{"conversations": [{"role": "user", "content": "Find all pairs of transactions where both transactions have the same nonce and from_address, but different transaction_id. Show both transaction IDs, the shared from_address, shared nonce, and their block numbers."}, {"role": "assistant", "content": "SELECT t1.transaction_id AS transaction_id_1, t2.transaction_id AS transaction_id_2, t1.from_address, t1.nonce, t1.block_number AS block_number_1, t2.block_number AS block_number_2\nFROM web3.transactions t1\nJOIN web3.transactions t2\n  ON t1.from_address = t2.from_address\n AND t1.nonce = t2.nonce\n AND t1.transaction_id < t2.transaction_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.transactions (\n    transaction_id character varying(64) NOT NULL,  -- unique identifier for the transaction\n    from_address character varying(128) NOT NULL, -- address of the sender\n    to_address character varying(128), -- address of the receiver (can be null for contract deployment)\n    value numeric(38,14) NOT NULL, -- value transferred\n    gas_used integer NOT NULL, -- amount of gas used by the transaction\n    gas_price numeric(38,14) NOT NULL, -- price of gas at the time of the transaction\n    block_number integer NOT NULL, -- block number containing the transaction\n    timestamp timestamp NOT NULL, -- time when the transaction was mined\n    input_data text, -- input data of the transaction (can be null)\n    status character varying(32) NOT NULL, -- status of the transaction (e.g., success, failed)\n    nonce integer NOT NULL, -- nonce of the sender at the time of the transaction\n    PRIMARY KEY (transaction_id)\n)\n"}
{"conversations": [{"role": "user", "content": "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": "List all claims along with the first and last names of the agent who is currently handling each claim."}, {"role": "assistant", "content": "SELECT c.claim_id, c.policy_id, c.incident_date, a.first_name AS agent_first_name, a.last_name AS agent_last_name\nFROM insurance.claims c\nJOIN insurance.agents a ON c.claim_handler_id = a.agent_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.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 character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, agency_name character varying(150), license_number character varying(100) NOT NULL UNIQUE, license_state character varying(50) NOT NULL, contact_email character varying(128) UNIQUE, contact_phone character varying(30), hire_date date, termination_date date, status character varying(20) NOT NULL DEFAULT 'Active', commission_rate numeric(5, 4) NOT NULL DEFAULT 0.05, manager_id character varying(64), PRIMARY KEY (agent_id) )\n"}
{"conversations": [{"role": "user", "content": "For each transaction status, what is the average transaction value?"}, {"role": "assistant", "content": "SELECT status, AVG(value) FROM web3.transactions GROUP BY status"}, {"role": "user", "content": "Could you filter this to only show statuses where the average value is greater than 100?"}, {"role": "assistant", "content": "SELECT status, AVG(value) FROM web3.transactions GROUP BY status HAVING AVG(value) > 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 web3.contracts (\n    contract_id character varying(64) NOT NULL,  -- unique identifier for the contract\n    address character varying(128) NOT NULL, -- address of the deployed contract\n    abi text NOT NULL, -- application binary interface of the contract\n    bytecode text NOT NULL, -- bytecode of the contract\n    deployer_address character varying(128) NOT NULL, -- address of the deployer\n    deployed_at timestamp NOT NULL, -- time when the contract was deployed\n    network_id character varying(64) NOT NULL, -- identifier of the network where the contract is deployed\n    status character varying(32) NOT NULL, -- status of the contract (e.g., active, deprecated)\n    PRIMARY KEY (contract_id)\n)\nCREATE TABLE web3.transactions (\n    transaction_id character varying(64) NOT NULL,  -- unique identifier for the transaction\n    from_address character varying(128) NOT NULL, -- address of the sender\n    to_address character varying(128), -- address of the receiver (can be null for contract deployment)\n    value numeric(38,14) NOT NULL, -- value transferred\n    gas_used integer NOT NULL, -- amount of gas used by the transaction\n    gas_price numeric(38,14) NOT NULL, -- price of gas at the time of the transaction\n    block_number integer NOT NULL, -- block number containing the transaction\n    timestamp timestamp NOT NULL, -- time when the transaction was mined\n    input_data text, -- input data of the transaction (can be null)\n    status character varying(32) NOT NULL, -- status of the transaction (e.g., success, failed)\n    nonce integer NOT NULL, -- nonce of the sender at the time of the transaction\n    PRIMARY KEY (transaction_id)\n)\nCREATE TABLE web3.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)\n"}
{"conversations": [{"role": "user", "content": "I need a count of appointments per patient that took place between '2024-04-01' and '2024-04-30', showing patient_id, first_name, last_name, and the total number of appointments."}, {"role": "assistant", "content": "SELECT p.patient_id, p.first_name, p.last_name, COUNT(a.appointment_id) AS appointment_count\nFROM healthcare.patients p\nJOIN healthcare.appointments a ON p.patient_id = a.patient_id\nWHERE a.appointment_time BETWEEN '2024-04-01' AND '2024-04-30'\nGROUP BY p.patient_id, p.first_name, p.last_name;"}, {"role": "user", "content": "Only include patients who had at least 2 appointments in that period."}, {"role": "assistant", "content": "SELECT p.patient_id, p.first_name, p.last_name, COUNT(a.appointment_id) AS appointment_count\nFROM healthcare.patients p\nJOIN healthcare.appointments a ON p.patient_id = a.patient_id\nWHERE a.appointment_time BETWEEN '2024-04-01' AND '2024-04-30'\nGROUP BY p.patient_id, p.first_name, p.last_name\nHAVING COUNT(a.appointment_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.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 )\n"}
{"conversations": [{"role": "user", "content": "For product types that have both active and inactive products, list each pair of product IDs along with the shared product_type and their is_active statuses."}, {"role": "assistant", "content": "SELECT p1.product_id AS active_id, p2.product_id AS inactive_id, p1.product_type, p1.is_active AS active_status, p2.is_active AS inactive_status FROM insurance.insurance_products p1 JOIN insurance.insurance_products p2 ON p1.product_type = p2.product_type AND p1.is_active = TRUE AND p2.is_active = FALSE;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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 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": "Show me all cryptocurrency assets that have been traded more than 50 times but have never been traded in quantities greater than 100, along with their average trade price."}, {"role": "assistant", "content": "SELECT a.asset_id, a.name, a.symbol, COUNT(t.trade_id) AS trade_count, AVG(t.price) AS avg_price FROM trading_platform.assets a JOIN trading_platform.trades t ON a.asset_id = t.asset_id WHERE a.type = 'cryptocurrency' GROUP BY a.asset_id, a.name, a.symbol HAVING COUNT(t.trade_id) > 50 AND MAX(t.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 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.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 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.utxos ( utxo_id character varying(64) NOT NULL, transaction_id character varying(64) NOT NULL, output_index integer NOT NULL, address character varying(128) NOT NULL, amount numeric(38,14) NOT NULL, spent boolean NOT NULL, PRIMARY KEY (utxo_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.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 ( 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.kyc_audit ( kyc_audit_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, status character varying(32) NOT NULL, reviewed_at timestamp NOT NULL, PRIMARY KEY (kyc_audit_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": "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": "Show the usernames of users who have liked a comment made by a user they are following."}, {"role": "assistant", "content": "SELECT DISTINCT T1.username FROM social_media.users AS T1 JOIN likes AS T2 ON T1.user_id = T2.user_id JOIN comments AS T3 ON T2.target_entity_id = T3.comment_id JOIN social_media.users AS T4 ON T3.user_id = T4.user_id JOIN follows AS T5 ON T1.user_id = T5.follower_user_id AND T4.user_id = T5.followed_user_id WHERE T2.target_entity_type = 'comment';"}, {"role": "user", "content": "Include the content of the comment and the username of the commenter."}, {"role": "assistant", "content": "SELECT T1.username AS liker_username, T4.username AS commenter_username, T3.content AS comment_content FROM social_media.users AS T1 JOIN likes AS T2 ON T1.user_id = T2.user_id JOIN comments AS T3 ON T2.target_entity_id = T3.comment_id JOIN social_media.users AS T4 ON T3.user_id = T4.user_id JOIN follows AS T5 ON T1.user_id = T5.follower_user_id AND T4.user_id = T5.followed_user_id WHERE T2.target_entity_type = 'comment';"}, {"role": "user", "content": "Filter to only show likes made in June 2024 and order by like creation time descending."}, {"role": "assistant", "content": "SELECT T1.username AS liker_username, T4.username AS commenter_username, T3.content AS comment_content, T2.created_at AS like_time FROM social_media.users AS T1 JOIN likes AS T2 ON T1.user_id = T2.user_id JOIN comments AS T3 ON T2.target_entity_id = T3.comment_id JOIN social_media.users AS T4 ON T3.user_id = T4.user_id JOIN follows AS T5 ON T1.user_id = T5.follower_user_id AND T4.user_id = T5.followed_user_id WHERE T2.target_entity_type = 'comment' AND T2.created_at >= '2024-06-01' AND T2.created_at < '2024-07-01' ORDER BY T2.created_at DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id 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 all managers (agents who have other agents reporting to them) along with their team sizes, sorted by team size in descending order."}, {"role": "assistant", "content": "SELECT m.agent_id, m.first_name, m.last_name, COUNT(a.agent_id) AS team_size FROM insurance.agents m JOIN insurance.agents a ON m.agent_id = a.manager_id GROUP BY m.agent_id, m.first_name, m.last_name ORDER BY team_size DESC;"}, {"role": "user", "content": "Now filter to only show managers with teams larger than 3 agents and include their commission rates."}, {"role": "assistant", "content": "SELECT m.agent_id, m.first_name, m.last_name, m.commission_rate, COUNT(a.agent_id) AS team_size FROM insurance.agents m JOIN insurance.agents a ON m.agent_id = a.manager_id GROUP BY m.agent_id, m.first_name, m.last_name, m.commission_rate HAVING COUNT(a.agent_id) > 3 ORDER BY team_size DESC;"}, {"role": "user", "content": "I also want to see the average commission rate of their team members."}, {"role": "assistant", "content": "SELECT m.agent_id, m.first_name, m.last_name, m.commission_rate, COUNT(a.agent_id) AS team_size, AVG(a.commission_rate) AS avg_team_commission FROM insurance.agents m JOIN insurance.agents a ON m.agent_id = a.manager_id GROUP BY m.agent_id, m.first_name, m.last_name, m.commission_rate HAVING COUNT(a.agent_id) > 3 ORDER BY team_size DESC;"}, {"role": "user", "content": "Finally, show me the highest commission rate in each manager's team."}, {"role": "assistant", "content": "SELECT m.agent_id, m.first_name, m.last_name, m.commission_rate, COUNT(a.agent_id) AS team_size, AVG(a.commission_rate) AS avg_team_commission, MAX(a.commission_rate) AS max_team_commission FROM insurance.agents m JOIN insurance.agents a ON m.agent_id = a.manager_id GROUP BY m.agent_id, m.first_name, m.last_name, m.commission_rate HAVING COUNT(a.agent_id) > 3 ORDER BY team_size 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.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 )\n"}
{"conversations": [{"role": "user", "content": "For each claim, show the corresponding product_type of the insurance product for the related policy."}, {"role": "assistant", "content": "SELECT cl.claim_id, ip.product_type\nFROM insurance.claims cl\nJOIN insurance.policies p ON cl.policy_id = p.policy_id\nJOIN insurance.insurance_products ip ON p.product_id = ip.product_id;"}, {"role": "user", "content": "Sorry, there is no policies table, I got an error. Can you try joining claims to insurance_products another way?"}, {"role": "assistant", "content": "-- Unable to join directly since there is no 'policies' table connecting claims to insurance_products. If policy_id equals product_id, you may try:\nSELECT claim_id, policy_id, product_type\nFROM insurance.claims\nJOIN insurance.insurance_products ON claims.policy_id = insurance_products.product_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.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 ( claim_id.text, policy_id.text, customer_id.text, incident_date.timestamp, reported_date.timestamp, description.text, estimated_loss.numeric, status.text, settlement_amount.numeric, settlement_date.date, claim_handler_id.text, police_report_number.text )\nCREATE TABLE insurance.insurance_products ( product_id.text, product_name.text, product_type.text, description.text, base_premium.numeric, coverage_details.text, underwriting_rules.text, is_active.boolean, created_at.timestamp, updated_at.timestamp )\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": "List all ERC20 tokens where the price is between $1 and $10, including their names, symbols, and contract addresses."}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address FROM token_metas tm JOIN token_prices_latest tpl ON tm.contract_address = tpl.address WHERE tm.is_erc20 = 1 AND tpl.price BETWEEN 1 AND 10;"}, {"role": "user", "content": "I think there's an error in your query - it should be joining with token_prices_latest on address not contract_address. Also, can you add the current price to the results?"}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address, tpl.price FROM token_metas tm JOIN token_prices_latest tpl ON tm.contract_address = tpl.address WHERE tm.is_erc20 = 1 AND 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 tm.name, tm.symbol, tm.contract_address, tpl.price FROM token_metas tm JOIN token_prices_latest tpl ON tm.contract_address = tpl.address WHERE tm.is_erc20 = 1 AND tpl.price BETWEEN 1 AND 10 AND tm.decimals = 18 ORDER BY tm.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 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 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 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_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": "Count the number of posts that have a media URL but no textual content."}, {"role": "assistant", "content": "SELECT COUNT(*) FROM social_media.posts AS T1 WHERE T1.media_url IS NOT NULL AND (T1.content IS NULL OR T1.content = '');"}], "system": "You are an SQL statement expert. Given the table structure 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.posts (\n    post_id character varying(64) NOT NULL, -- unique identifier for the post\n    user_id character varying(64) NOT NULL, -- identifier of the user who created the post (FK to users.user_id)\n    content text, -- textual content of the post\n    media_url text, -- URL to attached media (image/video)\n    media_type character varying(20), -- type of media ('image', 'video', null)\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of post creation\n    updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last post edit\n    visibility character varying(20) NOT NULL DEFAULT 'public', -- visibility ('public', 'friends', 'private')\n    location_lat numeric(9,6), -- latitude of post location\n    location_lon numeric(9,6), -- longitude of post location\n    PRIMARY KEY (post_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.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": "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 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": "Show me the content and creation time of comments made on posts authored by the user with ID 'user_X'."}, {"role": "assistant", "content": "SELECT T1.content, T1.created_at FROM social_media.comments AS T1 JOIN social_media.posts AS T2 ON T1.post_id = T2.post_id WHERE T2.user_id = 'user_X';"}, {"role": "user", "content": "Can you also include the username of the user who made each comment?"}, {"role": "assistant", "content": "SELECT T1.content, T1.created_at, T3.username FROM social_media.comments AS T1 JOIN social_media.posts AS T2 ON T1.post_id = T2.post_id JOIN social_media.users AS T3 ON T1.user_id = T3.user_id WHERE T2.user_id = 'user_X';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.comments (\n    comment_id character varying(64) NOT NULL, -- unique identifier for the comment\n    post_id character varying(64) NOT NULL, -- identifier of the post being commented on (FK to posts.post_id)\n    user_id character varying(64) NOT NULL, -- identifier of the user who made the comment (FK to users.user_id)\n    parent_comment_id character varying(64), -- identifier of the parent comment if it's a reply (FK to comments.comment_id)\n    content text NOT NULL, -- textual content of the comment\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of comment creation\n    updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last comment edit\n    PRIMARY KEY (comment_id)\n)\n"}
{"conversations": [{"role": "user", "content": "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": "Show me all pairs of cases led by the same lawyer, including both case names and the lead lawyer ID."}, {"role": "assistant", "content": "SELECT c1.lead_lawyer_id,\n       c1.case_name AS case_name_1,\n       c2.case_name AS case_name_2\nFROM legal_services.cases c1\nJOIN legal_services.cases c2\n  ON c1.lead_lawyer_id = c2.lead_lawyer_id\n  AND c1.case_id < c2.case_id;"}, {"role": "user", "content": "Actually, only include pairs where the case types are also the same."}, {"role": "assistant", "content": "SELECT c1.lead_lawyer_id,\n       c1.case_name AS case_name_1,\n       c2.case_name AS case_name_2\nFROM legal_services.cases c1\nJOIN legal_services.cases c2\n  ON c1.lead_lawyer_id = c2.lead_lawyer_id\n  AND c1.case_type = c2.case_type\n  AND c1.case_id < c2.case_id;"}, {"role": "user", "content": "Also, show me the earliest opening date between the two cases for each pair."}, {"role": "assistant", "content": "SELECT c1.lead_lawyer_id,\n       c1.case_name AS case_name_1,\n       c2.case_name AS case_name_2,\n       LEAST(c1.date_opened, c2.date_opened) AS earliest_open_date\nFROM legal_services.cases c1\nJOIN legal_services.cases c2\n  ON c1.lead_lawyer_id = c2.lead_lawyer_id\n  AND c1.case_type = c2.case_type\n  AND c1.case_id < c2.case_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.cases ( case_id text, case_number text, case_name text, client_id text, lead_lawyer_id text, case_type text, status text, date_opened timestamp, date_closed timestamp, description text, court_jurisdiction text )\n"}
{"conversations": [{"role": "user", "content": "For each group chat, list its ID, name, creation time, and the creation time of the next group chat created after it, ordered by creation time."}, {"role": "assistant", "content": "SELECT conversation_id, group_name, created_at, LEAD(created_at) OVER (ORDER BY created_at) AS next_group_chat_created_at FROM social_media.conversations WHERE is_group_chat = true ORDER BY created_at;"}, {"role": "user", "content": "Only show pairs where the next group chat was created within 48 hours of the current one, and also include the time difference in hours."}, {"role": "assistant", "content": "WITH RankedGroupChats AS ( SELECT conversation_id, group_name, created_at, LEAD(created_at) OVER (ORDER BY created_at) AS next_group_chat_created_at FROM social_media.conversations WHERE is_group_chat = true ) SELECT conversation_id, group_name, created_at, next_group_chat_created_at, EXTRACT(EPOCH FROM (next_group_chat_created_at - created_at)) / 3600 AS time_difference_hours FROM RankedGroupChats WHERE next_group_chat_created_at IS NOT NULL AND EXTRACT(EPOCH FROM (next_group_chat_created_at - created_at)) <= 48 * 3600 ORDER BY created_at;"}, {"role": "user", "content": "Further refine: Only include group chats whose names contain 'Discuss'."}, {"role": "assistant", "content": "WITH RankedGroupChats AS ( SELECT conversation_id, group_name, created_at, LEAD(created_at) OVER (ORDER BY created_at) AS next_group_chat_created_at FROM social_media.conversations WHERE is_group_chat = true ) SELECT conversation_id, group_name, created_at, next_group_chat_created_at, EXTRACT(EPOCH FROM (next_group_chat_created_at - created_at)) / 3600 AS time_difference_hours FROM RankedGroupChats WHERE next_group_chat_created_at IS NOT NULL AND EXTRACT(EPOCH FROM (next_group_chat_created_at - created_at)) <= 48 * 3600 AND group_name LIKE '%Discuss%' ORDER BY created_at;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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": "How many group chats have been created since January 1, 2024?"}, {"role": "assistant", "content": "SELECT COUNT(*) AS group_chat_count\nFROM social_media.conversations\nWHERE is_group_chat = TRUE\n  AND created_at >= '2024-01-01';"}], "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 social_media.posts ( post_id text, user_id text, content text, media_url text, media_type text, created_at timestamp, updated_at timestamp, visibility text, location_lat numeric, location_lon numeric )\nCREATE TABLE social_media.likes ( like_id text, user_id text, post_id text, comment_id text, created_at timestamp )\nCREATE TABLE social_media.hashtags ( hashtag_id text, tag_name text, created_at timestamp )\nCREATE TABLE social_media.conversations ( conversation_id text, created_at timestamp, last_message_at timestamp, is_group_chat boolean, group_name text )\n"}
{"conversations": [{"role": "user", "content": "Show the total value and total gas used for all transactions occurring in each distinct year."}, {"role": "assistant", "content": "SELECT EXTRACT(YEAR FROM timestamp) AS transaction_year, SUM(value) AS total_value, SUM(gas_used) AS total_gas_used FROM web3.transactions GROUP BY EXTRACT(YEAR FROM timestamp) ORDER BY transaction_year;"}, {"role": "user", "content": "Can you also include the count of transactions for each year, but only show years where the total value exceeds 1000?"}, {"role": "assistant", "content": "SELECT EXTRACT(YEAR FROM timestamp) AS transaction_year, COUNT(transaction_id) AS transaction_count, SUM(value) AS total_value, SUM(gas_used) AS total_gas_used FROM web3.transactions GROUP BY EXTRACT(YEAR FROM timestamp) HAVING SUM(value) > 1000 ORDER BY transaction_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 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 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 each user_id and the date of their latest log."}, {"role": "assistant", "content": "SELECT user_id, MAX(logged_at) AS latest_log\nFROM trading_platform.logs\nGROUP BY user_id;"}, {"role": "user", "content": "Please also show the total number of logs for each user_id in the result."}, {"role": "assistant", "content": "SELECT user_id, MAX(logged_at) AS latest_log, COUNT(*) AS log_count\nFROM trading_platform.logs\nGROUP BY user_id;"}, {"role": "user", "content": "Only include users who have more than one log entry."}, {"role": "assistant", "content": "SELECT user_id, MAX(logged_at) AS latest_log, COUNT(*) AS log_count\nFROM trading_platform.logs\nGROUP BY user_id\nHAVING COUNT(*) > 1;"}, {"role": "user", "content": "Instead, sort the result by latest_log in descending order."}, {"role": "assistant", "content": "SELECT user_id, MAX(logged_at) AS latest_log, COUNT(*) AS log_count\nFROM trading_platform.logs\nGROUP BY user_id\nHAVING COUNT(*) > 1\nORDER BY latest_log 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.utxos (\n    utxo_id character varying(64) NOT NULL,  -- unique identifier for the UTXO\n    transaction_id character varying(64) NOT NULL, -- identifier of the transaction that created the UTXO\n    output_index integer NOT NULL, -- index of the output in the transaction\n    address character varying(128) NOT NULL, -- address that can spend the UTXO\n    amount numeric(38,14) NOT NULL, -- amount of the asset in the UTXO\n    spent boolean NOT NULL, -- whether the UTXO has been spent\n    PRIMARY KEY (utxo_id)\n)\nCREATE TABLE trading_platform.dapps (\n    dapp_id character varying(64) NOT NULL,  -- unique identifier for the DApp\n    name character varying(128) NOT NULL, -- name of the DApp\n    description text NOT NULL, -- description of the DApp\n    url character varying(256) NOT NULL, -- URL of the DApp\n    PRIMARY KEY (dapp_id)\n)\nCREATE TABLE trading_platform.metadata (\n    metadata_id character varying(64) NOT NULL,  -- unique identifier for the metadata\n    asset_id character varying(64) NOT NULL, -- identifier of the asset the metadata is associated with\n    key character varying(128) NOT NULL, -- key of the metadata\n    value text NOT NULL, -- value of the metadata\n    PRIMARY KEY (metadata_id)\n)\nCREATE TABLE trading_platform.logs (\n    log_id character varying(64) NOT NULL,  -- unique identifier for the log entry\n    user_id character varying(64), -- identifier of the user associated with the log entry\n    action character varying(128) NOT NULL, -- action performed\n    details text NOT NULL, -- details of the action\n    logged_at timestamp NOT NULL, -- time when the log entry was created\n    PRIMARY KEY (log_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Show me all trips that were delayed by more than 1 hour, including their vehicle and driver IDs, along with the origin and destination location IDs."}, {"role": "assistant", "content": "SELECT trip_id, vehicle_id, driver_id, origin_location_id, destination_location_id FROM transportation.trips WHERE EXTRACT(EPOCH FROM (actual_departure - scheduled_departure))/3600 > 1 AND status = 'Completed';"}, {"role": "user", "content": "Now include the passenger count for these trips, but only show trips that had more than 5 passengers."}, {"role": "assistant", "content": "SELECT trip_id, vehicle_id, driver_id, origin_location_id, destination_location_id, passenger_count FROM transportation.trips WHERE EXTRACT(EPOCH FROM (actual_departure - scheduled_departure))/3600 > 1 AND status = 'Completed' AND passenger_count > 5;"}, {"role": "user", "content": "Can you order these results by the delay time in descending order, showing the longest delays first?"}, {"role": "assistant", "content": "SELECT trip_id, vehicle_id, driver_id, origin_location_id, destination_location_id, passenger_count, (actual_departure - scheduled_departure) AS delay_time FROM transportation.trips WHERE EXTRACT(EPOCH FROM (actual_departure - scheduled_departure))/3600 > 1 AND status = 'Completed' AND passenger_count > 5 ORDER BY delay_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.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": "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": "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": "For each asset, show its name and symbol, and the total number of completed orders that have resulted in at least one trade."}, {"role": "assistant", "content": "SELECT a.name, a.symbol, COUNT(DISTINCT o.order_id) AS completed_order_count\nFROM trading_platform.assets a\nJOIN trading_platform.orders o ON o.asset_id = a.asset_id AND o.status = 'filled'\nJOIN trading_platform.trades t ON t.order_id = o.order_id\nGROUP BY a.asset_id, a.name, a.symbol;"}, {"role": "user", "content": "Only include assets where the total number of completed orders with trades is greater than 5, and sort the results by completed_order_count descending."}, {"role": "assistant", "content": "SELECT a.name, a.symbol, COUNT(DISTINCT o.order_id) AS completed_order_count\nFROM trading_platform.assets a\nJOIN trading_platform.orders o ON o.asset_id = a.asset_id AND o.status = 'filled'\nJOIN trading_platform.trades t ON t.order_id = o.order_id\nGROUP BY a.asset_id, a.name, a.symbol\nHAVING COUNT(DISTINCT o.order_id) > 5\nORDER BY completed_order_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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 (\n    trade_id character varying(64) NOT NULL,  -- unique identifier for the trade\n    order_id character varying(64) NOT NULL, -- identifier of the order that led to the trade\n    buyer_id character varying(64) NOT NULL, -- identifier of the buyer\n    seller_id character varying(64) NOT NULL, -- identifier of the seller\n    asset_id character varying(64) NOT NULL, -- identifier of the asset being traded\n    quantity numeric(38,14) NOT NULL, -- quantity of the asset in the trade\n    price numeric(38,14) NOT NULL, -- price per unit of the asset\n    traded_at timestamp NOT NULL, -- time when the trade was executed\n    PRIMARY KEY (trade_id)\n)\nCREATE TABLE trading_platform.assets ( asset_id text, 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.kyc_audit (\n    kyc_audit_id character varying(64) NOT NULL,  -- unique identifier for the KYC audit\n    user_id character varying(64) NOT NULL, -- identifier of the user being audited\n    status character varying(32) NOT NULL, -- status of the KYC audit (e.g., pending, approved, rejected)\n    reviewed_at timestamp NOT NULL, -- time when the KYC audit was reviewed\n    PRIMARY KEY (kyc_audit_id)\n)\nCREATE TABLE trading_platform.notifications ( notification_id.text, user_id.text, message.text, sent_at.timestamp, read_at.timestamp )\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": "List all patients who have non-primary insurance plans from providers containing 'Care' in their name, including the policy number and expiration date."}, {"role": "assistant", "content": "SELECT pi.patient_id, pi.policy_number, pi.expiration_date FROM healthcare.patient_insurance pi JOIN healthcare.insurance_plans ip ON pi.plan_id = ip.plan_id WHERE pi.is_primary = false AND ip.insurance_provider LIKE '%Care%';"}, {"role": "user", "content": "Actually, I need to see only those plans that will expire within the next 90 days."}, {"role": "assistant", "content": "SELECT pi.patient_id, pi.policy_number, pi.expiration_date FROM healthcare.patient_insurance pi JOIN healthcare.insurance_plans ip ON pi.plan_id = ip.plan_id WHERE pi.is_primary = false AND ip.insurance_provider LIKE '%Care%' AND pi.expiration_date BETWEEN CURRENT_DATE AND (CURRENT_DATE + INTERVAL '90 days');"}, {"role": "user", "content": "Can you also include the insurance provider name in the results?"}, {"role": "assistant", "content": "SELECT pi.patient_id, ip.insurance_provider, pi.policy_number, pi.expiration_date FROM healthcare.patient_insurance pi JOIN healthcare.insurance_plans ip ON pi.plan_id = ip.plan_id WHERE pi.is_primary = false AND ip.insurance_provider LIKE '%Care%' AND pi.expiration_date BETWEEN CURRENT_DATE AND (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 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.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, plan_name.text, insurance_provider.text, plan_type.text, contact_phone.text, website.text )\nCREATE TABLE healthcare.patient_insurance (\n    patient_insurance_id character varying(64) NOT NULL, -- unique identifier for this patient-plan link\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    plan_id character varying(64) NOT NULL, -- FK to insurance_plans table\n    policy_number character varying(100) NOT NULL, -- patient's policy number\n    group_number character varying(100), -- group number, if applicable\n    subscriber_name character varying(200), -- name of the primary policy holder\n    effective_date date NOT NULL, -- date the coverage begins\n    expiration_date date, -- date the coverage ends (if known)\n    is_primary boolean NOT NULL DEFAULT true, -- indicates if this is the primary insurance\n    PRIMARY KEY (patient_insurance_id),\n    UNIQUE (patient_id, plan_id, policy_number) -- ensure a patient doesn't have the same policy twice\n)\n"}
{"conversations": [{"role": "user", "content": "Find all patients who have been prescribed medications with dosage greater than 50mg, along with their medication details and prescribing doctor's name."}, {"role": "assistant", "content": "SELECT p.patient_id, p.first_name, p.last_name, pr.dosage, pr.medication_id, pr.start_date, doc.first_name AS doctor_first_name, doc.last_name AS doctor_last_name FROM healthcare.patients p JOIN healthcare.prescriptions pr ON p.patient_id = pr.patient_id JOIN healthcare.doctors doc ON pr.doctor_id = doc.doctor_id WHERE CAST(SUBSTRING_INDEX(pr.dosage, 'mg', 1) AS UNSIGNED) > 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.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.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.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": "Calculate the total quantity traded for each asset, showing the asset name and symbol."}, {"role": "assistant", "content": "SELECT T1.name, T1.symbol, SUM(T2.quantity) FROM trading_platform.assets AS T1 JOIN trading_platform.trades AS T2 ON T1.asset_id = T2.asset_id GROUP BY 1, 2;"}, {"role": "user", "content": "Only show assets where the total quantity traded is more than 5000."}, {"role": "assistant", "content": "SELECT T1.name, T1.symbol, SUM(T2.quantity) FROM trading_platform.assets AS T1 JOIN trading_platform.trades AS T2 ON T1.asset_id = T2.asset_id GROUP BY 1, 2 HAVING SUM(T2.quantity) > 5000;"}, {"role": "user", "content": "Actually, instead of total quantity, show the average trade price for each asset."}, {"role": "assistant", "content": "SELECT T1.name, T1.symbol, AVG(T2.price) FROM trading_platform.assets AS T1 JOIN trading_platform.trades AS T2 ON T1.asset_id = T2.asset_id GROUP BY 1, 2;"}, {"role": "user", "content": "Sort those assets by the average price in descending order."}, {"role": "assistant", "content": "SELECT T1.name, T1.symbol, AVG(T2.price) FROM trading_platform.assets AS T1 JOIN trading_platform.trades AS T2 ON T1.asset_id = T2.asset_id GROUP BY 1, 2 ORDER BY AVG(T2.price) DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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 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 ( dapp_id text, name text, description text, url text )\nCREATE TABLE trading_platform.peers ( peer_id.text, ip_address.text, port.integer, last_seen.timestamp )\nCREATE TABLE trading_platform.metadata ( metadata_id 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.kyc_audit ( kyc_audit_id.text, 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, user_id text, message text, sent_at timestamp, read_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "List all employees who are currently active and were hired before 2022. Show employee_id, first_name, last_name, job_title, department, and hire_date."}, {"role": "assistant", "content": "SELECT\n  employee_id,\n  first_name,\n  last_name,\n  job_title,\n  department,\n  hire_date\nFROM financial_services.employees\nWHERE\n  status = 'Active' AND hire_date < '2022-01-01';"}, {"role": "user", "content": "Also, only include employees from the 'IT' or 'Operations' departments."}, {"role": "assistant", "content": "SELECT\n  employee_id,\n  first_name,\n  last_name,\n  job_title,\n  department,\n  hire_date\nFROM financial_services.employees\nWHERE\n  status = 'Active' AND hire_date < '2022-01-01' AND department IN ('IT', 'Operations');"}, {"role": "user", "content": "Sort the results by hire date ascending and limit to the first 5."}, {"role": "assistant", "content": "SELECT\n  employee_id,\n  first_name,\n  last_name,\n  job_title,\n  department,\n  hire_date\nFROM financial_services.employees\nWHERE\n  status = 'Active' AND hire_date < '2022-01-01' AND department IN ('IT', 'Operations')\nORDER BY\n  hire_date ASC\nLIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.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": "Can you show me the total number of passengers registered in the database?"}, {"role": "assistant", "content": "db.passengers.countDocuments({})"}], "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('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"}
{"conversations": [{"role": "user", "content": "Show me all insurance plans that have more than 3 patients enrolled as their primary insurance, along with the provider name and count of patients, sorted by patient count in descending order."}, {"role": "assistant", "content": "SELECT 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.insurance_provider HAVING COUNT(pi.patient_id) > 3 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 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 (\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 ( 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, 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.insurance_plans ( plan_id.text, plan_name.text, insurance_provider.text, plan_type.text, contact_phone.text, website.text )\nCREATE TABLE healthcare.patient_insurance (\n    patient_insurance_id character varying(64) NOT NULL, -- unique identifier for this patient-plan link\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    plan_id character varying(64) NOT NULL, -- FK to insurance_plans table\n    policy_number character varying(100) NOT NULL, -- patient's policy number\n    group_number character varying(100), -- group number, if applicable\n    subscriber_name character varying(200), -- name of the primary policy holder\n    effective_date date NOT NULL, -- date the coverage begins\n    expiration_date date, -- date the coverage ends (if known)\n    is_primary boolean NOT NULL DEFAULT true, -- indicates if this is the primary insurance\n    PRIMARY KEY (patient_insurance_id),\n    UNIQUE (patient_id, plan_id, policy_number) -- ensure a patient doesn't have the same policy twice\n)\n"}
