_level character varying(50), manager_employee_id character varying(64), PRIMARY KEY (employee_id) )\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 character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, application_id character varying(64), message_subject character varying(255), message_body text NOT NULL, channel character varying(30) NOT NULL, sent_at timestamp NOT NULL, status character varying(30) NOT NULL, related_entity_type character varying(50), related_entity_id character varying(64), PRIMARY KEY (notification_id) )\n"}
{"conversations": [{"role": "user", "content": "List the patient ID and subscriber name for all patients who have both at least one diagnosis recorded and at least one primary insurance policy."}, {"role": "assistant", "content": "SELECT DISTINCT pi.patient_id, pi.subscriber_name FROM healthcare.patient_insurance pi JOIN healthcare.diagnoses d ON pi.patient_id = d.patient_id WHERE pi.is_primary = true;"}, {"role": "user", "content": "Refine this list to only include patients whose most recent diagnosis is marked as chronic."}, {"role": "assistant", "content": "WITH LatestDiagnosis AS ( SELECT patient_id, diagnosis_id, diagnosis_date, is_chronic, ROW_NUMBER() OVER(PARTITION BY patient_id ORDER BY diagnosis_date DESC) as rn FROM healthcare.diagnoses ) SELECT DISTINCT pi.patient_id, pi.subscriber_name FROM healthcare.patient_insurance pi JOIN LatestDiagnosis ld ON pi.patient_id = ld.patient_id WHERE pi.is_primary = true AND ld.rn = 1 AND ld.is_chronic = 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.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.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 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": "Count the number of hashtags associated with each post."}, {"role": "assistant", "content": "SELECT post_id,\n       COUNT(hashtag_id) AS hashtag_count\nFROM social_media.post_hashtags\nGROUP BY post_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 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.post_hashtags ( post_hashtag_id.text, post_id.text, hashtag_id.text )\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) )\n"}
{"conversations": [{"role": "user", "content": "List the citizen IDs for individuals who have both uploaded documents and made payments."}, {"role": "assistant", "content": "SELECT DISTINCT T1.citizen_id FROM documents AS T1 JOIN payments 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.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.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) )\n"}
{"conversations": [{"role": "user", "content": "List each patient's first and last name along with their total number of appointments in 2024."}, {"role": "assistant", "content": "SELECT p.first_name, p.last_name, COUNT(a.appointment_id) AS appointment_count\nFROM healthcare.patients p\nLEFT JOIN healthcare.appointments a\n  ON p.patient_id = a.patient_id\n  AND a.appointment_time BETWEEN '2024-01-01' AND '2024-12-31'\nGROUP BY p.first_name, p.last_name;"}, {"role": "user", "content": "Now exclude all 'Cancelled' appointments from the count."}, {"role": "assistant", "content": "SELECT p.first_name, p.last_name, COUNT(a.appointment_id) AS appointment_count\nFROM healthcare.patients p\nLEFT JOIN healthcare.appointments a\n  ON p.patient_id = a.patient_id\n  AND a.appointment_time BETWEEN '2024-01-01' AND '2024-12-31'\n  AND a.status <> 'Cancelled'\nGROUP BY p.first_name, p.last_name;"}, {"role": "user", "content": "Also, only show patients who have more than 2 appointments and sort the result by appointment_count in descending order."}, {"role": "assistant", "content": "SELECT p.first_name, p.last_name, COUNT(a.appointment_id) AS appointment_count\nFROM healthcare.patients p\nLEFT JOIN healthcare.appointments a\n  ON p.patient_id = a.patient_id\n  AND a.appointment_time BETWEEN '2024-01-01' AND '2024-12-31'\n  AND a.status <> 'Cancelled'\nGROUP BY p.first_name, p.last_name\nHAVING COUNT(a.appointment_id) > 2\nORDER BY appointment_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.patients (\n    patient_id character varying(64) NOT NULL,  -- unique identifier for the patient\n    first_name character varying(100) NOT NULL, -- patient's first name\n    last_name character varying(100) NOT NULL, -- patient's last name\n    date_of_birth date NOT NULL, -- patient's date of birth\n    gender character varying(10), -- patient's gender (e.g., Male, Female, Other)\n    address text, -- patient's home address\n    phone_number character varying(20), -- patient's phone number\n    email character varying(128) UNIQUE, -- patient's email address\n    emergency_contact_name character varying(200), -- name of emergency contact\n    emergency_contact_phone character varying(20), -- phone number of emergency contact\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 (patient_id)\n)\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 (\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": "Which rooms on the 4th floor are non-smoking, along with their property IDs and type IDs?"}, {"role": "assistant", "content": "SELECT room_id, property_id, room_number, room_type_id FROM hospitality_technology.rooms WHERE floor = 4 AND 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 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) )\n"}
{"conversations": [{"role": "user", "content": "Find all pairs of distinct appointments for the same case that overlap in time. Show both appointment IDs, the case_id, and the start_time and end_time of each appointment."}, {"role": "assistant", "content": "SELECT a1.appointment_id AS appointment_id_1,\n       a2.appointment_id AS appointment_id_2,\n       a1.case_id,\n       a1.start_time AS start_time_1,\n       a1.end_time   AS end_time_1,\n       a2.start_time AS start_time_2,\n       a2.end_time   AS end_time_2\nFROM legal_services.appointments a1\nJOIN legal_services.appointments a2\n  ON a1.case_id = a2.case_id\n AND a1.appointment_id < a2.appointment_id\n AND a1.start_time < a2.end_time\n AND a2.start_time < a1.end_time;"}], "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": "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": "Show the names of all insurance plans and the number of patients enrolled in each plan."}, {"role": "assistant", "content": "SELECT ip.plan_name, COUNT(pi.patient_id) AS enrolled_patients FROM healthcare.insurance_plans ip JOIN healthcare.patient_insurance pi ON ip.plan_id = pi.plan_id GROUP BY ip.plan_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 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.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.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": "Find all medical records where the treatment plan includes 'physical therapy' and the patient has an active primary insurance plan, showing the patient ID, record date, and insurance provider details."