{"conversations": [{"role": "user", "content": "For each user, retrieve their first and last log actions along with the respective timestamps."}, {"role": "assistant", "content": "SELECT t.user_id,\n       lf.action AS first_action,\n       lf.logged_at AS first_time,\n       ll.action AS last_action,\n       ll.logged_at AS last_time\nFROM (\n    SELECT user_id,\n           MIN(logged_at) AS first_time,\n           MAX(logged_at) AS last_time\n    FROM trading_platform.logs\n    GROUP BY user_id\n) t\nJOIN trading_platform.logs lf\n  ON lf.user_id = t.user_id AND lf.logged_at = t.first_time\nJOIN trading_platform.logs ll\n  ON ll.user_id = t.user_id AND ll.logged_at = t.last_time;"}, {"role": "user", "content": "Filter to only include users with more than 5 log entries."}, {"role": "assistant", "content": "SELECT t.user_id,\n       lf.action AS first_action,\n       lf.logged_at AS first_time,\n       ll.action AS last_action,\n       ll.logged_at AS last_time\nFROM (\n    SELECT user_id,\n           MIN(logged_at) AS first_time,\n           MAX(logged_at) AS last_time\n    FROM trading_platform.logs\n    GROUP BY user_id\n    HAVING COUNT(*) > 5\n) t\nJOIN trading_platform.logs lf\n  ON lf.user_id = t.user_id AND lf.logged_at = t.first_time\nJOIN trading_platform.logs ll\n  ON ll.user_id = t.user_id AND ll.logged_at = t.last_time;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.logs ( log_id text PRIMARY KEY, user_id text, action text, details text, logged_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": "List the full name (first name and last name) of all citizens who have uploaded documents whose expiry date is in the past."}, {"role": "assistant", "content": "SELECT DISTINCT T1.first_name, T1.last_name FROM government_services.citizens AS T1 INNER JOIN government_services.documents AS T2 ON T1.citizen_id = T2.citizen_id WHERE T2.expiry_date < CURRENT_DATE;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id text PRIMARY KEY, national_id_number text, first_name text, last_name text, date_of_birth date, gender text, primary_address text, contact_email text, contact_phone text, registration_date timestamp, is_verified boolean )\nCREATE TABLE government_services.agencies ( agency_id text PRIMARY KEY, agency_name text, jurisdiction_level text, primary_contact_email text, main_phone_number text, website_url text, established_date date, parent_agency_id text )\nCREATE TABLE government_services.documents ( document_id text PRIMARY KEY, application_id text, citizen_id text, document_type text, file_reference text, upload_timestamp timestamp, expiry_date date, verification_status text, verified_by_employee_id text, verification_timestamp timestamp )\nCREATE TABLE government_services.payments ( payment_id text PRIMARY KEY, application_id text, citizen_id text, service_id text, amount numeric, currency text, payment_method text, payment_provider_reference text, payment_timestamp timestamp, status text, notes text )\nCREATE TABLE government_services.service_locations ( location_id text PRIMARY KEY, agency_id text, location_name text, address text, city text, state text, postal_code text, latitude numeric, longitude numeric, operating_hours text, contact_phone text, is_accessible boolean )\nCREATE TABLE government_services.appointments ( appointment_id text PRIMARY KEY, citizen_id text, employee_id text, location_id text, service_id text, scheduled_start_time timestamp, scheduled_end_time timestamp, purpose text, status text, booking_method text, created_at timestamp, notes text )\n"}
{"conversations": [{"role": "user", "content": "Show me all token names and their contract addresses along with the wallet addresses of users who created wallets in the last 30 days, sorted by wallet creation date."}, {"role": "assistant", "content": "SELECT t.token_name, t.contract_address, w.address AS wallet_address FROM web3.tokens t JOIN web3.wallets w ON 1=1 WHERE w.created_at >= CURRENT_DATE - INTERVAL '30 days' ORDER BY w.created_at;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.tokens ( token_id character varying(64) NOT NULL, contract_address character varying(128) NOT NULL, token_name character varying(128) NOT NULL, token_symbol character varying(32) NOT NULL, decimals integer NOT NULL, total_supply numeric(38,14) NOT NULL, PRIMARY KEY (token_id) )\nCREATE TABLE web3.wallets ( wallet_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, address character varying(128) NOT NULL, private_key text NOT NULL, created_at timestamp NOT NULL, PRIMARY KEY (wallet_id) )\n"}
{"conversations": [{"role": "user", "content": "For each trip, show the trip_id, vehicle's license plate, total fuel quantity, and number of fueling events."}, {"role": "assistant", "content": "SELECT t.trip_id, v.license_plate, SUM(f.quantity) AS total_fuel, COUNT(f.fuel_log_id) AS fueling_events FROM transportation.trips t JOIN transportation.fuel_logs f ON t.trip_id = f.trip_id JOIN transportation.vehicles v ON t.vehicle_id = v.vehicle_id GROUP BY t.trip_id, v.license_plate;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles (\n    vehicle_id character varying(64) NOT NULL,  -- unique identifier for the vehicle\n    license_plate character varying(32) NOT NULL UNIQUE, -- vehicle license plate\n    vin character varying(17) UNIQUE, -- vehicle identification number\n    make character varying(64) NOT NULL, -- manufacturer of the vehicle\n    model character varying(64) NOT NULL, -- model of the vehicle\n    year integer NOT NULL, -- manufacturing year\n    type character varying(32) NOT NULL, -- type of vehicle (e.g., Bus, Train, Truck, Car, Van)\n    capacity integer, -- passenger or cargo capacity\n    fuel_type character varying(32) NOT NULL, -- e.g., Diesel, Gasoline, Electric, Hydrogen\n    status character varying(32) NOT NULL, -- e.g., Active, Maintenance, Decommissioned\n    depot_id character varying(64), -- identifier of the home depot/base\n    acquisition_date date, -- date the vehicle was acquired\n    PRIMARY KEY (vehicle_id)\n)\nCREATE TABLE transportation.trips (\n    trip_id character varying(64) NOT NULL,  -- unique identifier for a specific trip instance\n    route_id character varying(64), -- identifier of the route being followed (can be null for ad-hoc trips)\n    vehicle_id character varying(64) NOT NULL, -- identifier of the vehicle used\n    driver_id character varying(64) NOT NULL, -- identifier of the driver operating\n    scheduled_departure timestamp with time zone NOT NULL, -- planned departure time\n    actual_departure timestamp with time zone, -- actual departure time\n    scheduled_arrival timestamp with time zone NOT NULL, -- planned arrival time\n    actual_arrival timestamp with time zone, -- actual arrival time\n    origin_location_id character varying(64) NOT NULL, -- actual starting location (could differ from route origin)\n    destination_location_id character varying(64) NOT NULL, -- actual ending location (could differ from route destination)\n    status character varying(32) NOT NULL, -- e.g., Scheduled, In Progress, Completed, Delayed, Cancelled\n    passenger_count integer, -- number of passengers (if applicable)\n    cargo_manifest_id character varying(64), -- link to cargo details (if applicable)\n    PRIMARY KEY (trip_id)\n)\nCREATE TABLE transportation.locations (\n    location_id character varying(64) NOT NULL,  -- unique identifier for the location\n    name character varying(255) NOT NULL, -- name of the location (e.g., Central Station, Depot Alpha, Pier 7)\n    type character varying(64) NOT NULL, -- e.g., Station, Stop, Depot, Port, Airport, Customer Address\n    address_line1 character varying(255), -- street address\n    city character varying(128), -- city name\n    state_province character varying(128), -- state or province\n    postal_code character