{"conversations": [{"role": "user", "content": "Which narrative and chain combination saw the highest total USD buy value in the first half of 2023? Also list the total token amount bought for each."}, {"role": "assistant", "content": "SELECT narrative, chain, SUM(usd_value) AS total_usd_bought, SUM(token_amount) AS total_token_bought\nFROM smart_money_token_inflow\nWHERE type = 1 AND to_char(cast(token_address AS text), 'YYYY-MM-DD') >= '2023-01-01' \n  AND to_char(cast(token_address AS text), 'YYYY-MM-DD') <= '2023-06-30'\nGROUP BY narrative, chain\nORDER BY total_usd_bought DESC\nLIMIT 1;"}, {"role": "user", "content": "Can you show the top 5 combinations instead of just the top one?"}, {"role": "assistant", "content": "SELECT narrative, chain, SUM(usd_value) AS total_usd_bought, SUM(token_amount) AS total_token_bought\nFROM smart_money_token_inflow\nWHERE type = 1 AND to_char(cast(token_address AS text), 'YYYY-MM-DD') >= '2023-01-01' \n  AND to_char(cast(token_address AS text), 'YYYY-MM-DD') <= '2023-06-30'\nGROUP BY narrative, chain\nORDER BY total_usd_bought DESC\nLIMIT 5;"}, {"role": "user", "content": "Please add the average price paid for each narrative-chain pair in the result."}, {"role": "assistant", "content": "SELECT narrative, chain, SUM(usd_value) AS total_usd_bought, SUM(token_amount) AS total_token_bought, AVG(avg_price) AS avg_price\nFROM smart_money_token_inflow\nWHERE type = 1 AND to_char(cast(token_address AS text), 'YYYY-MM-DD') >= '2023-01-01' \n  AND to_char(cast(token_address AS text), 'YYYY-MM-DD') <= '2023-06-30'\nGROUP BY narrative, chain\nORDER BY total_usd_bought DESC\nLIMIT 5;"}, {"role": "user", "content": "Now limit only to combinations where the total token amount bought is greater than 1000."}, {"role": "assistant", "content": "SELECT narrative, chain, SUM(usd_value) AS total_usd_bought, SUM(token_amount) AS total_token_bought, AVG(avg_price) AS avg_price\nFROM smart_money_token_inflow\nWHERE type = 1 AND to_char(cast(token_address AS text), 'YYYY-MM-DD') >= '2023-01-01'\n  AND to_char(cast(token_address AS text), 'YYYY-MM-DD') <= '2023-06-30'\nGROUP BY narrative, chain\nHAVING SUM(token_amount) > 1000\nORDER BY total_usd_bought 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 smart_money_token_inflow ( token_address character varying(100) NOT NULL, -- the token's address token_symbol character varying(100), -- the tokens's symbol token_amount numeric(38,2), -- the absolute value of the amount if user bought minus  the amount user sold of this token usd_value numeric(38,2), -- the absolute usd value of the bought token minus sold token avg_price numeric(38,6), -- the average cost price of user spent on this token type int, -- the direction of the trade on this token. 1 means buying, 2 means selling address_amount integer, -- the amount of the user bought this token narrative character varying(100), -- the category or narrative of the token chain character varying(100), -- the chain that the token resides ,PRIMARY KEY (token_address, chain) )\n"}
{"conversations": [{"role": "user", "content": "Find the service locations that are not accessible and located in the state of 'California'. List their name, address, and city."}, {"role": "assistant", "content": "SELECT location_name ,  address ,  city FROM government_services.service_locations WHERE is_accessible = false AND state = 'California'"}], "system": "You are an SQL statement expert. Given the table structure 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.service_locations ( location_id text, agency_id text, location_name text, address text, city text, state text, postal_code text, latitude numeric, longitude numeric, operating_hours text, contact_phone text, is_accessible boolean )\n"}
{"conversations": [{"role": "user", "content": "Count the number of transactions for each block that was created in 2023 and has a difficulty greater than 1000. Show the block ID and the transaction count."}, {"role": "assistant", "content": "SELECT B.block_id, COUNT(T.transaction_id) AS transaction_count FROM blockchain.blocks AS B JOIN blockchain.transactions AS T ON B.block_id = T.block_id WHERE B.timestamp >= '2023-01-01' AND B.timestamp < '2024-01-01' AND B.difficulty > 1000 GROUP BY B.block_id"}, {"role": "user", "content": "Only show blocks from that list that have more than 50 transactions."}, {"role": "assistant", "content": "SELECT B.block_id, COUNT(T.transaction_id) AS transaction_count FROM blockchain.blocks AS B JOIN blockchain.transactions AS T ON B.block_id = T.block_id WHERE B.timestamp >= '2023-01-01' AND B.timestamp < '2024-01-01' AND B.difficulty > 1000 GROUP BY B.block_id HAVING COUNT(T.transaction_id) > 50"}, {"role": "user", "content": "For those blocks, also include the total amount of all transactions within each block, and order the results by transaction count descending."}, {"role": "assistant", "content": "SELECT B.block_id, COUNT(T.transaction_id) AS transaction_count, SUM(T.amount) AS total_amount FROM blockchain.blocks AS B JOIN blockchain.transactions AS T ON B.block_id = T.block_id WHERE B.timestamp >= '2023-01-01' AND B.timestamp < '2024-01-01' AND B.difficulty > 1000 GROUP BY B.block_id HAVING COUNT(T.transaction_id) > 50 ORDER BY transaction_count DESC"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nCREATE TABLE blockchain.blocks ( block_id character varying(64) NOT NULL, previous_block_id character varying(64), timestamp timestamp NOT NULL, nonce integer NOT NULL, merkle_root character varying(128) NOT NULL, difficulty integer NOT NULL, PRIMARY KEY (block_id) )\nCREATE TABLE blockchain.transactions ( transaction_id character varying(64) NOT NULL, block_id character varying(64) NOT NULL, sender_address character varying(128) NOT NULL, receiver_address character varying(128) NOT NULL, amount numeric(38,14) NOT NULL, timestamp timestamp NOT NULL, signature text NOT NULL, PRIMARY KEY (transaction_id) )\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) )\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": "Show me all active loans (loan_id, loan_type, principal_amount) where the remaining term is between 12 and 24 months, along with their account_id and monthly_payment."}, {"role": "assistant", "content": "SELECT loan_id, loan_type, principal_amount, account_id, monthly_payment FROM financial_services.loans WHERE status = 'Active' AND (maturity_date - CURRENT_DATE) BETWEEN 365 AND 730;"}, {"role": "user", "content": "Now modify the query to only include loans with a principal_amount greater than $50,000 and sort them by remaining term in ascending order."}, {"role": "assistant", "content": "SELECT loan_id, loan_type, principal_amount, account_id, monthly_payment FROM financial_services.loans WHERE status = 'Active' AND (maturity_date - CURRENT_DATE) BETWEEN 365 AND 730 AND principal_amount > 50000 ORDER BY (maturity_date - CURRENT_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.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": "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": "List all managers (employees who have other employees reporting to them) along with the count of their direct reports, showing only those with more than 5 reports."}, {"role": "assistant", "content": "SELECT e.employee_id, e.first_name, e.last_name, COUNT(r.employee_id) as direct_reports_count FROM financial_services.employees e JOIN financial_services.employees r ON e.employee_id = r.manager_id WHERE e.status = 'Active' GROUP BY e.employee_id, e.first_name, e.last_name HAVING COUNT(r.employee_id) > 5 ORDER BY direct_reports_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.employees ( employee_id text PRIMARY KEY, first_name text, last_name text, job_title text, department text, branch_id text, email text, phone_extension text, hire_date date, termination_date date, manager_id text, status text )\n"}
{"conversations": [{"role": "user", "content": "List all smoking rooms, showing the property name, room number, and room type name."}, {"role": "assistant", "content": "SELECT T1.property_name, T2.room_number, T3.type_name FROM hospitality_technology.properties AS T1 JOIN hospitality_technology.rooms AS T2 ON T1.property_id = T2.property_id JOIN hospitality_technology.room_types AS T3 ON T2.room_type_id = T3.room_type_id WHERE T2.is_smoking = 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 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)\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": "Show me all wallet addresses that belong to user_id 'U1001', along with their private keys."}, {"role": "assistant", "content": "SELECT address_id, private_key FROM blockchain.wallets WHERE user_id = 'U1001';"}, {"role": "user", "content": "Now join this with another table to show the count of transactions for each of these wallet addresses."}, {"role": "assistant", "content": "Note: The schema only includes the wallets table. Without a transactions table in the schema, this query cannot be executed. Please provide the transactions table structure if you need this analysis."}], "system": "You are an SQL statement expert. Given the table structure 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": "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": "Which games have achievements where the points value is exactly 0? List the game title and the achievement name."}, {"role": "assistant", "content": "SELECT g.title AS game_title, a.name AS achievement_name\nFROM gaming_technology.achievements a\nJOIN gaming_technology.games g ON a.game_id = g.game_id\nWHERE a.points = 0;"}, {"role": "user", "content": "Show also the achievement's description and whether it is hidden."}, {"role": "assistant", "content": "SELECT g.title AS game_title, a.name AS achievement_name, a.description, a.hidden\nFROM gaming_technology.achievements a\nJOIN gaming_technology.games g ON a.game_id = g.game_id\nWHERE a.points = 0;"}, {"role": "user", "content": "Only show achievements released in games before 2020."}, {"role": "assistant", "content": "SELECT g.title AS game_title, a.name AS achievement_name, a.description, a.hidden\nFROM gaming_technology.achievements a\nJOIN gaming_technology.games g ON a.game_id = g.game_id\nWHERE a.points = 0 AND g.release_date < '2020-01-01';"}, {"role": "user", "content": "Sort the results by game_title ascending, then achievement_name ascending."}, {"role": "assistant", "content": "SELECT g.title AS game_title, a.name AS achievement_name, a.description, a.hidden\nFROM gaming_technology.achievements a\nJOIN gaming_technology.games g ON a.game_id = g.game_id\nWHERE a.points = 0 AND g.release_date < '2020-01-01'\nORDER BY g.title ASC, a.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 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": "Count the total number of invoices issued in each calendar year and month. Show the year, month, and the count, ordered chronologically."}, {"role": "assistant", "content": "SELECT EXTRACT(YEAR FROM issue_date) AS issue_year, EXTRACT(MONTH FROM issue_date) AS issue_month, COUNT(*) AS invoice_count FROM legal_services.invoices GROUP BY issue_year, issue_month ORDER BY issue_year, issue_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 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": "List all vehicles and their last maintenance service date along with the odometer reading, including only those that have not had a fuel refill in the past 30 days."}, {"role": "assistant", "content": "SELECT m.vehicle_id,\n       m.last_service_date,\n       m.last_odometer\nFROM (\n  SELECT l.vehicle_id,\n         MAX(l.service_date) AS last_service_date,\n         (SELECT odometer_reading\n          FROM transportation.maintenance_logs\n          WHERE vehicle_id = l.vehicle_id\n          ORDER BY service_date DESC\n          LIMIT 1) AS last_odometer\n  FROM transportation.maintenance_logs l\n  GROUP BY l.vehicle_id\n) AS m\nLEFT JOIN (\n  SELECT fl.vehicle_id,\n         MAX(fl.log_timestamp) AS last_fuel_date\n  FROM transportation.fuel_logs fl\n  GROUP BY fl.vehicle_id\n) AS f ON m.vehicle_id = f.vehicle_id\nWHERE COALESCE(f.last_fuel_date, '1900-01-01'::timestamp) < NOW() - 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.routes ( route_id character varying(64) NOT NULL, route_number character varying(32) NOT NULL UNIQUE, description text, origin_location_id character varying(64) NOT NULL, destination_location_id character varying(64) NOT NULL, distance_km numeric(10, 2), estimated_duration_minutes integer, type character varying(32) NOT NULL, PRIMARY KEY (route_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.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.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.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": "List all ERC20 tokens where the price is between $1 and $10, including their names, symbols, and contract addresses."}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address FROM token_metas tm JOIN token_prices_latest tpl ON tm.contract_address = tpl.contract_address WHERE tm.is_erc20 = 1 AND tpl.price BETWEEN 1 AND 10;"}, {"role": "user", "content": "I think there's an error in your query - the token_prices_latest table isn't in the schema. Can you modify it to use the token_balances table instead?"}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address FROM token_metas tm JOIN token_balances tb ON tm.contract_address = tb.wallet_address WHERE tm.is_erc20 = 1 AND CAST(tb.amount AS decimal) BETWEEN 1 AND 10;"}, {"role": "user", "content": "That doesn't seem right either. Let's just get the basic ERC20 token information without price filtering for now."}, {"role": "assistant", "content": "SELECT name, symbol, contract_address FROM token_metas WHERE is_erc20 = 1 LIMIT 100;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp.timestamp, block_number.bigint, transaction_hash.text, transaction_index.bigint, from_address.text, contract_address.text, symbol.text, total_supply.text, name.text, decimals.bigint, is_erc20.integer, is_erc721.integer, is_erc1155.integer, is_proxy.integer, extra_info.text, pk.integer )\nCREATE TABLE erc1155_approval_for_all ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar(66) NOT NULL, log_index integer NOT NULL, contract_address varchar(42) NOT NULL )\nCREATE TABLE erc20_balances ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE erc20_balances_historical ( block_number bigint, contract_address text, wallet_address text, amount text, pk integer )\nCREATE TABLE nft_holders ( block_number bigint, contract_address text, wallet_address text, token_id text, contract_type text, amount text, pk text )\nCREATE TABLE nft_holder_historical ( block_number.bigint, contract_address.text, wallet_address.text, token_id.text, contract_type.text, amount.text, pk.integer )\nCREATE TABLE sui_nfts ( object_id text, status text, collection_type text, package_id text, previous_transaction text, display text, owner text, name text )\nCREATE TABLE nft_collections ( blockchain text, contract_address text, name text, symbol text, deploy_block_number bigint, deploy_block_time bigint, erc_type text, owner text, traits text, description text, slug text, media_info text, image_url text, banner_image_url text, updated_at bigint, banner text, token_count bigint, floor_price text, floor_price_symbol text, floor_price_contract text, pk integer )\nCREATE TABLE erc20_approval ( block_number bigint NOT NULL, block_timestamp timestamp(6) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar NOT NULL, log_index integer NOT NULL, contract_address varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_balances ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply decimal, amount decimal )\nCREATE TABLE token_info (\n    block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n    block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n    tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n    tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n    tick varchar NOT NULL, -- Token tick\n    max_supply decimal(38,0) NOT NULL, -- Max supply\n    lim decimal(38,0) NOT NULL, -- Limit of each mint\n    wlim decimal(38,0) NOT NULL, -- Limit of each address can maximum mint\n    dec integer NOT NULL, -- Decimal for minimum divie\n    creator varchar(42) NOT NULL  -- Address originating the inscription (matches from_address in transactions table)\n)\nCREATE TABLE token_activities ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\nCREATE TABLE mud_holesky_redstone ( address varchar NOT NULL, table_id varchar NOT NULL, key_bytes varchar NOT NULL, key0 varchar NOT NULL, key1 varchar NOT NULL, static_data varchar NOT NULL, encoded_lengths varchar NOT NULL, dynamic_data varchar NOT NULL, is_deleted boolean NOT NULL, block_number bigint NOT NULL, log_index bigint NOT NULL )\nCREATE TABLE token_balances_bitcoin ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply varchar, amount varchar )\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar )\nCREATE TABLE token_activities_avalanche ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\nCREATE TABLE token_balances_avalanche (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n    tick varchar(20) NOT NULL, -- Ticker: Identifier of the inscription\n    wallet_address varchar(42) NOT NULL, -- Address of owner\n    total_supply decimal(38,0) NOT NULL, -- Max supply: Set max supply of the inscription\n    amount decimal(38,0) NOT NULL  -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id varchar )\n"}
{"conversations": [{"role": "user", "content": "What is the current number of passengers at station with ID 'ST123' right now?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information on the current number of passengers at a station. The data I have access to only includes static details about stations such as their name, location, and number of platforms, not real-time passenger counts."}], "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 (\n    station_id character varying(64) NOT NULL,  -- Unique identifier for the station\n    station_name character varying(128) NOT NULL, -- Name of the station\n    city character varying(100) NOT NULL, -- City where the station is located\n    state_province character varying(100), -- State or province\n    country_code character varying(3) NOT NULL, -- ISO country code\n    address text, -- Full address of the station\n    timezone character varying(64) NOT NULL, -- Timezone ID (e.g., 'America/New_York')\n    number_of_platforms integer NOT NULL DEFAULT 0, -- Total number of platforms\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- When the station record was created\n    last_updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- When the station record was last updated\n    PRIMARY KEY (station_id)\n)\n"}
{"conversations": [{"role": "user", "content": "How many claims were reported in the last 90 days?"}, {"role": "assistant", "content": "SELECT COUNT(*) FROM claims WHERE reported_date >= 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 insurance.policies ( policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, product_id character varying(64) NOT NULL, agent_id character varying(64), policy_number character varying(100) NOT NULL UNIQUE, start_date date NOT NULL, end_date date NOT NULL, premium_amount numeric(12, 2) NOT NULL, coverage_limit numeric(15, 2) NOT NULL, deductible numeric(10, 2) NOT NULL, status character varying(30) NOT NULL, issued_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, cancellation_date date, cancellation_reason text, PRIMARY KEY (policy_id) )\nCREATE TABLE insurance.claims ( claim_id character varying(64) NOT NULL, policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, incident_date timestamp NOT NULL, reported_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, description text NOT NULL, estimated_loss numeric(15, 2), status character varying(30) NOT NULL, settlement_amount numeric(15, 2), settlement_date date, claim_handler_id character varying(64), police_report_number character varying(100), PRIMARY KEY (claim_id) )\nCREATE TABLE insurance.insurance_products ( product_id character varying(64) NOT NULL, product_name character varying(150) NOT NULL, product_type character varying(50) NOT NULL, description text, base_premium numeric(10, 2) NOT NULL, coverage_details text, underwriting_rules text, is_active boolean NOT NULL DEFAULT true, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, updated_at timestamp, PRIMARY KEY (product_id) )\nCREATE TABLE insurance.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 )\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 )\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": "Show me the earliest created smart contract for each creator address."}, {"role": "assistant", "content": "SELECT sc1.contract_id, sc1.creator_address, sc1.timestamp FROM blockchain.smart_contracts sc1 WHERE sc1.timestamp = (SELECT MIN(sc2.timestamp) FROM blockchain.smart_contracts sc2 WHERE sc2.creator_address = sc1.creator_address);"}, {"role": "user", "content": "Now include the total number of contracts each creator has made alongside this information."}, {"role": "assistant", "content": "SELECT sc1.contract_id, sc1.creator_address, sc1.timestamp, (SELECT COUNT(*) FROM blockchain.smart_contracts sc2 WHERE sc2.creator_address = sc1.creator_address) AS total_contracts FROM blockchain.smart_contracts sc1 WHERE sc1.timestamp = (SELECT MIN(sc3.timestamp) FROM blockchain.smart_contracts sc3 WHERE sc3.creator_address = sc1.creator_address);"}, {"role": "user", "content": "Filter this to only show creators who have made at least 10 contracts."}, {"role": "assistant", "content": "SELECT sc1.contract_id, sc1.creator_address, sc1.timestamp, (SELECT COUNT(*) FROM blockchain.smart_contracts sc2 WHERE sc2.creator_address = sc1.creator_address) AS total_contracts FROM blockchain.smart_contracts sc1 WHERE sc1.timestamp = (SELECT MIN(sc3.timestamp) FROM blockchain.smart_contracts sc3 WHERE sc3.creator_address = sc1.creator_address) AND (SELECT COUNT(*) FROM blockchain.smart_contracts sc4 WHERE sc4.creator_address = sc1.creator_address) >= 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 blockchain.smart_contracts ( contract_id.text, creator_address.text, code.text, timestamp.timestamp )\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": "Show me the top 5 buyers by total trade volume (quantity * price) in the last 30 days, along with their trade count."}, {"role": "assistant", "content": "SELECT buyer_id, COUNT(trade_id) AS trade_count, SUM(quantity * price) AS total_volume FROM trading_platform.trades WHERE traded_at >= NOW() - INTERVAL '30 days' GROUP BY buyer_id ORDER BY total_volume DESC LIMIT 5"}, {"role": "user", "content": "Now modify the query to also include the average trade price for each buyer."}, {"role": "assistant", "content": "SELECT buyer_id, COUNT(trade_id) AS trade_count, SUM(quantity * price) AS total_volume, AVG(price) AS avg_price FROM trading_platform.trades WHERE traded_at >= NOW() - INTERVAL '30 days' GROUP BY buyer_id ORDER BY total_volume DESC LIMIT 5"}, {"role": "user", "content": "Actually, I want to see the results for sellers instead of buyers, and include the distinct asset count they traded."}, {"role": "assistant", "content": "SELECT seller_id, COUNT(trade_id) AS trade_count, COUNT(DISTINCT asset_id) AS distinct_assets, SUM(quantity * price) AS total_volume, AVG(price) AS avg_price FROM trading_platform.trades WHERE traded_at >= NOW() - INTERVAL '30 days' GROUP BY seller_id ORDER BY total_volume DESC LIMIT 5"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.trades ( trade_id character varying(64) NOT NULL, order_id character varying(64) NOT NULL, buyer_id character varying(64) NOT NULL, seller_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, quantity numeric(38,14) NOT NULL, price numeric(38,14) NOT NULL, traded_at timestamp NOT NULL, PRIMARY KEY (trade_id) )\n"}
{"conversations": [{"role": "user", "content": "Show me the total quantity traded and total amount for each security, identified by its ticker symbol, for trades in the last month."}, {"role": "assistant", "content": "SELECT T2.ticker_symbol, SUM(T1.quantity), SUM(T1.total_amount) FROM financial_services.trades AS T1 JOIN financial_services.securities AS T2 ON T1.security_id = T2.security_id WHERE T1.trade_timestamp >= DATE('now', '-1 month') GROUP BY 1"}, {"role": "user", "content": "Can you also show the average price per unit and filter to only include securities where the total quantity traded is greater than 5000?"}, {"role": "assistant", "content": "SELECT T2.ticker_symbol, SUM(T1.quantity), SUM(T1.total_amount), AVG(T1.price_per_unit) FROM financial_services.trades AS T1 JOIN financial_services.securities AS T2 ON T1.security_id = T2.security_id WHERE T1.trade_timestamp >= DATE('now', '-1 month') GROUP BY 1 HAVING SUM(T1.quantity) > 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.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) )\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": "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": "Find all contracts where the deployer address is the same as the contract address, indicating self-deployed contracts, and show their network IDs and deployment timestamps."}, {"role": "assistant", "content": "SELECT address, network_id, deployed_at FROM web3.contracts WHERE address = deployer_address;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.contracts ( contract_id character varying(64) NOT NULL, address character varying(128) NOT NULL, abi text NOT NULL, bytecode text NOT NULL, deployer_address character varying(128) NOT NULL, deployed_at timestamp NOT NULL, network_id character varying(64) NOT NULL, status character varying(32) NOT NULL, PRIMARY KEY (contract_id) )\n"}
{"conversations": [{"role": "user", "content": "List the first and last names of employees and the full name of the citizens for whom they have scheduled appointments."}, {"role": "assistant", "content": "SELECT T1.first_name ,  T1.last_name ,  T3.first_name ,  T3.last_name FROM government_services.employees AS T1 JOIN government_services.appointments AS T2 ON T1.employee_id  =  T2.employee_id JOIN government_services.citizens AS T3 ON T2.citizen_id  =  T3.citizen_id"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id text PRIMARY KEY, national_id_number text, first_name text, last_name text, date_of_birth date, gender text, primary_address text, contact_email text, contact_phone text, registration_date timestamp, is_verified boolean )\nCREATE TABLE government_services.agencies ( agency_id text PRIMARY KEY, agency_name text, jurisdiction_level text, primary_contact_email text, main_phone_number text, website_url text, established_date date, parent_agency_id text )\nCREATE TABLE government_services.services ( service_id text PRIMARY KEY, agency_id text, service_name text, description text, category text, eligibility_criteria text, standard_fee numeric, average_processing_time_days int, is_active boolean, online_application_url text )\nCREATE TABLE government_services.applications ( application_id text PRIMARY KEY, citizen_id text, service_id text, submitted_at timestamp, status text, last_updated_at timestamp, assigned_employee_id text, decision_date date, notes text, reference_number text )\nCREATE TABLE government_services.documents ( document_id text PRIMARY KEY, application_id text, citizen_id text, document_type text, file_reference text, upload_timestamp timestamp, expiry_date date, verification_status text, verified_by_employee_id text, verification_timestamp timestamp )\nCREATE TABLE government_services.payments ( payment_id text PRIMARY KEY, application_id text, citizen_id text, service_id text, amount numeric, currency text, payment_method text, payment_provider_reference text, payment_timestamp timestamp, status text, notes text )\nCREATE TABLE government_services.employees ( employee_id text PRIMARY KEY, agency_id text, first_name text, last_name text, job_title text, department text, work_email text, work_phone text, hire_date date, termination_date date, access_level text, manager_employee_id text )\nCREATE TABLE government_services.appointments ( appointment_id text PRIMARY KEY, citizen_id text, employee_id text, location_id text, service_id text, scheduled_start_time timestamp, scheduled_end_time timestamp, purpose text, status text, booking_method text, created_at timestamp, notes text )\nCREATE TABLE government_services.notifications ( notification_id text PRIMARY KEY, citizen_id text, application_id text, message_subject text, message_body text, channel text, sent_at timestamp, status text, related_entity_type text, related_entity_id text )\n"}
{"conversations": [{"role": "user", "content": "List game titles released on the 'PC' platform along with the count of servers currently hosting each game."}, {"role": "assistant", "content": "SELECT T1.title, count(T2.server_id) FROM games AS T1 JOIN servers AS T2 ON T1.game_id = T2.game_id WHERE T1.platform = 'PC' GROUP BY T1.title;"}, {"role": "user", "content": "Now, only show games with more than 3 servers and sort the results by the server count in descending order."}, {"role": "assistant", "content": "SELECT T1.title, count(T2.server_id) AS server_count FROM games AS T1 JOIN servers AS T2 ON T1.game_id = T2.game_id WHERE T1.platform = 'PC' GROUP BY T1.title HAVING count(T2.server_id) > 3 ORDER 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.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": "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": "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 me the top 5 NFT collections with the highest floor price on Ethereum, along with their names and contract addresses."}, {"role": "assistant", "content": "SELECT name, contract_address, floor_price FROM nft_collections WHERE blockchain = 'ethereum' ORDER BY CAST(floor_price AS decimal) DESC LIMIT 5;"}, {"role": "user", "content": "Can you also include the banner image URL and filter to only show ERC721 collections?"}, {"role": "assistant", "content": "SELECT name, contract_address, floor_price, banner_image_url FROM nft_collections WHERE blockchain = 'ethereum' AND erc_type = 'ERC721' ORDER BY CAST(floor_price AS decimal) DESC LIMIT 5;"}, {"role": "user", "content": "I think there's a typo in your query - it should be 'nft_collections' not 'nft_collections'. Also, can you join this with the nft_metadata table to include the average rarity score for these collections?"}, {"role": "assistant", "content": "SELECT nc.name, nc.contract_address, nc.floor_price, nc.banner_image_url, AVG(nm.rarity_score) as avg_rarity_score FROM nft_collections nc JOIN nft_metadata nm ON nc.contract_address = nm.contract_address WHERE nc.blockchain = 'ethereum' AND nc.erc_type = 'ERC721' GROUP BY nc.name, nc.contract_address, nc.floor_price, nc.banner_image_url ORDER BY CAST(nc.floor_price AS decimal) DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE erc1155_approval_for_all (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the transaction\n    transaction_index integer NOT NULL, -- Index of the transaction within the block\n    transaction_hash varchar(66) NOT NULL, -- Transaction hash\n    log_index integer NOT NULL, -- Log index\n    contract_address varchar(42) NOT NULL  -- Event contract address\n)\nCREATE TABLE erc20_balances ( block_number.bigint, contract_address.text, wallet_address.text, amount.text, pk.text )\nCREATE TABLE erc20_balances_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_metadata (\n    blockchain varchar NOT NULL, -- blockchain fields for the functionType  in contract\n    contract_address varchar NOT NULL, -- Contract address(with bloom filter)\n    token_id varchar NOT NULL, -- The number of the token\n    contract_name varchar NOT NULL, -- contract_name fields for the functionType  in contract\n    erc_type varchar NOT NULL, -- The type of token\n    amount bigint NOT NULL, -- amount fields for the functionType  in contract\n    minter varchar NOT NULL, -- minter fields for the functionType  in contract\n    owner varchar NOT NULL, -- owner fields for the functionType  in contract\n    mint_block_number bigint NOT NULL, -- mint_block_number fields for the functionType  in contract\n    mint_time bigint NOT NULL, -- mint_time fields for the functionType  in contract\n    mint_transaction_hash varchar NOT NULL, -- mint_transaction_hash fields for the functionType  in contract\n    mint_price varchar NOT NULL, -- mint_price fields for the functionType  in contract\n    token_uri varchar NOT NULL, -- token_uri fields for the functionType  in contract\n    metadata varchar NOT NULL, -- metadata fields for the functionType  in contract\n    name varchar NOT NULL, -- name fields for the functionType  in contract\n    image_uri varchar NOT NULL, -- image_uri fields for the functionType  in contract\n    traits varchar NOT NULL, -- traits fields for the functionType  in contract\n    updated_at bigint NOT NULL, -- updated_at fields for the functionType  in contract\n    status varchar NOT NULL, -- status fields for the functionType  in contract\n    rarity_score real NOT NULL, -- rarity_score fields for the functionType  in contract\n    rarity_rank integer NOT NULL, -- rarity_rank fields for the functionType  in contract\n    unique_attribute_count integer NOT NULL, -- unique_attribute_count fields for the functionType  in contract\n    pk integer NOT NULL  -- Partition key for the table(floor(mint_time / 1000 / 86400 / 30))\n)\nCREATE TABLE nft_collections ( blockchain.text, contract_address.text, name.text, symbol.text, deploy_block_number.bigint, deploy_block_time.bigint, erc_type.text, owner.text, traits.text, description.text, slug.text, media_info.text, image_url.text, banner_image_url.text, updated_at.bigint, banner.text, token_count.bigint, floor_price.text, floor_price_symbol.text, floor_price_contract.text, pk.integer )\nCREATE TABLE token_prices ( uuid varchar(36) NOT NULL, blockchain varchar(36) NOT NULL, address varchar(42) NOT NULL, decimals bigint NOT NULL, symbol varchar(36) NOT NULL, price real NOT NULL, timestamp timestamp(6) NOT NULL )\nCREATE TABLE erc20_approval ( block_number bigint NOT NULL, block_timestamp timestamp(6) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar NOT NULL, log_index integer NOT NULL, contract_address varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_info ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE mud_holesky_redstone (\n    address varchar NOT NULL, -- address fields for the functionType  in contract\n    table_id varchar NOT NULL, -- table_id fields for the functionType  in contract\n    key_bytes varchar NOT NULL, -- key_bytes fields for the functionType  in contract\n    key0 varchar NOT NULL, -- key0 fields for the functionType  in contract\n    key1 varchar NOT NULL, -- key1 fields for the functionType  in contract\n    static_data varchar NOT NULL, -- static_data fields for the functionType  in contract\n    encoded_lengths varchar NOT NULL, -- encoded_lengths fields for the functionType  in contract\n    dynamic_data varchar NOT NULL, -- dynamic_data fields for the functionType  in contract\n    is_deleted boolean NOT NULL, -- is_deleted fields for the functionType  in contract\n    block_number bigint NOT NULL, -- Block number uniquely identifying the block\n    log_index bigint NOT NULL  -- Index of the log within the transaction\n)\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar )\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id text )\n"}
{"conversations": [{"role": "user", "content": "For each reservation, show me the guest's full name, the property name, and the room type name."}, {"role": "assistant", "content": "SELECT r.reservation_id, g.first_name || ' ' || g.last_name AS guest_full_name, p.property_name, rt.type_name AS room_type_name\nFROM hospitality_technology.reservations r\nJOIN hospitality_technology.guests g ON r.guest_id = g.guest_id\nJOIN hospitality_technology.properties p ON r.property_id = p.property_id\nJOIN hospitality_technology.room_types rt ON r.room_type_id = rt.room_type_id;"}, {"role": "user", "content": "Can you only show those reservations where the number of children is at least 2, and order results by guest last name ascending?"}, {"role": "assistant", "content": "SELECT r.reservation_id, g.first_name || ' ' || g.last_name AS guest_full_name, p.property_name, rt.type_name AS room_type_name\nFROM hospitality_technology.reservations r\nJOIN hospitality_technology.guests g ON r.guest_id = g.guest_id\nJOIN hospitality_technology.properties p ON r.property_id = p.property_id\nJOIN hospitality_technology.room_types rt ON r.room_type_id = rt.room_type_id\nWHERE r.num_children >= 2\nORDER BY g.last_name ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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.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 )\n"}
{"conversations": [{"role": "user", "content": "List all customers who have two policies with overlapping coverage periods and show both policy numbers along with the overlap start and end dates."}, {"role": "assistant", "content": "SELECT p1.customer_id, p1.policy_number AS policy_number1, p2.policy_number AS policy_number2, GREATEST(p1.start_date, p2.start_date) AS overlap_start, LEAST(p1.end_date, p2.end_date) AS overlap_end FROM insurance.policies p1 JOIN insurance.policies p2 ON p1.customer_id = p2.customer_id AND p1.policy_id < p2.policy_id WHERE p1.start_date <= p2.end_date AND p2.start_date <= p1.end_date;"}, {"role": "user", "content": "Actually, I only want overlapping policies where both policies are currently active."}, {"role": "assistant", "content": "SELECT p1.customer_id, p1.policy_number AS policy_number1, p2.policy_number AS policy_number2, GREATEST(p1.start_date, p2.start_date) AS overlap_start, LEAST(p1.end_date, p2.end_date) AS overlap_end FROM insurance.policies p1 JOIN insurance.policies p2 ON p1.customer_id = p2.customer_id AND p1.policy_id < p2.policy_id WHERE p1.status = 'active' AND p2.status = 'active' AND p1.start_date <= p2.end_date AND p2.start_date <= p1.end_date;"}, {"role": "user", "content": "Also include the number of days of overlap as overlap_days."}, {"role": "assistant", "content": "SELECT p1.customer_id, p1.policy_number AS policy_number1, p2.policy_number AS policy_number2, GREATEST(p1.start_date, p2.start_date) AS overlap_start, LEAST(p1.end_date, p2.end_date) AS overlap_end, (LEAST(p1.end_date, p2.end_date) - GREATEST(p1.start_date, p2.start_date)) AS overlap_days FROM insurance.policies p1 JOIN insurance.policies p2 ON p1.customer_id = p2.customer_id AND p1.policy_id < p2.policy_id WHERE p1.status = 'active' AND p2.status = 'active' AND p1.start_date <= p2.end_date AND p2.start_date <= p1.end_date;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.policies ( policy_id text, customer_id text, product_id text, agent_id text, policy_number text, start_date date, end_date date, premium_amount numeric, coverage_limit numeric, deductible numeric, status text, issued_at timestamp, cancellation_date date, cancellation_reason text )\n"}