}, {"role": "assistant", "content": "SELECT mr.patient_id, mr.record_date, ip.insurance_provider, ip.plan_name, pi.policy_number FROM healthcare.medical_records mr JOIN healthcare.patients p ON mr.patient_id = p.patient_id JOIN healthcare.patient_insurance pi ON p.patient_id = pi.patient_id AND pi.is_primary = true JOIN healthcare.insurance_plans ip ON pi.plan_id = ip.plan_id WHERE mr.treatment_plan LIKE '%physical therapy%' AND (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.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.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 ( 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": "Show me all users who have wallets but have never placed any orders, along with their wallet addresses and creation dates."}, {"role": "assistant", "content": "SELECT u.user_id, u.email, w.address AS wallet_address, w.created_at FROM trading_platform.users u JOIN trading_platform.wallets w ON u.user_id = w.user_id LEFT JOIN trading_platform.orders o ON u.user_id = o.user_id WHERE o.order_id IS 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 trading_platform.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) )\nCREATE TABLE trading_platform.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) )\nCREATE TABLE trading_platform.orders ( order_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, wallet_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, order_type character varying(32) NOT NULL, quantity numeric(38,14) NOT NULL, price numeric(38,14) NOT NULL, status character varying(32) NOT NULL, created_at timestamp NOT NULL, PRIMARY KEY (order_id) )\nCREATE TABLE trading_platform.assets ( asset_id character varying(64) NOT NULL, name character varying(128) NOT NULL, symbol character varying(32) NOT NULL, type character varying(32) NOT NULL, PRIMARY KEY (asset_id) )\nCREATE TABLE trading_platform.dapps ( dapp_id character varying(64) NOT NULL, name character varying(128) NOT NULL, description text NOT NULL, url character varying(256) NOT NULL, PRIMARY KEY (dapp_id) )\nCREATE TABLE trading_platform.metadata ( metadata_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, key character varying(128) NOT NULL, value text NOT NULL, PRIMARY KEY (metadata_id) )\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) )\nCREATE TABLE trading_platform.notifications ( notification_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, message text NOT NULL, sent_at timestamp NOT NULL, read_at timestamp, PRIMARY KEY (notification_id) )\n"}
{"conversations": [{"role": "user", "content": "Show me the top 5 projects by valuation that completed fundraising rounds in the last 3 months, along with their narrative information if available."}, {"role": "assistant", "content": "SELECT pfr.project_name, pfr.valuation, pfr.rounds_name, pfr.investment_date, ni.narrative, ni.trend_rank FROM project_fundraising_record pfr LEFT JOIN token_basic_info tbi ON pfr.project_name = tbi.token_name LEFT JOIN narrative_info ni ON tbi.narrative = ni.narrative WHERE pfr.investment_date >= DATE_SUB(CURRENT_DATE, INTERVAL 3 MONTH) ORDER BY pfr.valuation DESC LIMIT 5;"}, {"role": "user", "content": "Can you also include the 24-hour trading volume for these projects' narratives and filter to only include projects with valuation over $50 million?"}, {"role": "assistant", "content": "SELECT pfr.project_name, pfr.valuation, pfr.rounds_name, pfr.investment_date, ni.narrative, ni.trend_rank, ni.volume_24h FROM project_fundraising_record pfr LEFT JOIN token_basic_info tbi ON pfr.project_name = tbi.token_name LEFT JOIN narrative_info ni ON tbi.narrative = ni.narrative WHERE pfr.investment_date >= DATE_SUB(CURRENT_DATE, INTERVAL 3 MONTH) AND pfr.valuation > 50000000 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\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, 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 \"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 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) )\n"}
{"conversations": [{"role": "user", "content": "Could you list each game_id along with the count of hidden achievements and the count of visible achievements?"}, {"role": "assistant", "content": "SELECT game_id,\n       SUM(CASE WHEN hidden THEN 1 ELSE 0 END) AS hidden_count,\n       SUM(CASE WHEN NOT hidden THEN 1 ELSE 0 END) AS visible_count\nFROM gaming_technology.achievements\nGROUP BY game_id;"}, {"role": "user", "content": "Actually, please provide pairs of one hidden and one visible achievement name for each game where both types exist."}, {"role": "assistant", "content": "SELECT h.game_id,\n       h.name AS hidden_name,\n       v.name AS visible_name\nFROM gaming_technology.achievements h\nJOIN gaming_technology.achievements v\n  ON h.game_id = v.game_id\n AND h.hidden = TRUE\n AND v.hidden = FALSE\nWHERE EXISTS (\n  SELECT 1 FROM gaming_technology.achievements x\n   WHERE x.game_id = h.game_id\n     AND x.hidden = FALSE\n)\nAND EXISTS (\n  SELECT 1 FROM gaming_technology.achievements y\n   WHERE y.game_id = h.game_id\n     AND y.hidden = TRUE\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.achievements ( achievement_id.uuid, game_id.uuid, name.text, description.text, icon_url.text, points.integer, hidden.boolean )\n"}
{"conversations": [{"role": "user", "content": "What is the total and average amount of unspent UTXOs per address?"}, {"role": "assistant", "content": "SELECT\n  address,\n  COUNT(*) AS utxo_count,\n  SUM(amount) AS total_unspent_amount,\n  AVG(amount) AS average_unspent_amount\nFROM trading_platform.utxos\nWHERE spent = FALSE\nGROUP BY 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 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.utxos ( utxo_id.text, transaction_id.text, output_index.integer, address.text, amount.numeric, spent.boolean )\nCREATE TABLE trading_platform.dapps ( dapp_id character varying(64) NOT NULL, name character varying(128) NOT NULL, description text NOT NULL, url character varying(256) NOT NULL, PRIMARY KEY (dapp_id) )\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": "Count the number of law firms founded in each decade. Show the decade (e.g., 1990s, 2000s) and the count."}, {"role": "assistant", "content": "SELECT CONCAT(FLOOR(EXTRACT(YEAR FROM founded_date) / 10) * 10, 's') AS decade, COUNT(*) AS firm_count FROM law_firms WHERE founded_date IS NOT NULL GROUP BY decade ORDER BY decade;"}], "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": "What are the environmental impact assessments for the production of the Airbus A350 model?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to data regarding the environmental impact assessments for the production of specific aircraft models like the Airbus A350. My information is limited to the technical specifications and basic details stored in the database, such as model name, manufacturer, and capacity. If you have a question related to the available data, I'd be happy to assist."}], "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 PRIMARY KEY, model_name text, manufacturer text, passenger_capacity int, max_range_km int, engine_type text, wingspan_m numeric, status text, first_flight_date date )\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 document names and versions for documents that share the same case_id, showing each pair of versions."