varying(32), -- postal code\n    country character varying(64) NOT NULL, -- country name\n    latitude numeric(9, 6), -- geographic latitude\n    longitude numeric(9, 6), -- geographic longitude\n    timezone character varying(64), -- IANA timezone name (e.g., America/New_York)\n    PRIMARY KEY (location_id)\n)\nCREATE TABLE transportation.maintenance_logs (\n    log_id character varying(64) NOT NULL,  -- unique identifier for the maintenance record\n    vehicle_id character varying(64) NOT NULL, -- identifier of the vehicle serviced\n    service_date date NOT NULL, -- date the service was performed\n    odometer_reading integer, -- vehicle mileage at time of service\n    service_type character varying(128) NOT NULL, -- type of service (e.g., Oil Change, Tire Rotation, Engine Repair)\n    description text NOT NULL, -- detailed description of work done\n    cost numeric(10, 2), -- cost of the service\n    mechanic_name character varying(128), -- name or ID of the mechanic/shop\n    next_service_due_date date, -- recommended date for next service\n    PRIMARY KEY (log_id)\n)\nCREATE TABLE transportation.fuel_logs (\n    fuel_log_id character varying(64) NOT NULL,  -- unique identifier for the fuel log entry\n    vehicle_id character varying(64) NOT NULL, -- identifier of the vehicle fueled\n    trip_id character varying(64), -- optional: identifier of the trip during which fueling occurred\n    log_timestamp timestamp with time zone NOT NULL, -- time when fueling occurred\n    fuel_type character varying(32) NOT NULL, -- type of fuel added (matches vehicle's fuel type)\n    quantity numeric(10, 3) NOT NULL, -- amount of fuel added (e.g., Liters, Gallons, kWh)\n    unit character varying(16) NOT NULL, -- unit of quantity (e.g., L, gal, kWh)\n    cost_per_unit numeric(8, 4), -- price per unit of fuel\n    total_cost numeric(10, 2) NOT NULL, -- total cost of the fuel purchase\n    odometer_reading integer, -- vehicle mileage at time of fueling\n    location_id character varying(64), -- identifier of the fueling station/location\n    PRIMARY KEY (fuel_log_id)\n)\nCREATE TABLE transportation.passengers (\n    passenger_id character varying(64) NOT NULL,  -- unique identifier for the passenger\n    first_name character varying(128) NOT NULL, -- passenger's first name\n    last_name character varying(128) NOT NULL, -- passenger's last name\n    email character varying(128) UNIQUE, -- email address\n    phone_number character varying(32) UNIQUE, -- phone number\n    date_of_birth date, -- passenger's date of birth\n    loyalty_program_id character varying(64), -- identifier for loyalty program membership\n    created_at timestamp with time zone NOT NULL, -- time when the passenger record was created\n    PRIMARY KEY (passenger_id)\n)\nCREATE TABLE transportation.bookings (\n    booking_id character varying(64) NOT NULL,  -- unique identifier for the booking\n    passenger_id character varying(64) NOT NULL, -- identifier of the passenger making the booking\n    trip_id character varying(64) NOT NULL, -- identifier of the trip being booked\n    seat_number character varying(16), -- assigned seat number (if applicable)\n    booking_time timestamp with time zone NOT NULL, -- time when the booking was made\n    status character varying(32) NOT NULL, -- e.g., Confirmed, Cancelled, Pending Payment\n    fare numeric(10, 2) NOT NULL, -- price paid for the booking\n    payment_transaction_id character varying(128), -- reference to the payment transaction\n    special_requests text, -- any special requests from the passenger\n    PRIMARY KEY (booking_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List all node pairs that operate on the same port and were last_seen within 30 minutes of each other, showing both node_ids, the port, and the time difference in minutes."}, {"role": "assistant", "content": "SELECT n1.node_id AS node1_id, n2.node_id AS node2_id, n1.port,\n       ABS(EXTRACT(EPOCH FROM (n1.last_seen - n2.last_seen))) / 60 AS minutes_diff\nFROM blockchain.nodes n1\nJOIN blockchain.nodes n2\n  ON n1.port = n2.port\n  AND n1.node_id < n2.node_id\nWHERE ABS(EXTRACT(EPOCH FROM (n1.last_seen - n2.last_seen))) <= 1800;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE blockchain.nodes ( node_id text PRIMARY KEY, ip_address text, port int, last_seen timestamp )\n"}
{"conversations": [{"role": "user", "content": "For each patient, calculate the total duration of all their completed appointments. Show the patient ID and the total duration in minutes, sorted by total duration descending."}, {"role": "assistant", "content": "SELECT patient_id, SUM(duration_minutes) AS total_completed_duration FROM healthcare.appointments WHERE status = 'Completed' GROUP BY patient_id ORDER BY total_completed_duration DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.appointments (\n    appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    doctor_id character varying(64) NOT NULL, -- FK to doctors table\n    appointment_time timestamp with time zone NOT NULL, -- date and time of the appointment\n    duration_minutes integer NOT NULL, -- expected duration in minutes\n    reason text, -- reason for the visit\n    status character varying(32) NOT NULL, -- e.g., Scheduled, Completed, Cancelled, No-show\n    location_id character varying(64), -- FK to a potential locations/clinics table\n    notes text, -- notes related to scheduling\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (appointment_id)\n)\n"}
{"conversations": [{"role": "user", "content": "For each player, show the player_id and the count of inventory items they acquired with a quantity greater than 1."}, {"role": "assistant", "content": "SELECT player_id, COUNT(inventory_id) AS items_qty_gt_1_count FROM gaming_technology.player_inventory WHERE quantity > 1 GROUP BY player_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.players ( player_id uuid NOT NULL DEFAULT gen_random_uuid(), username character varying(100) NOT NULL UNIQUE, email character varying(255) NOT NULL UNIQUE, password_hash text NOT NULL, registration_date timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, last_login timestamp with time zone, country_code character(2), status character varying(20) NOT NULL DEFAULT 'active', profile_data jsonb, PRIMARY KEY (player_id) )\nCREATE TABLE gaming_technology.games ( game_id uuid NOT NULL DEFAULT gen_random_uuid(), title character varying(200) NOT NULL, developer_id uuid NOT NULL, publisher_id uuid, genre character varying(100), release_date date, description text, platform character varying(50) NOT NULL, engine character varying(100), website character varying(255), PRIMARY KEY (game_id) )\nCREATE TABLE gaming_technology.servers ( server_id uuid NOT NULL DEFAULT gen_random_uuid(), game_id uuid NOT NULL, server_name character varying(150), region character varying(50) NOT NULL, ip_address character varying(45), port integer, current_players integer NOT NULL DEFAULT 0, max_players integer NOT NULL, status character varying(30) NOT NULL DEFAULT 'offline', last_heartbeat timestamp with time zone, PRIMARY KEY (server_id) )\nCREATE TABLE gaming_technology.in_game_items ( item_id uuid NOT NULL DEFAULT gen_random_uuid(), game_id uuid NOT NULL, item_name character varying(150) NOT NULL, item_type character varying(50) NOT NULL, description text, rarity character varying(30), cost_currency character varying(10), cost_amount numeric(12, 2), attributes jsonb, PRIMARY KEY (item_id) )\nCREATE TABLE gaming_technology.player_inventory ( inventory_id uuid NOT NULL DEFAULT gen_random_uuid(), player_id uuid NOT NULL, item_id uuid NOT NULL, quantity integer NOT NULL DEFAULT 1, acquired_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, instance_data jsonb, PRIMARY KEY (inventory_id) )\n"}