{"conversations": [{"role": "user", "content": "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": "Calculate the average number of days between when an incident occurred and when the claim was reported, but only for claims that were settled in the year 2023."}, {"role": "assistant", "content": "SELECT\n  AVG(EXTRACT(EPOCH FROM (reported_date - incident_date)) / 86400.0)::numeric(10, 2)\nFROM\n  insurance.claims\nWHERE\n  settlement_date IS NOT NULL AND EXTRACT(YEAR FROM settlement_date) = 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 insurance.claims (\n    claim_id character varying(64) NOT NULL, -- unique identifier for the claim\n    policy_id character varying(64) NOT NULL, -- identifier of the policy under which the claim is made (FK to policies)\n    customer_id character varying(64) NOT NULL, -- identifier of the customer making the claim (FK to customers)\n    incident_date timestamp NOT NULL, -- date and time of the incident leading to the claim\n    reported_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- date the claim was reported\n    description text NOT NULL, -- detailed description of the incident and claim\n    estimated_loss numeric(15, 2), -- initial estimated cost of the loss\n    status character varying(30) NOT NULL, -- e.g., Filed, Processing, Under Review, Approved, Denied, Settled\n    settlement_amount numeric(15, 2), -- final amount paid out\n    settlement_date date,\n    claim_handler_id character varying(64), -- identifier for the employee handling the claim (FK to employees/adjusters)\n    police_report_number character varying(100),\n    PRIMARY KEY (claim_id)\n)\n"}
{"conversations": [{"role": "user", "content": "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": "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 a report of each user with their username and the count of all log entries from the last 30 days."}, {"role": "assistant", "content": "SELECT u.user_id, u.username, COUNT(l.log_id) AS log_count\nFROM trading_platform.users u\nLEFT JOIN trading_platform.logs l\n  ON u.user_id = l.user_id\n  AND l.logged_at >= CURRENT_DATE - INTERVAL '30 days'\nGROUP BY u.user_id, u.username;"}, {"role": "user", "content": "Actually, show only logs where the action includes the word 'trade'."}, {"role": "assistant", "content": "SELECT u.user_id, u.username, COUNT(l.log_id) AS log_count\nFROM trading_platform.users u\nJOIN trading_platform.logs l\n  ON u.user_id = l.user_id\nWHERE l.logged_at >= CURRENT_DATE - INTERVAL '30 days'\n  AND l.action ILIKE '%trade%'\nGROUP BY u.user_id, u.username;"}, {"role": "user", "content": "Also include the earliest log date for each user in that period."}, {"role": "assistant", "content": "SELECT u.user_id,\n       u.username,\n       COUNT(l.log_id) AS log_count,\n       MIN(l.logged_at) AS first_log_date\nFROM trading_platform.users u\nJOIN trading_platform.logs l\n  ON u.user_id = l.user_id\nWHERE l.logged_at >= CURRENT_DATE - INTERVAL '30 days'\n  AND l.action ILIKE '%trade%'\nGROUP BY u.user_id, u.username;"}, {"role": "user", "content": "Finally, sort the results by log_count descending and limit to the top 5 users."}, {"role": "assistant", "content": "SELECT u.user_id,\n       u.username,\n       COUNT(l.log_id) AS log_count,\n       MIN(l.logged_at) AS first_log_date\nFROM trading_platform.users u\nJOIN trading_platform.logs l\n  ON u.user_id = l.user_id\nWHERE l.logged_at >= CURRENT_DATE - INTERVAL '30 days'\n  AND l.action ILIKE '%trade%'\nGROUP BY u.user_id, u.username\nORDER BY log_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 trading_platform.users (\n    user_id character varying(64) NOT NULL,  -- unique identifier for the user\n    username character varying(128) NOT NULL, -- username of the user\n    email character varying(128) NOT NULL, -- email address of the user\n    password_hash text NOT NULL, -- hashed password of the user\n    created_at timestamp NOT NULL, -- time when the user account was created\n    PRIMARY KEY (user_id)\n)\nCREATE TABLE trading_platform.orders (\n    order_id character varying(64) NOT NULL,  -- unique identifier for the order\n    user_id character varying(64) NOT NULL, -- identifier of the user placing the order\n    wallet_id character varying(64) NOT NULL, -- identifier of the wallet used for the order\n    asset_id character varying(64) NOT NULL, -- identifier of the asset being traded\n    order_type character varying(32) NOT NULL, -- type of the order (e.g., buy, sell)\n    quantity numeric(38,14) NOT NULL, -- quantity of the asset in the order\n    price numeric(38,14) NOT NULL, -- price per unit of the asset\n    status character varying(32) NOT NULL, -- status of the order (e.g., open, filled, canceled)\n    created_at timestamp NOT NULL, -- time when the order was created\n    PRIMARY KEY (order_id)\n)\nCREATE TABLE trading_platform.utxos (\n    utxo_id character varying(64) NOT NULL,  -- unique identifier for the UTXO\n    transaction_id character varying(64) NOT NULL, -- identifier of the transaction that created the UTXO\n    output_index integer NOT NULL, -- index of the output in the transaction\n    address character varying(128) NOT NULL, -- address that can spend the UTXO\n    amount numeric(38,14) NOT NULL, -- amount of the asset in the UTXO\n    spent boolean NOT NULL, -- whether the UTXO has been spent\n    PRIMARY KEY (utxo_id)\n)\nCREATE TABLE trading_platform.dapps (\n    dapp_id character varying(64) NOT NULL,  -- unique identifier for the DApp\n    name character varying(128) NOT NULL, -- name of the DApp\n    description text NOT NULL, -- description of the DApp\n    url character varying(256) NOT NULL, -- URL of the DApp\n    PRIMARY KEY (dapp_id)\n)\nCREATE TABLE trading_platform.peers (\n    peer_id character varying(64) NOT NULL,  -- unique identifier for the peer\n    ip_address character varying(15) NOT NULL, -- IP address of the peer\n    port integer NOT NULL, -- port number of the peer\n    last_seen timestamp NOT NULL, -- last time the peer was active\n    PRIMARY KEY (peer_id)\n)\nCREATE TABLE trading_platform.logs (\n    log_id character varying(64) NOT NULL,  -- unique identifier for the log entry\n    user_id character varying(64), -- identifier of the user associated with the log entry\n    action character varying(128) NOT NULL, -- action performed\n    details text NOT NULL, -- details of the action\n    logged_at timestamp NOT NULL, -- time when the log entry was created\n    PRIMARY KEY (log_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List all wallets holding the NFT with contract_address '0xabc123' and token_id '100' and the amount held."}, {"role": "assistant", "content": "SELECT wallet_address, amount\nFROM nft_holders\nWHERE contract_address = '0xabc123'\n  AND token_id = '100';"}, {"role": "user", "content": "Also include the NFT name from nft_metadata by joining on contract_address and token_id."}, {"role": "assistant", "content": "SELECT nh.wallet_address,\n       nh.amount,\n       nm.name\nFROM nft_holders nh\nJOIN nft_metadata nm ON nh.contract_address = nm.contract_address\n                   AND nh.token_id = nm.token_id\nWHERE nh.contract_address = '0xabc123'\n  AND nh.token_id = '100';"}, {"role": "user", "content": "Finally, add the collection name from nft_collections where blockchain is 'Ethereum'."}, {"role": "assistant", "content": "SELECT nh.wallet_address,\n       nh.amount,\n       nm.name,\n       nc.name AS collection_name\nFROM nft_holders nh\nJOIN nft_metadata nm ON nh.contract_address = nm.contract_address\n                   AND nh.token_id = nm.token_id\nJOIN nft_collections nc ON nh.contract_address = nc.contract_address\n                      AND nc.blockchain = 'Ethereum'\nWHERE nh.contract_address = '0xabc123'\n  AND nh.token_id = '100';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE erc1155_approval_for_all ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar(66) NOT NULL, log_index integer NOT NULL, contract_address varchar(42) NOT NULL )\nCREATE TABLE erc20_balances ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE erc20_balances_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_holders ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, token_id varchar NOT NULL, contract_type varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_coins_metadata ( object_id varchar NOT NULL, coin_type varchar NOT NULL, status varchar NOT NULL, decimals bigint NOT NULL, description varchar NOT NULL, icon_url varchar NOT NULL, symbol varchar NOT NULL, name varchar NOT NULL )\nCREATE TABLE sui_nfts ( object_id varchar NOT NULL, status varchar NOT NULL, collection_type varchar NOT NULL, package_id varchar NOT NULL, previous_transaction varchar NOT NULL, display varchar NOT NULL, owner varchar NOT NULL, name varchar NOT NULL )\nCREATE TABLE nft_metadata ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, token_id varchar NOT NULL, contract_name varchar NOT NULL, erc_type varchar NOT NULL, amount bigint NOT NULL, minter varchar NOT NULL, owner varchar NOT NULL, mint_block_number bigint NOT NULL, mint_time bigint NOT NULL, mint_transaction_hash varchar NOT NULL, mint_price varchar NOT NULL, token_uri varchar NOT NULL, metadata varchar NOT NULL, name varchar NOT NULL, image_uri varchar NOT NULL, traits varchar NOT NULL, updated_at bigint NOT NULL, status varchar NOT NULL, rarity_score real NOT NULL, rarity_rank integer NOT NULL, unique_attribute_count integer NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_collections ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, name varchar NOT NULL, symbol varchar NOT NULL, deploy_block_number bigint NOT NULL, deploy_block_time bigint NOT NULL, erc_type varchar NOT NULL, owner varchar NOT NULL, traits varchar NOT NULL, description varchar NOT NULL, slug varchar NOT NULL, media_info varchar NOT NULL, image_url varchar NOT NULL, banner_image_url varchar NOT NULL, updated_at bigint NOT NULL, banner varchar NOT NULL, token_count bigint NOT NULL, floor_price varchar NOT NULL, floor_price_symbol varchar NOT NULL, floor_price_contract varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_prices ( uuid varchar(36) NOT NULL, blockchain varchar(36) NOT NULL, address varchar(42) NOT NULL, decimals bigint NOT NULL, symbol varchar(36) NOT NULL, price real NOT NULL, timestamp timestamp(6) NOT NULL )\nCREATE TABLE token_prices_latest ( blockchain varchar(36) NOT NULL, address varchar(42) NOT NULL, decimals bigint NOT NULL, symbol varchar(36) NOT NULL, price real NOT NULL, timestamp timestamp(6) NOT NULL )\nCREATE TABLE erc20_approval ( block_number bigint NOT NULL, block_timestamp timestamp(6) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar NOT NULL, log_index integer NOT NULL, contract_address varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_balances ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar NOT NULL, wallet_address varchar(42) NOT NULL, total_supply decimal(38,0) NOT NULL, amount decimal(38,0) NOT NULL )\nCREATE TABLE token_info ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE token_activities ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar NOT NULL, tick varchar NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(42) NOT NULL, to_address varchar(42) NOT NULL )\nCREATE TABLE mud_holesky_redstone ( address varchar NOT NULL, table_id varchar NOT NULL, key_bytes varchar NOT NULL, key0 varchar NOT NULL, key1 varchar NOT NULL, static_data varchar NOT NULL, encoded_lengths varchar NOT NULL, dynamic_data varchar NOT NULL, is_deleted boolean NOT NULL, block_number bigint NOT NULL, log_index bigint NOT NULL )\nCREATE TABLE token_balances_bitcoin ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar(255) NOT NULL, wallet_address varchar(42) NOT NULL, total_supply varchar NOT NULL, amount varchar NOT NULL )\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar(255) NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar(20) NOT NULL, tick varchar(255) NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(62) NOT NULL, to_address varchar(62) NOT NULL )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar(20) NOT NULL, tick varchar(255) NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(42) NOT NULL, to_address varchar(42) NOT NULL )\nCREATE TABLE token_balances_avalanche ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar(20) NOT NULL, wallet_address varchar(42) NOT NULL, total_supply decimal(38,0) NOT NULL, amount decimal(38,0) NOT NULL )\n"}
{"conversations": [{"role": "user", "content": "What is the average number of wallets each user owns?"}, {"role": "assistant", "content": "SELECT\n  AVG(wallet_count) AS avg_wallets_per_user\nFROM (\n  SELECT user_id, COUNT(*) AS wallet_count\n  FROM web3.wallets\n  GROUP BY user_id\n) AS sub;"}, {"role": "user", "content": "Actually, calculate the average only for users who own more than one wallet."}, {"role": "assistant", "content": "SELECT\n  AVG(wallet_count) AS avg_wallets_per_user\nFROM (\n  SELECT user_id, COUNT(*) AS wallet_count\n  FROM web3.wallets\n  GROUP BY user_id\n  HAVING COUNT(*) > 1\n) AS sub;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.wallets ( wallet_id text PRIMARY KEY, user_id text, address text, private_key text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Find all wallet addresses that don't have an associated user_id."}, {"role": "assistant", "content": "SELECT address_id FROM blockchain.wallets WHERE user_id IS NULL;"}, {"role": "user", "content": "Now show me these addresses along with their private_key, and join with another table to see if they have any transactions."}, {"role": "assistant", "content": "SELECT w.address_id, w.private_key FROM blockchain.wallets w WHERE w.user_id IS NULL;"}, {"role": "user", "content": "Actually, I want to see the count of such wallet addresses grouped by the first 3 characters of their address_id."}, {"role": "assistant", "content": "SELECT SUBSTRING(address_id, 1, 3) as address_prefix, COUNT(*) as address_count FROM blockchain.wallets WHERE user_id IS NULL GROUP BY SUBSTRING(address_id, 1, 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.wallets ( wallet_id.text, user_id.text, address_id.text, private_key.text )\n"}
{"conversations": [{"role": "user", "content": "Show the number of employees in each department."}, {"role": "assistant", "content": "SELECT department, COUNT(*) AS employee_count\nFROM financial_services.employees\ngroup BY department;"}, {"role": "user", "content": "Exclude departments that have less than 3 employees."}, {"role": "assistant", "content": "SELECT department, COUNT(*) AS employee_count\nFROM financial_services.employees\ngroup BY department\nHAVING COUNT(*) >= 3;"}, {"role": "user", "content": "Can you also show the average hire_date for employees in each department?"}, {"role": "assistant", "content": "SELECT department, COUNT(*) AS employee_count, AVG(hire_date) AS average_hire_date\nFROM financial_services.employees\ngroup BY department\nHAVING 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 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 ( transaction_id text PRIMARY KEY, 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.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 bigserial PRIMARY KEY, 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 PRIMARY KEY, first_name text, last_name text, job_title text, department text, branch_id text, email text, phone_extension text, hire_date date, termination_date date, manager_id text, status text )\n"}
{"conversations": [{"role": "user", "content": "Show a list of all game developers with their name and founded year."}, {"role": "assistant", "content": "SELECT\n  name,\n  founded_year\nFROM gaming_technology.developers;"}, {"role": "user", "content": "Please filter the list to only include developers founded in the year 1998."}, {"role": "assistant", "content": "SELECT\n  name,\n  founded_year\nFROM gaming_technology.developers\nWHERE\n  founded_year = 1998;"}, {"role": "user", "content": "Can you also include the number of games each of these developers has released?"}, {"role": "assistant", "content": "SELECT\n  T1.name,\n  T1.founded_year,\n  COUNT(T2.game_id) AS game_count\nFROM gaming_technology.developers AS T1\nLEFT JOIN gaming_technology.games AS T2\n  ON T1.developer_id = T2.developer_id\nWHERE\n  T1.founded_year = 1998\nGROUP BY\n  T1.developer_id,\n  T1.name,\n  T1.founded_year;"}, {"role": "user", "content": "Now, only show the developers who have released exactly 2 games."}, {"role": "assistant", "content": "SELECT\n  T1.name,\n  T1.founded_year,\n  COUNT(T2.game_id) AS game_count\nFROM gaming_technology.developers AS T1\nJOIN gaming_technology.games AS T2\n  ON T1.developer_id = T2.developer_id\nWHERE\n  T1.founded_year = 1998\nGROUP BY\n  T1.developer_id,\n  T1.name,\n  T1.founded_year\nHAVING\n  COUNT(T2.game_id) = 2;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.players (\n    player_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the player\n    username character varying(100) NOT NULL UNIQUE, -- player's chosen display name\n    email character varying(255) NOT NULL UNIQUE, -- player's email address for login/recovery\n    password_hash text NOT NULL, -- securely hashed password\n    registration_date timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the player account was created\n    last_login timestamp with time zone, -- timestamp of the last successful login\n    country_code character(2), -- player's country (ISO 3166-1 alpha-2)\n    status character varying(20) NOT NULL DEFAULT 'active', -- account status (e.g., active, banned, suspended)\n    profile_data jsonb, -- flexible field for avatar url, bio, preferences etc.\n    PRIMARY KEY (player_id)\n)\nCREATE TABLE gaming_technology.games (\n    game_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game\n    title character varying(200) NOT NULL, -- official title of the game\n    developer_id uuid NOT NULL, -- FK linking to the developers table\n    publisher_id uuid, -- FK linking to a potential publishers table (optional)\n    genre character varying(100), -- primary genre (e.g., RPG, FPS, Strategy)\n    release_date date, -- official release date\n    description text, -- short description or synopsis of the game\n    platform character varying(50) NOT NULL, -- primary platform (e.g., PC, PlayStation 5, Xbox Series X, Mobile)\n    engine character varying(100), -- game engine used (e.g., Unreal Engine 5, Unity)\n    website character varying(255), -- official website URL\n    PRIMARY KEY (game_id)\n    -- FOREIGN KEY (developer_id) REFERENCES gaming_technology.developers(developer_id) -- Example FK constraint\n)\nCREATE TABLE gaming_technology.developers (\n    developer_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the developer studio\n    name character varying(150) NOT NULL UNIQUE, -- name of the development studio\n    country character varying(100), -- country where the studio is based\n    founded_year integer, -- year the studio was founded\n    website character varying(255), -- developer's official website\n    created_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP,\n    PRIMARY KEY (developer_id)\n)\nCREATE TABLE gaming_technology.game_sessions (\n    session_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game session\n    player_id uuid NOT NULL, -- FK linking to the players table\n    game_id uuid NOT NULL, -- FK linking to the games table\n    server_id uuid, -- FK linking to the servers table (nullable for single-player)\n    start_time timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the session began\n    end_time timestamp with time zone, -- when the session ended (null if ongoing)\n    duration_seconds integer, -- calculated duration of the session in seconds\n    score integer, -- player's score for the session, if applicable\n    session_data jsonb, -- flexible field for session-specific info (e.g., map played, character used)\n    PRIMARY KEY (session_id)\n    -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n    -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id),\n    -- FOREIGN KEY (server_id) REFERENCES gaming_technology.servers(server_id)\n)\nCREATE TABLE gaming_technology.servers (\n    server_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game server instance\n    game_id uuid NOT NULL, -- FK linking to the game this server hosts\n    server_name character varying(150), -- display name for the server\n    region character varying(50) NOT NULL, -- geographical region (e.g., us-east-1, eu-west-2)\n    ip_address character varying(45), -- IP address (IPv4 or IPv6)\n    port integer, -- network port number\n    current_players integer NOT NULL DEFAULT 0, -- number of players currently connected\n    max_players integer NOT NULL, -- maximum player capacity\n    status character varying(30) NOT NULL DEFAULT 'offline', -- server status (e.g., online, offline, maintenance)\n    last_heartbeat timestamp with time zone, -- last time the server reported its status\n    PRIMARY KEY (server_id)\n    -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id)\n)\nCREATE TABLE gaming_technology.achievements (\n    achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for an achievement definition\n    game_id uuid NOT NULL, -- FK linking to the game the achievement belongs to\n    name character varying(150) NOT NULL, -- name of the achievement\n    description text NOT NULL, -- how to unlock the achievement\n    icon_url character varying(255), -- URL for the achievement's icon\n    points integer DEFAULT 0, -- points awarded for unlocking (optional)\n    hidden boolean DEFAULT false, -- whether the achievement details are hidden until unlocked\n    PRIMARY KEY (achievement_id)\n    -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id)\n)\nCREATE TABLE gaming_technology.player_achievements (\n    player_achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for this unlock instance\n    player_id uuid NOT NULL, -- FK linking to the player who unlocked it\n    achievement_id uuid NOT NULL, -- FK linking to the achievement definition\n    unlocked_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the achievement was unlocked\n    PRIMARY KEY (player_achievement_id),\n    UNIQUE (player_id, achievement_id) -- Ensure a player can only unlock an achievement once\n    -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n    -- FOREIGN KEY (achievement_id) REFERENCES gaming_technology.achievements(achievement_id)\n)\n"}
{"conversations": [{"role": "user", "content": "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 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": "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": "Find all wallets created by users in the last 7 days along with any tokens that have a total supply greater than 10 million, showing the wallet address and token details."}, {"role": "assistant", "content": "SELECT w.address AS wallet_address, t.token_name, t.token_symbol, t.total_supply, t.contract_address FROM web3.wallets w JOIN web3.tokens t ON t.total_supply > 10000000 WHERE w.created_at >= CURRENT_DATE - INTERVAL '7 days';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.tokens ( token_id character varying(64) NOT NULL, contract_address character varying(128) NOT NULL, token_name character varying(128) NOT NULL, token_symbol character varying(32) NOT NULL, decimals integer NOT NULL, total_supply numeric(38,14) NOT NULL, PRIMARY KEY (token_id) )\nCREATE TABLE web3.wallets ( wallet_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, address character varying(128) NOT NULL, private_key text NOT NULL, created_at timestamp NOT NULL, PRIMARY KEY (wallet_id) )\n"}
{"conversations": [{"role": "user", "content": "What is the current operational status of the train car with car_id 'CAR123'?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information on the current operational status of the train car with car_id 'CAR123'. The data in the train_cars table does not include real-time status updates or operational conditions."}], "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.train_cars ( car_id text PRIMARY KEY, train_id text, car_number text, car_type text, class text, capacity int, features text )\n"}
{"conversations": [{"role": "user", "content": "How many likes were given to comments in June 2024?"}, {"role": "assistant", "content": "SELECT COUNT(*) AS comment_likes_count\nFROM social_media.likes\nWHERE comment_id IS NOT NULL \n  AND DATE_TRUNC('month', created_at) = '2024-06-01';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.comments ( comment_id character varying(64) NOT NULL, post_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, parent_comment_id character varying(64), content text NOT NULL, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (comment_id) )\nCREATE TABLE social_media.likes ( like_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, post_id character varying(64), comment_id character varying(64), created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (like_id), CONSTRAINT unique_user_like UNIQUE (user_id, post_id, comment_id), CONSTRAINT check_like_target CHECK (post_id IS NOT NULL OR comment_id IS NOT NULL) )\nCREATE TABLE social_media.post_hashtags ( post_hashtag_id character varying(64) NOT NULL, post_id character varying(64) NOT NULL, hashtag_id character varying(64) NOT NULL, PRIMARY KEY (post_hashtag_id), CONSTRAINT unique_post_hashtag UNIQUE (post_id, hashtag_id) )\nCREATE TABLE social_media.conversations ( conversation_id character varying(64) NOT NULL, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, last_message_at timestamp, is_group_chat boolean NOT NULL DEFAULT false, group_name character varying(100), PRIMARY KEY (conversation_id) )\nCREATE TABLE social_media.notifications ( notification_id character varying(64) NOT NULL, recipient_user_id character varying(64) NOT NULL, sender_user_id character varying(64), notification_type character varying(30) NOT NULL, target_entity_id character varying(64), target_entity_type character varying(20), created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, read_at timestamp, PRIMARY KEY (notification_id) )\nCREATE TABLE social_media.user_settings ( setting_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL UNIQUE, theme character varying(20) DEFAULT 'light', email_notifications_enabled boolean DEFAULT true, push_notifications_enabled boolean DEFAULT true, private_profile boolean DEFAULT false, updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (setting_id) )\n"}
{"conversations": [{"role": "user", "content": "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": "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 the product_name and description for all active products."}, {"role": "assistant", "content": "SELECT product_name, description FROM insurance.insurance_products WHERE is_active = true;"}, {"role": "user", "content": "Can you also include the product_type and order the results by product_name?"}, {"role": "assistant", "content": "SELECT product_name, description, product_type FROM insurance.insurance_products WHERE is_active = true ORDER BY product_name;"}, {"role": "user", "content": "Now, only show products of type 'Life' and exclude the description column."}, {"role": "assistant", "content": "SELECT product_name, product_type FROM insurance.insurance_products WHERE is_active = true AND product_type = 'Life' ORDER BY product_name;"}, {"role": "user", "content": "Finally, just count how many 'Life' products are active."}, {"role": "assistant", "content": "SELECT count(*) FROM insurance.insurance_products WHERE is_active = true AND product_type = 'Life';"}], "system": "You are an SQL statement expert. Given the table structure 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 character varying(64) NOT NULL, product_name character varying(150) NOT NULL, product_type character varying(50) NOT NULL, description text, base_premium numeric(10, 2) NOT NULL, coverage_details text, underwriting_rules text, is_active boolean NOT NULL DEFAULT true, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, updated_at timestamp, PRIMARY KEY (product_id) )\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": "List patient_id, full name, policy_number, plan_type, and insurance_provider for all active primary insurance policies."}, {"role": "assistant", "content": "SELECT pi.patient_id,\n       p.first_name,\n       p.last_name,\n       pi.policy_number,\n       ip.plan_type,\n       ip.insurance_provider\nFROM healthcare.patient_insurance pi\nJOIN healthcare.patients p\n  ON p.patient_id = pi.patient_id\nJOIN healthcare.insurance_plans ip\n  ON ip.plan_id = pi.plan_id\nWHERE pi.is_primary = TRUE\n  AND pi.effective_date <= CURRENT_DATE\n  AND pi.expiration_date >= CURRENT_DATE;"}, {"role": "user", "content": "Now also restrict to policies expiring within the next 30 days."}, {"role": "assistant", "content": "SELECT pi.patient_id,\n       p.first_name,\n       p.last_name,\n       pi.policy_number,\n       ip.plan_type,\n       ip.insurance_provider\nFROM healthcare.patient_insurance pi\nJOIN healthcare.patients p\n  ON p.patient_id = pi.patient_id\nJOIN healthcare.insurance_plans ip\n  ON ip.plan_id = pi.plan_id\nWHERE pi.is_primary = TRUE\n  AND pi.effective_date <= CURRENT_DATE\n  AND pi.expiration_date BETWEEN CURRENT_DATE AND CURRENT_DATE + INTERVAL '30 days';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id 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, 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 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": "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": "List all medical record IDs and the record date for records created by doctors specializing in 'Gastroenterology'."}, {"role": "assistant", "content": "SELECT mr.record_id, mr.record_date FROM healthcare.medical_records mr JOIN healthcare.doctors d ON mr.doctor_id = d.doctor_id WHERE d.specialty = 'Gastroenterology';"}, {"role": "user", "content": "Could you also include the patient's first and last name for these records?"}, {"role": "assistant", "content": "SELECT mr.record_id, mr.record_date, p.first_name, p.last_name FROM healthcare.medical_records mr JOIN healthcare.doctors d ON mr.doctor_id = d.doctor_id JOIN healthcare.patients p ON mr.patient_id = p.patient_id WHERE d.specialty = 'Gastroenterology';"}, {"role": "user", "content": "Now, only show records for male patients."}, {"role": "assistant", "content": "SELECT mr.record_id, mr.record_date, p.first_name, p.last_name FROM healthcare.medical_records mr JOIN healthcare.doctors d ON mr.doctor_id = d.doctor_id JOIN healthcare.patients p ON mr.patient_id = p.patient_id WHERE d.specialty = 'Gastroenterology' AND p.gender = 'Male';"}, {"role": "user", "content": "Additionally, restrict the results to medical records that have at least one associated diagnosis with status 'Resolved'."}, {"role": "assistant", "content": "SELECT DISTINCT mr.record_id, mr.record_date, p.first_name, p.last_name FROM healthcare.medical_records mr JOIN healthcare.doctors d ON mr.doctor_id = d.doctor_id JOIN healthcare.patients p ON mr.patient_id = p.patient_id JOIN healthcare.diagnoses diag ON mr.record_id = diag.record_id WHERE d.specialty = 'Gastroenterology' AND p.gender = 'Male' AND diag.status = 'Resolved';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id text, first_name text, last_name text, date_of_birth date, gender text, address text, phone_number text, email text, emergency_contact_name text, emergency_contact_phone text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.doctors ( doctor_id text, first_name text, last_name text, specialty text, license_number text, phone_number text, email text, hospital_affiliation_id text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.medical_records ( record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, appointment_id character varying(64) UNIQUE, doctor_id character varying(64) NOT NULL, record_date timestamp with time zone NOT NULL, chief_complaint text, present_illness_history text, past_medical_history text, physical_examination_notes text, assessment text, treatment_plan text, vitals jsonb, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (record_id) )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id text PRIMARY KEY, record_id text, patient_id text, doctor_id text, diagnosis_code text, code_type text, description text, diagnosis_date date, status text, is_chronic boolean )\nCREATE TABLE healthcare.prescriptions ( prescription_id character varying(64) NOT NULL, record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, doctor_id character varying(64) NOT NULL, medication_id character varying(64) NOT NULL, dosage character varying(100) NOT NULL, frequency character varying(100) NOT NULL, route character varying(50), start_date date NOT NULL, end_date date, quantity_dispensed numeric(10,2), refills_allowed integer NOT NULL DEFAULT 0, prescription_date timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (prescription_id) )\nCREATE TABLE healthcare.insurance_plans ( plan_id character varying(64) NOT NULL, plan_name character varying(200) NOT NULL, insurance_provider character varying(100) NOT NULL, plan_type character varying(50), contact_phone character varying(20), website character varying(255), PRIMARY KEY (plan_id) )\nCREATE TABLE healthcare.patient_insurance (\n    patient_insurance_id character varying(64) NOT NULL, -- unique identifier for this patient-plan link\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    plan_id character varying(64) NOT NULL, -- FK to insurance_plans table\n    policy_number character varying(100) NOT NULL, -- patient's policy number\n    group_number character varying(100), -- group number, if applicable\n    subscriber_name character varying(200), -- name of the primary policy holder\n    effective_date date NOT NULL, -- date the coverage begins\n    expiration_date date, -- date the coverage ends (if known)\n    is_primary boolean NOT NULL DEFAULT true, -- indicates if this is the primary insurance\n    PRIMARY KEY (patient_insurance_id),\n    UNIQUE (patient_id, plan_id, policy_number) -- ensure a patient doesn't have the same policy twice\n)\n"}
{"conversations": [{"role": "user", "content": "For projects that have completed more than one fundraising round, calculate the average investment value across all their recorded rounds. Display the project name and this average value."}, {"role": "assistant", "content": "SELECT project_name, AVG(investment_value) AS average_investment FROM project_fundraising_record GROUP BY project_name HAVING COUNT(*) > 1;"}, {"role": "user", "content": "Can you modify this to only show projects where the average investment value is greater than 10 million USD and order the results by average investment value descending?"}, {"role": "assistant", "content": "SELECT project_name, AVG(investment_value) AS average_investment FROM project_fundraising_record GROUP BY project_name HAVING COUNT(*) > 1 AND AVG(investment_value) > 10000000 ORDER BY average_investment DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE project_fundraising_record ( id character varying(32) NOT NULL,  -- 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 )\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": "Find the average percentage share among all beneficiaries for each distinct relationship type."}, {"role": "assistant", "content": "SELECT relationship, AVG(percentage_share) FROM insurance.policy_beneficiaries GROUP BY relationship ORDER BY relationship;"}], "system": "You are an SQL statement expert. Given the table structure 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 )\nCREATE TABLE insurance.policy_beneficiaries ( beneficiary_id text PRIMARY KEY, 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": "Retrieve the number of drivers grouped by their status."}, {"role": "assistant", "content": "SELECT status,\n       COUNT(*) AS driver_count\nFROM transportation.drivers\nGROUP BY status;"}, {"role": "user", "content": "Now, only show statuses where the driver_count is greater than 5 and order the results by driver_count descending."}, {"role": "assistant", "content": "SELECT status,\n       COUNT(*) AS driver_count\nFROM transportation.drivers\nGROUP BY status\nHAVING COUNT(*) > 5\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": "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": "Find the contract address and name for all NFT collections listed on the 'Ethereum' blockchain."}, {"role": "assistant", "content": "SELECT contract_address, name FROM nft_collections WHERE blockchain = 'Ethereum'"}, {"role": "user", "content": "For these collections, can you show the count of unique wallet addresses holding NFTs in each collection by joining with nft_holders?"}, {"role": "assistant", "content": "SELECT T1.contract_address, T1.name, COUNT(DISTINCT T2.wallet_address) AS unique_holder_count FROM nft_collections AS T1 JOIN nft_holders AS T2 ON T1.contract_address = T2.contract_address WHERE T1.blockchain = 'Ethereum' GROUP BY T1.contract_address, T1.name"}, {"role": "user", "content": "Please filter the results to only include collections that have more than 100 unique holders."}, {"role": "assistant", "content": "SELECT T1.contract_address, T1.name, COUNT(DISTINCT T2.wallet_address) AS unique_holder_count FROM nft_collections AS T1 JOIN nft_holders AS T2 ON T1.contract_address = T2.contract_address WHERE T1.blockchain = 'Ethereum' GROUP BY T1.contract_address, T1.name HAVING COUNT(DISTINCT T2.wallet_address) > 100"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp timestamp(6) NOT NULL, block_number bigint NOT NULL, transaction_hash varchar NOT NULL, transaction_index bigint NOT NULL, from_address varchar NOT NULL, contract_address varchar NOT NULL, symbol varchar NOT NULL, total_supply varchar NOT NULL, name varchar NOT NULL, decimals bigint NOT NULL, is_erc20 integer NOT NULL, is_erc721 integer NOT NULL, is_erc1155 integer NOT NULL, is_proxy integer NOT NULL, extra_info varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE erc20_balances_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_holders ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, token_id varchar NOT NULL, contract_type varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE nft_holder_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, token_id varchar NOT NULL, contract_type varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE nft_collections ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, name varchar NOT NULL, symbol varchar NOT NULL, deploy_block_number bigint NOT NULL, deploy_block_time bigint NOT NULL, erc_type varchar NOT NULL, owner varchar NOT NULL, traits varchar NOT NULL, description varchar NOT NULL, slug varchar NOT NULL, media_info varchar NOT NULL, image_url varchar NOT NULL, banner_image_url varchar NOT NULL, updated_at bigint NOT NULL, banner varchar NOT NULL, token_count bigint NOT NULL, floor_price varchar NOT NULL, floor_price_symbol varchar NOT NULL, floor_price_contract varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_prices ( uuid varchar(36) NOT NULL, blockchain varchar(36) NOT NULL, address varchar(42) NOT NULL, decimals bigint NOT NULL, symbol varchar(36) NOT NULL, price real NOT NULL, timestamp timestamp(6) NOT NULL )\nCREATE TABLE token_prices_latest ( blockchain varchar(36) NOT NULL, address varchar(42) NOT NULL, decimals bigint NOT NULL, symbol varchar(36) NOT NULL, price real NOT NULL, timestamp timestamp(6) NOT NULL )\nCREATE TABLE token_info ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE token_activities ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar NOT NULL, tick varchar NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(42) NOT NULL, to_address varchar(42) NOT NULL )\nCREATE TABLE token_balances_bitcoin ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar(255) NOT NULL, wallet_address varchar(42) NOT NULL, total_supply varchar NOT NULL, amount varchar NOT NULL )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar(20) NOT NULL, tick varchar(255) NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(62) NOT NULL, to_address varchar(62) NOT NULL )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar(20) NOT NULL, tick varchar(255) NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(42) NOT NULL, to_address varchar(42) NOT NULL )\nCREATE TABLE token_balances_avalanche ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar(20) NOT NULL, wallet_address varchar(42) NOT NULL, total_supply decimal(38,0) NOT NULL, amount decimal(38,0) NOT NULL )\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar(20) NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL, minted decimal(38,0) NOT NULL, holders decimal(38,0) NOT NULL, txs decimal(38,0) NOT NULL, updated_timestamp timestamp(3) NOT NULL, completed_timestamp timestamp(3) NOT NULL, id varchar(255) NOT NULL )\n"}