}, {"role": "assistant", "content": "SELECT d1.case_id, d1.document_name AS doc_name_v1, d1.version AS version1, d2.document_name AS doc_name_v2, d2.version AS version2 FROM legal_services.documents d1 JOIN legal_services.documents d2 ON d1.case_id = d2.case_id AND d1.version < d2.version;"}, {"role": "user", "content": "Actually, I only want to compare the highest version against the second highest version per case."}, {"role": "assistant", "content": "SELECT d_prev.case_id, d_prev.document_name AS prev_doc, d_prev.version AS prev_version, d_latest.document_name AS latest_doc, d_latest.version AS latest_version FROM legal_services.documents d_latest JOIN legal_services.documents d_prev ON d_latest.case_id = d_prev.case_id AND d_prev.version = d_latest.version - 1 WHERE d_latest.version = (SELECT MAX(version) FROM legal_services.documents d WHERE d.case_id = d_latest.case_id);"}, {"role": "user", "content": "Also include the upload timestamps and restrict to cases with at least three versions."}, {"role": "assistant", "content": "SELECT d_latest.case_id, d_prev.document_name AS prev_doc, d_prev.upload_timestamp AS prev_upload, d_latest.document_name AS latest_doc, d_latest.upload_timestamp AS latest_upload FROM legal_services.documents d_latest JOIN legal_services.documents d_prev ON d_latest.case_id = d_prev.case_id AND d_prev.version = d_latest.version - 1 WHERE d_latest.version = (SELECT MAX(version) FROM legal_services.documents d WHERE d.case_id = d_latest.case_id) AND (SELECT COUNT(*) FROM legal_services.documents d2 WHERE d2.case_id = d_latest.case_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 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)\n"}
{"conversations": [{"role": "user", "content": "Provide the total count of unique users who have created wallets."}, {"role": "assistant", "content": "SELECT COUNT(DISTINCT user_id) FROM web3.wallets;"}, {"role": "user", "content": "Now, refine that to show the number of users who own *more than one* wallet."}, {"role": "assistant", "content": "SELECT COUNT(*)\nFROM (\n    SELECT user_id\n    FROM web3.wallets\n    GROUP BY user_id\n    HAVING COUNT(*) > 1\n) AS UsersWithMultipleWallets;"}], "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 Bitcoin token tick, show me the creator address from the token_info_bitcoin table and the number of unique wallets currently holding that token."}, {"role": "assistant", "content": "SELECT ti.tick, ti.creator, COUNT(DISTINCT tb.wallet_address) AS unique_wallets FROM token_info_bitcoin ti JOIN token_balances_bitcoin tb ON ti.tick = tb.tick GROUP BY ti.tick, ti.creator;"}, {"role": "user", "content": "Now, only include ticks where there are more than 5 unique wallets, and order the result by the number of unique wallets descending."}, {"role": "assistant", "content": "SELECT ti.tick, ti.creator, COUNT(DISTINCT tb.wallet_address) AS unique_wallets FROM token_info_bitcoin ti JOIN token_balances_bitcoin tb ON ti.tick = tb.tick GROUP BY ti.tick, ti.creator HAVING COUNT(DISTINCT tb.wallet_address) > 5 ORDER BY unique_wallets 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 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 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_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 ( 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": "Show me all lawyers' full names, their bar number, and if they are partners, the full name of another partner from their firm."}, {"role": "assistant", "content": "SELECT l1.first_name || ' ' || l1.last_name AS lawyer_full_name, l1.bar_number,\n       CASE WHEN l1.is_partner = TRUE THEN (\n           SELECT l2.first_name || ' ' || l2.last_name\n           FROM legal_services.lawyers l2\n           WHERE l2.firm_id = l1.firm_id AND l2.is_partner = TRUE AND l2.lawyer_id <> l1.lawyer_id\n           LIMIT 1\n       ) ELSE NULL END AS another_partner_full_name\nFROM legal_services.lawyers l1;"}, {"role": "user", "content": "Only include lawyers who have an email address specified."}, {"role": "assistant", "content": "SELECT l1.first_name || ' ' || l1.last_name AS lawyer_full_name, l1.bar_number,\n       CASE WHEN l1.is_partner = TRUE THEN (\n           SELECT l2.first_name || ' ' || l2.last_name\n           FROM legal_services.lawyers l2\n           WHERE l2.firm_id = l1.firm_id AND l2.is_partner = TRUE AND l2.lawyer_id <> l1.lawyer_id\n           LIMIT 1\n       ) ELSE NULL END AS another_partner_full_name\nFROM legal_services.lawyers l1\nWHERE l1.email IS NOT NULL AND l1.email <> '';"}, {"role": "user", "content": "Actually, restrict it to lawyers hired in or after 2023."}, {"role": "assistant", "content": "SELECT l1.first_name || ' ' || l1.last_name AS lawyer_full_name, l1.bar_number,\n       CASE WHEN l1.is_partner = TRUE THEN (\n           SELECT l2.first_name || ' ' || l2.last_name\n           FROM legal_services.lawyers l2\n           WHERE l2.firm_id = l1.firm_id AND l2.is_partner = TRUE AND l2.lawyer_id <> l1.lawyer_id\n           LIMIT 1\n       ) ELSE NULL END AS another_partner_full_name\nFROM legal_services.lawyers l1\nWHERE l1.email IS NOT NULL AND l1.email <> '' AND l1.hire_date >= '2023-01-01';"}, {"role": "user", "content": "Sort the results by the lawyer's last name in descending order."}, {"role": "assistant", "content": "SELECT l1.first_name || ' ' || l1.last_name AS lawyer_full_name, l1.bar_number,\n       CASE WHEN l1.is_partner = TRUE THEN (\n           SELECT l2.first_name || ' ' || l2.last_name\n           FROM legal_services.lawyers l2\n           WHERE l2.firm_id = l1.firm_id AND l2.is_partner = TRUE AND l2.lawyer_id <> l1.lawyer_id\n           LIMIT 1\n       ) ELSE NULL END AS another_partner_full_name\nFROM legal_services.lawyers l1\nWHERE l1.email IS NOT NULL AND l1.email <> '' AND l1.hire_date >= '2023-01-01'\nORDER BY l1.last_name 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, first_name.text, last_name.text, bar_number.text, firm_id.text, email.text, phone.text, specialization.text, hire_date.timestamp, is_partner.boolean )\n"}