{"conversations": [{"role": "user", "content": "Which projects raised funds in January 2022?"}, {"role": "assistant", "content": "SELECT project_name, rounds_name, investment_value, investment_date FROM project_fundraising_record WHERE investment_date >= '2022-01-01' AND investment_date < '2022-02-01';"}, {"role": "user", "content": "Please also show their introductions."}, {"role": "assistant", "content": "SELECT project_name, rounds_name, investment_value, investment_date, introduction FROM project_fundraising_record WHERE investment_date >= '2022-01-01' AND investment_date < '2022-02-01';"}], "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 project_fundraising_record ( id.text, project_id.text, project_name.text, rounds_name.text, investment_value.numeric, investment_date.text, introduction.text, valuation.numeric )\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": "List all unique claim handler IDs present in the claims table."}, {"role": "assistant", "content": "SELECT DISTINCT claim_handler_id FROM insurance.claims WHERE claim_handler_id IS NOT NULL"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.claims ( claim_id text PRIMARY KEY, policy_id text, customer_id text, incident_date timestamp, reported_date timestamp, description text, estimated_loss numeric, status text, settlement_amount numeric, settlement_date date, claim_handler_id text, police_report_number text )\n"}
{"conversations": [{"role": "user", "content": "Show me all chronic diagnoses along with their descriptions and the patient IDs, sorted by diagnosis date in descending order."}, {"role": "assistant", "content": "SELECT patient_id, description, diagnosis_date FROM healthcare.diagnoses WHERE is_chronic = true ORDER BY diagnosis_date DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.diagnoses ( diagnosis_id text PRIMARY KEY, record_id text, patient_id text, doctor_id text, diagnosis_code text, code_type text, description text, diagnosis_date date, status text, is_chronic boolean )\n"}
{"conversations": [{"role": "user", "content": "List all rooms, including their room number, the name of the property they belong to, and their room type name, specifically for rooms with 'Maintenance' status."}, {"role": "assistant", "content": "SELECT T1.room_number, T2.property_name, T3.type_name FROM rooms AS T1 JOIN properties AS T2 ON T1.property_id = T2.property_id JOIN room_types AS T3 ON T1.room_type_id = T3.room_type_id WHERE T1.status = 'Maintenance'"}, {"role": "user", "content": "Also include the floor number and filter to only show rooms located on floors 5 or higher. Sort the results by property name and then by floor."}, {"role": "assistant", "content": "SELECT T1.room_number, T2.property_name, T3.type_name, T1.floor FROM rooms AS T1 JOIN properties AS T2 ON T1.property_id = T2.property_id JOIN room_types AS T3 ON T1.room_type_id = T3.room_type_id WHERE T1.status = 'Maintenance' AND T1.floor >= 5 ORDER BY T2.property_name, T1.floor"}], "system": "You are an SQL statement expert. Given the table structure 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": "Show the first name, last name, relationship, and percentage share for all policy beneficiaries added after January 1st, 2024."}, {"role": "assistant", "content": "SELECT first_name, last_name, relationship, percentage_share FROM insurance.policy_beneficiaries WHERE added_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 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.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.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 (\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": "List all claim IDs that have both an 'Accident Report' and a 'Damage Assessment' document, and show the earliest upload timestamp for each type."}, {"role": "assistant", "content": "SELECT a.claim_id,\n       MIN(a.uploaded_at) AS accident_report_date,\n       MIN(d.uploaded_at) AS damage_assessment_date\nFROM insurance.claim_documents AS a\nJOIN insurance.claim_documents AS d\n  ON a.claim_id = d.claim_id\nWHERE a.document_type = 'Accident Report'\n  AND d.document_type = 'Damage Assessment'\nGROUP BY a.claim_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.claim_documents ( document_id.text, claim_id.text, document_type.text, file_name.text, file_path.text, file_size_bytes.integer, mime_type.text, uploaded_by.text, uploaded_at.timestamp, description.text )\n"}
{"conversations": [{"role": "user", "content": "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": "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": "What is the current address of the employee with ID 'EMP234'?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide the current address of an employee as this information is not stored in the database table."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE manufacturing.employees ( employee_id.text, first_name.text, last_name.text, job_title.text, skill_certifications.text, hire_date.date, assigned_line_id.text, employment_status.text, supervisor_employee_id.text )\n"}
{"conversations": [{"role": "user", "content": "List all game titles and the count of online servers 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 T2.status = 'online' GROUP BY T1.title;"}, {"role": "user", "content": "Only include games that have more than 2 online servers."}, {"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 T2.status = 'online' GROUP BY T1.title HAVING count(T2.server_id) > 2;"}, {"role": "user", "content": "Also, include the average current player count for these online servers per game."}, {"role": "assistant", "content": "SELECT T1.title, count(T2.server_id), avg(T2.current_players) FROM games AS T1 JOIN servers AS T2 ON T1.game_id = T2.game_id WHERE T2.status = 'online' GROUP BY T1.title HAVING count(T2.server_id) > 2;"}, {"role": "user", "content": "Sort the results by the average current player count in descending order."}, {"role": "assistant", "content": "SELECT T1.title, count(T2.server_id), avg(T2.current_players) FROM games AS T1 JOIN servers AS T2 ON T1.game_id = T2.game_id WHERE T2.status = 'online' GROUP BY T1.title HAVING count(T2.server_id) > 2 ORDER BY avg(T2.current_players) DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.players ( player_id uuid PRIMARY KEY, username text, email text, password_hash text, registration_date timestamptz, last_login timestamptz, country_code text, status text, profile_data jsonb )\nCREATE TABLE gaming_technology.games ( game_id.uuid, title.text, developer_id.uuid, publisher_id.uuid, genre.text, release_date.date, description.text, platform.text, engine.text, website.text )\nCREATE TABLE gaming_technology.servers ( server_id.uuid, 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.in_game_items ( item_id uuid PRIMARY KEY, game_id uuid, item_name text, item_type text, description text, rarity text, cost_currency text, cost_amount numeric, attributes jsonb )\n"}