{"conversations": [{"role": "user", "content": "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": "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": "Show me the top 5 NFT collections with the highest token count on Ethereum, along with their names, symbols, and floor prices."}, {"role": "assistant", "content": "SELECT n.name, n.symbol, n.floor_price, n.token_count FROM nft_collections n WHERE n.blockchain = 'ethereum' ORDER BY n.token_count DESC LIMIT 5;"}, {"role": "user", "content": "Now, join this with the nft_metadata table to include the average rarity score for each collection."}, {"role": "assistant", "content": "SELECT n.name, n.symbol, n.floor_price, n.token_count, AVG(m.rarity_score) as avg_rarity_score FROM nft_collections n JOIN nft_metadata m ON n.contract_address = m.contract_address WHERE n.blockchain = 'ethereum' GROUP BY n.name, n.symbol, n.floor_price, n.token_count ORDER BY n.token_count DESC LIMIT 5;"}, {"role": "user", "content": "Can you filter these results to only show collections with an average rarity score greater than 80?"}, {"role": "assistant", "content": "SELECT n.name, n.symbol, n.floor_price, n.token_count, AVG(m.rarity_score) as avg_rarity_score FROM nft_collections n JOIN nft_metadata m ON n.contract_address = m.contract_address WHERE n.blockchain = 'ethereum' GROUP BY n.name, n.symbol, n.floor_price, n.token_count HAVING AVG(m.rarity_score) > 80 ORDER BY n.token_count DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp timestamp, block_number bigint, transaction_hash text, transaction_index bigint, from_address text, contract_address text, symbol text, total_supply text, name text, decimals bigint, is_erc20 integer, is_erc721 integer, is_erc1155 integer, is_proxy integer, extra_info text, pk integer )\nCREATE TABLE erc1155_approval_for_all ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash text, log_index integer, contract_address text )\nCREATE TABLE erc20_balances ( block_number bigint, contract_address text, wallet_address text, amount text, pk text )\nCREATE TABLE sui_coins ( object_id text, status text, coin_type text, balance text, owner text )\nCREATE TABLE sui_coins_metadata ( object_id text, coin_type text, status text, decimals bigint, description text, icon_url text, symbol text, name text )\nCREATE TABLE sui_nfts ( object_id text, status text, collection_type text, package_id text, previous_transaction text, display text, owner text, name text )\nCREATE TABLE nft_metadata ( blockchain text, contract_address text, token_id text, contract_name text, erc_type text, amount bigint, minter text, owner text, mint_block_number bigint, mint_time bigint, mint_transaction_hash text, mint_price text, token_uri text, metadata text, name text, image_uri text, traits text, updated_at bigint, status text, rarity_score real, rarity_rank integer, unique_attribute_count integer, pk integer )\nCREATE TABLE nft_collections ( blockchain text, contract_address text, name text, symbol text, deploy_block_number bigint, deploy_block_time bigint, erc_type text, owner text, traits text, description text, slug text, media_info text, image_url text, banner_image_url text, updated_at bigint, banner text, token_count bigint, floor_price text, floor_price_symbol text, floor_price_contract text, pk integer )\nCREATE TABLE token_prices ( uuid text, blockchain text, address text, decimals bigint, symbol text, price real, timestamp timestamp )\nCREATE TABLE token_prices_latest ( blockchain text, address text, decimals bigint, symbol text, price real, timestamp timestamp )\nCREATE TABLE token_balances ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply decimal, amount decimal )\nCREATE TABLE token_info ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text )\nCREATE TABLE token_activities ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE mud_holesky_redstone ( address text, table_id text, key_bytes text, key0 text, key1 text, static_data text, encoded_lengths text, dynamic_data text, is_deleted boolean, block_number bigint, log_index bigint )\nCREATE TABLE token_balances_bitcoin ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply text, amount text )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_balances_avalanche ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply decimal, amount decimal )\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id text )\n"}
{"conversations": [{"role": "user", "content": "List 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": "For each driver, list that driver and the next-hired driver, showing both driver IDs, full names, and their hire dates."}, {"role": "assistant", "content": "SELECT\n  d1.driver_id      AS driver_id,\n  d1.first_name || ' ' || d1.last_name AS driver_name,\n  d1.hire_date      AS hire_date,\n  d2.driver_id      AS next_driver_id,\n  d2.first_name || ' ' || d2.last_name AS next_driver_name,\n  d2.hire_date      AS next_hire_date\nFROM transportation.drivers d1\nJOIN transportation.drivers d2\n  ON d2.hire_date = (\n    SELECT MIN(hire_date)\n    FROM transportation.drivers d3\n    WHERE d3.hire_date > d1.hire_date\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 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": "What is the detailed repair history of the equipment used by the staff with staff_id 'STAFF123' during maintenance tasks?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information on the detailed repair history of equipment used by staff members. The data in the maintenance_records table only includes information about maintenance tasks, such as record_id, asset_id, maintenance type, and staff_id, but does not cover equipment repair histories."}], "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 the top 5 users who have created the most wallets, along with their email addresses and the creation date of their first wallet."}, {"role": "assistant", "content": "SELECT u.user_id, u.email, MIN(w.created_at) AS first_wallet_date, COUNT(w.wallet_id) AS wallet_count FROM trading_platform.users u JOIN trading_platform.wallets w ON u.user_id = w.user_id GROUP BY u.user_id, u.email ORDER BY wallet_count DESC LIMIT 5;"}, {"role": "user", "content": "Now modify the query to only include wallets created in the last 6 months."}, {"role": "assistant", "content": "SELECT u.user_id, u.email, MIN(w.created_at) AS first_wallet_date, COUNT(w.wallet_id) AS wallet_count FROM trading_platform.users u JOIN trading_platform.wallets w ON u.user_id = w.user_id WHERE w.created_at >= NOW() - INTERVAL '6 months' GROUP BY u.user_id, u.email ORDER BY wallet_count DESC LIMIT 5;"}, {"role": "user", "content": "Actually, I want to see the total balance across all wallets for each of these users, calculated from unspent UTXOs."}, {"role": "assistant", "content": "SELECT u.user_id, u.email, MIN(w.created_at) AS first_wallet_date, COUNT(w.wallet_id) AS wallet_count, COALESCE(SUM(ut.amount), 0) AS total_balance FROM trading_platform.users u JOIN trading_platform.wallets w ON u.user_id = w.user_id LEFT JOIN trading_platform.utxos ut ON w.address = ut.address AND ut.spent = false WHERE w.created_at >= NOW() - INTERVAL '6 months' GROUP BY u.user_id, u.email 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 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.wallets (\n    wallet_id character varying(64) NOT NULL,  -- unique identifier for the wallet\n    user_id character varying(64) NOT NULL, -- identifier of the user owning the wallet\n    address character varying(128) NOT NULL, -- address of the wallet\n    private_key text NOT NULL, -- private key of the wallet\n    created_at timestamp NOT NULL, -- time when the wallet was created\n    PRIMARY KEY (wallet_id)\n)\nCREATE TABLE trading_platform.orders (\n    order_id character varying(64) NOT NULL,  -- unique identifier for the order\n    user_id character varying(64) NOT NULL, -- identifier of the user placing the order\n    wallet_id character varying(64) NOT NULL, -- identifier of the wallet used for the order\n    asset_id character varying(64) NOT NULL, -- identifier of the asset being traded\n    order_type character varying(32) NOT NULL, -- type of the order (e.g., buy, sell)\n    quantity numeric(38,14) NOT NULL, -- quantity of the asset in the order\n    price numeric(38,14) NOT NULL, -- price per unit of the asset\n    status character varying(32) NOT NULL, -- status of the order (e.g., open, filled, canceled)\n    created_at timestamp NOT NULL, -- time when the order was created\n    PRIMARY KEY (order_id)\n)\nCREATE TABLE trading_platform.trades (\n    trade_id character varying(64) NOT NULL,  -- unique identifier for the trade\n    order_id character varying(64) NOT NULL, -- identifier of the order that led to the trade\n    buyer_id character varying(64) NOT NULL, -- identifier of the buyer\n    seller_id character varying(64) NOT NULL, -- identifier of the seller\n    asset_id character varying(64) NOT NULL, -- identifier of the asset being traded\n    quantity numeric(38,14) NOT NULL, -- quantity of the asset in the trade\n    price numeric(38,14) NOT NULL, -- price per unit of the asset\n    traded_at timestamp NOT NULL, -- time when the trade was executed\n    PRIMARY KEY (trade_id)\n)\nCREATE TABLE trading_platform.assets (\n    asset_id character varying(64) NOT NULL,  -- unique identifier for the asset\n    name character varying(128) NOT NULL, -- name of the asset\n    symbol character varying(32) NOT NULL, -- symbol of the asset\n    type character varying(32) NOT NULL, -- type of the asset (e.g., cryptocurrency, stock)\n    PRIMARY KEY (asset_id)\n)\nCREATE TABLE trading_platform.utxos (\n    utxo_id character varying(64) NOT NULL,  -- unique identifier for the UTXO\n    transaction_id character varying(64) NOT NULL, -- identifier of the transaction that created the UTXO\n    output_index integer NOT NULL, -- index of the output in the transaction\n    address character varying(128) NOT NULL, -- address that can spend the UTXO\n    amount numeric(38,14) NOT NULL, -- amount of the asset in the UTXO\n    spent boolean NOT NULL, -- whether the UTXO has been spent\n    PRIMARY KEY (utxo_id)\n)\nCREATE TABLE trading_platform.dapps (\n    dapp_id character varying(64) NOT NULL,  -- unique identifier for the DApp\n    name character varying(128) NOT NULL, -- name of the DApp\n    description text NOT NULL, -- description of the DApp\n    url character varying(256) NOT NULL, -- URL of the DApp\n    PRIMARY KEY (dapp_id)\n)\nCREATE TABLE trading_platform.peers (\n    peer_id character varying(64) NOT NULL,  -- unique identifier for the peer\n    ip_address character varying(15) NOT NULL, -- IP address of the peer\n    port integer NOT NULL, -- port number of the peer\n    last_seen timestamp NOT NULL, -- last time the peer was active\n    PRIMARY KEY (peer_id)\n)\nCREATE TABLE trading_platform.metadata (\n    metadata_id character varying(64) NOT NULL,  -- unique identifier for the metadata\n    asset_id character varying(64) NOT NULL, -- identifier of the asset the metadata is associated with\n    key character varying(128) NOT NULL, -- key of the metadata\n    value text NOT NULL, -- value of the metadata\n    PRIMARY KEY (metadata_id)\n)\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": "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": "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": "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": "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": "Can you narrow this down to only show cases where the case type is 'Criminal'?"}, {"role": "assistant", "content": "SELECT case_name, case_number, date_opened FROM legal_services.cases WHERE lead_lawyer_id = 'lawyer_abc' AND status = 'Open' AND case_type = 'Criminal';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.cases ( case_id.text, case_number.text, case_name.text, client_id.text, lead_lawyer_id.text, case_type.text, status.text, date_opened.timestamp, date_closed.timestamp, description.text, court_jurisdiction.text )\n"}
{"conversations": [{"role": "user", "content": "Show me all rooms that were last cleaned more than 3 days ago, along with their room numbers and cleaning status."}, {"role": "assistant", "content": "SELECT room_number, current_condition FROM hospitality_technology.rooms WHERE last_cleaned_at < CURRENT_DATE - INTERVAL '3 days';"}, {"role": "user", "content": "Now, join this with another query to show only rooms that are currently 'Available' and have a 'Jacuzzi' in their features."}, {"role": "assistant", "content": "SELECT r.room_number, r.current_condition FROM hospitality_technology.rooms r WHERE r.last_cleaned_at < CURRENT_DATE - INTERVAL '3 days' AND r.status = 'available' AND r.features LIKE '%Jacuzzi%';"}, {"role": "user", "content": "The query is missing the floor information. Can you include that as well?"}, {"role": "assistant", "content": "SELECT r.room_number, r.current_condition, r.floor FROM hospitality_technology.rooms r WHERE r.last_cleaned_at < CURRENT_DATE - INTERVAL '3 days' AND r.status = 'available' AND r.features LIKE '%Jacuzzi%';"}, {"role": "user", "content": "Actually, I need to see the results ordered by floor in descending order, then by room_number."}, {"role": "assistant", "content": "SELECT r.room_number, r.current_condition, r.floor FROM hospitality_technology.rooms r WHERE r.last_cleaned_at < CURRENT_DATE - INTERVAL '3 days' AND r.status = 'available' AND r.features LIKE '%Jacuzzi%' ORDER BY r.floor DESC, r.room_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 hospitality_technology.rooms ( room_id text PRIMARY KEY, property_id text, room_number text, room_type_id text, floor int, status text, is_smoking boolean, features text, current_condition text, last_cleaned_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "List users who have received notifications triggered by another user (non-system notifications). Show the recipient username, notification type, and the sender username."}, {"role": "assistant", "content": "SELECT T1.username AS recipient_username, T2.notification_type, T3.username AS sender_username FROM social_media.users AS T1 JOIN social_media.notifications AS T2 ON T1.user_id = T2.recipient_user_id JOIN social_media.users AS T3 ON T2.sender_user_id = T3.user_id;"}, {"role": "user", "content": "Refine the list from Turn 1 to only include notifications of type 'follow' or 'mention'."}, {"role": "assistant", "content": "SELECT T1.username AS recipient_username, T2.notification_type, T3.username AS sender_username FROM social_media.users AS T1 JOIN social_media.notifications AS T2 ON T1.user_id = T2.recipient_user_id JOIN social_media.users AS T3 ON T2.sender_user_id = T3.user_id WHERE T2.notification_type IN ('follow', 'mention');"}, {"role": "user", "content": "Further filter to only include notifications created in 2024 and order the results by notification creation time descending."}, {"role": "assistant", "content": "SELECT T1.username AS recipient_username, T2.notification_type, T3.username AS sender_username FROM social_media.users AS T1 JOIN social_media.notifications AS T2 ON T1.user_id = T2.recipient_user_id JOIN social_media.users AS T3 ON T2.sender_user_id = T3.user_id WHERE T2.notification_type IN ('follow', 'mention') AND EXTRACT(YEAR FROM T2.created_at) = 2024 ORDER BY T2.created_at DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users (\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.posts (\n    post_id character varying(64) NOT NULL, -- unique identifier for the post\n    user_id character varying(64) NOT NULL, -- identifier of the user who created the post (FK to users.user_id)\n    content text, -- textual content of the post\n    media_url text, -- URL to attached media (image/video)\n    media_type character varying(20), -- type of media ('image', 'video', null)\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of post creation\n    updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last post edit\n    visibility character varying(20) NOT NULL DEFAULT 'public', -- visibility ('public', 'friends', 'private')\n    location_lat numeric(9,6), -- latitude of post location\n    location_lon numeric(9,6), -- longitude of post location\n    PRIMARY KEY (post_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.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": "Show me the top 3 smart money addresses by profit across all chains, along with their most profitable token and chain information."}, {"role": "assistant", "content": "SELECT address, profit, most_profit_token, chain\nFROM smart_money_profit\nORDER BY profit DESC\nLIMIT 3;"}, {"role": "user", "content": "Actually, I only want to see addresses from Ethereum chain with ROI over 30%."}, {"role": "assistant", "content": "SELECT address, profit, most_profit_token, roi\nFROM smart_money_profit\nWHERE chain = 'Ethereum' AND roi > 30\nORDER BY profit DESC\nLIMIT 3;"}, {"role": "user", "content": "Can you add their realized profit ratio and filter to only show results with profit over $100,000?"}, {"role": "assistant", "content": "SELECT address, profit, most_profit_token, roi, realized_ratio\nFROM smart_money_profit\nWHERE chain = 'Ethereum' AND roi > 30 AND profit > 100000\nORDER BY profit DESC\nLIMIT 3;"}, {"role": "user", "content": "Now order these results by ROI in descending order instead of profit."}, {"role": "assistant", "content": "SELECT address, profit, most_profit_token, roi, realized_ratio\nFROM smart_money_profit\nWHERE chain = 'Ethereum' AND roi > 30 AND profit > 100000\nORDER BY roi 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 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 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 smart_money_profit ( address character varying(100) NOT NULL, -- the user's address rank INT, -- the rank of the address in trade performance, value 1 expresses the best address. profit numeric(38,6), -- the profit user made in a month roi numeric(38,2), -- the roi of the user in a month realized_ratio numeric(38,2), -- the percentage of the user's realized profit most_profit_token character varying(100), -- the token symbol of the user's most profitable trade last_trade_time character varying(100), -- the last trade time of the user chain character varying(100), -- the chain that the address resides PRIMARY KEY (address, chain) )\n"}
{"conversations": [{"role": "user", "content": "Find the total amount paid for all premium payments made in the last 30 days."}, {"role": "assistant", "content": "SELECT SUM(amount_paid) FROM insurance.premium_payments WHERE payment_date >= CURRENT_DATE - INTERVAL '30 day';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.policies (\n    policy_id character varying(64) NOT NULL, -- unique identifier for the policy\n    customer_id character varying(64) NOT NULL, -- identifier for the policyholder (FK to customers)\n    product_id character varying(64) NOT NULL, -- identifier for the insurance product (FK to insurance_products)\n    agent_id character varying(64), -- identifier for the agent who sold the policy (FK to agents)\n    policy_number character varying(100) NOT NULL UNIQUE, -- customer-facing policy number\n    start_date date NOT NULL, -- date the policy coverage begins\n    end_date date NOT NULL, -- date the policy coverage ends\n    premium_amount numeric(12, 2) NOT NULL, -- total premium for the policy term\n    coverage_limit numeric(15, 2) NOT NULL, -- maximum amount covered\n    deductible numeric(10, 2) NOT NULL, -- amount customer pays before coverage kicks in\n    status character varying(30) NOT NULL, -- e.g., Active, Expired, Cancelled, Pending\n    issued_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the policy was issued\n    cancellation_date date,\n    cancellation_reason text,\n    PRIMARY KEY (policy_id)\n)\nCREATE TABLE insurance.insurance_products (\n    product_id character varying(64) NOT NULL, -- unique identifier for the insurance product\n    product_name character varying(150) NOT NULL, -- name of the insurance product (e.g., 'Comprehensive Auto Insurance')\n    product_type character varying(50) NOT NULL, -- category like 'Auto', 'Home', 'Life', 'Health', 'Travel'\n    description text, -- detailed description of the product\n    base_premium numeric(10, 2) NOT NULL, -- starting premium before adjustments\n    coverage_details text, -- details about what is covered (could be JSON or structured text)\n    underwriting_rules text, -- rules used for assessing risk and eligibility\n    is_active boolean NOT NULL DEFAULT true, -- whether the product is currently offered\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n    updated_at timestamp,\n    PRIMARY KEY (product_id)\n)\nCREATE TABLE insurance.premium_payments (\n    payment_id character varying(64) NOT NULL, -- unique identifier for the payment\n    policy_id character varying(64) NOT NULL, -- identifier of the policy the payment is for (FK to policies)\n    customer_id character varying(64) NOT NULL, -- identifier of the customer making the payment (FK to customers)\n    payment_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- date the payment was received\n    amount_paid numeric(12, 2) NOT NULL, -- amount of the payment\n    payment_method character varying(50), -- e.g., Credit Card, Bank Transfer, Check\n    transaction_reference character varying(128) UNIQUE, -- reference from payment processor\n    due_date date, -- due date for this payment installment\n    payment_period_start date, -- start date of the period this payment covers\n    payment_period_end date, -- end date of the period this payment covers\n    status character varying(30) NOT NULL DEFAULT 'Completed', -- e.g., Completed, Pending, Failed, Refunded\n    PRIMARY KEY (payment_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Show me the total transfer volume and number of transfers for each token tick on Bitcoin in the past 7 days."}, {"role": "assistant", "content": "SELECT tick, SUM(amt) AS total_volume, COUNT(*) AS transfer_count\nFROM token_activities_bitcoin\nWHERE block_timestamp >= NOW() - INTERVAL '7 days'\nGROUP BY tick;"}, {"role": "user", "content": "Can you also include the creator of each token by joining with token_info_bitcoin?"}, {"role": "assistant", "content": "SELECT ta.tick, ti.creator, SUM(ta.amt) AS total_volume, COUNT(*) AS transfer_count\nFROM token_activities_bitcoin ta\nLEFT JOIN (\n    SELECT tick, creator FROM token_info_bitcoin WHERE (tick, block_timestamp) IN (\n        SELECT tick, MAX(block_timestamp) FROM token_info_bitcoin GROUP BY tick\n    )\n) ti ON ta.tick = ti.tick\nWHERE ta.block_timestamp >= NOW() - INTERVAL '7 days'\nGROUP BY ta.tick, ti.creator;"}, {"role": "user", "content": "Only include tokens where the total_volume is greater than 1000 and sort by total_volume descending, limit to top 5 tokens."}, {"role": "assistant", "content": "SELECT ta.tick, ti.creator, SUM(ta.amt) AS total_volume, COUNT(*) AS transfer_count\nFROM token_activities_bitcoin ta\nLEFT JOIN (\n    SELECT tick, creator FROM token_info_bitcoin WHERE (tick, block_timestamp) IN (\n        SELECT tick, MAX(block_timestamp) FROM token_info_bitcoin GROUP BY tick\n    )\n) ti ON ta.tick = ti.tick\nWHERE ta.block_timestamp >= NOW() - INTERVAL '7 days'\nGROUP BY ta.tick, ti.creator\nHAVING SUM(ta.amt) > 1000\nORDER BY total_volume DESC\nLIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp timestamp, block_number bigint, transaction_hash text, transaction_index bigint, from_address text, contract_address text, symbol text, total_supply text, name text, decimals bigint, is_erc20 integer, is_erc721 integer, is_erc1155 integer, is_proxy integer, extra_info text, pk integer )\nCREATE TABLE erc1155_approval_for_all ( 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 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 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_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 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 all tokens on the 'Arbitrum' chain from DEX pools that have a 24-hour trading volume between $100,000 and $500,000. Display token symbol, price, and volume_24h."}, {"role": "assistant", "content": "SELECT\n  token_symbol,\n  price,\n  volume_24h\nFROM token_dexpool_info\nWHERE\n  chain = 'Arbitrum' AND volume_24h BETWEEN 100000 AND 500000;"}, {"role": "user", "content": "Include their liquidity and 6-hour price change percentage in the results."}, {"role": "assistant", "content": "SELECT\n  token_symbol,\n  price,\n  volume_24h,\n  liquidity,\n  price_change_percentage_6h\nFROM token_dexpool_info\nWHERE\n  chain = 'Arbitrum' AND volume_24h BETWEEN 100000 AND 500000;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE project_fundraising_record ( id character varying(32) NOT NULL, project_id character varying(32) NOT NULL, project_name character varying(128) NOT NULL, rounds_name character varying(32), investment_value numeric(38,14), investment_date character varying(128), introduction character varying(128), valuation numeric(38,14) )\nCREATE TABLE token_basic_info ( coin_id text, token_name text, token_symbol text, token_address text, chain text, price numeric, price_change_percentage_1h numeric, price_change_percentage_24h numeric, price_change_percentage_7d numeric, highest_price_24h numeric, lowest_price_24h numeric, market_cap numeric, market_cap_rank numeric, market_cap_change_percentage_24h text, total_volume text, narrative text, trend_rank numeric )\n \"CREATE TABLE narrative_info (\",\n    \"narrative character varying(512) NOT NULL, -- the id of narrative\",\n    \"top_3_coins text, -- the top 3 tokens in the narrative\",\n    \"price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour in the narrative\",\n    \"price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours in the narrative\",\n    \"price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days in the narrative\",\n    \"market_cap double precision, -- the market cap of the narrative\",\n    \"volume_24h double precision, -- the trade volume of the narrative\",\n    \"trend_rank bigint, -- the trending rank of the narrative, value 1 expresses the most popular narrative\",\n    \"token_num bigint, -- total token number in the narrative\",\n    \",PRIMARY KEY (narrative));\"\n\nCREATE TABLE token_dexpool_info ( pair_address character varying(512) NOT NULL, -- the id of dexpool token_name character varying(100) NOT NULL, -- the name of the token in the dexpool token_symbol character varying(100) NOT NULL, -- the token's symbol chain text, -- the chain that the dexpool resides price double precision, -- the current price of the token price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour price_change_percentage_6h double precision, -- change in value divided by the absolute price value of the original token price in 6 hours price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours makers_24h double precision, -- the makers of the dex pool in 24 hours volume_24h double precision, -- the trade volume of the dex pool in 24 hours liquidity double precision, -- the liquidity of the dex pool market_cap double precision, -- the market cap of the token trend_rank bigint, -- the rank of token in the dex pool of recent trending, value 1 expresses the most popular token. ,PRIMARY KEY (pair_address, chain) )\n  \"CREATE TABLE cex_token_balance (\",\n    \"snapshot_time character varying(32) NOT NULL,  -- the snapshot time of record, converted from original timestamp\",\n    \"chain character varying(128) NOT NULL, -- the chain that the token resides\",\n    \"address character varying(128) NOT NULL, -- the address that holds the assets, owned by a CEX\",\n    \"exchange character varying(512) NOT NULL, -- a centralized exchange name\",\n    \"token_address character varying(128) NOT NULL, -- token contract address\",\n    \"token_symbol character varying(512), --token symbol\",\n    \"balance numeric(38,10), -- token balance\",\n    \"usd_value numeric(38,14), -- value of the token held in USD\",\n    \"price double precision, --price of the token in USD\",\n    \",PRIMARY KEY (snapshot_time, exchange, address, chain, token_address));\"\n\nCREATE TABLE smart_money_profit ( address character varying(100) NOT NULL, -- the user's address rank INT, -- the rank of the address in trade performance, value 1 expresses the best address. profit numeric(38,6), -- the profit user made in a month roi numeric(38,2), -- the roi of the user in a month realized_ratio numeric(38,2), -- the percentage of the user's realized profit most_profit_token character varying(100), -- the token symbol of the user's most profitable trade last_trade_time character varying(100), -- the last trade time of the user chain character varying(100), -- the chain that the address resides PRIMARY KEY (address, chain) )\nCREATE TABLE smart_money_token_performance ( token_address text, token_symbol text, pnl numeric, net_flow numeric, avg_cost numeric, price numeric, realized_ratio numeric, roi numeric, chain text )\n"}
{"conversations": [{"role": "user", "content": "What is the total number of billable hours worked by each lawyer?"}, {"role": "assistant", "content": "SELECT lawyer_id,\n       SUM(hours_spent) AS total_billable_hours\nFROM legal_services.time_entries\nWHERE is_billable = TRUE\nGROUP BY lawyer_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, case_id.text, lawyer_id.text, date_worked.date, hours_spent.numeric, billing_rate.numeric, description.text, is_billable.boolean, is_billed.boolean, invoice_id.text, created_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "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": "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": "Identify all instances where a vehicle's odometer_reading increased by more than 500 miles between two consecutive fuel log entries."}, {"role": "assistant", "content": "SELECT a.vehicle_id,\n       a.fuel_log_id                         AS previous_log_id,\n       b.fuel_log_id                         AS next_log_id,\n       a.log_timestamp                       AS previous_time,\n       b.log_timestamp                       AS next_time,\n       b.odometer_reading - a.odometer_reading AS mile_increase\nFROM transportation.fuel_logs a\nJOIN transportation.fuel_logs b\n  ON a.vehicle_id = b.vehicle_id\n AND b.log_timestamp = (\n      SELECT MIN(log_timestamp)\n      FROM transportation.fuel_logs\n      WHERE vehicle_id = a.vehicle_id\n        AND log_timestamp > a.log_timestamp\n    )\nWHERE b.odometer_reading - a.odometer_reading > 500;"}, {"role": "user", "content": "Now restrict these increases to those where the time difference between entries is less than 7 days."}, {"role": "assistant", "content": "SELECT a.vehicle_id,\n       a.fuel_log_id                         AS previous_log_id,\n       b.fuel_log_id                         AS next_log_id,\n       a.log_timestamp                       AS previous_time,\n       b.log_timestamp                       AS next_time,\n       b.odometer_reading - a.odometer_reading AS mile_increase,\n       EXTRACT(epoch FROM (b.log_timestamp - a.log_timestamp))/3600 AS hours_diff\nFROM transportation.fuel_logs a\nJOIN transportation.fuel_logs b\n  ON a.vehicle_id = b.vehicle_id\n AND b.log_timestamp = (\n      SELECT MIN(log_timestamp)\n      FROM transportation.fuel_logs\n      WHERE vehicle_id = a.vehicle_id\n        AND log_timestamp > a.log_timestamp\n    )\nWHERE b.odometer_reading - a.odometer_reading > 500\n  AND b.log_timestamp - a.log_timestamp < INTERVAL '7 days';"}, {"role": "user", "content": "Also include both the mile increase and the time difference in hours in the final output columns."}, {"role": "assistant", "content": "SELECT a.vehicle_id,\n       a.fuel_log_id                         AS previous_log_id,\n       b.fuel_log_id                         AS next_log_id,\n       b.odometer_reading - a.odometer_reading AS mile_increase,\n       EXTRACT(epoch FROM (b.log_timestamp - a.log_timestamp))/3600 AS hours_difference\nFROM transportation.fuel_logs a\nJOIN transportation.fuel_logs b\n  ON a.vehicle_id = b.vehicle_id\n AND b.log_timestamp = (\n      SELECT MIN(log_timestamp)\n      FROM transportation.fuel_logs\n      WHERE vehicle_id = a.vehicle_id\n        AND log_timestamp > a.log_timestamp\n    )\nWHERE b.odometer_reading - a.odometer_reading > 500\n  AND b.log_timestamp - a.log_timestamp < INTERVAL '7 days';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.fuel_logs ( fuel_log_id.text, vehicle_id.text, trip_id.text, log_timestamp.timestamp, fuel_type.text, quantity.numeric, unit.text, cost_per_unit.numeric, total_cost.numeric, odometer_reading.integer, location_id.text )\n"}