{"conversations": [{"role": "user", "content": "Show me all terminated staff members along with their termination dates and the names of their managers, ordered by termination date."}, {"role": "assistant", "content": "SELECT s.staff_id, s.first_name, s.last_name, s.termination_date, m.first_name AS manager_first_name, m.last_name AS manager_last_name FROM hospitality_technology.staff s LEFT JOIN hospitality_technology.staff m ON s.manager_id = m.staff_id WHERE s.termination_date IS NOT NULL ORDER BY s.termination_date;"}, {"role": "user", "content": "Now, include only terminations that occurred in the last 6 months and show their property IDs."}, {"role": "assistant", "content": "SELECT s.staff_id, s.first_name, s.last_name, s.termination_date, s.property_id, m.first_name AS manager_first_name, m.last_name AS manager_last_name FROM hospitality_technology.staff s LEFT JOIN hospitality_technology.staff m ON s.manager_id = m.staff_id WHERE s.termination_date IS NOT NULL AND s.termination_date >= CURRENT_DATE - INTERVAL '6 months' ORDER BY s.termination_date;"}, {"role": "user", "content": "The query should also show the duration of their employment in days."}, {"role": "assistant", "content": "SELECT s.staff_id, s.first_name, s.last_name, s.termination_date, s.property_id, m.first_name AS manager_first_name, m.last_name AS manager_last_name, (s.termination_date - s.hire_date) AS employment_duration_days FROM hospitality_technology.staff s LEFT JOIN hospitality_technology.staff m ON s.manager_id = m.staff_id WHERE s.termination_date IS NOT NULL AND s.termination_date >= CURRENT_DATE - INTERVAL '6 months' ORDER BY s.termination_date;"}, {"role": "user", "content": "Actually, I need to see the results grouped by property ID and ordered by termination count in descending order."}, {"role": "assistant", "content": "SELECT s.property_id, COUNT(s.staff_id) AS termination_count FROM hospitality_technology.staff s WHERE s.termination_date IS NOT NULL AND s.termination_date >= CURRENT_DATE - INTERVAL '6 months' GROUP BY s.property_id ORDER BY termination_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.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)\n"}
{"conversations": [{"role": "user", "content": "List the content and sent time for messages sent by user 'U101'."}, {"role": "assistant", "content": "SELECT content, sent_at FROM social_media.messages WHERE sender_user_id = 'U101';"}, {"role": "user", "content": "Could you also include the group name for those messages and only show messages sent in group chats?"}, {"role": "assistant", "content": "SELECT m.content, m.sent_at, c.name AS group_name FROM social_media.messages m JOIN social_media.conversations c ON m.conversation_id = c.conversation_id WHERE m.sender_user_id = 'U101' AND c.type = 'group';"}, {"role": "user", "content": "Now filter to include only messages sent in June 2024 and order them by sent time descending."}, {"role": "assistant", "content": "SELECT m.content, m.sent_at, c.name AS group_name FROM social_media.messages m JOIN social_media.conversations c ON m.conversation_id = c.conversation_id WHERE m.sender_user_id = 'U101' AND c.type = 'group' AND m.sent_at >= '2024-06-01' AND m.sent_at < '2024-07-01' ORDER BY m.sent_at DESC;"}, {"role": "user", "content": "Also limit the results to the top 15."}, {"role": "assistant", "content": "SELECT m.content, m.sent_at, c.name AS group_name FROM social_media.messages m JOIN social_media.conversations c ON m.conversation_id = c.conversation_id WHERE m.sender_user_id = 'U101' AND c.type = 'group' AND m.sent_at >= '2024-06-01' AND m.sent_at < '2024-07-01' ORDER BY m.sent_at DESC LIMIT 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 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)\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": "Show me all insurance plans that have more than 5 patients enrolled as their primary insurance, along with the provider name and count of patients."}, {"role": "assistant", "content": "SELECT ip.plan_id, ip.plan_name, ip.insurance_provider, COUNT(pi.patient_id) AS patient_count FROM healthcare.insurance_plans ip JOIN healthcare.patient_insurance pi ON ip.plan_id = pi.plan_id WHERE pi.is_primary = true GROUP BY ip.plan_id, ip.plan_name, ip.insurance_provider HAVING COUNT(pi.patient_id) > 5 ORDER BY patient_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.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.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) )\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": "List all medical record entries where the treatment_plan mentions a medication name. Return patient_id, record_id, and the matching medication_name."}, {"role": "assistant", "content": "SELECT mr.patient_id,\n       mr.record_id,\n       m.medication_name\nFROM healthcare.medical_records AS mr\nJOIN healthcare.medications AS m\n  ON mr.treatment_plan ILIKE '%' || m.medication_name || '%';"}, {"role": "user", "content": "Actually, only include medications manufactured by 'Pfizer'."}, {"role": "assistant", "content": "SELECT mr.patient_id,\n       mr.record_id,\n       m.medication_name\nFROM healthcare.medical_records AS mr\nJOIN healthcare.medications AS m\n  ON mr.treatment_plan ILIKE '%' || m.medication_name || '%'\nWHERE m.manufacturer = 'Pfizer';"}, {"role": "user", "content": "Also sort the results by record_date descending."}, {"role": "assistant", "content": "SELECT mr.patient_id,\n       mr.record_id,\n       m.medication_name\nFROM healthcare.medical_records AS mr\nJOIN healthcare.medications AS m\n  ON mr.treatment_plan ILIKE '%' || m.medication_name || '%'\nWHERE m.manufacturer = 'Pfizer'\nORDER BY mr.record_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 (\n    patient_id character varying(64) NOT NULL,  -- unique identifier for the patient\n    first_name character varying(100) NOT NULL, -- patient's first name\n    last_name character varying(100) NOT NULL, -- patient's last name\n    date_of_birth date NOT NULL, -- patient's date of birth\n    gender character varying(10), -- patient's gender (e.g., Male, Female, Other)\n    address text, -- patient's home address\n    phone_number character varying(20), -- patient's phone number\n    email character varying(128) UNIQUE, -- patient's email address\n    emergency_contact_name character varying(200), -- name of emergency contact\n    emergency_contact_phone character varying(20), -- phone number of emergency contact\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 (patient_id)\n)\nCREATE TABLE healthcare.doctors (\n    doctor_id character varying(64) NOT NULL,  -- unique identifier for the doctor\n    first_name character varying(100) NOT NULL, -- doctor's first name\n    last_name character varying(100) NOT NULL, -- doctor's last name\n    specialty character varying(100) NOT NULL, -- doctor's medical specialty\n    license_number character varying(50) UNIQUE NOT NULL, -- doctor's medical license number\n    phone_number character varying(20), -- doctor's contact phone\n    email character varying(128) UNIQUE, -- doctor's contact email\n    hospital_affiliation_id character varying(64), -- FK to hospitals table (optional)\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 (doctor_id)\n)\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 (\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.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.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 (\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 number of game servers in each region and the average maximum number of players they can accommodate. Exclude any servers that are currently offline."}, {"role": "assistant", "content": "SELECT region, COUNT(server_id) AS server_count, AVG(max_players) AS average_max_players FROM gaming_technology.servers WHERE status != 'offline' GROUP BY region;"}, {"role": "user", "content": "Please filter the results to only include regions that have more than 5 active servers."