{"conversations": [{"role": "user", "content": "Show me all insurance plans that cover more than 10 patients as their primary insurance, along with the provider name and contact information."}, {"role": "assistant", "content": "SELECT ip.plan_name, ip.insurance_provider, ip.contact_phone, ip.website, COUNT(pi.patient_id) AS patient_count FROM healthcare.insurance_plans ip JOIN healthcare.patient_insurance pi ON ip.plan_id = pi.plan_id WHERE pi.is_primary = true GROUP BY ip.plan_id HAVING COUNT(pi.patient_id) > 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients (\n    patient_id character varying(64) NOT NULL,  -- unique identifier for the patient\n    first_name character varying(100) NOT NULL, -- patient's first name\n    last_name character varying(100) NOT NULL, -- patient's last name\n    date_of_birth date NOT NULL, -- patient's date of birth\n    gender character varying(10), -- patient's gender (e.g., Male, Female, Other)\n    address text, -- patient's home address\n    phone_number character varying(20), -- patient's phone number\n    email character varying(128) UNIQUE, -- patient's email address\n    emergency_contact_name character varying(200), -- name of emergency contact\n    emergency_contact_phone character varying(20), -- phone number of emergency contact\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, -- record creation time\n    updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, -- record last update time\n    PRIMARY KEY (patient_id)\n)\nCREATE TABLE healthcare.doctors (\n    doctor_id character varying(64) NOT NULL,  -- unique identifier for the doctor\n    first_name character varying(100) NOT NULL, -- doctor's first name\n    last_name character varying(100) NOT NULL, -- doctor's last name\n    specialty character varying(100) NOT NULL, -- doctor's medical specialty\n    license_number character varying(50) UNIQUE NOT NULL, -- doctor's medical license number\n    phone_number character varying(20), -- doctor's contact phone\n    email character varying(128) UNIQUE, -- doctor's contact email\n    hospital_affiliation_id character varying(64), -- FK to hospitals table (optional)\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (doctor_id)\n)\nCREATE TABLE healthcare.appointments (\n    appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    doctor_id character varying(64) NOT NULL, -- FK to doctors table\n    appointment_time timestamp with time zone NOT NULL, -- date and time of the appointment\n    duration_minutes integer NOT NULL, -- expected duration in minutes\n    reason text, -- reason for the visit\n    status character varying(32) NOT NULL, -- e.g., Scheduled, Completed, Cancelled, No-show\n    location_id character varying(64), -- FK to a potential locations/clinics table\n    notes text, -- notes related to scheduling\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (appointment_id)\n)\nCREATE TABLE healthcare.diagnoses (\n    diagnosis_id character varying(64) NOT NULL, -- unique identifier for the diagnosis entry\n    record_id character varying(64) NOT NULL, -- FK linking to the specific medical record entry\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    doctor_id character varying(64) NOT NULL, -- FK to doctors table (diagnosing doctor)\n    diagnosis_code character varying(20) NOT NULL, -- standard code (e.g., ICD-10)\n    code_type character varying(10) NOT NULL DEFAULT 'ICD-10', -- type of code used\n    description text, -- textual description of the diagnosis\n    diagnosis_date date NOT NULL, -- date the diagnosis was made\n    status character varying(32) NOT NULL, -- e.g., Active, Resolved, Ruled Out\n    is_chronic boolean DEFAULT false, -- flag for chronic conditions\n    PRIMARY KEY (diagnosis_id)\n)\nCREATE TABLE healthcare.medications (\n    medication_id character varying(64) NOT NULL, -- unique identifier for the medication type\n    medication_name character varying(255) NOT NULL, -- common or brand name\n    generic_name character varying(255), -- generic chemical name\n    manufacturer character varying(100), -- drug manufacturer\n    ndc_code character varying(20) UNIQUE, -- National Drug Code (optional but useful)\n    description text, -- description of the medication\n    PRIMARY KEY (medication_id)\n)\nCREATE TABLE healthcare.prescriptions (\n    prescription_id character varying(64) NOT NULL, -- unique identifier for the prescription\n    record_id character varying(64) NOT NULL, -- FK linking to the medical record where it was prescribed\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    doctor_id character varying(64) NOT NULL, -- FK to prescribing doctor\n    medication_id character varying(64) NOT NULL, -- FK to medications table\n    dosage character varying(100) NOT NULL, -- e.g., '100mg', '1 tablet'\n    frequency character varying(100) NOT NULL, -- e.g., 'Once daily', 'Twice a day with meals'\n    route character varying(50), -- e.g., 'Oral', 'Topical', 'Intravenous'\n    start_date date NOT NULL, -- date prescription begins\n    end_date date, -- date prescription ends (if applicable)\n    quantity_dispensed numeric(10,2), -- amount dispensed (e.g., number of tablets)\n    refills_allowed integer NOT NULL DEFAULT 0, -- number of allowed refills\n    prescription_date timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (prescription_id)\n)\nCREATE TABLE healthcare.insurance_plans (\n    plan_id character varying(64) NOT NULL, -- unique identifier for the insurance plan\n    plan_name character varying(200) NOT NULL, -- name of the insurance plan\n    insurance_provider character varying(100) NOT NULL, -- name of the insurance company\n    plan_type character varying(50), -- e.g., PPO, HMO, EPO\n    contact_phone character varying(20), -- provider contact number\n    website character varying(255), -- provider website\n    PRIMARY KEY (plan_id)\n)\nCREATE TABLE healthcare.patient_insurance (\n    patient_insurance_id character varying(64) NOT NULL, -- unique identifier for this patient-plan link\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    plan_id character varying(64) NOT NULL, -- FK to insurance_plans table\n    policy_number character varying(100) NOT NULL, -- patient's policy number\n    group_number character varying(100), -- group number, if applicable\n    subscriber_name character varying(200), -- name of the primary policy holder\n    effective_date date NOT NULL, -- date the coverage begins\n    expiration_date date, -- date the coverage ends (if known)\n    is_primary boolean NOT NULL DEFAULT true, -- indicates if this is the primary insurance\n    PRIMARY KEY (patient_insurance_id),\n    UNIQUE (patient_id, plan_id, policy_number) -- ensure a patient doesn't have the same policy twice\n)\n"}
{"conversations": [{"role": "user", "content": "List all medical report documents with descriptions containing 'x-ray', showing their claim IDs and upload dates."}, {"role": "assistant", "content": "SELECT claim_id, document_id, uploaded_at FROM insurance.claim_documents WHERE document_type = 'medical_report' AND description LIKE '%x-ray%';"}, {"role": "user", "content": "Now include only documents uploaded in the last 3 months and sort them by upload date descending."}, {"role": "assistant", "content": "SELECT claim_id, document_id, uploaded_at FROM insurance.claim_documents WHERE document_type = 'medical_report' AND description LIKE '%x-ray%' AND uploaded_at >= NOW() - INTERVAL '3 months' ORDER BY uploaded_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.claim_documents ( document_id text, claim_id text, document_type text, file_name text, file_path text, file_size_bytes integer, mime_type text, uploaded_by text, uploaded_at timestamp, description text )\n"}
{"conversations": [{"role": "user", "content": "For each developer, can you find the next developer in the same country using a self join, returning developer_ids and names?"}, {"role": "assistant", "content": "SELECT d1.developer_id   AS current_dev,\n       d1.name           AS current_name,\n       d2.developer_id   AS next_dev,\n       d2.name           AS next_name,\n       d2.founded_year - d1.founded_year AS years_diff\nFROM developers d1\nJOIN developers d2\n  ON d1.country = d2.country\n  AND d2.founded_year > d1.founded_year;"}, {"role": "user", "content": "Exclude developers who don't have a next developer, and ensure we only pick the closest next by founded_year."}, {"role": "assistant", "content": "SELECT d1.developer_id   AS current_dev,\n       d1.name           AS current_name,\n       d2.developer_id   AS next_dev,\n       d2.name           AS next_name,\n       d2.founded_year - d1.founded_year AS years_diff\nFROM developers d1\nJOIN LATERAL (\n  SELECT d2.developer_id, d2.name, d2.founded_year\n  FROM developers d2\n  WHERE d2.country = d1.country\n    AND d2.founded_year > d1.founded_year\n  ORDER BY d2.founded_year ASC\n  LIMIT 1\n) d2 ON true;"}, {"role": "user", "content": "Finally, only include pairs where the difference in founded years is at most 5 years."}, {"role": "assistant", "content": "SELECT d1.developer_id   AS current_dev,\n       d1.name           AS current_name,\n       d2.developer_id   AS next_dev,\n       d2.name           AS next_name,\n       d2.founded_year - d1.founded_year AS years_diff\nFROM developers d1\nJOIN LATERAL (\n  SELECT d2.developer_id, d2.name, d2.founded_year\n  FROM developers d2\n  WHERE d2.country = d1.country\n    AND d2.founded_year > d1.founded_year\n  ORDER BY d2.founded_year ASC\n  LIMIT 1\n) d2 ON true\nWHERE (d2.founded_year - d1.founded_year) <= 5\nORDER BY d1.developer_id, years_diff ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.developers ( developer_id uuid PRIMARY KEY, name text, country text, founded_year int, website text, created_at timestamptz )\n"}