{"conversations": [{"role": "user", "content": "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": "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": "List all claims, including the claim ID, incident date, estimated loss, and the name of the insurance product associated with the policy under which the claim was made."}, {"role": "assistant", "content": "SELECT\n  c.claim_id,\n  c.incident_date,\n  c.estimated_loss,\n  ip.product_name\nFROM insurance.claims AS c\nJOIN insurance.policies AS p\n  ON c.policy_id = p.policy_id\nJOIN insurance.insurance_products AS ip\n  ON p.product_id = ip.product_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.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": "For each state, count the number of customers and display state as state and the count as customer_count, ordered by customer_count descending."}, {"role": "assistant", "content": "SELECT state,\n       COUNT(*) AS customer_count\nFROM insurance.customers\nGROUP BY state\nORDER BY customer_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.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": "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": "For each open case, find the latest document uploaded: include case_number, document_name, and upload_timestamp."}, {"role": "assistant", "content": "SELECT c.case_number,\n       d.document_name,\n       d.upload_timestamp\nFROM legal_services.cases c\nJOIN (\n  SELECT case_id,\n         document_name,\n         upload_timestamp,\n         ROW_NUMBER() OVER (PARTITION BY case_id ORDER BY upload_timestamp DESC) AS rn\n  FROM legal_services.documents\n) d ON c.case_id = d.case_id AND d.rn = 1\nWHERE c.status = 'Open';"}, {"role": "user", "content": "Only include document types 'Brief' or 'Evidence' and order by upload_timestamp descending."}, {"role": "assistant", "content": "SELECT c.case_number,\n       d.document_name,\n       d.upload_timestamp\nFROM legal_services.cases c\nJOIN (\n  SELECT case_id,\n         document_name,\n         upload_timestamp,\n         document_type,\n         ROW_NUMBER() OVER (PARTITION BY case_id ORDER BY upload_timestamp DESC) AS rn\n  FROM legal_services.documents\n  WHERE document_type IN ('Brief', 'Evidence')\n) d ON c.case_id = d.case_id AND d.rn = 1\nWHERE c.status = 'Open'\nORDER BY d.upload_timestamp DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.law_firms ( firm_id text, firm_name text, address text, phone text, website text, founded_date date, managing_partner_id text )\nCREATE TABLE legal_services.cases ( case_id 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.text, case_id.text, document_name.text, document_type.text, storage_path.text, uploaded_by_lawyer_id.text, upload_timestamp.timestamp, version.integer, description.text )\nCREATE TABLE legal_services.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": "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": "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": "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": "List all log entries associated with users who have participated in any trade, showing the log details and the trade ID."}, {"role": "assistant", "content": "SELECT T1.log_id, T1.action, T1.details, T1.logged_at, T2.trade_id, T2.buyer_id, T2.seller_id FROM logs AS T1 JOIN trades AS T2 ON T1.user_id = T2.buyer_id OR T1.user_id = T2.seller_id;"}, {"role": "user", "content": "Only show logs and trades that occurred in the last week."}, {"role": "assistant", "content": "SELECT T1.log_id, T1.action, T1.details, T1.logged_at, T2.trade_id, T2.buyer_id, T2.seller_id FROM logs AS T1 JOIN trades AS T2 ON T1.user_id = T2.buyer_id OR T1.user_id = T2.seller_id WHERE T1.logged_at >= datetime('now', '-7 days') AND T2.traded_at >= datetime('now', '-7 days');"}, {"role": "user", "content": "Can you instead provide a count of such log entries per user who traded, for the last week?"}, {"role": "assistant", "content": "SELECT T1.user_id, COUNT(DISTINCT T1.log_id) AS log_count FROM logs AS T1 JOIN trades AS T2 ON T1.user_id = T2.buyer_id OR T1.user_id = T2.seller_id WHERE T1.logged_at >= datetime('now', '-7 days') AND T2.traded_at >= datetime('now', '-7 days') GROUP BY T1.user_id;"}, {"role": "user", "content": "Also include the total number of trades for each user in the same period and sort by trade count descending."}, {"role": "assistant", "content": "SELECT T1.user_id, COUNT(DISTINCT T1.log_id) AS log_count, COUNT(DISTINCT T2.trade_id) AS trade_count FROM logs AS T1 JOIN trades AS T2 ON T1.user_id = T2.buyer_id OR T1.user_id = T2.seller_id WHERE T1.logged_at >= datetime('now', '-7 days') AND T2.traded_at >= datetime('now', '-7 days') GROUP BY T1.user_id ORDER BY trade_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 trading_platform.wallets ( wallet_id.text, user_id.text, address.text, private_key.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.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.logs ( log_id.text, user_id.text, action.text, details.text, logged_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "What is the schedule of trains arriving at platform 1A at station XYZ on December 25th, 2023?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information about train schedules or specific arrival times as this data is not included in the platform management table. For train schedules, please refer to the train timetable or contact the station's customer 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.platforms (\n    platform_id character varying(64) NOT NULL, -- Unique identifier for the platform\n    station_id character varying(64) NOT NULL, -- Foreign key referencing stations\n    platform_number character varying(10) NOT NULL, -- Platform identifier (e.g., '1A', '5')\n    track_number character varying(10), -- Associated track number, if different\n    status character varying(32) NOT NULL DEFAULT 'Operational', -- e.g., Operational, Maintenance, Closed\n    length_meters numeric(8,2), -- Length of the platform in meters\n    accessible boolean NOT NULL DEFAULT false, -- Is the platform accessible (e.g., wheelchair)?\n    PRIMARY KEY (platform_id),\n    FOREIGN KEY (station_id) REFERENCES train_station_management.stations(station_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List the diagnosis_id, patient_id, and doctor_id for all diagnoses with status 'Pending' and is_chronic set to TRUE."}, {"role": "assistant", "content": "SELECT diagnosis_id, patient_id, doctor_id FROM healthcare.diagnoses WHERE status = 'Pending' AND 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 ( 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 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": "List projects that raised funds in 2023 and have an associated token in token_basic_info. Show project_name, rounds_name, investment_value, token_symbol, and chain."}, {"role": "assistant", "content": "SELECT p.project_name, p.rounds_name, p.investment_value, t.token_symbol, t.chain FROM project_fundraising_record p JOIN token_basic_info t ON LOWER(p.project_name) = LOWER(t.token_name) WHERE p.investment_date LIKE '2023%';"}, {"role": "user", "content": "The results are empty. Please modify the join to match where the token_name contains project_name or project_name contains token_name, case-insensitive."}, {"role": "assistant", "content": "SELECT p.project_name, p.rounds_name, p.investment_value, t.token_symbol, t.chain FROM project_fundraising_record p JOIN token_basic_info t ON LOWER(t.token_name) LIKE '%'||LOWER(p.project_name)||'%' OR LOWER(p.project_name) LIKE '%'||LOWER(t.token_name)||'%' WHERE p.investment_date LIKE '2023%';"}, {"role": "user", "content": "Now only include records where investment_value > 1000000 and token price > 10, and order by price descending."}, {"role": "assistant", "content": "SELECT p.project_name, p.rounds_name, p.investment_value, t.token_symbol, t.chain FROM project_fundraising_record p JOIN token_basic_info t ON (LOWER(t.token_name) LIKE '%'||LOWER(p.project_name)||'%' OR LOWER(p.project_name) LIKE '%'||LOWER(t.token_name)||'%') WHERE p.investment_date LIKE '2023%' AND p.investment_value > 1000000 AND t.price > 10 ORDER BY t.price DESC;"}, {"role": "user", "content": "Finally, include the token's narrative and market_cap, and limit the results to the top 5."}, {"role": "assistant", "content": "SELECT p.project_name, p.rounds_name, p.investment_value, t.token_symbol, t.chain, t.narrative, t.market_cap FROM project_fundraising_record p JOIN token_basic_info t ON (LOWER(t.token_name) LIKE '%'||LOWER(p.project_name)||'%' OR LOWER(p.project_name) LIKE '%'||LOWER(t.token_name)||'%') WHERE p.investment_date LIKE '2023%' AND p.investment_value > 1000000 AND t.price > 10 ORDER BY t.price 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, project_id character varying(32) NOT NULL, project_name character varying(128) NOT NULL, rounds_name character varying(32), investment_value numeric(38,14), investment_date character varying(128), introduction character varying(128), valuation numeric(38,14) )\nCREATE TABLE token_basic_info ( coin_id character varying(100) NOT NULL, token_name character varying(100) NOT NULL, token_symbol character varying(100) NOT NULL, token_address character varying(100) NOT NULL, chain text, price double precision, price_change_percentage_1h double precision, price_change_percentage_24h double precision, price_change_percentage_7d double precision, highest_price_24h double precision, lowest_price_24h double precision, market_cap double precision, market_cap_rank bigint, market_cap_change_percentage_24h text, total_volume text, narrative text, trend_rank bigint )\nCREATE TABLE narrative_info ( narrative character varying(512) NOT NULL, top_3_coins text, price_change_percentage_1h double precision, price_change_percentage_24h double precision, price_change_percentage_7d double precision, market_cap double precision, volume_24h double precision, trend_rank bigint, token_num bigint )\nCREATE TABLE cex_token_balance ( snapshot_time character varying(32) NOT NULL, chain character varying(128) NOT NULL, address character varying(128) NOT NULL, exchange character varying(512) NOT NULL, token_address character varying(128) NOT NULL, token_symbol character varying(512), balance numeric(38,10), usd_value numeric(38,14), price double precision )\nCREATE TABLE smart_money_profit ( address character varying(100) NOT NULL, rank INT, profit numeric(38,6), roi numeric(38,2), realized_ratio numeric(38,2), most_profit_token character varying(100), last_trade_time character varying(100), chain character varying(100) )\nCREATE TABLE smart_money_token_performance ( token_address character varying(100) NOT NULL, token_symbol character varying(100), pnl numeric(38,2), net_flow numeric(38,2), avg_cost numeric(38,16), price double precision, realized_ratio numeric(10,2), roi numeric(10,2), chain character varying(100) )\nCREATE TABLE smart_money_token_inflow ( token_address character varying(100) NOT NULL, token_symbol character varying(100), token_amount numeric(38,2), usd_value numeric(38,2), avg_price numeric(38,6), type int, address_amount integer, narrative character varying(100), chain character varying(100) )\n"}
{"conversations": [{"role": "user", "content": "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": "For all NFT collections on the Ethereum blockchain, show me the collection name and the current floor price. Sort by floor price descending."}, {"role": "assistant", "content": "SELECT name, floor_price FROM nft_collections WHERE blockchain = 'Ethereum' ORDER BY CAST(floor_price AS FLOAT) DESC;"}, {"role": "user", "content": "Include also the collection symbol and the number of tokens in each collection."}, {"role": "assistant", "content": "SELECT name, symbol, floor_price, token_count FROM nft_collections WHERE blockchain = 'Ethereum' ORDER BY CAST(floor_price AS FLOAT) DESC;"}, {"role": "user", "content": "Can you also show the owner of each collection in the result?"}, {"role": "assistant", "content": "SELECT name, symbol, floor_price, token_count, owner FROM nft_collections WHERE blockchain = 'Ethereum' ORDER BY CAST(floor_price AS FLOAT) DESC;"}, {"role": "user", "content": "Now only include collections whose floor price is greater than 1 ETH."}, {"role": "assistant", "content": "SELECT name, symbol, floor_price, token_count, owner FROM nft_collections WHERE blockchain = 'Ethereum' AND CAST(floor_price AS FLOAT) > 1 AND floor_price_symbol = 'ETH' ORDER BY CAST(floor_price AS FLOAT) 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(6) NOT NULL, block_number bigint NOT NULL, transaction_hash varchar NOT NULL, transaction_index bigint NOT NULL, from_address varchar NOT NULL, contract_address varchar NOT NULL, symbol varchar NOT NULL, total_supply varchar NOT NULL, name varchar NOT NULL, decimals bigint NOT NULL, is_erc20 integer NOT NULL, is_erc721 integer NOT NULL, is_erc1155 integer NOT NULL, is_proxy integer NOT NULL, extra_info varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE erc20_balances ( block_number bigint 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 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_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_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 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": "Provide a count of citizens registered per calendar year."}, {"role": "assistant", "content": "SELECT CAST(EXTRACT(YEAR FROM registration_date) AS INTEGER) AS registration_year, COUNT(*) AS citizen_count FROM government_services.citizens GROUP BY 1 ORDER BY 1;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens (\n    citizen_id character varying(64) NOT NULL,  -- unique identifier for the citizen\n    national_id_number character varying(128) NOT NULL UNIQUE, -- official national identification number\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    date_of_birth date NOT NULL,\n    gender character varying(20),\n    primary_address text NOT NULL, -- full primary residential address\n    contact_email character varying(128) UNIQUE,\n    contact_phone character varying(32),\n    registration_date timestamp NOT NULL, -- when the citizen profile was created\n    is_verified boolean DEFAULT false, -- whether identity has been officially verified\n    PRIMARY KEY (citizen_id)\n)\n"}
{"conversations": [{"role": "user", "content": "For each city that has a fueling location, show the city name and the total quantity of fuel refueled."}, {"role": "assistant", "content": "SELECT T2.city ,  SUM(T1.quantity) FROM transportation.fuel_logs AS T1 JOIN transportation.locations AS T2 ON T1.location_id  =  T2.location_id GROUP BY T2.city"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.locations ( location_id text PRIMARY KEY, name text, type text, address_line1 text, city text, state_province text, postal_code text, country text, latitude numeric, longitude numeric, timezone text )\nCREATE TABLE transportation.fuel_logs ( fuel_log_id text PRIMARY KEY, vehicle_id text, trip_id text, log_timestamp timestamp, fuel_type text, quantity numeric, unit text, cost_per_unit numeric, total_cost numeric, odometer_reading int, location_id text )\nCREATE TABLE transportation.bookings ( booking_id text PRIMARY KEY, passenger_id text, trip_id text, seat_number text, booking_time timestamp, status text, fare numeric, payment_transaction_id text, special_requests text )\n"}
{"conversations": [{"role": "user", "content": "List all unspent UTXOs with an amount greater than 10."}, {"role": "assistant", "content": "SELECT utxo_id, transaction_id, address, amount FROM utxos WHERE spent = FALSE AND amount > 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.wallets ( wallet_id.text, user_id.text, address.text, private_key.text, created_at.timestamp )\nCREATE TABLE trading_platform.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.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.logs ( log_id.text, user_id.text, action.text, details.text, logged_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "For each route type, show the total number of trips taken and the total distance covered across all trips for that type."}, {"role": "assistant", "content": "SELECT T1.type, COUNT(T2.trip_id), SUM(T1.distance_km) FROM transportation.routes AS T1 JOIN transportation.trips AS T2 ON T1.route_id = T2.route_id GROUP BY T1.type;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles ( vehicle_id.text, license_plate.text, vin.text, make.text, model.text, year.integer, type.text, capacity.integer, fuel_type.text, status.text, depot_id.text, acquisition_date.date )\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.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.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": "Get the number of agents grouped by status. Return status and agent_count."}, {"role": "assistant", "content": "SELECT status,\n       COUNT(*) AS agent_count\n  FROM insurance.agents\n GROUP BY 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 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 )\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": "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": "For each user, list all the distinct actions they have performed along with the count of each action."}, {"role": "assistant", "content": "SELECT user_id, action, COUNT(*) FROM trading_platform.logs GROUP BY user_id, action ORDER BY user_id, action;"}, {"role": "user", "content": "Now, only show users who have performed more than 5 distinct actions."}, {"role": "assistant", "content": "SELECT user_id FROM trading_platform.logs GROUP BY user_id HAVING COUNT(DISTINCT action) > 5 ORDER BY user_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.logs ( log_id character varying(64) NOT NULL, user_id character varying(64), action character varying(128) NOT NULL, details text NOT NULL, logged_at timestamp NOT NULL, PRIMARY KEY (log_id) )\n"}
{"conversations": [{"role": "user", "content": "List all patients who have insurance plans with group numbers, showing their patient IDs and the count of such plans per patient."}, {"role": "assistant", "content": "SELECT patient_id, COUNT(*) AS plan_count FROM healthcare.patient_insurance WHERE group_number IS NOT NULL GROUP BY patient_id;"}, {"role": "user", "content": "Actually, I only need patients who have more than 2 such plans."}, {"role": "assistant", "content": "SELECT patient_id, COUNT(*) AS plan_count FROM healthcare.patient_insurance WHERE group_number IS NOT NULL GROUP BY patient_id HAVING COUNT(*) > 2;"}, {"role": "user", "content": "Can you also include the earliest effective date among these plans for each patient?"}, {"role": "assistant", "content": "SELECT patient_id, COUNT(*) AS plan_count, MIN(effective_date) AS earliest_effective_date FROM healthcare.patient_insurance WHERE group_number IS NOT NULL GROUP BY patient_id HAVING COUNT(*) > 2;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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": "I need to find all components associated with a specific supplier. Can you help with that?"}, {"role": "assistant", "content": "HGETALL component:<component_id>\nIF HGET component:<component_id> supplier_id = 'sup:ACME_AERO' THEN INCLUDE"}, {"role": "user", "content": "Can you also show me the material ID for each of these components?"}, {"role": "assistant", "content": "HGETALL component:<component_id>\nIF HGET component:<component_id> supplier_id = 'sup:ACME_AERO' THEN INCLUDE\nHGET component:<component_id> material_id"}, {"role": "user", "content": "What if I want to exclude components with a specific material ID?"}, {"role": "assistant", "content": "HGETALL component:<component_id>\nIF HGET component:<component_id> supplier_id = 'sup:ACME_AERO' THEN INCLUDE\nHGET component:<component_id> material_id\nIF HGET component:<component_id> material_id != 'mat:TI64' THEN INCLUDE"}, {"role": "user", "content": "Can you add the component name to the result as well?"}, {"role": "assistant", "content": "HGETALL component:<component_id>\nIF HGET component:<component_id> supplier_id = 'sup:ACME_AERO' THEN INCLUDE\nHGET component:<component_id> material_id\nIF HGET component:<component_id> material_id != 'mat:TI64' THEN INCLUDE\nHGET component:<component_id> component_name"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nUse Hashes. Key pattern: 'component:<component_id>'. Example: HSET component:LGSTRUT01 part_number \"PN-5521-A\" component_name \"Landing Gear Strut\" material_id \"mat:TI64\" supplier_id \"sup:ACME_AERO\" ... Consider Sets for reverse lookups (e.g., 'material_components:<material_id>' -> Set<component_id>).\n"}
{"conversations": [{"role": "user", "content": "List 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": "List all auto loans (loan_id, principal_amount, interest_rate) where the current principal balance is less than 40% of the original principal amount, along with the account_id and the difference between principal_amount and current_principal_balance."}, {"role": "assistant", "content": "SELECT loan_id, principal_amount, interest_rate, account_id, (principal_amount - current_principal_balance) AS amount_paid FROM financial_services.loans WHERE loan_type = 'Auto' AND current_principal_balance < (0.4 * principal_amount);"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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 the total number of documents uploaded by each citizen along with their first and last names."}, {"role": "assistant", "content": "SELECT c.citizen_id, c.first_name, c.last_name, COUNT(d.document_id) AS document_count\nFROM government_services.citizens c\nLEFT JOIN government_services.documents d ON c.citizen_id = d.citizen_id\nGROUP BY c.citizen_id, c.first_name, c.last_name;"}, {"role": "user", "content": "Actually, I only want to include those citizens who have uploaded documents in the last 30 days."}, {"role": "assistant", "content": "SELECT c.citizen_id, c.first_name, c.last_name, COUNT(d.document_id) AS document_count\nFROM government_services.citizens c\nJOIN government_services.documents d ON c.citizen_id = d.citizen_id\nWHERE d.upload_timestamp >= NOW() - INTERVAL '30 days'\nGROUP BY c.citizen_id, c.first_name, c.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 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.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.payments ( payment_id text, application_id text, citizen_id text, service_id text, amount numeric, currency text, payment_method text, payment_provider_reference text, payment_timestamp timestamp, status text, notes text )\nCREATE TABLE government_services.employees (\n    employee_id character varying(64) NOT NULL, -- unique identifier for the government employee\n    agency_id character varying(64) NOT NULL, -- FK to agencies table\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    job_title character varying(150) NOT NULL,\n    department character varying(100),\n    work_email character varying(128) NOT NULL UNIQUE,\n    work_phone character varying(32),\n    hire_date date NOT NULL,\n    termination_date date, -- null if currently employed\n    access_level character varying(50), -- Role or permission level\n    manager_employee_id character varying(64), -- FK to self for reporting structure\n    PRIMARY KEY (employee_id)\n)\nCREATE TABLE government_services.appointments ( appointment_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, employee_id character varying(64), location_id character varying(64), service_id character varying(64), scheduled_start_time timestamp NOT NULL, scheduled_end_time timestamp, purpose text NOT NULL, status character varying(30) NOT NULL, booking_method character varying(50), created_at timestamp NOT NULL, notes text, PRIMARY KEY (appointment_id) )\n"}
{"conversations": [{"role": "user", "content": "For each event, display its event_id, the event_id of the previous event in the same transaction (if any), and the log_index of both events."}, {"role": "assistant", "content": "SELECT curr.event_id   AS current_event_id,\n       prev.event_id   AS previous_event_id,\n       curr.log_index  AS current_log_index,\n       prev.log_index  AS previous_log_index,\n       curr.transaction_id\nFROM web3.events curr\nLEFT JOIN web3.events prev\n  ON curr.transaction_id = prev.transaction_id\n AND curr.log_index = prev.log_index + 1;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.events ( event_id character varying(64) NOT NULL, contract_id character varying(64) NOT NULL, event_name character varying(128) NOT NULL, data text NOT NULL, emitted_at timestamp NOT NULL, transaction_id character varying(64) NOT NULL, log_index integer NOT NULL, PRIMARY KEY (event_id) )\n"}
{"conversations": [{"role": "user", "content": "Show me the top 5 tokens by 24-hour trading volume on the Ethereum chain, along with their narrative and 7-day price change percentage."}, {"role": "assistant", "content": "SELECT t.token_symbol, t.narrative, t.price_change_percentage_7d FROM token_basic_info t WHERE t.chain = 'Ethereum' ORDER BY CAST(t.total_volume AS numeric) DESC LIMIT 5;"}, {"role": "user", "content": "Can you also include their liquidity from the token_dexpool_info table?"}, {"role": "assistant", "content": "SELECT t.token_symbol, t.narrative, t.price_change_percentage_7d, d.liquidity FROM token_basic_info t JOIN token_dexpool_info d ON t.token_symbol = d.token_symbol AND t.chain = d.chain WHERE t.chain = 'Ethereum' ORDER BY CAST(t.total_volume AS 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 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, -- the id of dexpool token_name character varying(100) NOT NULL, -- the name of the token in the dexpool token_symbol character varying(100) NOT NULL, -- the token's symbol chain text, -- the chain that the dexpool resides price double precision, -- the current price of the token price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour price_change_percentage_6h double precision, -- change in value divided by the absolute price value of the original token price in 6 hours price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours makers_24h double precision, -- the makers of the dex pool in 24 hours volume_24h double precision, -- the trade volume of the dex pool in 24 hours liquidity double precision, -- the liquidity of the dex pool market_cap double precision, -- the market cap of the token trend_rank bigint, -- the rank of token in the dex pool of recent trending, value 1 expresses the most popular token. ,PRIMARY KEY (pair_address, chain) )\nCREATE TABLE smart_money_profit ( address character varying(100) NOT NULL, -- the user's address rank INT, -- the rank of the address in trade performance, value 1 expresses the best address. profit numeric(38,6), -- the profit user made in a month roi numeric(38,2), -- the roi of the user in a month realized_ratio numeric(38,2), -- the percentage of the user's realized profit most_profit_token character varying(100), -- the token symbol of the user's most profitable trade last_trade_time character varying(100), -- the last trade time of the user chain character varying(100), -- the chain that the address resides PRIMARY KEY (address, chain) )\nCREATE TABLE smart_money_token_performance ( token_address character varying(100) NOT NULL, -- the token's address token_symbol character varying(100), -- the tokens's symbol pnl numeric(38,2), -- the profit users made on this token net_flow numeric(38,2), -- the netflow of the token, means the money user spent minus the the money user sold of this token avg_cost numeric(38,16), -- the average cost price of user spent on this token price double precision, -- the current price of the token realized_ratio numeric(10,2), -- the ratio user sold of the token roi numeric(10,2), -- the roi users made of this token chain character varying(100), -- the chain that the token resides PRIMARY KEY (token_address, chain) )\nCREATE TABLE smart_money_token_inflow ( token_address character varying(100) NOT NULL, -- the token's address token_symbol character varying(100), -- the tokens's symbol token_amount numeric(38,2), -- the absolute value of the amount if user bought minus  the amount user sold of this token usd_value numeric(38,2), -- the absolute usd value of the bought token minus sold token avg_price numeric(38,6), -- the average cost price of user spent on this token type int, -- the direction of the trade on this token. 1 means buying, 2 means selling address_amount integer, -- the amount of the user bought this token narrative character varying(100), -- the category or narrative of the token chain character varying(100), -- the chain that the token resides ,PRIMARY KEY (token_address, chain) )\n"}
{"conversations": [{"role": "user", "content": "Show each user and the count of users who registered before them."}, {"role": "assistant", "content": "SELECT u.username,\n       COUNT(prev.user_id) AS earlier_count\nFROM trading_platform.users u\nLEFT JOIN trading_platform.users prev\n  ON prev.created_at < u.created_at\nGROUP BY u.username;"}, {"role": "user", "content": "Filter to only include users who have at least 5 earlier users."}, {"role": "assistant", "content": "SELECT u.username,\n       COUNT(prev.user_id) AS earlier_count\nFROM trading_platform.users u\nLEFT JOIN trading_platform.users prev\n  ON prev.created_at < u.created_at\nGROUP BY u.username\nHAVING COUNT(prev.user_id) >= 5;"}, {"role": "user", "content": "Also include their email and the earliest registration date among the earlier users."}, {"role": "assistant", "content": "SELECT u.username,\n       u.email,\n       COUNT(prev.user_id) AS earlier_count,\n       MIN(prev.created_at) AS earliest_prev_created\nFROM trading_platform.users u\nLEFT JOIN trading_platform.users prev\n  ON prev.created_at < u.created_at\nGROUP BY u.username, u.email\nHAVING COUNT(prev.user_id) >= 5;"}, {"role": "user", "content": "Finally, order the results by the earliest_prev_created ascending and limit to the top 10."}, {"role": "assistant", "content": "SELECT u.username,\n       u.email,\n       COUNT(prev.user_id) AS earlier_count,\n       MIN(prev.created_at) AS earliest_prev_created\nFROM trading_platform.users u\nLEFT JOIN trading_platform.users prev\n  ON prev.created_at < u.created_at\nGROUP BY u.username, u.email\nHAVING COUNT(prev.user_id) >= 5\nORDER BY earliest_prev_created 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 trading_platform.users ( user_id text PRIMARY KEY, username text, email text, password_hash text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show me pairs of passengers who share the same loyalty program, including their IDs, first and last names, and the loyalty_program_id."}, {"role": "assistant", "content": "SELECT p1.passenger_id AS passenger1_id, p1.first_name AS first1, p1.last_name AS last1, p2.passenger_id AS passenger2_id, p2.first_name AS first2, p2.last_name AS last2, p1.loyalty_program_id FROM transportation.passengers p1 JOIN transportation.passengers p2 ON p1.loyalty_program_id = p2.loyalty_program_id AND p1.passenger_id < p2.passenger_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.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": "Show all comments that are replies, including the comment_id, parent_comment_id, and post_id."}, {"role": "assistant", "content": "SELECT comment_id, parent_comment_id, post_id FROM social_media.comments WHERE parent_comment_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 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 )\n"}
{"conversations": [{"role": "user", "content": "I need a list of users who have commented on their own posts. For each, return user_id, username, and the total number of such comments, ordered by comment count descending."}, {"role": "assistant", "content": "SELECT u.user_id,\n       u.username,\n       COUNT(c.comment_id) AS comment_count\nFROM social_media.users u\nJOIN social_media.posts p ON u.user_id = p.user_id\nJOIN social_media.comments c ON p.post_id = c.post_id AND c.user_id = u.user_id\nGROUP BY u.user_id, u.username\nORDER BY comment_count DESC;"}, {"role": "user", "content": "Actually, please include only comments made after '2024-06-01'."}, {"role": "assistant", "content": "SELECT u.user_id,\n       u.username,\n       COUNT(c.comment_id) AS comment_count\nFROM social_media.users u\nJOIN social_media.posts p ON u.user_id = p.user_id\nJOIN social_media.comments c ON p.post_id = c.post_id\n  AND c.user_id = u.user_id\nWHERE c.created_at > '2024-06-01'\nGROUP BY u.user_id, u.username\nORDER BY comment_count DESC;"}, {"role": "user", "content": "And include only users where is_verified is true."}, {"role": "assistant", "content": "SELECT u.user_id,\n       u.username,\n       COUNT(c.comment_id) AS comment_count\nFROM social_media.users u\nJOIN social_media.posts p ON u.user_id = p.user_id\nJOIN social_media.comments c ON p.post_id = c.post_id\n  AND c.user_id = u.user_id\nWHERE c.created_at > '2024-06-01'\n  AND u.is_verified = TRUE\nGROUP BY u.user_id, u.username\nORDER BY comment_count DESC;"}, {"role": "user", "content": "Finally, order the results by username ascending instead of comment count."}, {"role": "assistant", "content": "SELECT u.user_id,\n       u.username,\n       COUNT(c.comment_id) AS comment_count\nFROM social_media.users u\nJOIN social_media.posts p ON u.user_id = p.user_id\nJOIN social_media.comments c ON p.post_id = c.post_id\n  AND c.user_id = u.user_id\nWHERE c.created_at > '2024-06-01'\n  AND u.is_verified = TRUE\nGROUP BY u.user_id, u.username\nORDER BY u.username 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 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 all beneficiaries who have a percentage share greater than 75%. Show their first name, last name, and percentage share."}, {"role": "assistant", "content": "SELECT T1.first_name, T1.last_name, T1.percentage_share FROM insurance.policy_beneficiaries AS T1 WHERE T1.percentage_share > 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 insurance.claims (\n    claim_id character varying(64) NOT NULL, -- unique identifier for the claim\n    policy_id character varying(64) NOT NULL, -- identifier of the policy under which the claim is made (FK to policies)\n    customer_id character varying(64) NOT NULL, -- identifier of the customer making the claim (FK to customers)\n    incident_date timestamp NOT NULL, -- date and time of the incident leading to the claim\n    reported_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- date the claim was reported\n    description text NOT NULL, -- detailed description of the incident and claim\n    estimated_loss numeric(15, 2), -- initial estimated cost of the loss\n    status character varying(30) NOT NULL, -- e.g., Filed, Processing, Under Review, Approved, Denied, Settled\n    settlement_amount numeric(15, 2), -- final amount paid out\n    settlement_date date,\n    claim_handler_id character varying(64), -- identifier for the employee handling the claim (FK to employees/adjusters)\n    police_report_number character varying(100),\n    PRIMARY KEY (claim_id)\n)\nCREATE TABLE insurance.insurance_products (\n    product_id character varying(64) NOT NULL, -- unique identifier for the insurance product\n    product_name character varying(150) NOT NULL, -- name of the insurance product (e.g., 'Comprehensive Auto Insurance')\n    product_type character varying(50) NOT NULL, -- category like 'Auto', 'Home', 'Life', 'Health', 'Travel'\n    description text, -- detailed description of the product\n    base_premium numeric(10, 2) NOT NULL, -- starting premium before adjustments\n    coverage_details text, -- details about what is covered (could be JSON or structured text)\n    underwriting_rules text, -- rules used for assessing risk and eligibility\n    is_active boolean NOT NULL DEFAULT true, -- whether the product is currently offered\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n    updated_at timestamp,\n    PRIMARY KEY (product_id)\n)\nCREATE TABLE insurance.premium_payments (\n    payment_id character varying(64) NOT NULL, -- unique identifier for the payment\n    policy_id character varying(64) NOT NULL, -- identifier of the policy the payment is for (FK to policies)\n    customer_id character varying(64) NOT NULL, -- identifier of the customer making the payment (FK to customers)\n    payment_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- date the payment was received\n    amount_paid numeric(12, 2) NOT NULL, -- amount of the payment\n    payment_method character varying(50), -- e.g., Credit Card, Bank Transfer, Check\n    transaction_reference character varying(128) UNIQUE, -- reference from payment processor\n    due_date date, -- due date for this payment installment\n    payment_period_start date, -- start date of the period this payment covers\n    payment_period_end date, -- end date of the period this payment covers\n    status character varying(30) NOT NULL DEFAULT 'Completed', -- e.g., Completed, Pending, Failed, Refunded\n    PRIMARY KEY (payment_id)\n)\nCREATE TABLE insurance.policy_beneficiaries (\n    beneficiary_id character varying(64) NOT NULL, -- unique identifier for the beneficiary entry\n    policy_id character varying(64) NOT NULL, -- identifier of the life/relevant policy (FK to policies)\n    customer_id character varying(64) NOT NULL, -- identifier of the beneficiary (could be FK to customers or store info directly)\n    first_name character varying(100) NOT NULL, -- beneficiary first name (if not linking to customers table)\n    last_name character varying(100) NOT NULL, -- beneficiary last name\n    relationship character varying(50) NOT NULL, -- relationship to the policyholder (e.g., Spouse, Child, Parent)\n    percentage_share numeric(5, 2) NOT NULL CHECK (percentage_share > 0 AND percentage_share <= 100), -- percentage of payout\n    contact_info text, -- contact details for the beneficiary\n    added_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n    PRIMARY KEY (beneficiary_id),\n    UNIQUE (policy_id, customer_id) -- Ensure a person is listed only once per policy\n)\n"}
{"conversations": [{"role": "user", "content": "I’d like to get the count of notifications each user received for their own posts in the last 30 days."}, {"role": "assistant", "content": "SELECT u.user_id, u.username, COUNT(n.notification_id) AS notification_count\nFROM social_media.notifications n\nJOIN social_media.posts p ON n.target_entity_type = 'post' AND n.target_entity_id = p.post_id\nJOIN social_media.users u ON p.user_id = u.user_id\nWHERE n.created_at >= now() - interval '30 days'\nGROUP BY u.user_id, u.username;"}, {"role": "user", "content": "Now, I only want notifications of type 'like' or 'comment'."}, {"role": "assistant", "content": "SELECT u.user_id, u.username, COUNT(n.notification_id) AS notification_count\nFROM social_media.notifications n\nJOIN social_media.posts p ON n.target_entity_type = 'post' AND n.target_entity_id = p.post_id\nJOIN social_media.users u ON p.user_id = u.user_id\nWHERE n.created_at >= now() - interval '30 days'\n  AND n.notification_type IN ('like', 'comment')\nGROUP BY u.user_id, u.username;"}, {"role": "user", "content": "Show me only the top 3 users by notification_count."}, {"role": "assistant", "content": "SELECT u.user_id, u.username, COUNT(n.notification_id) AS notification_count\nFROM social_media.notifications n\nJOIN social_media.posts p ON n.target_entity_type = 'post' AND n.target_entity_id = p.post_id\nJOIN social_media.users u ON p.user_id = u.user_id\nWHERE n.created_at >= now() - interval '30 days'\n  AND n.notification_type IN ('like', 'comment')\nGROUP BY u.user_id, u.username\nORDER BY notification_count DESC\nLIMIT 3;"}, {"role": "user", "content": "Also include the email of these top users."}, {"role": "assistant", "content": "SELECT u.user_id, u.username, u.email, COUNT(n.notification_id) AS notification_count\nFROM social_media.notifications n\nJOIN social_media.posts p ON n.target_entity_type = 'post' AND n.target_entity_id = p.post_id\nJOIN social_media.users u ON p.user_id = u.user_id\nWHERE n.created_at >= now() - interval '30 days'\n  AND n.notification_type IN ('like', 'comment')\nGROUP BY u.user_id, u.username, u.email\nORDER BY notification_count 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 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.hashtags ( hashtag_id text, tag_name text, created_at timestamp )\nCREATE TABLE social_media.messages ( message_id text, conversation_id text, sender_user_id text, content text, media_url text, media_type text, sent_at timestamp, read_at timestamp )\nCREATE TABLE social_media.conversations ( conversation_id text, created_at timestamp, last_message_at timestamp, is_group_chat boolean, group_name text )\nCREATE TABLE social_media.conversation_participants ( participant_id text, conversation_id text, user_id text, joined_at timestamp, last_read_at timestamp )\nCREATE TABLE social_media.notifications ( notification_id text, recipient_user_id text, sender_user_id text, notification_type text, target_entity_id text, target_entity_type text, created_at timestamp, read_at timestamp )\nCREATE TABLE social_media.user_settings ( setting_id text, user_id text, theme text, email_notifications_enabled boolean, push_notifications_enabled boolean, private_profile boolean, updated_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Retrieve all documents uploaded in 2024, showing document_id, uploaded_by, and uploaded_at."}, {"role": "assistant", "content": "SELECT document_id,\n       uploaded_by,\n       uploaded_at\nFROM insurance.claim_documents\nWHERE uploaded_at >= '2024-01-01'\n  AND uploaded_at < '2025-01-01';"}, {"role": "user", "content": "Actually, please only include documents larger than 1MB."}, {"role": "assistant", "content": "SELECT document_id,\n       uploaded_by,\n       uploaded_at,\n       file_size_bytes\nFROM insurance.claim_documents\nWHERE uploaded_at >= '2024-01-01'\n  AND uploaded_at < '2025-01-01'\n  AND file_size_bytes > 1048576;"}, {"role": "user", "content": "And sort them by file_size_bytes descending."}, {"role": "assistant", "content": "SELECT document_id,\n       uploaded_by,\n       uploaded_at,\n       file_size_bytes\nFROM insurance.claim_documents\nWHERE uploaded_at >= '2024-01-01'\n  AND uploaded_at < '2025-01-01'\n  AND file_size_bytes > 1048576\nORDER BY file_size_bytes DESC;"}, {"role": "user", "content": "Limit the results to the first 5 entries."}, {"role": "assistant", "content": "SELECT document_id,\n       uploaded_by,\n       uploaded_at,\n       file_size_bytes\nFROM insurance.claim_documents\nWHERE uploaded_at >= '2024-01-01'\n  AND uploaded_at < '2025-01-01'\n  AND file_size_bytes > 1048576\nORDER BY file_size_bytes 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.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": "Find all addresses that have only sent tokens (appear in from_address) but have never received any (do not appear in to_address)."}, {"role": "assistant", "content": "SELECT DISTINCT from_address FROM web3.token_transfers WHERE from_address NOT IN (SELECT DISTINCT to_address FROM web3.token_transfers);"}, {"role": "user", "content": "For these addresses that have only sent tokens, show the total value of tokens each has sent."}, {"role": "assistant", "content": "SELECT t1.from_address, SUM(t1.value) AS total_sent_value FROM web3.token_transfers AS t1 WHERE t1.from_address NOT IN (SELECT DISTINCT to_address FROM web3.token_transfers) GROUP BY t1.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 ( 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": "Show me the top 5 narratives by market cap, along with their top 3 coins and 24-hour trading volume."}, {"role": "assistant", "content": "SELECT narrative, top_3_coins, volume_24h FROM narrative_info ORDER BY market_cap DESC LIMIT 5;"}, {"role": "user", "content": "Can you also include the 7-day price change percentage and filter for narratives with a positive 7-day price change?"}, {"role": "assistant", "content": "SELECT narrative, top_3_coins, volume_24h, price_change_percentage_7d FROM narrative_info WHERE price_change_percentage_7d > 0 ORDER BY market_cap 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 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) )\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": "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": "Show me all prescriptions for medication with ID 'MED123' along with the patient IDs and dosages."}, {"role": "assistant", "content": "SELECT prescription_id, patient_id, dosage FROM healthcare.prescriptions WHERE medication_id = 'MED123';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.prescriptions ( prescription_id text 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 )\n"}