}, {"role": "assistant", "content": "SELECT region, COUNT(server_id) AS server_count, AVG(max_players) AS average_max_players FROM gaming_technology.servers WHERE status != 'offline' GROUP BY region HAVING COUNT(server_id) > 5;"}, {"role": "user", "content": "Can you also include the total number of current players across all active servers in each of those regions?"}, {"role": "assistant", "content": "SELECT region, COUNT(server_id) AS server_count, AVG(max_players) AS average_max_players, SUM(current_players) AS total_current_players FROM gaming_technology.servers WHERE status != 'offline' GROUP BY region HAVING COUNT(server_id) > 5;"}, {"role": "user", "content": "Order the final results by the total number of current players in descending order."}, {"role": "assistant", "content": "SELECT region, COUNT(server_id) AS server_count, AVG(max_players) AS average_max_players, SUM(current_players) AS total_current_players FROM gaming_technology.servers WHERE status != 'offline' GROUP BY region HAVING COUNT(server_id) > 5 ORDER BY total_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.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)\nCREATE TABLE gaming_technology.in_game_items (\n    item_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the item definition\n    game_id uuid NOT NULL, -- FK linking to the game this item belongs to\n    item_name character varying(150) NOT NULL, -- name of the item\n    item_type character varying(50) NOT NULL, -- type (e.g., Cosmetic, Consumable, Weapon, Armor)\n    description text, -- description of the item\n    rarity character varying(30), -- item rarity (e.g., Common, Rare, Epic, Legendary)\n    cost_currency character varying(10), -- currency code if purchasable (e.g., USD, EUR, GOLD)\n    cost_amount numeric(12, 2), -- price if purchasable\n    attributes jsonb, -- flexible field for item stats or properties\n    PRIMARY KEY (item_id)\n    -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id)\n)\nCREATE TABLE gaming_technology.player_inventory (\n    inventory_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for an inventory entry\n    player_id uuid NOT NULL, -- FK linking to the player owning the item\n    item_id uuid NOT NULL, -- FK linking to the item definition\n    quantity integer NOT NULL DEFAULT 1, -- number of items held (for stackable items)\n    acquired_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the item was acquired\n    instance_data jsonb, -- data specific to this instance (e.g., weapon mods, durability)\n    PRIMARY KEY (inventory_id),\n    -- Optional unique constraint if items are non-stackable or unique instances\n    -- UNIQUE (player_id, item_id) -- Use if quantity is always 1\n    -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n    -- FOREIGN KEY (item_id) REFERENCES gaming_technology.in_game_items(item_id)\n)\n"}
{"conversations": [{"role": "user", "content": "I want a list of each department's top 3 longest-tenured active employees, showing their full names, hire_date, and their manager’s full names."}, {"role": "assistant", "content": "WITH ranked AS (\n  SELECT\n    e.department,\n    e.employee_id,\n    e.first_name || ' ' || e.last_name AS employee_full_name,\n    e.hire_date,\n    e.manager_id,\n    ROW_NUMBER() OVER (PARTITION BY e.department ORDER BY e.hire_date ASC) AS rn\n  FROM financial_services.employees e\n  WHERE e.status = 'Active'\n)\nSELECT\n  r.department,\n  r.employee_full_name,\n  r.hire_date,\n  m.first_name || ' ' || m.last_name AS manager_full_name\nFROM ranked r\nLEFT JOIN financial_services.employees m ON r.manager_id = m.employee_id\nWHERE r.rn <= 3;"}, {"role": "user", "content": "Actually, only include employees hired before '2018-01-01'."}, {"role": "assistant", "content": "WITH ranked AS (\n  SELECT\n    e.department,\n    e.employee_id,\n    e.first_name || ' ' || e.last_name AS employee_full_name,\n    e.hire_date,\n    e.manager_id,\n    ROW_NUMBER() OVER (PARTITION BY e.department ORDER BY e.hire_date ASC) AS rn\n  FROM financial_services.employees e\n  WHERE e.status = 'Active'\n    AND e.hire_date < '2018-01-01'\n)\nSELECT\n  r.department,\n  r.employee_full_name,\n  r.hire_date,\n  m.first_name || ' ' || m.last_name AS manager_full_name\nFROM ranked r\nLEFT JOIN financial_services.employees m ON r.manager_id = m.employee_id\nWHERE r.rn <= 3;"}, {"role": "user", "content": "Also, only consider departments that have at least 5 active employees in total before applying the top 3 filter."}, {"role": "assistant", "content": "WITH dept_counts AS (\n  SELECT department\n  FROM financial_services.employees\n  WHERE status = 'Active'\n  GROUP BY department\n  HAVING COUNT(*) >= 5\n),\nranked AS (\n  SELECT\n    e.department,\n    e.employee_id,\n    e.first_name || ' ' || e.last_name AS employee_full_name,\n    e.hire_date,\n    e.manager_id,\n    ROW_NUMBER() OVER (PARTITION BY e.department ORDER BY e.hire_date ASC) AS rn\n  FROM financial_services.employees e\n  JOIN dept_counts d ON e.department = d.department\n  WHERE e.status = 'Active'\n    AND e.hire_date < '2018-01-01'\n)\nSELECT\n  r.department,\n  r.employee_full_name,\n  r.hire_date,\n  m.first_name || ' ' || m.last_name AS manager_full_name\nFROM ranked r\nLEFT JOIN financial_services.employees m ON r.manager_id = m.employee_id\nWHERE r.rn <= 3;"}, {"role": "user", "content": "Finally, sort the result by department ascending and hire_date ascending."}, {"role": "assistant", "content": "WITH dept_counts AS (\n  SELECT department\n  FROM financial_services.employees\n  WHERE status = 'Active'\n  GROUP BY department\n  HAVING COUNT(*) >= 5\n),\nranked AS (\n  SELECT\n    e.department,\n    e.employee_id,\n    e.first_name || ' ' || e.last_name AS employee_full_name,\n    e.hire_date,\n    e.manager_id,\n    ROW_NUMBER() OVER (PARTITION BY e.department ORDER BY e.hire_date ASC) AS rn\n  FROM financial_services.employees e\n  JOIN dept_counts d ON e.department = d.department\n  WHERE e.status = 'Active'\n    AND e.hire_date < '2018-01-01'\n)\nSELECT\n  r.department,\n  r.employee_full_name,\n  r.hire_date,\n  m.first_name || ' ' || m.last_name AS manager_full_name\nFROM ranked r\nLEFT JOIN financial_services.employees m ON r.manager_id = m.employee_id\nWHERE r.rn <= 3\nORDER BY r.department ASC, r.hire_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 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.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(100) NOT NULL, department character varying(100), branch_id character varying(64), email character varying(128) NOT NULL UNIQUE, phone_extension character varying(20), hire_date date NOT NULL, termination_date date, manager_id character varying(64), status character varying(32) NOT NULL, PRIMARY KEY (employee_id), FOREIGN KEY (branch_id) REFERENCES financial_services.branches(branch_id), FOREIGN KEY (manager_id) REFERENCES financial_services.employees(employee_id) )\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": "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 me all appointments scheduled for tomorrow with a duration longer than 45 minutes, including patient_id, doctor_id, and appointment_time."