{"conversations": [{"role": "user", "content": "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 each lawyer's full name with the full name of the partner at the same firm."}, {"role": "assistant", "content": "SELECT l.lawyer_id,\n       CONCAT(l.first_name, ' ', l.last_name) AS lawyer_name,\n       CONCAT(p.first_name, ' ', p.last_name) AS partner_name\nFROM legal_services.lawyers l\nJOIN legal_services.lawyers p\n  ON l.firm_id = p.firm_id\n AND p.is_partner = true;"}, {"role": "user", "content": "Actually, I only want those lawyers whose specialization includes 'Corporate Law'. Could you update the query?"}, {"role": "assistant", "content": "SELECT l.lawyer_id,\n       CONCAT(l.first_name, ' ', l.last_name) AS lawyer_name,\n       CONCAT(p.first_name, ' ', p.last_name) AS partner_name\nFROM legal_services.lawyers l\nJOIN legal_services.lawyers p\n  ON l.firm_id = p.firm_id\n AND p.is_partner = true\nWHERE l.specialization ILIKE '%Corporate Law%';"}, {"role": "user", "content": "Also only show those who were hired after 2020-01-01."}, {"role": "assistant", "content": "SELECT l.lawyer_id,\n       CONCAT(l.first_name, ' ', l.last_name) AS lawyer_name,\n       CONCAT(p.first_name, ' ', p.last_name) AS partner_name\nFROM legal_services.lawyers l\nJOIN legal_services.lawyers p\n  ON l.firm_id = p.firm_id\n AND p.is_partner = true\nWHERE l.specialization ILIKE '%Corporate Law%'\n  AND l.hire_date > '2020-01-01';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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": "For each server, show its name and the total number of achievements available for the game it hosts."}, {"role": "assistant", "content": "SELECT s.server_name, s.region, COUNT(a.achievement_id) AS achievement_count\nFROM gaming_technology.servers s\nLEFT JOIN gaming_technology.achievements a ON s.game_id = a.game_id\nGROUP BY s.server_name, s.region;"}, {"role": "user", "content": "Exclude servers hosting games with no achievements."}, {"role": "assistant", "content": "SELECT s.server_name, s.region, COUNT(a.achievement_id) AS achievement_count\nFROM gaming_technology.servers s\nLEFT JOIN gaming_technology.achievements a ON s.game_id = a.game_id\nGROUP BY s.server_name, s.region\nHAVING COUNT(a.achievement_id) > 0;"}, {"role": "user", "content": "Also include each server's current_players and max_players."}, {"role": "assistant", "content": "SELECT s.server_name, s.region, s.current_players, s.max_players, COUNT(a.achievement_id) AS achievement_count\nFROM gaming_technology.servers s\nLEFT JOIN gaming_technology.achievements a ON s.game_id = a.game_id\nGROUP BY s.server_name, s.region, s.current_players, s.max_players\nHAVING COUNT(a.achievement_id) > 0;"}, {"role": "user", "content": "Sort by usage ratio (current_players divided by max_players) in descending order."}, {"role": "assistant", "content": "SELECT s.server_name, s.region, s.current_players, s.max_players, COUNT(a.achievement_id) AS achievement_count\nFROM gaming_technology.servers s\nLEFT JOIN gaming_technology.achievements a ON s.game_id = a.game_id\nGROUP BY s.server_name, s.region, s.current_players, s.max_players\nHAVING COUNT(a.achievement_id) > 0\nORDER BY (s.current_players::numeric / s.max_players) DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.developers ( developer_id uuid NOT NULL DEFAULT gen_random_uuid(), name character varying(150) NOT NULL UNIQUE, country character varying(100), founded_year integer, website character varying(255), created_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (developer_id) )\nCREATE TABLE gaming_technology.game_sessions ( session_id uuid NOT NULL DEFAULT gen_random_uuid(), player_id uuid NOT NULL, game_id uuid NOT NULL, server_id uuid, start_time timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, end_time timestamp with time zone, duration_seconds integer, score integer, session_data jsonb, PRIMARY KEY (session_id) )\nCREATE TABLE gaming_technology.servers ( server_id uuid NOT NULL DEFAULT gen_random_uuid(), game_id uuid NOT NULL, server_name character varying(150), region character varying(50) NOT NULL, ip_address character varying(45), port integer, current_players integer NOT NULL DEFAULT 0, max_players integer NOT NULL, status character varying(30) NOT NULL DEFAULT 'offline', last_heartbeat timestamp with time zone, PRIMARY KEY (server_id) )\nCREATE TABLE gaming_technology.achievements ( achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), game_id uuid NOT NULL, name character varying(150) NOT NULL, description text NOT NULL, icon_url character varying(255), points integer DEFAULT 0, hidden boolean DEFAULT false, PRIMARY KEY (achievement_id) )\n"}
{"conversations": [{"role": "user", "content": "Show each policy number and the total amount paid for it across all premium payments received so far."}, {"role": "assistant", "content": "SELECT T1.policy_number, SUM(T2.amount_paid) FROM insurance.policies AS T1 JOIN insurance.premium_payments AS T2 ON T1.policy_id = T2.policy_id GROUP BY T1.policy_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 insurance.customers ( customer_id text PRIMARY KEY, first_name text, last_name text, date_of_birth date, ssn_hash text, address_line1 text, address_line2 text, city text, state text, zip_code text, country text, phone_number text, email text, created_at timestamp, updated_at timestamp, status text )\nCREATE TABLE insurance.policies ( policy_id 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.insurance_products ( product_id text PRIMARY KEY, 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.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 ( document_id character varying(64) NOT NULL, claim_id character varying(64) NOT NULL, document_type character varying(50) NOT NULL, file_name character varying(255) NOT NULL, file_path character varying(512) NOT NULL, file_size_bytes integer, mime_type character varying(100), uploaded_by character varying(64), uploaded_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, description text, PRIMARY KEY (document_id) )\n"}