{"conversations": [{"role": "user", "content": "Show me the top 5 most recently minted NFTs on the Ethereum blockchain with their contract_address, token_id, name, and rarity_score from nft_metadata."}, {"role": "assistant", "content": "SELECT contract_address, token_id, name, rarity_score\nFROM nft_metadata\nWHERE blockchain = 'Ethereum'\nORDER BY mint_block_number DESC\nLIMIT 5;"}, {"role": "user", "content": "Also include the collection name, floor_price, and token_count from nft_collections for each NFT's collection."}, {"role": "assistant", "content": "SELECT m.contract_address AS nft_contract,\n       m.token_id,\n       m.name,\n       m.rarity_score,\n       c.name       AS collection_name,\n       c.floor_price,\n       c.token_count\nFROM nft_metadata m\nJOIN nft_collections c\n  ON m.blockchain = c.blockchain\n AND m.contract_address = c.contract_address\nWHERE m.blockchain = 'Ethereum'\nORDER BY m.mint_block_number 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 erc20_balances ( block_number bigint, contract_address varchar, wallet_address varchar, amount varchar, pk varchar )\nCREATE TABLE erc20_balances_historical ( block_number bigint, contract_address text, wallet_address text, amount text, pk integer )\nCREATE TABLE nft_holders ( block_number.bigint, contract_address.text, wallet_address.text, token_id.text, contract_type.text, amount.text, pk.text )\nCREATE TABLE nft_holder_historical (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    contract_address varchar NOT NULL, -- Event contract address\n    wallet_address varchar NOT NULL, -- The wallet address for the contract(with bloom filter)\n    token_id varchar NOT NULL, -- NFT token id\n    contract_type varchar NOT NULL, -- NFT contract type\n    amount varchar NOT NULL, -- The quantity held in the wallet\n    pk integer NOT NULL  -- Partition key for the table(floor(block_number / 7200))\n)\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_coins_metadata (\n    object_id varchar NOT NULL, -- object id of the coin metadata object\n    coin_type varchar NOT NULL, -- coin type, eg. 0x...66::reap_token::REAP_TOKEN\n    status varchar NOT NULL, -- coin status, eg. exists, deleted\n    decimals bigint NOT NULL, -- decimals of the coin\n    description varchar NOT NULL, -- description of the coin\n    icon_url varchar NOT NULL, -- icon url of the coin\n    symbol varchar NOT NULL, -- symbol of the coin\n    name varchar NOT NULL  -- name of the coin\n)\nCREATE TABLE 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.text, blockchain.text, address.text, decimals.bigint, symbol.text, 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_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_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 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": "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": "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": "Retrieve the username and email for every user, along with the wallet ID and associated address ID for any wallets they own."}, {"role": "assistant", "content": "SELECT\n    u.username,\n    u.email,\n    w.wallet_id,\n    w.address_id\nFROM\n    blockchain.users AS u\nLEFT JOIN\n    blockchain.wallets AS w ON u.user_id = w.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 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 character varying(128) NOT NULL, public_key text NOT NULL, balance numeric(38,14) NOT NULL, PRIMARY KEY (address_id) )\nCREATE TABLE blockchain.wallets ( wallet_id.text, user_id.text, address_id.text, private_key.text )\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) )\nCREATE TABLE blockchain.smart_contracts ( contract_id character varying(64) NOT NULL, creator_address character varying(128) NOT NULL, code text NOT NULL, timestamp timestamp NOT NULL, PRIMARY KEY (contract_id) )\n"}
{"conversations": [{"role": "user", "content": "What is the performance review score for employee with ID 'EMP456' for the last quarter?"}, {"role": "assistant", "content": "I'm sorry, but I can't assist with information about performance review scores as this data is not included in the employees table."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE manufacturing.employees ( employee_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, job_title character varying(128) NOT NULL, skill_certifications text, hire_date date NOT NULL, assigned_line_id character varying(64), employment_status character varying(50) NOT NULL, supervisor_employee_id character varying(64), PRIMARY KEY (employee_id) )\n"}
{"conversations": [{"role": "user", "content": "Show 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": "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": "Get me all unbilled billable time entries with their entry_id, case_id, lawyer_id, hours_spent, and billing_rate."}, {"role": "assistant", "content": "SELECT entry_id,\n       case_id,\n       lawyer_id,\n       hours_spent,\n       billing_rate\nFROM legal_services.time_entries\nWHERE is_billable = TRUE\n  AND is_billed = FALSE;"}, {"role": "user", "content": "Actually, I only want entries for lawyer 'lawyer_123'."}, {"role": "assistant", "content": "SELECT entry_id,\n       case_id,\n       lawyer_id,\n       hours_spent,\n       billing_rate\nFROM legal_services.time_entries\nWHERE is_billable = TRUE\n  AND is_billed = FALSE\n  AND lawyer_id = 'lawyer_123';"}, {"role": "user", "content": "Also, sort the results by hours_spent in descending order."}, {"role": "assistant", "content": "SELECT entry_id,\n       case_id,\n       lawyer_id,\n       hours_spent,\n       billing_rate\nFROM legal_services.time_entries\nWHERE is_billable = TRUE\n  AND is_billed = FALSE\n  AND lawyer_id = 'lawyer_123'\nORDER BY 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.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": "Find the address that has the highest total amount across all its UTXOs."}, {"role": "assistant", "content": "SELECT address FROM utxos GROUP BY address ORDER BY SUM(amount) DESC LIMIT 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 trading_platform.users ( user_id.text, username.text, email.text, password_hash.text, created_at.timestamp )\nCREATE TABLE trading_platform.trades ( trade_id.text, order_id.text, buyer_id.text, seller_id.text, asset_id.text, quantity.numeric, price.numeric, traded_at.timestamp )\nCREATE TABLE trading_platform.assets ( asset_id.text, name.text, symbol.text, type.text )\nCREATE TABLE trading_platform.utxos ( utxo_id.text, transaction_id.text, output_index.integer, address.text, amount.numeric, spent.boolean )\nCREATE TABLE trading_platform.dapps ( dapp_id.text, name.text, description.text, url.text )\nCREATE TABLE trading_platform.peers ( peer_id.text, ip_address.text, port.integer, last_seen.timestamp )\nCREATE TABLE trading_platform.metadata ( metadata_id.text, asset_id.text, key.text, value.text )\nCREATE TABLE trading_platform.kyc_audit ( kyc_audit_id.text, user_id.text, status.text, reviewed_at.timestamp )\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": "List the first and last name of each citizen along with the city and state of the service location for their agency."}, {"role": "assistant", "content": "SELECT c.first_name, c.last_name, sl.city, sl.state\nFROM government_services.citizens c\nJOIN government_services.payments p ON c.citizen_id = p.citizen_id\nJOIN government_services.employees e ON p.application_id IS NOT NULL AND e.agency_id IS NOT NULL\nJOIN government_services.service_locations sl ON e.agency_id = sl.agency_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id text, national_id_number text, first_name text, last_name text, date_of_birth date, gender text, primary_address text, contact_email text, contact_phone text, registration_date timestamp, is_verified boolean )\nCREATE TABLE government_services.payments ( payment_id text, application_id text, citizen_id text, service_id text, amount numeric, currency text, payment_method text, payment_provider_reference text, payment_timestamp timestamp, status text, notes text )\nCREATE TABLE government_services.employees ( employee_id text, agency_id text, first_name text, last_name text, job_title text, department text, work_email text, work_phone text, hire_date date, termination_date date, access_level text, manager_employee_id text )\nCREATE TABLE government_services.service_locations ( location_id text, agency_id text, location_name text, address text, city text, state text, postal_code text, latitude numeric, longitude numeric, operating_hours text, contact_phone text, is_accessible boolean )\n"}
{"conversations": [{"role": "user", "content": "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": "How many documents are there for each document_type? Show document_type and count ordered by the count in descending order."}, {"role": "assistant", "content": "SELECT document_type,\n       COUNT(*) AS count\nFROM legal_services.documents\nGROUP BY document_type\nORDER BY count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.documents ( document_id.text, case_id.text, document_name.text, document_type.text, storage_path.text, uploaded_by_lawyer_id.text, upload_timestamp.timestamp, version.integer, description.text )\n"}
{"conversations": [{"role": "user", "content": "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": "How many games are available in each genre? List genre and game_count."}, {"role": "assistant", "content": "SELECT genre, COUNT(*) AS game_count\nFROM gaming_technology.games\nGROUP BY genre;"}, {"role": "user", "content": "Now only include genres with at least 5 games."}, {"role": "assistant", "content": "SELECT genre, COUNT(*) AS game_count\nFROM gaming_technology.games\nGROUP BY genre\nHAVING COUNT(*) >= 5;"}, {"role": "user", "content": "Also show the earliest release_date for each of these genres."}, {"role": "assistant", "content": "SELECT genre, COUNT(*) AS game_count, MIN(release_date) AS earliest_release\nFROM gaming_technology.games\nGROUP BY genre\nHAVING COUNT(*) >= 5;"}, {"role": "user", "content": "Sort by game_count descending and limit to top 3."}, {"role": "assistant", "content": "SELECT genre, COUNT(*) AS game_count, MIN(release_date) AS earliest_release\nFROM gaming_technology.games\nGROUP BY genre\nHAVING COUNT(*) >= 5\nORDER BY game_count 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 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 )\n"}
{"conversations": [{"role": "user", "content": "Show me the total transaction amount by transaction_type for all transactions processed by employees in the 'Trading' department, along with their department name."}, {"role": "assistant", "content": "SELECT t.transaction_type, SUM(t.amount) AS total_amount, e.department\nFROM financial_services.transactions t\nJOIN financial_services.employees e ON t.account_id IN (\n    SELECT account_id \n    FROM financial_services.accounts \n    WHERE branch_id = e.branch_id\n)\nWHERE e.department = 'Trading'\nGROUP BY t.transaction_type, e.department;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.transactions (\n    transaction_id character varying(64) NOT NULL, -- unique identifier for the transaction\n    account_id character varying(64) NOT NULL, -- account involved in the transaction\n    related_account_id character varying(64), -- counterpart account for transfers\n    transaction_type character varying(50) NOT NULL, -- e.g., Deposit, Withdrawal, Transfer, Payment, Fee, Interest\n    amount numeric(19, 4) NOT NULL, -- transaction amount\n    currency character varying(3) NOT NULL, -- transaction currency\n    transaction_date timestamp NOT NULL, -- exact time of the transaction\n    effective_date date NOT NULL, -- date the transaction affects the balance\n    description text, -- description or memo of the transaction\n    status character varying(32) NOT NULL, -- e.g., Pending, Completed, Failed, Reversed\n    reference_number character varying(128), -- external reference if applicable (e.g., check number)\n    PRIMARY KEY (transaction_id),\n    FOREIGN KEY (account_id) REFERENCES financial_services.accounts(account_id),\n    FOREIGN KEY (related_account_id) REFERENCES financial_services.accounts(account_id)\n)\nCREATE TABLE financial_services.employees ( employee_id text, first_name text, last_name text, job_title text, department text, branch_id text, email text, phone_extension text, hire_date date, termination_date date, manager_id text, status text )\n"}
{"conversations": [{"role": "user", "content": "For each user, find the next user who registered after them. Return the first user's user_id and username, the second user's user_id and username, and the time difference in hours."}, {"role": "assistant", "content": "SELECT\n  u1.user_id AS user1_id,\n  u1.username AS user1_name,\n  u2.user_id AS user2_id,\n  u2.username AS user2_name,\n  EXTRACT(EPOCH FROM (u2.created_at - u1.created_at)) / 3600 AS hours_diff\nFROM web3.users u1\nJOIN web3.users u2\n  ON u2.created_at = (\n    SELECT MIN(created_at)\n    FROM web3.users\n    WHERE created_at > u1.created_at\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.users ( user_id.text, username.text, email.text, password_hash.text, created_at.timestamp )\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": "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": "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 the names of agencies along with their website URLs which were established before the year 2000."}, {"role": "assistant", "content": "SELECT agency_name, website_url\nFROM government_services.agencies\nWHERE established_date < '2000-01-01';"}], "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.citizens ( citizen_id text PRIMARY KEY, national_id_number text, first_name text, last_name text, date_of_birth date, gender text, primary_address text, contact_email text, contact_phone text, registration_date timestamp, is_verified boolean )\nCREATE TABLE government_services.agencies ( agency_id.text, agency_name.text, jurisdiction_level.text, primary_contact_email.text, main_phone_number.text, website_url.text, established_date.date, parent_agency_id.text )\nCREATE TABLE government_services.services ( service_id text, agency_id text, service_name text, description text, category text, eligibility_criteria text, standard_fee numeric, average_processing_time_days integer, is_active boolean, online_application_url text )\nCREATE TABLE government_services.applications ( application_id.text, citizen_id.text, service_id.text, submitted_at.timestamp, status.text, last_updated_at.timestamp, assigned_employee_id.text, decision_date.date, notes.text, reference_number.text )\nCREATE TABLE government_services.payments ( payment_id character varying(64) NOT NULL, application_id character varying(64), citizen_id character varying(64) NOT NULL, service_id character varying(64), amount numeric(12, 2) NOT NULL, currency character varying(3) NOT NULL DEFAULT 'USD', payment_method character varying(50), payment_provider_reference character varying(128), payment_timestamp timestamp NOT NULL, status character varying(30) NOT NULL, notes text, PRIMARY KEY (payment_id) )\nCREATE TABLE government_services.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 (\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 ( 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": "For each snapshot_time in cex_token_balance, calculate the total usd_value across all exchanges and order by snapshot_time ascending."}, {"role": "assistant", "content": "SELECT snapshot_time,\n       SUM(usd_value) AS total_usd_value\nFROM cex_token_balance\nGROUP BY snapshot_time\nORDER BY snapshot_time 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 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": "How many 'ApprovalForAll' events are recorded for each ERC1155 contract address 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": "For these contracts, can you include the collection name from the `nft_collections` table and filter to only show collections on the 'Ethereum' blockchain that have more than 100 approval events?"}, {"role": "assistant", "content": "SELECT a.contract_address, c.name, COUNT(a.contract_address) AS approval_count FROM erc1155_approval_for_all AS a JOIN nft_collections AS c ON a.contract_address = c.contract_address WHERE c.blockchain = 'Ethereum' GROUP BY a.contract_address, c.name HAVING COUNT(a.contract_address) > 100 ORDER BY approval_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 erc1155_approval_for_all ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash varchar, log_index integer, contract_address varchar )\nCREATE TABLE erc20_balances ( block_number bigint, contract_address 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 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 (\n    blockchain varchar NOT NULL, -- blockchain fields for the functionType  in contract\n    contract_address varchar NOT NULL, -- Contract address(with bloom filter)\n    name varchar NOT NULL, -- name fields for the functionType  in contract\n    symbol varchar NOT NULL, -- symbol fields for the functionType  in contract\n    deploy_block_number bigint NOT NULL, -- deploy_block_number fields for the functionType  in contract\n    deploy_block_time bigint NOT NULL, -- deploy_block_time fields for the functionType  in contract\n    erc_type varchar NOT NULL, -- The type of token\n    owner varchar NOT NULL, -- owner fields for the functionType  in contract\n    traits varchar NOT NULL, -- traits fields for the functionType  in contract\n    description varchar NOT NULL, -- description fields for the functionType  in contract\n    slug varchar NOT NULL, -- slug fields for the functionType  in contract\n    media_info varchar NOT NULL, -- media_info fields for the functionType  in contract\n    image_url varchar NOT NULL, -- image_url fields for the functionType  in contract\n    banner_image_url varchar NOT NULL, -- banner_image_url fields for the functionType  in contract\n    updated_at bigint NOT NULL, -- updated_at fields for the functionType  in contract\n    banner varchar NOT NULL, -- banner fields for the functionType  in contract\n    token_count bigint NOT NULL, -- token_count fields for the functionType  in contract\n    floor_price varchar NOT NULL, -- floor_price fields for the functionType  in contract\n    floor_price_symbol varchar NOT NULL, -- floor_price_symbol fields for the functionType  in contract\n    floor_price_contract varchar NOT NULL, -- floor_price_contract fields for the functionType  in contract\n    pk integer NOT NULL  -- Partition key for the table(floor(deploy_block_time / 1000 / 86400 / 30))\n)\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 ( 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 ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar(255) NOT NULL, wallet_address varchar(42) NOT NULL, total_supply varchar NOT NULL, amount varchar NOT NULL )\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp, 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 varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp(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 (\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(20) NOT NULL, -- Ticker:  Identifier of the inscription\n    max_supply decimal(38,0) NOT NULL, -- Max supply: Set max supply of the inscription\n    lim decimal(38,0) NOT NULL, -- Mint limit: limit per inscription\n    wlim decimal(38,0) NOT NULL, -- Limit of each address can maximum mint\n    dec integer NOT NULL, -- Decimal for minimum divie\n    creator varchar(42) NOT NULL, -- Address originating the inscription (matches from_address in transactions table)\n    minted decimal(38,0) NOT NULL, -- Sum of minted amount\n    holders decimal(38,0) NOT NULL, -- Count of holders\n    txs decimal(38,0) NOT NULL, -- Count of transactions\n    updated_timestamp timestamp(3) NOT NULL, -- Timestamp of update\n    completed_timestamp timestamp(3) NOT NULL, -- Timestamp of minted completed\n    id varchar(255) NOT NULL  -- id fields for the functionType  in contract asc20\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": "List the first name, last name, license number, and status for all drivers whose license expires in the next 6 months."}, {"role": "assistant", "content": "SELECT\n  first_name,\n  last_name,\n  license_number,\n  status\nFROM transportation.drivers\nWHERE\n  license_expiry_date BETWEEN CURRENT_DATE AND CURRENT_DATE + INTERVAL '6 month'\nORDER BY\n  license_expiry_date;"}, {"role": "user", "content": "Now, count how many drivers from that list have an 'Active' status."}, {"role": "assistant", "content": "SELECT\n  COUNT(*)\nFROM transportation.drivers\nWHERE\n  license_expiry_date BETWEEN CURRENT_DATE AND CURRENT_DATE + INTERVAL '6 month' AND status = 'Active';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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 )\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": "Give me the total billed amount for each invoice in 2024."}, {"role": "assistant", "content": "SELECT invoice_id, SUM(hours_spent * billing_rate) AS total_billed_amount FROM legal_services.time_entries WHERE is_billed = TRUE AND EXTRACT(YEAR FROM date_worked) = 2024 GROUP BY invoice_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.time_entries ( entry_id text PRIMARY KEY, case_id text, lawyer_id text, date_worked date, hours_spent numeric, billing_rate numeric, description text, is_billable bool, is_billed bool, invoice_id text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show me all documents uploaded in 2024 that do not have a description."}, {"role": "assistant", "content": "SELECT document_id, file_name, uploaded_at\nFROM insurance.claim_documents\nWHERE uploaded_at >= '2024-01-01'\n  AND uploaded_at < '2025-01-01'\n  AND (description IS NULL OR description = '');"}], "system": "You are an SQL statement expert. Given the table structure 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 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": "Find documents that have the same document_name but are associated with different cases. Show the document name and the two different case IDs."}, {"role": "assistant", "content": "SELECT d1.document_name, d1.case_id AS case_id_1, d2.case_id AS case_id_2 FROM legal_services.documents AS d1 JOIN legal_services.documents AS d2 ON d1.document_name = d2.document_name WHERE d1.case_id <> d2.case_id AND d1.document_id < d2.document_id;"}, {"role": "user", "content": "Actually, only show pairs where at least one of the documents is of document_type 'Contract'."}, {"role": "assistant", "content": "SELECT d1.document_name, d1.case_id AS case_id_1, d2.case_id AS case_id_2 FROM legal_services.documents AS d1 JOIN legal_services.documents AS d2 ON d1.document_name = d2.document_name WHERE d1.case_id <> d2.case_id AND d1.document_id < d2.document_id AND (d1.document_type = 'Contract' OR d2.document_type = 'Contract');"}, {"role": "user", "content": "Also, only include pairs where both documents were uploaded in the year 2024."}, {"role": "assistant", "content": "SELECT d1.document_name, d1.case_id AS case_id_1, d2.case_id AS case_id_2 FROM legal_services.documents AS d1 JOIN legal_services.documents AS d2 ON d1.document_name = d2.document_name WHERE d1.case_id <> d2.case_id AND d1.document_id < d2.document_id AND (d1.document_type = 'Contract' OR d2.document_type = 'Contract') AND YEAR(d1.upload_timestamp) = 2024 AND YEAR(d2.upload_timestamp) = 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 legal_services.documents ( document_id.text, case_id.text, document_name.text, document_type.text, storage_path.text, uploaded_by_lawyer_id.text, upload_timestamp.timestamp, version.integer, description.text )\n"}
{"conversations": [{"role": "user", "content": "Show me the top 5 tokens by market cap on the Ethereum chain, along with their 24-hour trading volume and price from the token_basic_info table."}, {"role": "assistant", "content": "SELECT token_name, token_symbol, market_cap, total_volume, price FROM token_basic_info WHERE chain = 'Ethereum' ORDER BY market_cap DESC LIMIT 5;"}, {"role": "user", "content": "Can you also include their 7-day price change percentage and filter for tokens with a positive 24-hour price change?"}, {"role": "assistant", "content": "SELECT token_name, token_symbol, market_cap, total_volume, price, price_change_percentage_7d FROM token_basic_info WHERE chain = 'Ethereum' AND price_change_percentage_24h > 0 ORDER BY market_cap 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_basic_info ( coin_id character varying(100) NOT NULL, token_name character varying(100) NOT NULL, token_symbol character varying(100) NOT NULL, token_address character varying(100) NOT NULL, chain text, price double precision, price_change_percentage_1h double precision, price_change_percentage_24h double precision, price_change_percentage_7d double precision, highest_price_24h double precision, lowest_price_24h double precision, market_cap double precision, market_cap_rank bigint, market_cap_change_percentage_24h text, total_volume text, narrative text, trend_rank bigint )\nCREATE TABLE narrative_info ( narrative character varying(512) NOT NULL, top_3_coins text, price_change_percentage_1h double precision, price_change_percentage_24h double precision, price_change_percentage_7d double precision, market_cap double precision, volume_24h double precision, trend_rank bigint, token_num bigint )\nCREATE TABLE cex_token_balance ( snapshot_time character varying(32) NOT NULL, chain character varying(128) NOT NULL, address character varying(128) NOT NULL, exchange character varying(512) NOT NULL, token_address character varying(128) NOT NULL, token_symbol character varying(512), balance numeric(38,10), usd_value numeric(38,14), price double precision )\nCREATE TABLE smart_money_token_performance ( token_address character varying(100) NOT NULL, token_symbol character varying(100), pnl numeric(38,2), net_flow numeric(38,2), avg_cost numeric(38,16), price double precision, realized_ratio numeric(10,2), roi numeric(10,2), chain character varying(100) )\nCREATE TABLE smart_money_token_inflow ( token_address character varying(100) NOT NULL, token_symbol character varying(100), token_amount numeric(38,2), usd_value numeric(38,2), avg_price numeric(38,6), type int, address_amount integer, narrative character varying(100), chain character varying(100) )\n"}
{"conversations": [{"role": "user", "content": "What is the average speed of train number T9876 during its last journey?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information on the average speed of train number T9876 during its last journey. The data in the trains table does not include details about travel speed or journey-specific performance metrics."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.trains ( train_id.text, train_number.text, model.text, manufacturer.text, year_manufactured.integer, capacity.integer, status.text, last_maintenance_date.date, next_maintenance_date.date )\n"}
{"conversations": [{"role": "user", "content": "List group conversation names and the number of messages sent in each conversation after January 1, 2023."}, {"role": "assistant", "content": "SELECT c.group_name, COUNT(m.message_id) FROM social_media.conversations c JOIN social_media.messages m ON c.conversation_id = m.conversation_id WHERE c.is_group_chat = true AND m.sent_at >= '2023-01-01' GROUP BY c.conversation_id, c.group_name;"}, {"role": "user", "content": "Only show conversations that have more than 100 messages sent after that date."}, {"role": "assistant", "content": "SELECT c.group_name, COUNT(m.message_id) FROM social_media.conversations c JOIN social_media.messages m ON c.conversation_id = m.conversation_id WHERE c.is_group_chat = true AND m.sent_at >= '2023-01-01' GROUP BY c.conversation_id, c.group_name HAVING COUNT(m.message_id) > 100;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id text, username text, email text, password_hash text, full_name text, profile_picture_url text, bio text, location text, created_at timestamp, updated_at timestamp, is_verified boolean )\nCREATE TABLE social_media.posts ( post_id text, user_id text, content text, media_url text, media_type text, created_at timestamp, updated_at timestamp, visibility text, location_lat numeric, location_lon numeric )\nCREATE TABLE social_media.likes ( like_id text, user_id text, post_id text, comment_id text, created_at timestamp )\nCREATE TABLE social_media.follows ( follow_id text, follower_user_id text, following_user_id text, created_at timestamp )\nCREATE TABLE social_media.post_hashtags ( post_hashtag_id text, post_id text, hashtag_id text )\nCREATE TABLE social_media.messages ( message_id text, conversation_id text, sender_user_id text, content text, media_url text, media_type text, sent_at timestamp, read_at timestamp )\nCREATE TABLE social_media.conversations ( conversation_id text, created_at timestamp, last_message_at timestamp, is_group_chat boolean, group_name text )\nCREATE TABLE social_media.conversation_participants ( participant_id text, conversation_id text, user_id text, joined_at timestamp, last_read_at timestamp )\nCREATE TABLE social_media.notifications ( notification_id text, recipient_user_id text, sender_user_id text, notification_type text, target_entity_id text, target_entity_type text, created_at timestamp, read_at timestamp )\nCREATE TABLE social_media.user_settings ( setting_id text, user_id text, theme text, email_notifications_enabled boolean, push_notifications_enabled boolean, private_profile boolean, updated_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "List 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 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 fuel efficiency of the train car with car_id 'TC456'?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to information about the fuel efficiency of specific train cars. The data available in the train_cars table only includes details such as car_id, train_id, car_number, car_type, class, capacity, and features. If you have another question or need assistance with something else, 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.train_cars ( car_id.text, train_id.text, car_number.text, car_type.text, class.text, capacity.integer, features.text )\n"}
{"conversations": [{"role": "user", "content": "What are the training programs or certifications completed by a staff member with the role of Platform Supervisor?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to information about the training programs or certifications completed by staff members. The data available to me only includes basic staff details such as name, role, and contact information. For details on training or certifications, please refer to the HR department or relevant training records."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.staff ( staff_id text PRIMARY KEY, first_name text, last_name text, role text, primary_station_id text, employee_number text UNIQUE, hire_date date, contact_email text UNIQUE, contact_phone text, is_active boolean )\n"}
{"conversations": [{"role": "user", "content": "List 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": "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": "List the names of citizens who have submitted applications for services with a standard fee greater than 50."}, {"role": "assistant", "content": "SELECT DISTINCT T1.first_name, T1.last_name FROM government_services.citizens AS T1 JOIN government_services.applications AS T2 ON T1.citizen_id = T2.citizen_id JOIN government_services.services AS T3 ON T2.service_id = T3.service_id WHERE T3.standard_fee > 50;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( 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 (\n    service_id character varying(64) NOT NULL, -- unique identifier for the service\n    agency_id character varying(64) NOT NULL, -- FK to agencies table\n    service_name character varying(255) NOT NULL, -- name of the service (e.g., Driver's License Renewal)\n    description text,\n    category character varying(100), -- e.g., Licensing, Benefits, Taxation, Permits\n    eligibility_criteria text, -- description of who is eligible\n    standard_fee numeric(10, 2) DEFAULT 0.00, -- typical fee for the service\n    average_processing_time_days integer, -- estimated processing time\n    is_active boolean DEFAULT true, -- whether the service is currently offered\n    online_application_url character varying(255),\n    PRIMARY KEY (service_id)\n)\nCREATE TABLE government_services.applications ( 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 PRIMARY KEY, application_id text, citizen_id text, service_id text, amount numeric, currency text, payment_method text, payment_provider_reference text, payment_timestamp timestamp, status text, notes text )\nCREATE TABLE government_services.employees ( employee_id text, 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": "List all agents who have a commission rate above 0.1, showing their full names and agency names."}, {"role": "assistant", "content": "SELECT agent_id, first_name, last_name, agency_name, commission_rate FROM insurance.agents WHERE commission_rate > 0.1 AND status = 'Active';"}, {"role": "user", "content": "Now include only agents who were hired in the last 2 years."}, {"role": "assistant", "content": "SELECT agent_id, first_name, last_name, agency_name, commission_rate, hire_date FROM insurance.agents WHERE commission_rate > 0.1 AND status = 'Active' AND hire_date >= CURRENT_DATE - INTERVAL '2 years';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.policies (\n    policy_id character varying(64) NOT NULL, -- unique identifier for the policy\n    customer_id character varying(64) NOT NULL, -- identifier for the policyholder (FK to customers)\n    product_id character varying(64) NOT NULL, -- identifier for the insurance product (FK to insurance_products)\n    agent_id character varying(64), -- identifier for the agent who sold the policy (FK to agents)\n    policy_number character varying(100) NOT NULL UNIQUE, -- customer-facing policy number\n    start_date date NOT NULL, -- date the policy coverage begins\n    end_date date NOT NULL, -- date the policy coverage ends\n    premium_amount numeric(12, 2) NOT NULL, -- total premium for the policy term\n    coverage_limit numeric(15, 2) NOT NULL, -- maximum amount covered\n    deductible numeric(10, 2) NOT NULL, -- amount customer pays before coverage kicks in\n    status character varying(30) NOT NULL, -- e.g., Active, Expired, Cancelled, Pending\n    issued_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the policy was issued\n    cancellation_date date,\n    cancellation_reason text,\n    PRIMARY KEY (policy_id)\n)\nCREATE TABLE insurance.insurance_products (\n    product_id character varying(64) NOT NULL, -- unique identifier for the insurance product\n    product_name character varying(150) NOT NULL, -- name of the insurance product (e.g., 'Comprehensive Auto Insurance')\n    product_type character varying(50) NOT NULL, -- category like 'Auto', 'Home', 'Life', 'Health', 'Travel'\n    description text, -- detailed description of the product\n    base_premium numeric(10, 2) NOT NULL, -- starting premium before adjustments\n    coverage_details text, -- details about what is covered (could be JSON or structured text)\n    underwriting_rules text, -- rules used for assessing risk and eligibility\n    is_active boolean NOT NULL DEFAULT true, -- whether the product is currently offered\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n    updated_at timestamp,\n    PRIMARY KEY (product_id)\n)\nCREATE TABLE insurance.agents (\n    agent_id character varying(64) NOT NULL, -- unique identifier for the agent\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    agency_name character varying(150),\n    license_number character varying(100) NOT NULL UNIQUE, -- state insurance license number\n    license_state character varying(50) NOT NULL,\n    contact_email character varying(128) UNIQUE,\n    contact_phone character varying(30),\n    hire_date date,\n    termination_date date,\n    status character varying(20) NOT NULL DEFAULT 'Active', -- e.g., Active, Terminated, On Leave\n    commission_rate numeric(5, 4) NOT NULL DEFAULT 0.05, -- percentage commission\n    manager_id character varying(64), -- identifier for the agent's manager (FK to agents or employees)\n    PRIMARY KEY (agent_id)\n)\nCREATE TABLE insurance.premium_payments (\n    payment_id character varying(64) NOT NULL, -- unique identifier for the payment\n    policy_id character varying(64) NOT NULL, -- identifier of the policy the payment is for (FK to policies)\n    customer_id character varying(64) NOT NULL, -- identifier of the customer making the payment (FK to customers)\n    payment_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- date the payment was received\n    amount_paid numeric(12, 2) NOT NULL, -- amount of the payment\n    payment_method character varying(50), -- e.g., Credit Card, Bank Transfer, Check\n    transaction_reference character varying(128) UNIQUE, -- reference from payment processor\n    due_date date, -- due date for this payment installment\n    payment_period_start date, -- start date of the period this payment covers\n    payment_period_end date, -- end date of the period this payment covers\n    status character varying(30) NOT NULL DEFAULT 'Completed', -- e.g., Completed, Pending, Failed, Refunded\n    PRIMARY KEY (payment_id)\n)\nCREATE TABLE insurance.claim_documents (\n    document_id character varying(64) NOT NULL, -- unique identifier for the document\n    claim_id character varying(64) NOT NULL, -- identifier of the claim this document relates to (FK to claims)\n    document_type character varying(50) NOT NULL, -- e.g., Police Report, Photo, Invoice, Medical Bill\n    file_name character varying(255) NOT NULL, -- original name of the uploaded file\n    file_path character varying(512) NOT NULL, -- storage path (e.g., S3 URL, network path)\n    file_size_bytes integer, -- size of the file in bytes\n    mime_type character varying(100), -- MIME type of the file (e.g., 'image/jpeg', 'application/pdf')\n    uploaded_by character varying(64), -- identifier of the user/system who uploaded (FK to users/customers)\n    uploaded_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- time of upload\n    description text, -- optional description of the document\n    PRIMARY KEY (document_id)\n)\nCREATE TABLE insurance.policy_beneficiaries (\n    beneficiary_id character varying(64) NOT NULL, -- unique identifier for the beneficiary entry\n    policy_id character varying(64) NOT NULL, -- identifier of the life/relevant policy (FK to policies)\n    customer_id character varying(64) NOT NULL, -- identifier of the beneficiary (could be FK to customers or store info directly)\n    first_name character varying(100) NOT NULL, -- beneficiary first name (if not linking to customers table)\n    last_name character varying(100) NOT NULL, -- beneficiary last name\n    relationship character varying(50) NOT NULL, -- relationship to the policyholder (e.g., Spouse, Child, Parent)\n    percentage_share numeric(5, 2) NOT NULL CHECK (percentage_share > 0 AND percentage_share <= 100), -- percentage of payout\n    contact_info text, -- contact details for the beneficiary\n    added_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n    PRIMARY KEY (beneficiary_id),\n    UNIQUE (policy_id, customer_id) -- Ensure a person is listed only once per policy\n)\n"}