}, {"role": "assistant", "content": "SELECT patient_id, doctor_id, appointment_time FROM healthcare.appointments WHERE DATE(appointment_time) = DATE(NOW() + INTERVAL 1 DAY) AND duration_minutes > 45;"}], "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": "Retrieve all room types where the base rate exceeds 200, listing the type name and base rate."}, {"role": "assistant", "content": "SELECT type_name, base_rate FROM hospitality_technology.room_types WHERE base_rate > 200"}, {"role": "user", "content": "Now, only show the ones with a maximum occupancy of 3 or more."}, {"role": "assistant", "content": "SELECT type_name, base_rate FROM hospitality_technology.room_types WHERE base_rate > 200 AND max_occupancy >= 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, 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": "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": "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": "Show me all items of rarity 'Epic', displaying the item's name and type, along with the title of the game it is part of."}, {"role": "assistant", "content": "SELECT igi.item_name, igi.item_type, g.title FROM gaming_technology.in_game_items igi JOIN gaming_technology.games g ON igi.game_id = g.game_id WHERE igi.rarity = 'Epic';"}, {"role": "user", "content": "Only include games released after the year 2020."}, {"role": "assistant", "content": "SELECT igi.item_name, igi.item_type, g.title FROM gaming_technology.in_game_items igi JOIN gaming_technology.games g ON igi.game_id = g.game_id WHERE igi.rarity = 'Epic' AND g.release_date > '2020-12-31';"}, {"role": "user", "content": "For these items, also show the total quantity of each item across all player inventories."}, {"role": "assistant", "content": "SELECT igi.item_name, igi.item_type, g.title, SUM(pi.quantity) AS total_inventory_quantity FROM gaming_technology.in_game_items igi JOIN gaming_technology.games g ON igi.game_id = g.game_id JOIN gaming_technology.player_inventory pi ON igi.item_id = pi.item_id WHERE igi.rarity = 'Epic' AND g.release_date > '2020-12-31' GROUP BY igi.item_name, igi.item_type, g.title;"}, {"role": "user", "content": "Only show items where the total inventory quantity is at least 100."}, {"role": "assistant", "content": "SELECT igi.item_name, igi.item_type, g.title, SUM(pi.quantity) AS total_inventory_quantity FROM gaming_technology.in_game_items igi JOIN gaming_technology.games g ON igi.game_id = g.game_id JOIN gaming_technology.player_inventory pi ON igi.item_id = pi.item_id WHERE igi.rarity = 'Epic' AND g.release_date > '2020-12-31' GROUP BY igi.item_name, igi.item_type, g.title HAVING SUM(pi.quantity) >= 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 gaming_technology.player_inventory (\n    inventory_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for an inventory entry\n    player_id uuid NOT NULL, -- FK linking to the player owning the item\n    item_id uuid NOT NULL, -- FK linking to the item definition\n    quantity integer NOT NULL DEFAULT 1, -- number of items held (for stackable items)\n    acquired_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the item was acquired\n    instance_data jsonb, -- data specific to this instance (e.g., weapon mods, durability)\n    PRIMARY KEY (inventory_id),\n    -- Optional unique constraint if items are non-stackable or unique instances\n    -- UNIQUE (player_id, item_id) -- Use if quantity is always 1\n    -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n    -- FOREIGN KEY (item_id) REFERENCES gaming_technology.in_game_items(item_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Which route numbers connect locations with a distance less than 80 km and more than 5 words in their description? Include the route type in the results."}, {"role": "assistant", "content": "SELECT route_number, type FROM transportation.routes WHERE distance_km < 80 AND array_length(regexp_split_to_array(description, '\\s+'), 1) > 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 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 )\n"}
{"conversations": [{"role": "user", "content": "List all applications that have at least one document with a verification status of 'Verified'. Show the application reference number and the name of the service associated with the application."}, {"role": "assistant", "content": "SELECT\n  T1.reference_number,\n  T2.service_name\nFROM government_services.applications AS T1\nINNER JOIN government_services.services AS T2\n  ON T1.service_id = T2.service_id\nWHERE EXISTS (\n  SELECT\n    1\n  FROM government_services.documents AS T3\n  WHERE\n    T3.application_id = T1.application_id AND T3.verification_status = 'Verified'\n);"}, {"role": "user", "content": "Now, only include applications that were submitted in the year 2024."}, {"role": "assistant", "content": "SELECT\n  T1.reference_number,\n  T2.service_name\nFROM government_services.applications AS T1\nINNER JOIN government_services.services AS T2\n  ON T1.service_id = T2.service_id\nWHERE EXISTS (\n  SELECT\n    1\n  FROM government_services.documents AS T3\n  WHERE\n    T3.application_id = T1.application_id AND T3.verification_status = 'Verified'\n)\nAND EXTRACT(YEAR FROM T1.submitted_at) = 2024;"}], "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 (\n    agency_id character varying(64) NOT NULL, -- unique identifier for the agency\n    agency_name character varying(255) NOT NULL, -- full name of the government agency\n    jurisdiction_level character varying(50) NOT NULL, -- e.g., Federal, State, County, City\n    primary_contact_email character varying(128),\n    main_phone_number character varying(32),\n    website_url character varying(255),\n    established_date date,\n    parent_agency_id character varying(64), -- FK to self for hierarchical structure\n    PRIMARY KEY (agency_id)\n)\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 (\n    document_id character varying(64) NOT NULL, -- unique identifier for the document instance\n    application_id character varying(64), -- FK to applications table (optional, could be linked to citizen directly)\n    citizen_id character varying(64) NOT NULL, -- FK to citizens table\n    document_type character varying(100) NOT NULL, -- e.g., Passport Scan, Proof of Address, Birth Certificate\n    file_reference text NOT NULL, -- reference to the stored file (e.g., S3 URL, internal path)\n    upload_timestamp timestamp NOT NULL,\n    expiry_date date,\n    verification_status character varying(30) DEFAULT 'Pending', -- e.g., Pending, Verified, Rejected\n    verified_by_employee_id character varying(64), -- FK to employees table\n    verification_timestamp timestamp,\n    PRIMARY KEY (document_id)\n)\nCREATE TABLE government_services.appointments (\n    appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment\n    citizen_id character varying(64) NOT NULL, -- FK to citizens table\n    employee_id character varying(64), -- FK to employees table (optional, if assigned)\n    location_id character varying(64), -- FK to service_locations table (if physical)\n    service_id character varying(64), -- FK to services table (optional, if related to