{"conversations": [{"role": "user", "content": "What is the maintenance schedule for the platforms at the station with ID 'ST234' for the next month?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to the maintenance schedule for the platforms at any station. The data I have only includes basic station information such as station ID, name, location, and number of platforms. For maintenance schedules, you may need to contact the station management or relevant authorities."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.stations ( station_id text PRIMARY KEY, station_name text, city text, state_province text, country_code text, address text, timezone text, number_of_platforms int, created_at timestamp, last_updated_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "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 all pairs of clients who registered on the same day, showing each client's first_name, last_name, and the registration date."}, {"role": "assistant", "content": "SELECT c1.first_name AS first_name_1, c1.last_name AS last_name_1, c2.first_name AS first_name_2, c2.last_name AS last_name_2, DATE(c1.date_registered) AS registration_date FROM legal_services.clients c1 JOIN legal_services.clients c2 ON DATE(c1.date_registered) = DATE(c2.date_registered) AND c1.client_id < c2.client_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.clients ( client_id text, first_name text, last_name text, company_name text, email text, phone text, address text, date_registered timestamp, status text )\n"}
{"conversations": [{"role": "user", "content": "For each city and state, show the number of service locations available along with their accessibility status."}, {"role": "assistant", "content": "SELECT city, state, is_accessible, COUNT(*) AS location_count FROM government_services.service_locations GROUP BY city, state, is_accessible;"}], "system": "You are an SQL statement expert. Given the table structure 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": "Show me all reservations with their guest IDs and room IDs where the total amount is greater than $500 and the status is 'Confirmed', ordered by check-in date."}, {"role": "assistant", "content": "SELECT reservation_id, guest_id, room_id, check_in_date, total_amount FROM hospitality_technology.reservations WHERE total_amount > 500 AND status = 'Confirmed' ORDER BY check_in_date;"}, {"role": "user", "content": "Now, join this with the service_orders table to include the total price of all services ordered for each reservation."}, {"role": "assistant", "content": "SELECT r.reservation_id, r.guest_id, r.room_id, r.check_in_date, r.total_amount, SUM(so.total_price) AS total_service_price FROM hospitality_technology.reservations r LEFT JOIN hospitality_technology.service_orders so ON r.reservation_id = so.reservation_id WHERE r.total_amount > 500 AND r.status = 'Confirmed' GROUP BY r.reservation_id, r.guest_id, r.room_id, r.check_in_date, r.total_amount ORDER BY r.check_in_date;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.reservations ( reservation_id.text, property_id.text, guest_id.text, room_id.text, room_type_id.text, check_in_date.date, check_out_date.date, actual_check_in_ts.timestamp, actual_check_out_ts.timestamp, num_adults.integer, num_children.integer, status.text, booking_source.text, rate_plan_id.text, total_amount.numeric, amount_paid.numeric, special_requests.text, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE hospitality_technology.service_orders ( order_id character varying(64) NOT NULL, reservation_id character varying(64), guest_id character varying(64) NOT NULL, service_id character varying(64) NOT NULL, staff_id_ordered character varying(64), staff_id_delivered character varying(64), order_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, delivery_timestamp timestamp with time zone, quantity integer NOT NULL DEFAULT 1, unit_price numeric(10, 2) NOT NULL, total_price numeric(12, 2) NOT NULL, status character varying(50) NOT NULL, notes text, bill_id character varying(64), PRIMARY KEY (order_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (service_id) REFERENCES hospitality_technology.services(service_id), FOREIGN KEY (staff_id_ordered) REFERENCES hospitality_technology.staff(staff_id), FOREIGN KEY (staff_id_delivered) REFERENCES hospitality_technology.staff(staff_id) )\nCREATE TABLE hospitality_technology.reviews ( review_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, reservation_id character varying(64) UNIQUE, guest_id character varying(64) NOT NULL, rating_overall integer, rating_cleanliness integer, rating_service integer, rating_location integer, rating_value integer, comment text, review_source character varying(100), review_date timestamp with time zone NOT NULL DEFAULT current_timestamp, is_public boolean DEFAULT true, staff_response text, response_staff_id character varying(64), response_date timestamp with time zone, PRIMARY KEY (review_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (response_staff_id) REFERENCES hospitality_technology.staff(staff_id) )\n"}
{"conversations": [{"role": "user", "content": "Can you list the number of citizens registered each month in 2024? Please show the month and the citizen count."}, {"role": "assistant", "content": "SELECT TO_CHAR(registration_date, 'YYYY-MM') AS registration_month, COUNT(*) AS citizen_count FROM government_services.citizens WHERE registration_date >= '2024-01-01' AND registration_date < '2025-01-01' GROUP BY registration_month ORDER BY registration_month;"}, {"role": "user", "content": "Now, can you also show the number of verified citizens for each month?"}, {"role": "assistant", "content": "SELECT TO_CHAR(registration_date, 'YYYY-MM') AS registration_month, COUNT(*) AS citizen_count, SUM(CASE WHEN is_verified = true THEN 1 ELSE 0 END) AS verified_citizen_count FROM government_services.citizens WHERE registration_date >= '2024-01-01' AND registration_date < '2025-01-01' GROUP BY registration_month ORDER BY registration_month;"}, {"role": "user", "content": "I see some months with zero verified citizens, but they still show up. Can you exclude months with zero verified citizens from the result?"}, {"role": "assistant", "content": "SELECT registration_month, citizen_count, verified_citizen_count FROM (SELECT TO_CHAR(registration_date, 'YYYY-MM') AS registration_month, COUNT(*) AS citizen_count, SUM(CASE WHEN is_verified = true THEN 1 ELSE 0 END) AS verified_citizen_count FROM government_services.citizens WHERE registration_date >= '2024-01-01' AND registration_date < '2025-01-01' GROUP BY registration_month) sub WHERE verified_citizen_count > 0 ORDER BY registration_month;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id character varying(64) NOT NULL, national_id_number character varying(128) NOT NULL UNIQUE, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, gender character varying(20), primary_address text NOT NULL, contact_email character varying(128) UNIQUE, contact_phone character varying(32), registration_date timestamp NOT NULL, is_verified boolean DEFAULT false, PRIMARY KEY (citizen_id) )\n"}
{"conversations": [{"role": "user", "content": "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": "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": "Find all pairs of different insurance records that share the same group_number, and show group_number, the patient_insurance_id of both records, and their corresponding patient_ids."}, {"role": "assistant", "content": "SELECT a.group_number,\n       a.patient_insurance_id AS pi_id1,\n       a.patient_id            AS patient1_id,\n       b.patient_insurance_id AS pi_id2,\n       b.patient_id            AS patient2_id\nFROM healthcare.patient_insurance a\nJOIN healthcare.patient_insurance b\n  ON a.group_number = b.group_number\n AND a.patient_insurance_id < b.patient_insurance_id\nWHERE a.group_number IS NOT NULL;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id text, patient_id text, plan_id text, policy_number text, group_number text, subscriber_name text, effective_date date, expiration_date date, is_primary boolean )\n"}