{"conversations": [{"role": "user", "content": "How many smart money addresses fall into each rank bracket: 1-100, 101-1000, and 1001-5000? Show the bracket and the count of addresses."}, {"role": "assistant", "content": "SELECT CASE WHEN rank BETWEEN 1 AND 100 THEN '1-100' WHEN rank BETWEEN 101 AND 1000 THEN '101-1000' WHEN rank BETWEEN 1001 AND 5000 THEN '1001-5000' ELSE 'Other' END AS rank_bracket, COUNT(address) AS address_count FROM smart_money_profit WHERE rank BETWEEN 1 AND 5000 GROUP BY rank_bracket ORDER BY MIN(rank);"}], "system": "You are an SQL statement expert. Given the 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 cex_token_balance (\",\n    \"snapshot_time character varying(32) NOT NULL,  -- the snapshot time of record, converted from original timestamp\",\n    \"chain character varying(128) NOT NULL, -- the chain that the token resides\",\n    \"address character varying(128) NOT NULL, -- the address that holds the assets, owned by a CEX\",\n    \"exchange character varying(512) NOT NULL, -- a centralized exchange name\",\n    \"token_address character varying(128) NOT NULL, -- token contract address\",\n    \"token_symbol character varying(512), --token symbol\",\n    \"balance numeric(38,10), -- token balance\",\n    \"usd_value numeric(38,14), -- value of the token held in USD\",\n    \"price double precision, --price of the token in USD\",\n    \",PRIMARY KEY (snapshot_time, exchange, address, chain, token_address));\"\n\nCREATE TABLE smart_money_profit ( address character varying(100) NOT NULL, -- the user's address rank INT, -- the rank of the address in trade performance, value 1 expresses the best address. profit numeric(38,6), -- the profit user made in a month roi numeric(38,2), -- the roi of the user in a month realized_ratio numeric(38,2), -- the percentage of the user's realized profit most_profit_token character varying(100), -- the token symbol of the user's most profitable trade last_trade_time character varying(100), -- the last trade time of the user chain character varying(100), -- the chain that the address resides PRIMARY KEY (address, chain) )\n"}
{"conversations": [{"role": "user", "content": "For each guest, list reservation_id, guest_id, check_in_date, and the next reservation_id and its check_in_date."}, {"role": "assistant", "content": "SELECT r1.reservation_id,\n       r1.guest_id,\n       r1.check_in_date,\n       r2.reservation_id AS next_reservation_id,\n       r2.check_in_date   AS next_check_in_date\nFROM reservations r1\nLEFT JOIN reservations r2\n  ON r1.guest_id = r2.guest_id\n AND r2.check_in_date = (\n       SELECT MIN(check_in_date)\n       FROM reservations\n       WHERE guest_id = r1.guest_id\n         AND check_in_date > r1.check_in_date\n     );"}, {"role": "user", "content": "Only include guests who have at least two reservations."}, {"role": "assistant", "content": "SELECT r1.reservation_id,\n       r1.guest_id,\n       r1.check_in_date,\n       r2.reservation_id AS next_reservation_id,\n       r2.check_in_date   AS next_check_in_date\nFROM reservations r1\nLEFT JOIN reservations r2\n  ON r1.guest_id = r2.guest_id\n AND r2.check_in_date = (\n       SELECT MIN(check_in_date)\n       FROM reservations\n       WHERE guest_id = r1.guest_id\n         AND check_in_date > r1.check_in_date\n     )\nWHERE r1.guest_id IN (\n  SELECT guest_id\n  FROM reservations\n  GROUP BY guest_id\n  HAVING COUNT(*) >= 2\n);"}, {"role": "user", "content": "Also, only show next reservations that occur within 30 days of the current reservation."}, {"role": "assistant", "content": "SELECT r1.reservation_id,\n       r1.guest_id,\n       r1.check_in_date,\n       r2.reservation_id AS next_reservation_id,\n       r2.check_in_date   AS next_check_in_date\nFROM reservations r1\nLEFT JOIN reservations r2\n  ON r1.guest_id = r2.guest_id\n AND r2.check_in_date = (\n       SELECT MIN(check_in_date)\n       FROM reservations\n       WHERE guest_id = r1.guest_id\n         AND check_in_date > r1.check_in_date\n     )\n   AND r2.check_in_date <= r1.check_in_date + INTERVAL '30 days'\nWHERE r1.guest_id IN (\n  SELECT guest_id\n  FROM reservations\n  GROUP BY guest_id\n  HAVING COUNT(*) >= 2\n);"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.reservations ( reservation_id text, property_id text, guest_id text, room_id text, room_type_id text, check_in_date date, check_out_date date, actual_check_in_ts timestamp, actual_check_out_ts timestamp, num_adults integer, num_children integer, status text, booking_source text, rate_plan_id text, total_amount numeric, amount_paid numeric, special_requests text, created_at timestamp, updated_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show me 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": "How many policies were canceled in the previous month, grouped by cancellation reason?"}, {"role": "assistant", "content": "SELECT cancellation_reason,\n       COUNT(*) AS canceled_count\nFROM insurance.policies\nWHERE cancellation_date BETWEEN date_trunc('month', CURRENT_DATE) - INTERVAL '1 month'\n                             AND date_trunc('month', CURRENT_DATE) - INTERVAL '1 day'\nGROUP BY cancellation_reason;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.policies ( policy_id text, customer_id text, product_id text, agent_id text, policy_number text, start_date date, end_date date, premium_amount numeric, coverage_limit numeric, deductible numeric, status text, issued_at timestamp, cancellation_date date, cancellation_reason text )\n"}
{"conversations": [{"role": "user", "content": "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": "For each trip, show the trip ID, the scheduled departure time, and the name of the origin and destination locations."}, {"role": "assistant", "content": "SELECT t.trip_id, t.scheduled_departure, lo.name AS origin_location_name, ld.name AS destination_location_name\nFROM transportation.trips t\nJOIN transportation.locations lo ON t.origin_location_id = lo.location_id\nJOIN transportation.locations ld ON t.destination_location_id = ld.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.drivers (\n    driver_id character varying(64) NOT NULL,  -- unique identifier for the driver\n    employee_id character varying(64) NOT NULL UNIQUE, -- employee reference number\n    first_name character varying(128) NOT NULL, -- driver's first name\n    last_name character varying(128) NOT NULL, -- driver's last name\n    license_number character varying(64) NOT NULL UNIQUE, -- driving license number\n    license_expiry_date date NOT NULL, -- expiry date of the license\n    contact_number character varying(32), -- phone number\n    email character varying(128) UNIQUE, -- email address\n    hire_date date NOT NULL, -- date the driver was hired\n    status character varying(32) NOT NULL, -- e.g., Active, On Leave, Terminated\n    PRIMARY KEY (driver_id)\n)\nCREATE TABLE transportation.routes (\n    route_id character varying(64) NOT NULL,  -- unique identifier for the route\n    route_number character varying(32) NOT NULL UNIQUE, -- public-facing route number/name\n    description text, -- description of the route\n    origin_location_id character varying(64) NOT NULL, -- identifier of the starting location\n    destination_location_id character varying(64) NOT NULL, -- identifier of the ending location\n    distance_km numeric(10, 2), -- estimated distance in kilometers\n    estimated_duration_minutes integer, -- estimated travel time in minutes\n    type character varying(32) NOT NULL, -- e.g., City Bus, Intercity Train, Cargo Delivery\n    PRIMARY KEY (route_id)\n)\nCREATE TABLE transportation.trips (\n    trip_id character varying(64) NOT NULL,  -- unique identifier for a specific trip instance\n    route_id character varying(64), -- identifier of the route being followed (can be null for ad-hoc trips)\n    vehicle_id character varying(64) NOT NULL, -- identifier of the vehicle used\n    driver_id character varying(64) NOT NULL, -- identifier of the driver operating\n    scheduled_departure timestamp with time zone NOT NULL, -- planned departure time\n    actual_departure timestamp with time zone, -- actual departure time\n    scheduled_arrival timestamp with time zone NOT NULL, -- planned arrival time\n    actual_arrival timestamp with time zone, -- actual arrival time\n    origin_location_id character varying(64) NOT NULL, -- actual starting location (could differ from route origin)\n    destination_location_id character varying(64) NOT NULL, -- actual ending location (could differ from route destination)\n    status character varying(32) NOT NULL, -- e.g., Scheduled, In Progress, Completed, Delayed, Cancelled\n    passenger_count integer, -- number of passengers (if applicable)\n    cargo_manifest_id character varying(64), -- link to cargo details (if applicable)\n    PRIMARY KEY (trip_id)\n)\nCREATE TABLE transportation.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 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 guests who have never left a review, including their full name and email."}, {"role": "assistant", "content": "SELECT g.guest_id, g.first_name, g.last_name, g.email \nFROM hospitality_technology.guests g \nLEFT JOIN hospitality_technology.reviews r ON g.guest_id = r.guest_id \nWHERE r.review_id IS NULL;"}, {"role": "user", "content": "Can you also include their phone number?"}, {"role": "assistant", "content": "SELECT g.guest_id, g.first_name, g.last_name, g.email, g.phone_number \nFROM hospitality_technology.guests g \nLEFT JOIN hospitality_technology.reviews r ON g.guest_id = r.guest_id \nWHERE r.review_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 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 ( room_id text PRIMARY KEY, property_id text, room_number text, room_type_id text, floor int, status text, is_smoking boolean, features text, current_condition text, last_cleaned_at timestamp )\nCREATE TABLE hospitality_technology.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.services ( service_id text PRIMARY KEY, property_id text, service_name text, description text, category text, price numeric, unit text, is_available boolean, department text )\nCREATE TABLE hospitality_technology.service_orders ( order_id text PRIMARY KEY, reservation_id text, guest_id text, service_id text, staff_id_ordered text, staff_id_delivered text, order_timestamp timestamp, delivery_timestamp timestamp, quantity int, unit_price numeric, total_price numeric, status text, notes text, bill_id text )\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 )\nCREATE TABLE hospitality_technology.reviews ( review_id text PRIMARY KEY, property_id text, reservation_id text, guest_id text, rating_overall int, rating_cleanliness int, rating_service int, rating_location int, rating_value int, 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 all ERC20 tokens with their names and symbols where the price is greater than $100, sorted by price in descending order."}, {"role": "assistant", "content": "SELECT scm.name, scm.symbol, tpl.price FROM sui_coins_metadata scm JOIN token_prices_latest tpl ON scm.coin_type = tpl.address WHERE tpl.price > 100 ORDER BY tpl.price DESC;"}, {"role": "user", "content": "I think there's an error in your query - it should be joining on address not coin_type. Also, can you add the decimals to the results?"}, {"role": "assistant", "content": "SELECT scm.name, scm.symbol, scm.decimals, tpl.price FROM sui_coins_metadata scm JOIN token_prices_latest tpl ON scm.object_id = tpl.address WHERE tpl.price > 100 ORDER BY tpl.price DESC;"}, {"role": "user", "content": "Now filter these results to only show tokens with decimals equal to 18 and limit to the top 10."}, {"role": "assistant", "content": "SELECT scm.name, scm.symbol, scm.decimals, tpl.price FROM sui_coins_metadata scm JOIN token_prices_latest tpl ON scm.object_id = tpl.address WHERE tpl.price > 100 AND scm.decimals = 18 ORDER BY tpl.price DESC LIMIT 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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_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_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 ( 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 a list of group chat names with their conversation_id, the total number of participants, and the total number of messages sent in each group chat."}, {"role": "assistant", "content": "SELECT c.conversation_id,\n       c.group_name,\n       COUNT(cp.participant_id) AS participant_count,\n       COUNT(m.message_id) AS message_count\nFROM social_media.conversations c\nJOIN social_media.conversation_participants cp ON c.conversation_id = cp.conversation_id\nLEFT JOIN social_media.messages m ON c.conversation_id = m.conversation_id\nWHERE c.is_group_chat = TRUE\nGROUP BY c.conversation_id, c.group_name;"}, {"role": "user", "content": "Please filter to include only group chats that have at least 5 participants."}, {"role": "assistant", "content": "SELECT c.conversation_id,\n       c.group_name,\n       COUNT(cp.participant_id) AS participant_count,\n       COUNT(m.message_id) AS message_count\nFROM social_media.conversations c\nJOIN social_media.conversation_participants cp ON c.conversation_id = cp.conversation_id\nLEFT JOIN social_media.messages m ON c.conversation_id = m.conversation_id\nWHERE c.is_group_chat = TRUE\nGROUP BY c.conversation_id, c.group_name\nHAVING COUNT(cp.participant_id) >= 5;"}, {"role": "user", "content": "Now order the results by message_count descending and limit to the top 10 group chats."}, {"role": "assistant", "content": "SELECT c.conversation_id,\n       c.group_name,\n       COUNT(cp.participant_id) AS participant_count,\n       COUNT(m.message_id) AS message_count\nFROM social_media.conversations c\nJOIN social_media.conversation_participants cp ON c.conversation_id = cp.conversation_id\nLEFT JOIN social_media.messages m ON c.conversation_id = m.conversation_id\nWHERE c.is_group_chat = TRUE\nGROUP BY c.conversation_id, c.group_name\nHAVING COUNT(cp.participant_id) >= 5\nORDER BY message_count 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 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.likes ( like_id.text, user_id.text, post_id.text, comment_id.text, created_at.timestamp )\nCREATE TABLE social_media.hashtags ( hashtag_id character varying(64) NOT NULL, tag_name character varying(100) NOT NULL UNIQUE, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (hashtag_id) )\nCREATE TABLE social_media.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 ( 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 (\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 ( participant_id text PRIMARY KEY, conversation_id text, user_id text, joined_at timestamp, last_read_at timestamp )\nCREATE TABLE social_media.notifications ( notification_id.text, recipient_user_id.text, sender_user_id.text, notification_type.text, target_entity_id.text, target_entity_type.text, created_at.timestamp, read_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "What is the total market cap for all tokens listed on the 'Polygon' chain?"}, {"role": "assistant", "content": "SELECT SUM(market_cap) FROM token_dexpool_info WHERE chain = 'Polygon';"}, {"role": "user", "content": "Only sum the market cap for tokens on 'Polygon' that have a 24-hour volume greater than 500000."}, {"role": "assistant", "content": "SELECT SUM(market_cap) FROM token_dexpool_info WHERE chain = 'Polygon' AND volume_24h > 500000;"}, {"role": "user", "content": "Also show the number of unique tokens that meet these criteria."}, {"role": "assistant", "content": "SELECT COUNT(DISTINCT token_symbol), SUM(market_cap) FROM token_dexpool_info WHERE chain = 'Polygon' AND volume_24h > 500000;"}, {"role": "user", "content": "Can you show the total market cap and token count for *each* chain that meets these volume criteria, ordered by total market cap descending?"}, {"role": "assistant", "content": "SELECT chain, COUNT(DISTINCT token_symbol) AS token_count, SUM(market_cap) AS total_market_cap FROM token_dexpool_info WHERE volume_24h > 500000 GROUP BY chain ORDER BY total_market_cap DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_dexpool_info ( pair_address character varying(512) NOT NULL, -- the id of dexpool token_name character varying(100) NOT NULL, -- the name of the token in the dexpool token_symbol character varying(100) NOT NULL, -- the token's symbol chain text, -- the chain that the dexpool resides price double precision, -- the current price of the token price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour price_change_percentage_6h double precision, -- change in value divided by the absolute price value of the original token price in 6 hours price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours makers_24h double precision, -- the makers of the dex pool in 24 hours volume_24h double precision, -- the trade volume of the dex pool in 24 hours liquidity double precision, -- the liquidity of the dex pool market_cap double precision, -- the market cap of the token trend_rank bigint, -- the rank of token in the dex pool of recent trending, value 1 expresses the most popular token. ,PRIMARY KEY (pair_address, chain) )\n"}
{"conversations": [{"role": "user", "content": "List all agencies that do not have a website URL specified. Return their agency_id, agency_name, and main_phone_number."}, {"role": "assistant", "content": "SELECT agency_id, agency_name, main_phone_number FROM government_services.agencies WHERE website_url IS NULL OR website_url = '';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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) )\n"}
{"conversations": [{"role": "user", "content": "For each transaction ID, provide a count of unspent UTXOs."}, {"role": "assistant", "content": "SELECT transaction_id, COUNT(*) FROM utxos WHERE spent = FALSE GROUP BY 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 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)\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": "I want to list each security alongside another security issued by the same issuer."}, {"role": "assistant", "content": "SELECT a.security_id, a.ticker_symbol, b.security_id AS other_security_id, b.ticker_symbol AS other_ticker, a.issuer_name\nFROM financial_services.securities a\nJOIN financial_services.securities b ON a.issuer_name = b.issuer_name AND a.security_id <> b.security_id;"}, {"role": "user", "content": "Only include cases where the issuer has issued more than one security."}, {"role": "assistant", "content": "SELECT a.security_id, a.ticker_symbol, b.security_id AS other_security_id, b.ticker_symbol AS other_ticker, a.issuer_name\nFROM financial_services.securities a\nJOIN financial_services.securities b ON a.issuer_name = b.issuer_name AND a.security_id <> b.security_id\nWHERE a.issuer_name IN (\n  SELECT issuer_name\n  FROM financial_services.securities\n  GROUP BY issuer_name\n  HAVING COUNT(*) > 1\n);"}, {"role": "user", "content": "Sort the result by issuer_name, then by a.ticker_symbol."}, {"role": "assistant", "content": "SELECT a.security_id, a.ticker_symbol, b.security_id AS other_security_id, b.ticker_symbol AS other_ticker, a.issuer_name\nFROM financial_services.securities a\nJOIN financial_services.securities b ON a.issuer_name = b.issuer_name AND a.security_id <> b.security_id\nWHERE a.issuer_name IN (\n  SELECT issuer_name\n  FROM financial_services.securities\n  GROUP BY issuer_name\n  HAVING COUNT(*) > 1\n)\nORDER BY a.issuer_name, a.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.securities ( security_id text PRIMARY KEY, ticker_symbol text, isin_code text, cusip_code text, security_name text, security_type text, exchange text, currency text, issuer_name text, sector text, last_updated timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show 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": "List all the appointments that overlap in time for the same location, showing both appointment IDs, their start and end times, and the location."}, {"role": "assistant", "content": "SELECT a1.appointment_id AS appointment_id_1, a2.appointment_id AS appointment_id_2,\n       a1.start_time AS start_1, a1.end_time AS end_1,\n       a2.start_time AS start_2, a2.end_time AS end_2,\n       a1.location\nFROM legal_services.appointments a1\nJOIN legal_services.appointments a2\n  ON a1.location = a2.location\n AND a1.appointment_id < a2.appointment_id\n AND a1.start_time < a2.end_time\n AND a2.start_time < a1.end_time;"}, {"role": "user", "content": "Can you narrow this to only show overlapping appointments that are both in 'Scheduled' status?"}, {"role": "assistant", "content": "SELECT a1.appointment_id AS appointment_id_1, a2.appointment_id AS appointment_id_2,\n       a1.start_time AS start_1, a1.end_time AS end_1,\n       a2.start_time AS start_2, a2.end_time AS end_2,\n       a1.location\nFROM legal_services.appointments a1\nJOIN legal_services.appointments a2\n  ON a1.location = a2.location\n AND a1.appointment_id < a2.appointment_id\n AND a1.start_time < a2.end_time\n AND a2.start_time < a1.end_time\nWHERE a1.status = 'Scheduled' AND a2.status = 'Scheduled';"}, {"role": "user", "content": "Also, please only show overlaps that last longer than 10 minutes."}, {"role": "assistant", "content": "SELECT a1.appointment_id AS appointment_id_1, a2.appointment_id AS appointment_id_2,\n       a1.start_time AS start_1, a1.end_time AS end_1,\n       a2.start_time AS start_2, a2.end_time AS end_2,\n       a1.location\nFROM legal_services.appointments a1\nJOIN legal_services.appointments a2\n  ON a1.location = a2.location\n AND a1.appointment_id < a2.appointment_id\n AND a1.start_time < a2.end_time\n AND a2.start_time < a1.end_time\nWHERE a1.status = 'Scheduled' AND a2.status = 'Scheduled'\n  AND EXTRACT(EPOCH FROM (LEAST(a1.end_time, a2.end_time) - GREATEST(a1.start_time, a2.start_time))) > 600;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.appointments ( appointment_id.text, client_id.text, lawyer_id.text, case_id.text, start_time.timestamp, end_time.timestamp, location.text, subject.text, notes.text, status.text, created_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show all routes including their number, type, and description."}, {"role": "assistant", "content": "SELECT route_number ,  type ,  description FROM transportation.routes"}, {"role": "user", "content": "Only show routes of type 'City Bus'."}, {"role": "assistant", "content": "SELECT route_number ,  type ,  description FROM transportation.routes WHERE type  =  'City Bus'"}, {"role": "user", "content": "For these 'City Bus' routes, include the origin and destination city names."}, {"role": "assistant", "content": "SELECT T1.route_number ,  T1.type ,  T1.description ,  T2.city AS origin_city ,  T3.city AS destination_city FROM transportation.routes AS T1 JOIN transportation.locations AS T2 ON T1.origin_location_id  =  T2.location_id JOIN transportation.locations AS T3 ON T1.destination_location_id  =  T3.location_id WHERE T1.type  =  'City Bus'"}, {"role": "user", "content": "Order the results by route number in ascending order and limit to the first 10."}, {"role": "assistant", "content": "SELECT T1.route_number ,  T1.type ,  T1.description ,  T2.city AS origin_city ,  T3.city AS destination_city FROM transportation.routes AS T1 JOIN transportation.locations AS T2 ON T1.origin_location_id  =  T2.location_id JOIN transportation.locations AS T3 ON T1.destination_location_id  =  T3.location_id WHERE T1.type  =  'City Bus' ORDER BY T1.route_number ASC LIMIT 10"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles (\n    vehicle_id character varying(64) NOT NULL,  -- unique identifier for the vehicle\n    license_plate character varying(32) NOT NULL UNIQUE, -- vehicle license plate\n    vin character varying(17) UNIQUE, -- vehicle identification number\n    make character varying(64) NOT NULL, -- manufacturer of the vehicle\n    model character varying(64) NOT NULL, -- model of the vehicle\n    year integer NOT NULL, -- manufacturing year\n    type character varying(32) NOT NULL, -- type of vehicle (e.g., Bus, Train, Truck, Car, Van)\n    capacity integer, -- passenger or cargo capacity\n    fuel_type character varying(32) NOT NULL, -- e.g., Diesel, Gasoline, Electric, Hydrogen\n    status character varying(32) NOT NULL, -- e.g., Active, Maintenance, Decommissioned\n    depot_id character varying(64), -- identifier of the home depot/base\n    acquisition_date date, -- date the vehicle was acquired\n    PRIMARY KEY (vehicle_id)\n)\nCREATE TABLE transportation.drivers (\n    driver_id character varying(64) NOT NULL,  -- unique identifier for the driver\n    employee_id character varying(64) NOT NULL UNIQUE, -- employee reference number\n    first_name character varying(128) NOT NULL, -- driver's first name\n    last_name character varying(128) NOT NULL, -- driver's last name\n    license_number character varying(64) NOT NULL UNIQUE, -- driving license number\n    license_expiry_date date NOT NULL, -- expiry date of the license\n    contact_number character varying(32), -- phone number\n    email character varying(128) UNIQUE, -- email address\n    hire_date date NOT NULL, -- date the driver was hired\n    status character varying(32) NOT NULL, -- e.g., Active, On Leave, Terminated\n    PRIMARY KEY (driver_id)\n)\nCREATE TABLE transportation.routes (\n    route_id character varying(64) NOT NULL,  -- unique identifier for the route\n    route_number character varying(32) NOT NULL UNIQUE, -- public-facing route number/name\n    description text, -- description of the route\n    origin_location_id character varying(64) NOT NULL, -- identifier of the starting location\n    destination_location_id character varying(64) NOT NULL, -- identifier of the ending location\n    distance_km numeric(10, 2), -- estimated distance in kilometers\n    estimated_duration_minutes integer, -- estimated travel time in minutes\n    type character varying(32) NOT NULL, -- e.g., City Bus, Intercity Train, Cargo Delivery\n    PRIMARY KEY (route_id)\n)\nCREATE TABLE transportation.locations (\n    location_id character varying(64) NOT NULL,  -- unique identifier for the location\n    name character varying(255) NOT NULL, -- name of the location (e.g., Central Station, Depot Alpha, Pier 7)\n    type character varying(64) NOT NULL, -- e.g., Station, Stop, Depot, Port, Airport, Customer Address\n    address_line1 character varying(255), -- street address\n    city character varying(128), -- city name\n    state_province character varying(128), -- state or province\n    postal_code character varying(32), -- postal code\n    country character varying(64) NOT NULL, -- country name\n    latitude numeric(9, 6), -- geographic latitude\n    longitude numeric(9, 6), -- geographic longitude\n    timezone character varying(64), -- IANA timezone name (e.g., America/New_York)\n    PRIMARY KEY (location_id)\n)\nCREATE TABLE transportation.fuel_logs (\n    fuel_log_id character varying(64) NOT NULL,  -- unique identifier for the fuel log entry\n    vehicle_id character varying(64) NOT NULL, -- identifier of the vehicle fueled\n    trip_id character varying(64), -- optional: identifier of the trip during which fueling occurred\n    log_timestamp timestamp with time zone NOT NULL, -- time when fueling occurred\n    fuel_type character varying(32) NOT NULL, -- type of fuel added (matches vehicle's fuel type)\n    quantity numeric(10, 3) NOT NULL, -- amount of fuel added (e.g., Liters, Gallons, kWh)\n    unit character varying(16) NOT NULL, -- unit of quantity (e.g., L, gal, kWh)\n    cost_per_unit numeric(8, 4), -- price per unit of fuel\n    total_cost numeric(10, 2) NOT NULL, -- total cost of the fuel purchase\n    odometer_reading integer, -- vehicle mileage at time of fueling\n    location_id character varying(64), -- identifier of the fueling station/location\n    PRIMARY KEY (fuel_log_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List all invoices that were paid within 7 days of their issue date. Show invoice number, issue date, payment date, and total amount."}, {"role": "assistant", "content": "SELECT invoice_number, issue_date, payment_date, total_amount FROM legal_services.invoices WHERE status = 'Paid' AND payment_date IS NOT NULL AND (payment_date::DATE - issue_date) <= 7;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.lawyers ( lawyer_id.text, first_name.text, last_name.text, bar_number.text, firm_id.text, email.text, phone.text, specialization.text, hire_date.timestamp, is_partner.boolean )\nCREATE TABLE legal_services.invoices ( invoice_id text, invoice_number text, client_id text, case_id text, issue_date date, due_date date, total_amount numeric, amount_paid numeric, status text, payment_date timestamp, notes text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "For each player, list the total number of 'Legendary' rarity items they have in their inventory, along with the titles of the respective games those items belong to."}, {"role": "assistant", "content": "SELECT pi.player_id, g.game_id, g.title, COUNT(*) AS legendary_item_count\nFROM gaming_technology.player_inventory pi\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\nWHERE i.rarity = 'Legendary'\nGROUP BY pi.player_id, g.game_id, g.title;"}, {"role": "user", "content": "Please modify the query to only include players who have more than 2 'Legendary' items per game."}, {"role": "assistant", "content": "SELECT pi.player_id, g.game_id, g.title, COUNT(*) AS legendary_item_count\nFROM gaming_technology.player_inventory pi\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\nWHERE i.rarity = 'Legendary'\nGROUP BY pi.player_id, g.game_id, g.title\nHAVING COUNT(*) > 2;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.game_sessions ( session_id uuid PRIMARY KEY, player_id uuid, game_id uuid, server_id uuid, start_time timestamptz, end_time timestamptz, duration_seconds int, score int, session_data jsonb )\nCREATE TABLE gaming_technology.servers ( server_id.uuid, game_id.uuid, server_name.text, region.text, ip_address.text, port.integer, current_players.integer, max_players.integer, status.text, last_heartbeat.timestamptz )\nCREATE TABLE gaming_technology.player_achievements ( player_achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), player_id uuid NOT NULL, achievement_id uuid NOT NULL, unlocked_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (player_achievement_id), UNIQUE (player_id, achievement_id) )\nCREATE TABLE gaming_technology.in_game_items ( item_id uuid, game_id uuid, item_name text, item_type text, description text, rarity text, cost_currency text, cost_amount numeric, attributes jsonb )\n"}
{"conversations": [{"role": "user", "content": "Retrieve the first_name, last_name, and email of all passengers who have never made a booking."}, {"role": "assistant", "content": "SELECT\n  p.first_name,\n  p.last_name,\n  p.email\nFROM transportation.passengers p\nLEFT JOIN transportation.bookings b\n  ON p.passenger_id = b.passenger_id\nWHERE b.booking_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 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.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 ( passenger_id.text, first_name.text, last_name.text, email.text, phone_number.text, date_of_birth.date, loyalty_program_id.text, created_at.timestamp )\nCREATE TABLE transportation.bookings ( booking_id.text, passenger_id.text, trip_id.text, seat_number.text, booking_time.timestamp, status.text, fare.numeric, payment_transaction_id.text, special_requests.text )\n"}
{"conversations": [{"role": "user", "content": "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": "List the first name and last name of the driver and the license plate of the vehicle used for each trip."}, {"role": "assistant", "content": "SELECT T1.first_name , T1.last_name , T3.license_plate FROM transportation.drivers AS T1 JOIN transportation.trips AS T2 ON T1.driver_id = T2.driver_id JOIN transportation.vehicles AS T3 ON T2.vehicle_id = T3.vehicle_id"}, {"role": "user", "content": "Now, restrict this list to only include trips where the vehicle's fuel type is 'Electric'."}, {"role": "assistant", "content": "SELECT T1.first_name , T1.last_name , T3.license_plate FROM transportation.drivers AS T1 JOIN transportation.trips AS T2 ON T1.driver_id = T2.driver_id JOIN transportation.vehicles AS T3 ON T2.vehicle_id = T3.vehicle_id WHERE T3.fuel_type = 'Electric'"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles ( vehicle_id.text, license_plate.text, vin.text, make.text, model.text, year.integer, type.text, capacity.integer, fuel_type.text, status.text, depot_id.text, acquisition_date.date )\nCREATE TABLE transportation.drivers ( driver_id.text, employee_id.text, first_name.text, last_name.text, license_number.text, license_expiry_date.date, contact_number.text, email.text, hire_date.date, status.text )\nCREATE TABLE transportation.routes ( route_id.text, route_number.text, description.text, origin_location_id.text, destination_location_id.text, distance_km.numeric, estimated_duration_minutes.integer, type.text )\nCREATE TABLE transportation.trips ( trip_id.text, route_id.text, vehicle_id.text, driver_id.text, scheduled_departure.timestamp, actual_departure.timestamp, scheduled_arrival.timestamp, actual_arrival.timestamp, origin_location_id.text, destination_location_id.text, status.text, passenger_count.integer, cargo_manifest_id.text )\nCREATE TABLE transportation.maintenance_logs ( log_id.text, vehicle_id.text, service_date.date, odometer_reading.integer, service_type.text, description.text, cost.numeric, mechanic_name.text, next_service_due_date.date )\nCREATE TABLE transportation.fuel_logs ( fuel_log_id.text, vehicle_id.text, trip_id.text, log_timestamp.timestamp, fuel_type.text, quantity.numeric, unit.text, cost_per_unit.numeric, total_cost.numeric, odometer_reading.integer, location_id.text )\nCREATE TABLE transportation.passengers ( passenger_id.text, first_name.text, last_name.text, email.text, phone_number.text, date_of_birth.date, loyalty_program_id.text, created_at.timestamp )\nCREATE TABLE transportation.bookings ( booking_id.text, passenger_id.text, trip_id.text, seat_number.text, booking_time.timestamp, status.text, fare.numeric, payment_transaction_id.text, special_requests.text )\n"}