specific service)\n    scheduled_start_time timestamp NOT NULL,\n    scheduled_end_time timestamp,\n    purpose text NOT NULL, -- reason for the appointment\n    status character varying(30) NOT NULL, -- e.g., Scheduled, Completed, Cancelled, No-Show\n    booking_method character varying(50), -- e.g., Online, Phone, In-Person\n    created_at timestamp NOT NULL, -- when the appointment was booked\n    notes text,\n    PRIMARY KEY (appointment_id)\n)\nCREATE TABLE government_services.notifications (\n    notification_id character varying(64) NOT NULL, -- unique identifier for the notification\n    citizen_id character varying(64) NOT NULL, -- FK to citizens table\n    application_id character varying(64), -- FK to applications table (optional)\n    message_subject character varying(255),\n    message_body text NOT NULL,\n    channel character varying(30) NOT NULL, -- e.g., Email, SMS, Portal Message, Mail\n    sent_at timestamp NOT NULL,\n    status character varying(30) NOT NULL, -- e.g., Queued, Sent, Delivered, Failed, Read\n    related_entity_type character varying(50), -- e.g., Application, Appointment, Document Request\n    related_entity_id character varying(64), -- ID of the related entity\n    PRIMARY KEY (notification_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List the first name, last name, email, and phone number of all clients who have a case of type 'Bankruptcy', along with the name of the case."}, {"role": "assistant", "content": "SELECT T1.first_name ,  T1.last_name ,  T1.email ,  T1.phone ,  T2.case_name FROM legal_services.clients AS T1 JOIN legal_services.cases AS T2 ON T1.client_id  =  T2.client_id WHERE T2.case_type  =  'Bankruptcy'"}], "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 (\n    firm_id character varying(64) NOT NULL,  -- unique identifier for the law firm\n    firm_name character varying(200) NOT NULL, -- official name of the law firm\n    address text NOT NULL, -- primary address of the firm\n    phone character varying(32), -- firm's main phone number\n    website character varying(255), -- firm's website URL\n    founded_date date, -- date the firm was established\n    managing_partner_id character varying(64), -- FK to lawyers table (optional)\n    PRIMARY KEY (firm_id)\n)\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.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.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 all electric vehicles that have completed trips in the last month, along with the count of trips each vehicle has completed."}, {"role": "assistant", "content": "SELECT v.vehicle_id, v.make, v.model, COUNT(t.trip_id) AS trip_count FROM transportation.vehicles v JOIN transportation.trips t ON v.vehicle_id = t.vehicle_id WHERE v.fuel_type = 'electric' AND t.status = 'completed' AND t.actual_arrival >= NOW() - INTERVAL '1 month' GROUP BY v.vehicle_id, v.make, v.model ORDER BY trip_count DESC;"}, {"role": "user", "content": "Now include the average passenger count for these trips per vehicle."}, {"role": "assistant", "content": "SELECT v.vehicle_id, v.make, v.model, COUNT(t.trip_id) AS trip_count, AVG(t.passenger_count) AS avg_passengers FROM transportation.vehicles v JOIN transportation.trips t ON v.vehicle_id = t.vehicle_id WHERE v.fuel_type = 'electric' AND t.status = 'completed' AND t.actual_arrival >= NOW() - INTERVAL '1 month' GROUP BY v.vehicle_id, v.make, v.model ORDER BY trip_count DESC;"}, {"role": "user", "content": "Filter this to only show vehicles that have completed more than 5 trips and had an average passenger count greater than 10."}, {"role": "assistant", "content": "SELECT v.vehicle_id, v.make, v.model, COUNT(t.trip_id) AS trip_count, AVG(t.passenger_count) AS avg_passengers FROM transportation.vehicles v JOIN transportation.trips t ON v.vehicle_id = t.vehicle_id WHERE v.fuel_type = 'electric' AND t.status = 'completed' AND t.actual_arrival >= NOW() - INTERVAL '1 month' GROUP BY v.vehicle_id, v.make, v.model HAVING COUNT(t.trip_id) > 5 AND AVG(t.passenger_count) > 10 ORDER BY trip_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 transportation.vehicles ( vehicle_id character varying(64) NOT NULL, license_plate character varying(32) NOT NULL UNIQUE, vin character varying(17) UNIQUE, make character varying(64) NOT NULL, model character varying(64) NOT NULL, year integer NOT NULL, type character varying(32) NOT NULL, capacity integer, fuel_type character varying(32) NOT NULL, status character varying(32) NOT NULL, depot_id character varying(64), acquisition_date date, PRIMARY KEY (vehicle_id) )\nCREATE TABLE transportation.trips ( trip_id character varying(64) NOT NULL, route_id character varying(64), vehicle_id character varying(64) NOT NULL, driver_id character varying(64) NOT NULL, scheduled_departure timestamp with time zone NOT NULL, actual_departure timestamp with time zone, scheduled_arrival timestamp with time zone NOT NULL, actual_arrival timestamp with time zone, origin_location_id character varying(64) NOT NULL, destination_location_id character varying(64) NOT NULL, status character varying(32) NOT NULL, passenger_count integer, cargo_manifest_id character varying(64), PRIMARY KEY (trip_id) )\nCREATE TABLE transportation.fuel_logs ( fuel_log_id character varying(64) NOT NULL, vehicle_id character varying(64) NOT NULL, trip_id character varying(64), log_timestamp timestamp with time zone NOT NULL, fuel_type character varying(32) NOT NULL, quantity numeric(10, 3) NOT NULL, unit character varying(16) NOT NULL, cost_per_unit numeric(8, 4), total_cost numeric(10, 2) NOT NULL, odometer_reading integer, location_id character varying(64), PRIMARY KEY (fuel_log_id) )\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": "Find the most recent verified document for each application, showing application_id, document_id, and verification_timestamp."}, {"role": "assistant", "content": "SELECT d.document_id, d.application_id, d.verification_timestamp\nFROM government_services.documents d\nJOIN (\n  SELECT application_id, MAX(verification_timestamp) AS latest_ts\n  FROM government_services.documents\n  WHERE verification_status = 'Verified'\n  GROUP BY application_id\n) m ON d.application_id = m.application_id\n    AND d.verification_timestamp = m.latest_ts;"}], "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 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 )\n"}