{"conversations": [{"role": "user", "content": "List the appointment ID, start time, and the case number for all appointments that are linked to a case."}, {"role": "assistant", "content": "SELECT T1.appointment_id, T1.start_time, T2.case_number FROM legal_services.appointments AS T1 JOIN legal_services.cases AS T2 ON T1.case_id = T2.case_id"}, {"role": "user", "content": "Refine this to only show appointments with status 'completed' associated with cases with status 'Closed'."}, {"role": "assistant", "content": "SELECT T1.appointment_id, T1.start_time, T2.case_number FROM legal_services.appointments AS T1 JOIN legal_services.cases AS T2 ON T1.case_id = T2.case_id WHERE T1.status = 'completed' AND T2.status = 'Closed'"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.cases ( case_id text, case_number text, case_name text, client_id text, lead_lawyer_id text, case_type text, status text, date_opened timestamp, date_closed timestamp, description text, court_jurisdiction text )\nCREATE TABLE legal_services.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": "For each premium payment, list all previous payments made by the same customer. Show customer_id, previous_payment_id, previous_payment_date, current_payment_id, current_payment_date, and amount difference."}, {"role": "assistant", "content": "SELECT p1.customer_id,\n       p1.payment_id AS previous_payment_id,\n       p1.payment_date AS previous_payment_date,\n       p2.payment_id AS current_payment_id,\n       p2.payment_date AS current_payment_date,\n       p2.amount_paid - p1.amount_paid AS amount_diff\nFROM insurance.premium_payments p1\nJOIN insurance.premium_payments p2\n  ON p1.customer_id = p2.customer_id\n  AND p1.payment_date < p2.payment_date;"}, {"role": "user", "content": "Actually, only include pairs where the current payment date is in 2024."}, {"role": "assistant", "content": "SELECT p1.customer_id,\n       p1.payment_id AS previous_payment_id,\n       p1.payment_date AS previous_payment_date,\n       p2.payment_id AS current_payment_id,\n       p2.payment_date AS current_payment_date,\n       p2.amount_paid - p1.amount_paid AS amount_diff\nFROM insurance.premium_payments p1\nJOIN insurance.premium_payments p2\n  ON p1.customer_id = p2.customer_id\n  AND p1.payment_date < p2.payment_date\nWHERE p2.payment_date BETWEEN '2024-01-01' AND '2024-12-31';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.premium_payments ( payment_id text, policy_id text, customer_id text, payment_date timestamp, amount_paid numeric, payment_method text, transaction_reference text, due_date date, payment_period_start date, payment_period_end date, status text )\n"}
{"conversations": [{"role": "user", "content": "List each document_name along with the count of its versions, but only include those document_names that have more than 3 versions."}, {"role": "assistant", "content": "SELECT document_name,\n       COUNT(version) AS version_count\nFROM legal_services.documents\nGROUP BY document_name\nHAVING COUNT(version) > 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 ( 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 all room types with a base rate over $200 and max occupancy of at least 4, along with their property IDs and amenities."}, {"role": "assistant", "content": "SELECT room_type_id, property_id, type_name, base_rate, max_occupancy, amenities FROM hospitality_technology.room_types WHERE base_rate > 200 AND max_occupancy >= 4;"}, {"role": "user", "content": "Now, join this with the guests table to show only room types from properties where the guest's country code is 'USA'."}, {"role": "assistant", "content": "SELECT rt.room_type_id, rt.property_id, rt.type_name, rt.base_rate, rt.max_occupancy, rt.amenities FROM hospitality_technology.room_types rt JOIN hospitality_technology.guests g ON rt.property_id = g.property_id WHERE rt.base_rate > 200 AND rt.max_occupancy >= 4 AND g.country_code = 'USA';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.room_types ( room_type_id text PRIMARY KEY, property_id text, type_name text, description text, base_rate numeric, max_occupancy int, bed_type text, area_sqft numeric, amenities text )\nCREATE TABLE hospitality_technology.guests ( guest_id text, first_name text, last_name text, email text, phone_number text, date_of_birth date, address_line1 text, city text, state_province text, postal_code text, country_code text, preferences text, loyalty_member_id text, communication_consent boolean, created_at timestamp, updated_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "List the service_id, service_name, and agency_id for all active services that have an online application URL provided."}, {"role": "assistant", "content": "SELECT service_id,\n       service_name,\n       agency_id\nFROM government_services.services\nWHERE is_active = TRUE\n  AND online_application_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 government_services.citizens ( citizen_id text PRIMARY KEY, national_id_number text, first_name text, last_name text, date_of_birth date, gender text, primary_address text, contact_email text, contact_phone text, registration_date timestamp, is_verified boolean )\nCREATE TABLE government_services.services ( service_id text, 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.documents (\n    document_id character varying(64) NOT NULL, -- unique identifier for the document instance\n    application_id character varying(64), -- FK to applications table (optional, could be linked to citizen directly)\n    citizen_id character varying(64) NOT NULL, -- FK to citizens table\n    document_type character varying(100) NOT NULL, -- e.g., Passport Scan, Proof of Address, Birth Certificate\n    file_reference text NOT NULL, -- reference to the stored file (e.g., S3 URL, internal path)\n    upload_timestamp timestamp NOT NULL,\n    expiry_date date,\n    verification_status character varying(30) DEFAULT 'Pending', -- e.g., Pending, Verified, Rejected\n    verified_by_employee_id character varying(64), -- FK to employees table\n    verification_timestamp timestamp,\n    PRIMARY KEY (document_id)\n)\nCREATE TABLE government_services.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": "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 passengers who have booked a trip to a city named 'Chicago'. Show their first name, last name, email, and the booking ID."}, {"role": "assistant", "content": "SELECT p.first_name, p.last_name, p.email, b.booking_id\nFROM transportation.bookings b\nJOIN transportation.passengers p ON b.passenger_id = p.passenger_id\nJOIN transportation.trips t ON b.trip_id = t.trip_id\nJOIN transportation.locations l ON t.destination_location_id = l.location_id\nWHERE l.city = 'Chicago';"}], "system": "You are an SQL statement expert. Given the table structure 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 (\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.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": "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": "Which smart money address on the Ethereum chain has the lowest ROI, and what are their profit and rank?"}, {"role": "assistant", "content": "SELECT address, roi, profit, rank FROM smart_money_profit WHERE chain = 'Ethereum' ORDER BY roi ASC LIMIT 1;"}, {"role": "user", "content": "Can you also include the realized_ratio for this address?"}, {"role": "assistant", "content": "SELECT address, roi, profit, rank, realized_ratio FROM smart_money_profit WHERE chain = 'Ethereum' ORDER BY roi ASC 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 smart_money_profit ( address.text, rank.numeric, profit.numeric, roi.numeric, realized_ratio.numeric, most_profit_token.text, last_trade_time.text, chain.text )\n"}