{"conversations": [{"role": "user", "content": "Count the number of policies issued in each calendar year, and show the year and the count."}, {"role": "assistant", "content": "SELECT EXTRACT(YEAR FROM issued_at), COUNT(*) FROM insurance.policies WHERE issued_at IS NOT NULL GROUP BY 1 ORDER BY 1;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.customers ( customer_id text, first_name text, last_name text, date_of_birth date, ssn_hash text, address_line1 text, address_line2 text, city text, state text, zip_code text, country text, phone_number text, email text, created_at timestamp, updated_at timestamp, status text )\nCREATE TABLE insurance.policies ( policy_id text, customer_id text, product_id text, agent_id text, policy_number text, start_date date, end_date date, premium_amount numeric, coverage_limit numeric, deductible numeric, status text, issued_at timestamp, cancellation_date date, cancellation_reason text )\nCREATE TABLE insurance.insurance_products ( product_id text, product_name text, product_type text, description text, base_premium numeric, coverage_details text, underwriting_rules text, is_active boolean, created_at timestamp, updated_at timestamp )\nCREATE TABLE insurance.agents ( agent_id text, first_name text, last_name text, agency_name text, license_number text, license_state text, contact_email text, contact_phone text, hire_date date, termination_date date, status text, commission_rate numeric, manager_id text )\nCREATE TABLE insurance.policy_beneficiaries ( beneficiary_id text, policy_id text, customer_id text, first_name text, last_name text, relationship text, percentage_share numeric, contact_info text, added_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "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": "Show me all room types with 'King' in the bed_type field, along with their property IDs and base rates."}, {"role": "assistant", "content": "SELECT room_type_id, property_id, type_name, bed_type, base_rate FROM hospitality_technology.room_types WHERE bed_type LIKE '%King%';"}, {"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' and the guest is a loyalty member."}, {"role": "assistant", "content": "SELECT rt.room_type_id, rt.property_id, rt.type_name, rt.bed_type, rt.base_rate FROM hospitality_technology.room_types rt JOIN hospitality_technology.guests g ON rt.property_id = g.property_id WHERE rt.bed_type LIKE '%King%' AND g.country_code = 'USA' AND g.loyalty_member_id IS NOT NULL;"}, {"role": "user", "content": "The query is missing the max occupancy. Can you include that as well?"}, {"role": "assistant", "content": "SELECT rt.room_type_id, rt.property_id, rt.type_name, rt.bed_type, rt.base_rate, rt.max_occupancy FROM hospitality_technology.room_types rt JOIN hospitality_technology.guests g ON rt.property_id = g.property_id WHERE rt.bed_type LIKE '%King%' AND g.country_code = 'USA' AND g.loyalty_member_id IS NOT NULL;"}, {"role": "user", "content": "Actually, I need to see only room types with a base rate below $300, and order them by max occupancy in descending order."}, {"role": "assistant", "content": "SELECT rt.room_type_id, rt.property_id, rt.type_name, rt.bed_type, rt.base_rate, rt.max_occupancy FROM hospitality_technology.room_types rt JOIN hospitality_technology.guests g ON rt.property_id = g.property_id WHERE rt.bed_type LIKE '%King%' AND g.country_code = 'USA' AND g.loyalty_member_id IS NOT NULL AND rt.base_rate < 300 ORDER BY rt.max_occupancy 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.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 the usernames and emails of all users who registered on the same day as at least one other user, along with the registration date."}, {"role": "assistant", "content": "SELECT u1.username, u1.email, u1.created_at\nFROM web3.users u1\nJOIN web3.users u2\n  ON u1.created_at::date = u2.created_at::date\n  AND u1.user_id <> u2.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": "Can you list all SUI coins with 'active' status and their owner addresses and balances?"}, {"role": "assistant", "content": "SELECT object_id, coin_type, owner, balance\nFROM sui_coins\nWHERE status = 'active';"}, {"role": "user", "content": "Add the coin symbol and name from the sui_coins_metadata table."}, {"role": "assistant", "content": "SELECT sc.object_id, sc.coin_type, sc.owner, sc.balance, scm.symbol, scm.name\nFROM sui_coins sc\nLEFT JOIN sui_coins_metadata scm ON sc.coin_type = scm.coin_type\nWHERE sc.status = 'active';"}, {"role": "user", "content": "Only include coins where the description mentions 'utility'."}, {"role": "assistant", "content": "SELECT sc.object_id, sc.coin_type, sc.owner, sc.balance, scm.symbol, scm.name\nFROM sui_coins sc\nLEFT JOIN sui_coins_metadata scm ON sc.coin_type = scm.coin_type\nWHERE sc.status = 'active' AND scm.description ILIKE '%utility%';"}, {"role": "user", "content": "Limit the output to the top 10 coins sorted by balance descending."}, {"role": "assistant", "content": "SELECT sc.object_id, sc.coin_type, sc.owner, sc.balance, scm.symbol, scm.name\nFROM sui_coins sc\nLEFT JOIN sui_coins_metadata scm ON sc.coin_type = scm.coin_type\nWHERE sc.status = 'active' AND scm.description ILIKE '%utility%'\nORDER BY CAST(sc.balance AS BIGINT) 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 erc1155_approval_for_all ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash varchar, log_index integer, contract_address varchar )\nCREATE TABLE erc20_balances_historical ( block_number bigint, contract_address varchar, wallet_address varchar, amount varchar, pk integer )\nCREATE TABLE nft_holders ( block_number bigint, contract_address varchar, wallet_address varchar, token_id varchar, contract_type varchar, amount varchar, pk varchar )\nCREATE TABLE nft_holder_historical ( block_number bigint, contract_address varchar, wallet_address varchar, token_id varchar, contract_type varchar, amount varchar, pk integer )\nCREATE TABLE sui_coins ( object_id varchar, status varchar, coin_type varchar, balance varchar, owner varchar )\nCREATE TABLE sui_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 ( object_id varchar, status varchar, collection_type varchar, package_id varchar, previous_transaction varchar, display varchar, owner varchar, name varchar )\nCREATE TABLE nft_metadata ( blockchain varchar, contract_address varchar, token_id varchar, contract_name varchar, erc_type varchar, amount bigint, minter varchar, owner varchar, mint_block_number bigint, mint_time bigint, mint_transaction_hash varchar, mint_price varchar, token_uri varchar, metadata varchar, name varchar, image_uri varchar, traits varchar, updated_at bigint, status varchar, rarity_score real, rarity_rank integer, unique_attribute_count integer, pk integer )\nCREATE TABLE nft_collections ( blockchain varchar, contract_address varchar, name varchar, symbol varchar, deploy_block_number bigint, deploy_block_time bigint, erc_type varchar, owner varchar, traits varchar, description varchar, slug varchar, media_info varchar, image_url varchar, banner_image_url varchar, updated_at bigint, banner varchar, token_count bigint, floor_price varchar, floor_price_symbol varchar, floor_price_contract varchar, pk integer )\nCREATE TABLE token_prices ( uuid varchar, blockchain varchar, address varchar, decimals bigint, symbol varchar, price real, timestamp timestamp )\nCREATE TABLE token_prices_latest ( blockchain varchar, address varchar, decimals bigint, symbol varchar, price real, timestamp timestamp )\nCREATE TABLE erc20_approval ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash varchar, log_index integer, contract_address varchar, pk integer )\nCREATE TABLE token_balances ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply decimal, amount decimal )\nCREATE TABLE token_info ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar )\nCREATE TABLE token_activities ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\nCREATE TABLE mud_holesky_redstone ( address varchar, table_id varchar, key_bytes varchar, key0 varchar, key1 varchar, static_data varchar, encoded_lengths varchar, dynamic_data varchar, is_deleted boolean, block_number bigint, log_index bigint )\nCREATE TABLE token_balances_bitcoin ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply varchar, amount varchar )\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\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": "Retrieve the most recent log entry for each user, including action and logged_at."}, {"role": "assistant", "content": "SELECT l1.user_id,\n       l1.action,\n       l1.logged_at\nFROM trading_platform.logs l1\nWHERE l1.logged_at = (\n  SELECT MAX(l2.logged_at)\n  FROM trading_platform.logs l2\n  WHERE l2.user_id = l1.user_id\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 trading_platform.users (\n    user_id character varying(64) NOT NULL,  -- unique identifier for the user\n    username character varying(128) NOT NULL, -- username of the user\n    email character varying(128) NOT NULL, -- email address of the user\n    password_hash text NOT NULL, -- hashed password of the user\n    created_at timestamp NOT NULL, -- time when the user account was created\n    PRIMARY KEY (user_id)\n)\nCREATE TABLE trading_platform.orders (\n    order_id character varying(64) NOT NULL,  -- unique identifier for the order\n    user_id character varying(64) NOT NULL, -- identifier of the user placing the order\n    wallet_id character varying(64) NOT NULL, -- identifier of the wallet used for the order\n    asset_id character varying(64) NOT NULL, -- identifier of the asset being traded\n    order_type character varying(32) NOT NULL, -- type of the order (e.g., buy, sell)\n    quantity numeric(38,14) NOT NULL, -- quantity of the asset in the order\n    price numeric(38,14) NOT NULL, -- price per unit of the asset\n    status character varying(32) NOT NULL, -- status of the order (e.g., open, filled, canceled)\n    created_at timestamp NOT NULL, -- time when the order was created\n    PRIMARY KEY (order_id)\n)\nCREATE TABLE trading_platform.dapps (\n    dapp_id character varying(64) NOT NULL,  -- unique identifier for the DApp\n    name character varying(128) NOT NULL, -- name of the DApp\n    description text NOT NULL, -- description of the DApp\n    url character varying(256) NOT NULL, -- URL of the DApp\n    PRIMARY KEY (dapp_id)\n)\nCREATE TABLE trading_platform.peers (\n    peer_id character varying(64) NOT NULL,  -- unique identifier for the peer\n    ip_address character varying(15) NOT NULL, -- IP address of the peer\n    port integer NOT NULL, -- port number of the peer\n    last_seen timestamp NOT NULL, -- last time the peer was active\n    PRIMARY KEY (peer_id)\n)\nCREATE TABLE trading_platform.metadata (\n    metadata_id character varying(64) NOT NULL,  -- unique identifier for the metadata\n    asset_id character varying(64) NOT NULL, -- identifier of the asset the metadata is associated with\n    key character varying(128) NOT NULL, -- key of the metadata\n    value text NOT NULL, -- value of the metadata\n    PRIMARY KEY (metadata_id)\n)\nCREATE TABLE trading_platform.logs (\n    log_id character varying(64) NOT NULL,  -- unique identifier for the log entry\n    user_id character varying(64), -- identifier of the user associated with the log entry\n    action character varying(128) NOT NULL, -- action performed\n    details text NOT NULL, -- details of the action\n    logged_at timestamp NOT NULL, -- time when the log entry was created\n    PRIMARY KEY (log_id)\n)\n"}
{"conversations": [{"role": "user", "content": "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 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": "能否帮我统计特定车站(station_id 为 'station_xyz')的所有工作人员数量？"}, {"role": "assistant", "content": "MATCH (s:Station {station_id: 'station_xyz'})<-[:BASED_AT]-(staff:Staff)\nRETURN COUNT(staff) AS total_staff"}], "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// Node Label: :Station\n// Properties:\n//   station_id: String (Constraint: UNIQUE)\n//   station_name: String\n//   city: String (Index recommended)\n//   state_province: String\n//   country_code: String\n//   address: String\n//   timezone: String\n//   number_of_platforms: Integer\n//   created_at: DateTime\n//   last_updated_at: DateTime\n// Example Cypher CREATE:\n// CREATE (:Station {station_id: 'station_xyz', station_name: 'Grand Central Terminal', city: 'New York', ...})\n// Node Label: :Platform\n// Properties:\n//   platform_id: String (Constraint: UNIQUE)\n//   platform_number: String\n//   track_number: String\n//   status: String\n//   length_meters: Float\n//   accessible: Boolean\n// Relationship: (:Platform)-[:LOCATED_AT]->(:Station)\n// Example Cypher CREATE:\n// MATCH (s:Station {station_id: 'station_xyz'})\n// CREATE (p:Platform {platform_id: 'plat_123', ...})-[:LOCATED_AT]->(s)\n// Node Label: :Train\n// Properties:\n//   train_id: String (Constraint: UNIQUE)\n//   train_number: String (Constraint: UNIQUE)\n//   model: String\n//   manufacturer: String\n//   year_manufactured: Integer\n//   capacity: Integer\n//   status: String\n//   last_maintenance_date: Date\n//   next_maintenance_date: Date\n// Example Cypher CREATE:\n// CREATE (:Train {train_id: 'train_789', train_number: 'Acela 2151', ...})\n// Node Label: :TrainCar\n// Properties:\n//   car_id: String (Constraint: UNIQUE)\n//   car_number: String\n//   car_type: String\n//   class: String\n//   capacity: Integer\n//   features: String (Or List<String> if driver supports)\n// Relationship: (:TrainCar)-[:PART_OF_TRAIN]->(:Train)\n// Example Cypher CREATE:\n// MATCH (t:Train {train_id: 'train_789'})\n// CREATE (c:TrainCar {car_id: 'car_abc', ...})-[:PART_OF_TRAIN]->(t)\n// Node Label: :Route\n// Properties:\n//   route_id: String (Constraint: UNIQUE)\n//   route_name: String\n//   description: String\n//   is_active: Boolean\n// Relationships:\n//   (:Route)-[:STARTS_AT]->(:Station)\n//   (:Route)-[:ENDS_AT]->(:Station)\n// Example Cypher CREATE:\n// MATCH (origin:Station {station_id: 'station_bos'}), (dest:Station {station_id: 'station_was'})\n// CREATE (r:Route {route_id: 'route_ne_corr', ...})-[:STARTS_AT]->(origin), (r)-[:ENDS_AT]->(dest)\n// Relationship: (:Route)-[rel:HAS_STOP]->(:Station)\n// Relationship Properties on :HAS_STOP:\n//   sequence_order: Integer\n//   distance_from_previous_km: Float\n//   typical_stop_duration_minutes: Integer\n// Example Cypher CREATE:\n// MATCH (r:Route {route_id: 'route_ne_corr'}), (s:Station {station_id: 'station_pvd'})\n// CREATE (r)-[:HAS_STOP {sequence_order: 2, distance_from_previous_km: 70.5, ...}]->(s)\n// Node Label: :ScheduledTrip (or just :Trip)\n// Properties:\n//   schedule_id: String (Constraint: UNIQUE)\n//   departure_datetime: DateTime\n//   arrival_datetime: DateTime\n//   status: String\n//   notes: String\n// Relationships:\n//   (:ScheduledTrip)-[:USES_TRAIN]->(:Train)\n//   (:ScheduledTrip)-[:FOLLOWS_ROUTE]->(:Route)\n// Example Cypher CREATE:\n// MATCH (t:Train {train_id: 'train_789'}), (r:Route {route_id: 'route_ne_corr'})\n// CREATE (sched:ScheduledTrip {schedule_id: 'sched_1122', ...})-[:USES_TRAIN]->(t), (sched)-[:FOLLOWS_ROUTE]->(r)\n// Relationship: (:ScheduledTrip)-[rel:SCHEDULED_STOP]->(:Station)\n// Relationship Properties on :SCHEDULED_STOP:\n//   sequence_order: Integer\n//   platform_id: String (references Platform node if modeled, or just store ID)\n//   scheduled_arrival_time: DateTime\n//   scheduled_departure_time: DateTime\n//   actual_arrival_time: DateTime\n//   actual_departure_time: DateTime\n//   status: String\n// Example Cypher CREATE:\n// MATCH (sched:ScheduledTrip {schedule_id: 'sched_1122'}), (s:Station {station_id: 'station_pvd'})\n// CREATE (sched)-[:SCHEDULED_STOP {sequence_order: 2, platform_id: 'plat_pvd_1', ...}]->(s)\n// Node Label: :Passenger\n// Properties:\n//   passenger_id: String (Constraint: UNIQUE)\n//   first_name: String\n//   last_name: String\n//   email: String (Constraint: UNIQUE, if not null)\n//   phone_number: String (Constraint: UNIQUE, if not null)\n//   date_of_birth: Date\n//   loyalty_program_id: String\n//   created_at: DateTime\n// Example Cypher CREATE:\n// CREATE (:Passenger {passenger_id: 'pass_pqr', first_name: 'Alice', ...})\n// Node Label: :Booking\n// Properties:\n//   booking_id: String (Constraint: UNIQUE)\n//   booking_datetime: DateTime\n//   status: String\n//   total_price: Float\n//   currency_code: String\n//   special_requests: String\n// Relationships:\n//   (:Passenger)-[:MADE_BOOKING]->(:Booking)\n//   (:Booking)-[:FOR_TRIP]->(:ScheduledTrip)\n// Example Cypher CREATE:\n// MATCH (p:Passenger {passenger_id: 'pass_pqr'}), (sched:ScheduledTrip {schedule_id: 'sched_1122'})\n// CREATE (p)-[:MADE_BOOKING]->(b:Booking {booking_id: 'book_zyx', ...})-[:FOR_TRIP]->(sched)\n// Node Label: :Ticket\n// Properties:\n//   ticket_id: String (Constraint: UNIQUE)\n//   seat_number: String\n//   ticket_type: String\n//   price: Float\n//   is_checked_in: Boolean\n//   qr_code_data: String\n// Relationships:\n//   (:Ticket)-[:PART_OF_BOOKING]->(:Booking)\n//   (:Ticket)-[:ASSIGNED_TO_CAR]->(:TrainCar)\n// Example Cypher CREATE:\n// MATCH (b:Booking {booking_id: 'book_zyx'}), (c:TrainCar {car_id: 'car_abc'})\n// CREATE (t:Ticket {ticket_id: 'tkt_1a2b', ...})-[:PART_OF_BOOKING]->(b), (t)-[:ASSIGNED_TO_CAR]->(c)\n// Node Label: :Staff\n// Properties:\n//   staff_id: String (Constraint: UNIQUE)\n//   first_name: String\n//   last_name: String\n//   role: String\n//   employee_number: String (Constraint: UNIQUE)\n//   hire_date: Date\n//   contact_email: String (Constraint: UNIQUE, if not null)\n//   contact_phone: String\n//   is_active: Boolean\n// Relationship (Optional):\n//   (:Staff)-[:BASED_AT]->(:Station)\n// Example Cypher CREATE:\n// CREATE (:Staff {staff_id: 'staff_mno', first_name: 'Bob', ...})\n// OPTIONAL MATCH (s:Station {station_id: 'station_xyz'}) // If primary_station_id exists\n// WITH s, staff_mno // Need to get the created staff node reference\n// WHERE s IS NOT NULL\n// CREATE (staff_mno)-[:BASED_AT]->(s)\n"}
{"conversations": [{"role": "user", "content": "List all pairs of tokens (show token_id for both) that share the same contract address, excluding pairs where the token_id is the same."}, {"role": "assistant", "content": "SELECT t1.token_id AS token_id1, t2.token_id AS token_id2, t1.contract_address FROM web3.tokens AS t1 JOIN web3.tokens AS t2 ON t1.contract_address = t2.contract_address WHERE t1.token_id < t2.token_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.tokens ( token_id character varying(64) NOT NULL, contract_address character varying(128) NOT NULL, token_name character varying(128) NOT NULL, token_symbol character varying(32) NOT NULL, decimals integer NOT NULL, total_supply numeric(38,14) NOT NULL, PRIMARY KEY (token_id) )\n"}
{"conversations": [{"role": "user", "content": "List the usernames and user IDs of all users whose bio contains the word 'developer'."}, {"role": "assistant", "content": "SELECT user_id, username\nFROM social_media.users\nWHERE bio ILIKE '%developer%';"}], "system": "You are an SQL statement expert. Given the table structure 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.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": "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 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": "For each agency, list the agency name and the count of distinct service categories they offer."}, {"role": "assistant", "content": "SELECT ag.agency_name, COUNT(DISTINCT s.category) AS category_count\nFROM government_services.agencies ag\nJOIN government_services.services s ON ag.agency_id = s.agency_id\nGROUP BY ag.agency_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 government_services.agencies ( agency_id.text, agency_name.text, jurisdiction_level.text, primary_contact_email.text, main_phone_number.text, website_url.text, established_date.date, parent_agency_id.text )\nCREATE TABLE government_services.services ( service_id.text, agency_id.text, service_name.text, description.text, category.text, eligibility_criteria.text, standard_fee.numeric, average_processing_time_days.integer, is_active.boolean, online_application_url.text )\nCREATE TABLE government_services.applications ( application_id.text, citizen_id.text, service_id.text, submitted_at.timestamp, status.text, last_updated_at.timestamp, assigned_employee_id.text, decision_date.date, notes.text, reference_number.text )\nCREATE TABLE government_services.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.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 )\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 all loans (loan_id, loan_type, principal_amount) where the current principal balance is less than 30% of the original principal amount, along with their account_id and status."}, {"role": "assistant", "content": "SELECT loan_id, loan_type, principal_amount, account_id, status FROM financial_services.loans WHERE current_principal_balance < 0.3 * principal_amount;"}, {"role": "user", "content": "Now modify the query to only include active loans (status = 'Active') and sort them by principal_amount in descending order."}, {"role": "assistant", "content": "SELECT loan_id, loan_type, principal_amount, account_id, status FROM financial_services.loans WHERE current_principal_balance < 0.3 * principal_amount AND status = 'Active' ORDER BY principal_amount 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.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": "Show me each service order along with the next order placed by the same guest, including both order IDs and the time difference in minutes between the two orders."}, {"role": "assistant", "content": "SELECT a.order_id,\n       b.order_id AS next_order_id,\n       EXTRACT(EPOCH FROM (b.order_timestamp - a.order_timestamp)) / 60 AS diff_minutes\nFROM hospitality_technology.service_orders a\nJOIN hospitality_technology.service_orders b\n  ON a.guest_id = b.guest_id\n AND b.order_timestamp > a.order_timestamp;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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 the guest's full name, reservation ID, check-in date, and status for all reservations made via 'Phone'."}, {"role": "assistant", "content": "SELECT g.first_name, g.last_name, r.reservation_id, r.check_in_date, r.status FROM hospitality_technology.reservations r JOIN hospitality_technology.guests g ON r.guest_id = g.guest_id WHERE r.booking_source = 'Phone';"}, {"role": "user", "content": "Now, only show reservations with a status of 'Confirmed' or 'Pending'."}, {"role": "assistant", "content": "SELECT g.first_name, g.last_name, r.reservation_id, r.check_in_date, r.status FROM hospitality_technology.reservations r JOIN hospitality_technology.guests g ON r.guest_id = g.guest_id WHERE r.booking_source = 'Phone' AND r.status IN ('Confirmed', 'Pending');"}, {"role": "user", "content": "Sort the results by check-in date descending and limit to the first 20."}, {"role": "assistant", "content": "SELECT g.first_name, g.last_name, r.reservation_id, r.check_in_date, r.status FROM hospitality_technology.reservations r JOIN hospitality_technology.guests g ON r.guest_id = g.guest_id WHERE r.booking_source = 'Phone' AND r.status IN ('Confirmed', 'Pending') ORDER BY r.check_in_date DESC LIMIT 20;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.guests ( guest_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, email character varying(255) UNIQUE, phone_number character varying(30), date_of_birth date, address_line1 character varying(255), city character varying(100), state_province character varying(100), postal_code character varying(20), country_code character varying(3), preferences text, loyalty_member_id character varying(64) UNIQUE, communication_consent boolean DEFAULT true, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (guest_id) )\nCREATE TABLE hospitality_technology.reservations (\n    reservation_id character varying(64) NOT NULL,  -- unique identifier for the booking\n    property_id character varying(64) NOT NULL, -- FK to properties table\n    guest_id character varying(64) NOT NULL, -- FK to guests table (primary guest)\n    room_id character varying(64), -- FK to rooms table (assigned room, might be null initially)\n    room_type_id character varying(64) NOT NULL, -- FK to room_types table (booked room type)\n    check_in_date date NOT NULL, -- scheduled check-in date\n    check_out_date date NOT NULL, -- scheduled check-out date\n    actual_check_in_ts timestamp with time zone, -- actual check-in time\n    actual_check_out_ts timestamp with time zone, -- actual check-out time\n    num_adults integer NOT NULL, -- number of adults\n    num_children integer DEFAULT 0, -- number of children\n    status character varying(50) NOT NULL, -- e.g., Pending, Confirmed, CheckedIn, CheckedOut, Cancelled, NoShow\n    booking_source character varying(100), -- e.g., Website, OTA (Expedia, Booking.com), Phone, WalkIn\n    rate_plan_id character varying(64), -- FK to rate_plans table (optional)\n    total_amount numeric(12, 2), -- estimated or final total cost\n    amount_paid numeric(12, 2) DEFAULT 0.00, -- amount already paid\n    special_requests text, -- specific guest requests for this booking\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 (reservation_id),\n    FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n    FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id),\n    FOREIGN KEY (room_id) REFERENCES hospitality_technology.rooms(room_id),\n    FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id)\n)\nCREATE TABLE hospitality_technology.staff (\n    staff_id character varying(64) NOT NULL,  -- unique identifier for the staff member\n    property_id character varying(64) NOT NULL, -- FK to properties table (primary property)\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    position character varying(100) NOT NULL, -- e.g., Front Desk Agent, Housekeeper, Manager, Concierge\n    work_email character varying(255) UNIQUE, -- staff member's work email\n    work_phone character varying(30),\n    hire_date date NOT NULL,\n    termination_date date, -- date employment ended (if applicable)\n    is_active boolean NOT NULL DEFAULT true, -- currently employed flag\n    access_level integer NOT NULL, -- permission level within systems (e.g., 1=basic, 5=admin)\n    manager_id character varying(64), -- FK to staff table (self-referencing for supervisor)\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (staff_id),\n    FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n    FOREIGN KEY (manager_id) REFERENCES hospitality_technology.staff(staff_id)\n)\nCREATE TABLE hospitality_technology.services ( service_id.text, property_id.text, service_name.text, description.text, category.text, price.numeric, unit.text, is_available.boolean, department.text )\n"}
{"conversations": [{"role": "user", "content": "Please show me all locations that do not have a state or province recorded. Include the location name, city, and country."}, {"role": "assistant", "content": "SELECT name, city, country\nFROM transportation.locations\nWHERE state_province IS NULL OR state_province = '';"}, {"role": "user", "content": "For these locations, also include their location_id and type."}, {"role": "assistant", "content": "SELECT location_id, name, type, city, country\nFROM transportation.locations\nWHERE state_province IS NULL OR state_province = '';"}, {"role": "user", "content": "Could you additionally list any routes for which these locations are either the origin or the destination? Show the location name, route number, and specify if the location is origin or destination."}, {"role": "assistant", "content": "SELECT l.name, r.route_number,\n  CASE \n    WHEN r.origin_location_id = l.location_id THEN 'origin'\n    WHEN r.destination_location_id = l.location_id THEN 'destination'\n  END AS role\nFROM transportation.locations l\nJOIN transportation.routes r\n  ON r.origin_location_id = l.location_id OR r.destination_location_id = l.location_id\nWHERE l.state_province IS NULL OR l.state_province = '';"}], "system": "You are an SQL statement expert. Given the table structure 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.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.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 group chats and the total count of messages sent in each one."}, {"role": "assistant", "content": "SELECT T1.group_name, count(T2.message_id) AS message_count FROM social_media.conversations AS T1 JOIN social_media.messages AS T2 ON T1.conversation_id = T2.conversation_id WHERE T1.is_group_chat = TRUE GROUP BY T1.group_name;"}, {"role": "user", "content": "Can you refine that to only show group chats that have more than 100 messages?"}, {"role": "assistant", "content": "SELECT T1.group_name, count(T2.message_id) AS message_count FROM social_media.conversations AS T1 JOIN social_media.messages AS T2 ON T1.conversation_id = T2.conversation_id WHERE T1.is_group_chat = TRUE GROUP BY T1.group_name HAVING count(T2.message_id) > 100;"}, {"role": "user", "content": "Great, now please also include the creation time of these group chats and order the results by the message count in descending order."}, {"role": "assistant", "content": "SELECT T1.group_name, T1.created_at, count(T2.message_id) AS message_count FROM social_media.conversations AS T1 JOIN social_media.messages AS T2 ON T1.conversation_id = T2.conversation_id WHERE T1.is_group_chat = TRUE GROUP BY T1.group_name, T1.created_at HAVING count(T2.message_id) > 100 ORDER BY message_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 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.posts (\n    post_id character varying(64) NOT NULL, -- unique identifier for the post\n    user_id character varying(64) NOT NULL, -- identifier of the user who created the post (FK to users.user_id)\n    content text, -- textual content of the post\n    media_url text, -- URL to attached media (image/video)\n    media_type character varying(20), -- type of media ('image', 'video', null)\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of post creation\n    updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last post edit\n    visibility character varying(20) NOT NULL DEFAULT 'public', -- visibility ('public', 'friends', 'private')\n    location_lat numeric(9,6), -- latitude of post location\n    location_lon numeric(9,6), -- longitude of post location\n    PRIMARY KEY (post_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)\n"}
{"conversations": [{"role": "user", "content": "List the name and symbol for all assets that do not have a corresponding entry with the key 'website' in the metadata table."}, {"role": "assistant", "content": "SELECT T1.name , T1.symbol FROM trading_platform.assets AS T1 LEFT JOIN trading_platform.metadata AS T2 ON T1.asset_id  =  T2.asset_id AND T2.key  =  'website' WHERE T2.metadata_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 text PRIMARY KEY, user_id text, wallet_id text, asset_id text, order_type text, quantity numeric, price numeric, status text, created_at timestamp )\nCREATE TABLE trading_platform.trades (\n    trade_id character varying(64) NOT NULL,  -- unique identifier for the trade\n    order_id character varying(64) NOT NULL, -- identifier of the order that led to the trade\n    buyer_id character varying(64) NOT NULL, -- identifier of the buyer\n    seller_id character varying(64) NOT NULL, -- identifier of the seller\n    asset_id character varying(64) NOT NULL, -- identifier of the asset being traded\n    quantity numeric(38,14) NOT NULL, -- quantity of the asset in the trade\n    price numeric(38,14) NOT NULL, -- price per unit of the asset\n    traded_at timestamp NOT NULL, -- time when the trade was executed\n    PRIMARY KEY (trade_id)\n)\nCREATE TABLE trading_platform.assets ( asset_id text PRIMARY KEY, 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.metadata (\n    metadata_id character varying(64) NOT NULL,  -- unique identifier for the metadata\n    asset_id character varying(64) NOT NULL, -- identifier of the asset the metadata is associated with\n    key character varying(128) NOT NULL, -- key of the metadata\n    value text NOT NULL, -- value of the metadata\n    PRIMARY KEY (metadata_id)\n)\nCREATE TABLE trading_platform.kyc_audit (\n    kyc_audit_id character varying(64) NOT NULL,  -- unique identifier for the KYC audit\n    user_id character varying(64) NOT NULL, -- identifier of the user being audited\n    status character varying(32) NOT NULL, -- status of the KYC audit (e.g., pending, approved, rejected)\n    reviewed_at timestamp NOT NULL, -- time when the KYC audit was reviewed\n    PRIMARY KEY (kyc_audit_id)\n)\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": "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 the names of services and the total number of times each service has been ordered. Only include services that have been ordered at least once."}, {"role": "assistant", "content": "SELECT T1.service_name, count(T2.order_id) AS order_count FROM hospitality_technology.services AS T1 JOIN hospitality_technology.service_orders AS T2 ON T1.service_id = T2.service_id GROUP BY T1.service_name;"}, {"role": "user", "content": "Now, filter this list to only show services from the 'Food & Beverage' or 'Activities' categories, and sort by the order count in descending order."}, {"role": "assistant", "content": "SELECT T1.service_name, count(T2.order_id) AS order_count FROM hospitality_technology.services AS T1 JOIN hospitality_technology.service_orders AS T2 ON T1.service_id = T2.service_id WHERE T1.category IN ('Food & Beverage', 'Activities') GROUP BY T1.service_name ORDER BY order_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.properties ( property_id character varying(64) NOT NULL, property_name character varying(255) NOT NULL, address_line1 character varying(255) NOT NULL, address_line2 character varying(255), city character varying(100) NOT NULL, state_province character varying(100), postal_code character varying(20) NOT NULL, country_code character varying(3) NOT NULL, phone_number character varying(30), email_address character varying(255), property_type character varying(50) NOT NULL, star_rating numeric(2,1), timezone character varying(64) NOT NULL, manager_staff_id character varying(64), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (property_id) )\nCREATE TABLE hospitality_technology.rooms ( room_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, room_number character varying(10) NOT NULL, room_type_id character varying(64) NOT NULL, floor integer, status character varying(50) NOT NULL, is_smoking boolean NOT NULL DEFAULT false, features text, current_condition text, last_cleaned_at timestamp with time zone, PRIMARY KEY (room_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id) )\nCREATE TABLE hospitality_technology.room_types ( room_type_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, type_name character varying(100) NOT NULL, description text, base_rate numeric(10, 2) NOT NULL, max_occupancy integer NOT NULL, bed_type character varying(50), area_sqft numeric(8,2), amenities text, PRIMARY KEY (room_type_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id) )\nCREATE TABLE hospitality_technology.guests ( guest_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, email character varying(255) UNIQUE, phone_number character varying(30), date_of_birth date, address_line1 character varying(255), city character varying(100), state_province character varying(100), postal_code character varying(20), country_code character varying(3), preferences text, loyalty_member_id character varying(64) UNIQUE, communication_consent boolean DEFAULT true, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (guest_id) )\nCREATE TABLE hospitality_technology.reservations ( reservation_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, guest_id character varying(64) NOT NULL, room_id character varying(64), room_type_id character varying(64) NOT NULL, check_in_date date NOT NULL, check_out_date date NOT NULL, actual_check_in_ts timestamp with time zone, actual_check_out_ts timestamp with time zone, num_adults integer NOT NULL, num_children integer DEFAULT 0, status character varying(50) NOT NULL, booking_source character varying(100), rate_plan_id character varying(64), total_amount numeric(12, 2), amount_paid numeric(12, 2) DEFAULT 0.00, special_requests text, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (reservation_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (room_id) REFERENCES hospitality_technology.rooms(room_id), FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id) )\nCREATE TABLE hospitality_technology.services ( service_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, service_name character varying(150) NOT NULL, description text, category character varying(100), price numeric(10, 2) NOT NULL, unit character varying(30), is_available boolean NOT NULL DEFAULT true, department character varying(100), PRIMARY KEY (service_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id) )\nCREATE TABLE hospitality_technology.service_orders ( order_id character varying(64) NOT NULL, reservation_id character varying(64), guest_id character varying(64) NOT NULL, service_id character varying(64) NOT NULL, staff_id_ordered character varying(64), staff_id_delivered character varying(64), order_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, delivery_timestamp timestamp with time zone, quantity integer NOT NULL DEFAULT 1, unit_price numeric(10, 2) NOT NULL, total_price numeric(12, 2) NOT NULL, status character varying(50) NOT NULL, notes text, bill_id character varying(64), PRIMARY KEY (order_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (service_id) REFERENCES hospitality_technology.services(service_id), FOREIGN KEY (staff_id_ordered) REFERENCES hospitality_technology.staff(staff_id), FOREIGN KEY (staff_id_delivered) REFERENCES hospitality_technology.staff(staff_id) )\nCREATE TABLE hospitality_technology.payments ( payment_id character varying(64) NOT NULL, reservation_id character varying(64), guest_id character varying(64) NOT NULL, bill_id character varying(64), amount numeric(12,2) NOT NULL, currency_code character varying(3) NOT NULL, payment_method character varying(50) NOT NULL, card_type character varying(50), card_last_four character varying(4), transaction_ref character varying(128), payment_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, status character varying(50) NOT NULL, staff_id_processed character varying(64), notes text, PRIMARY KEY (payment_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (staff_id_processed) REFERENCES hospitality_technology.staff(staff_id) )\nCREATE TABLE hospitality_technology.reviews ( review_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, reservation_id character varying(64) UNIQUE, guest_id character varying(64) NOT NULL, rating_overall integer, rating_cleanliness integer, rating_service integer, rating_location integer, rating_value integer, comment text, review_source character varying(100), review_date timestamp with time zone NOT NULL DEFAULT current_timestamp, is_public boolean DEFAULT true, staff_response text, response_staff_id character varying(64), response_date timestamp with time zone, PRIMARY KEY (review_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (response_staff_id) REFERENCES hospitality_technology.staff(staff_id) )\n"}
{"conversations": [{"role": "user", "content": "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"}