{"conversations": [{"role": "user", "content": "List all pairs of law firms that were founded on the same month and day, showing their names, and the shared founding date. Exclude firms founded on January 1st."}, {"role": "assistant", "content": "SELECT t1.firm_name AS firm1_name, t2.firm_name AS firm2_name, t1.founded_date FROM legal_services.law_firms AS t1 JOIN legal_services.law_firms AS t2 ON MONTH(t1.founded_date) = MONTH(t2.founded_date) AND DAY(t1.founded_date) = DAY(t2.founded_date) AND t1.firm_id < t2.firm_id WHERE MONTH(t1.founded_date) <> 1 OR DAY(t1.founded_date) <> 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.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) )\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 need to retrieve asset IDs along with their category and website metadata values for assets that have both entries."}, {"role": "assistant", "content": "SELECT m_cat.asset_id,\n       m_cat.value AS category,\n       m_web.value AS website_url\nFROM trading_platform.metadata m_cat\nJOIN trading_platform.metadata m_web\n  ON m_cat.asset_id = m_web.asset_id\nWHERE m_cat.key = 'category'\n  AND m_web.key = 'website';"}, {"role": "user", "content": "Actually, filter to include only those assets where the category value is 'defi'."}, {"role": "assistant", "content": "SELECT m_cat.asset_id,\n       m_cat.value AS category,\n       m_web.value AS website_url\nFROM trading_platform.metadata m_cat\nJOIN trading_platform.metadata m_web\n  ON m_cat.asset_id = m_web.asset_id\nWHERE m_cat.key = 'category'\n  AND m_web.key = 'website'\n  AND m_cat.value = 'defi';"}], "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 ( metadata_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, key character varying(128) NOT NULL, value text NOT NULL, PRIMARY KEY (metadata_id) )\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 name, symbol, address FROM token_prices_latest WHERE price BETWEEN 1 AND 10 AND blockchain = 'ethereum';"}, {"role": "user", "content": "I think there's an error in your query - it should be joining with sui_coins_metadata on coin_type not address. Also, can you add the current price to the results?"}, {"role": "assistant", "content": "SELECT scm.name, scm.symbol, scm.coin_type, tpl.price FROM sui_coins_metadata scm JOIN token_prices_latest tpl ON scm.coin_type = tpl.address WHERE tpl.price BETWEEN 1 AND 10;"}, {"role": "user", "content": "Now filter these results to only show tokens with decimals equal to 18 and sort by name alphabetically."}, {"role": "assistant", "content": "SELECT scm.name, scm.symbol, scm.coin_type, tpl.price FROM sui_coins_metadata scm JOIN token_prices_latest tpl ON scm.coin_type = tpl.address WHERE tpl.price BETWEEN 1 AND 10 AND scm.decimals = 18 ORDER BY scm.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 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_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_metadata ( object_id varchar, coin_type varchar, status varchar, decimals bigint, description varchar, icon_url varchar, symbol varchar, name varchar )\nCREATE TABLE sui_nfts (\n    object_id varchar NOT NULL, -- object id of the nft\n    status varchar NOT NULL, -- status of the package, exists or deleted\n    collection_type varchar NOT NULL, -- collection type of the nft, eg. 0x...123::avatars::Avatar\n    package_id varchar NOT NULL, -- which package the nft belongs to, eg. 0x...123::avatars belongs to 0x...123\n    previous_transaction varchar NOT NULL, -- previous transaction of the nft\n    display varchar NOT NULL, -- nft metadata json object\n    owner varchar NOT NULL, -- nft owner\n    name varchar NOT NULL  -- nft name\n)\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 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, address varchar, decimals bigint, symbol varchar, price real, timestamp timestamp )\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_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(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_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": "Show the top 10 most expensive fuel log entries including fuel_log_id, vehicle make and model, location name and city, and total_cost."}, {"role": "assistant", "content": "SELECT f.fuel_log_id,\n       v.make,\n       v.model,\n       loc.name AS location_name,\n       loc.city,\n       f.total_cost\nFROM transportation.fuel_logs f\nJOIN transportation.vehicles v ON f.vehicle_id = v.vehicle_id\nJOIN transportation.locations loc ON f.location_id = loc.location_id\nORDER BY f.total_cost 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 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 ( driver_id character varying(64) NOT NULL, employee_id character varying(64) NOT NULL UNIQUE, first_name character varying(128) NOT NULL, last_name character varying(128) NOT NULL, license_number character varying(64) NOT NULL UNIQUE, license_expiry_date date NOT NULL, contact_number character varying(32), email character varying(128) UNIQUE, hire_date date NOT NULL, status character varying(32) NOT NULL, PRIMARY KEY (driver_id) )\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 (\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.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 )\nCREATE TABLE transportation.maintenance_logs ( log_id character varying(64) NOT NULL, vehicle_id character varying(64) NOT NULL, service_date date NOT NULL, odometer_reading integer, service_type character varying(128) NOT NULL, description text NOT NULL, cost numeric(10, 2), mechanic_name character varying(128), next_service_due_date date, PRIMARY KEY (log_id) )\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": "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": "I need to find pairs of nodes that share the same port but have different IP addresses. Can you write a query for that?"}, {"role": "assistant", "content": "SELECT n1.node_id AS node1_id,\n       n2.node_id AS node2_id,\n       n1.port\nFROM blockchain.nodes n1\nJOIN blockchain.nodes n2\n  ON n1.port = n2.port\n AND n1.ip_address <> n2.ip_address;"}, {"role": "user", "content": "Great. Now include the time difference in hours between their last_seen timestamps."}, {"role": "assistant", "content": "SELECT n1.node_id AS node1_id,\n       n2.node_id AS node2_id,\n       n1.port,\n       ABS(EXTRACT(EPOCH FROM (n1.last_seen - n2.last_seen)) / 3600) AS hour_diff\nFROM blockchain.nodes n1\nJOIN blockchain.nodes n2\n  ON n1.port = n2.port\n AND n1.ip_address <> n2.ip_address;"}, {"role": "user", "content": "Actually, I only want those pairs where the time difference is less than 1 hour, and order the results by the smallest time difference first."}, {"role": "assistant", "content": "SELECT n1.node_id AS node1_id,\n       n2.node_id AS node2_id,\n       n1.port,\n       ABS(EXTRACT(EPOCH FROM (n1.last_seen - n2.last_seen)) / 3600) AS hour_diff\nFROM blockchain.nodes n1\nJOIN blockchain.nodes n2\n  ON n1.port = n2.port\n AND n1.ip_address <> n2.ip_address\nWHERE ABS(EXTRACT(EPOCH FROM (n1.last_seen - n2.last_seen)) / 3600) < 1\nORDER BY hour_diff ASC;"}, {"role": "user", "content": "One more thing: can you add a count of how many such pairs exist for each port?"}, {"role": "assistant", "content": "SELECT port,\n       COUNT(*) AS pair_count\nFROM (\n  SELECT 1\n  FROM blockchain.nodes n1\n  JOIN blockchain.nodes n2\n    ON n1.port = n2.port\n   AND n1.ip_address <> n2.ip_address\n  WHERE ABS(EXTRACT(EPOCH FROM (n1.last_seen - n2.last_seen)) / 3600) < 1\n) sub\nGROUP BY port;"}], "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.nodes ( node_id character varying(64) NOT NULL, ip_address character varying(15) NOT NULL, port integer NOT NULL, last_seen timestamp NOT NULL, PRIMARY KEY (node_id) )\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"}