{"conversations": [{"role": "user", "content": "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": "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": "Show me the wallet addresses holding the ERC20 token with contract address '0xabcdeffedcba9876543210abcdefedcba9876'. Include the amount they hold."}, {"role": "assistant", "content": "SELECT wallet_address, amount FROM erc20_balances WHERE contract_address = '0xabcdeffedcba9876543210abcdefedcba9876';"}, {"role": "user", "content": "Instead of contract address, can you do this for a token symbol like 'USDC'?"}, {"role": "assistant", "content": "SELECT eb.wallet_address, eb.amount FROM erc20_balances eb JOIN token_metas tm ON eb.contract_address = tm.contract_address WHERE tm.symbol = 'USDC' AND tm.is_erc20 = 1;"}, {"role": "user", "content": "Filter the results to only show wallets holding more than 1000 of this token."}, {"role": "assistant", "content": "SELECT eb.wallet_address, eb.amount FROM erc20_balances eb JOIN token_metas tm ON eb.contract_address = tm.contract_address WHERE tm.symbol = 'USDC' AND tm.is_erc20 = 1 AND CAST(eb.amount AS DECIMAL) > 1000;"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nCREATE TABLE token_metas ( block_timestamp timestamp, block_number bigint, transaction_hash 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 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_latest ( blockchain text, address text, decimals bigint, symbol text, price real, timestamp timestamp )\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_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 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": "Show me all fuel logs where the location is 'LOC456', including the vehicle ID, fuel type, and quantity."}, {"role": "assistant", "content": "SELECT fuel_log_id, vehicle_id, fuel_type, quantity FROM transportation.fuel_logs WHERE location_id = 'LOC456';"}, {"role": "user", "content": "Can you also include the trip ID and filter to only show logs from the last 3 months?"}, {"role": "assistant", "content": "SELECT fuel_log_id, vehicle_id, trip_id, fuel_type, quantity FROM transportation.fuel_logs WHERE location_id = 'LOC456' AND log_timestamp >= CURRENT_DATE - INTERVAL '3 months';"}, {"role": "user", "content": "Now group these results by fuel type and show the total quantity for each type."}, {"role": "assistant", "content": "SELECT fuel_type, SUM(quantity) AS total_quantity FROM transportation.fuel_logs WHERE location_id = 'LOC456' AND log_timestamp >= CURRENT_DATE - INTERVAL '3 months' GROUP BY fuel_type;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.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": "Show me all accounts (account_id, account_number, balance) that have a balance greater than $50,000 and are in USD currency, along with the security details (ticker_symbol, security_name) for securities traded on the same exchange as the account's last_updated_at date."}, {"role": "assistant", "content": "SELECT a.account_id, a.account_number, a.balance, s.ticker_symbol, s.security_name FROM financial_services.accounts a JOIN financial_services.securities s ON a.currency = s.currency WHERE a.balance > 50000 AND a.currency = 'USD' AND s.exchange IS NOT NULL;"}, {"role": "user", "content": "Now modify the query to only include accounts with status 'Open' and securities from the 'Technology' sector, sorted by account balance in descending order."}, {"role": "assistant", "content": "SELECT a.account_id, a.account_number, a.balance, s.ticker_symbol, s.security_name FROM financial_services.accounts a JOIN financial_services.securities s ON a.currency = s.currency WHERE a.balance > 50000 AND a.currency = 'USD' AND a.status = 'Open' AND s.sector = 'Technology' AND s.exchange IS NOT NULL ORDER BY a.balance DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.accounts (\n    account_id character varying(64) NOT NULL, -- unique identifier for the account\n    customer_id character varying(64) NOT NULL, -- foreign key linking to the customer\n    account_number character varying(128) NOT NULL UNIQUE, -- unique account number visible to customer\n    account_type character varying(50) NOT NULL, -- e.g., Checking, Savings, Investment, Loan, Credit Card\n    balance numeric(19, 4) NOT NULL DEFAULT 0.00, -- current account balance\n    currency character varying(3) NOT NULL, -- currency code (e.g., USD, EUR)\n    opened_date date NOT NULL, -- date the account was opened\n    status character varying(32) NOT NULL, -- e.g., Open, Closed, Frozen\n    interest_rate numeric(5, 4), -- annual interest rate, if applicable\n    last_updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last account update\n    PRIMARY KEY (account_id),\n    FOREIGN KEY (customer_id) REFERENCES financial_services.customers(customer_id)\n)\nCREATE TABLE financial_services.securities (\n    security_id character varying(64) NOT NULL, -- unique identifier for the security\n    ticker_symbol character varying(20) NOT NULL UNIQUE, -- stock ticker or fund symbol\n    isin_code character varying(12) UNIQUE, -- International Securities Identification Number\n    cusip_code character varying(9) UNIQUE, -- CUSIP number\n    security_name text NOT NULL, -- full name of the security\n    security_type character varying(50) NOT NULL, -- e.g., Stock, Bond, ETF, Mutual Fund, Option, Future\n    exchange character varying(50), -- primary exchange where traded (e.g., NYSE, NASDAQ)\n    currency character varying(3) NOT NULL, -- currency the security is denominated in\n    issuer_name character varying(255), -- name of the issuing entity\n    sector character varying(100), -- industry sector\n    last_updated timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n    PRIMARY KEY (security_id)\n)\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": "Retrieve the vehicle_id, make, model, and the next_service_due_date for each vehicle based on the most recent maintenance log."}, {"role": "assistant", "content": "SELECT DISTINCT ON (ml.vehicle_id) v.vehicle_id, v.make, v.model, ml.next_service_due_date FROM transportation.maintenance_logs ml JOIN transportation.vehicles v ON v.vehicle_id = ml.vehicle_id ORDER BY ml.vehicle_id, ml.service_date DESC;"}, {"role": "user", "content": "Now, only include vehicles with status 'Active' and whose next_service_due_date is within the next 30 days, ordering by next_service_due_date ascending."}, {"role": "assistant", "content": "SELECT v.vehicle_id, v.make, v.model, ml.next_service_due_date FROM transportation.vehicles v JOIN (SELECT DISTINCT ON (vehicle_id) vehicle_id, next_service_due_date FROM transportation.maintenance_logs ORDER BY vehicle_id, service_date DESC) ml ON v.vehicle_id = ml.vehicle_id WHERE v.status = 'Active' AND ml.next_service_due_date BETWEEN current_date AND current_date + INTERVAL '30 days' ORDER BY ml.next_service_due_date ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles ( vehicle_id text PRIMARY KEY, license_plate text, vin text, make text, model text, year int, type text, capacity int, fuel_type text, status text, depot_id text, acquisition_date date )\nCREATE TABLE transportation.drivers ( driver_id text PRIMARY KEY, employee_id text, first_name text, last_name text, license_number text, license_expiry_date date, contact_number text, email text, hire_date date, status text )\nCREATE TABLE transportation.routes ( route_id text PRIMARY KEY, route_number text, description text, origin_location_id text, destination_location_id text, distance_km numeric, estimated_duration_minutes int, type text )\nCREATE TABLE transportation.trips ( trip_id text PRIMARY KEY, route_id text, vehicle_id text, driver_id text, scheduled_departure timestamp, actual_departure timestamp, scheduled_arrival timestamp, actual_arrival timestamp, origin_location_id text, destination_location_id text, status text, passenger_count int, cargo_manifest_id text )\nCREATE TABLE transportation.locations ( location_id text PRIMARY KEY, name text, type text, address_line1 text, city text, state_province text, postal_code text, country text, latitude numeric, longitude numeric, timezone text )\nCREATE TABLE transportation.maintenance_logs ( log_id text PRIMARY KEY, vehicle_id text, service_date date, odometer_reading int, service_type text, description text, cost numeric, mechanic_name text, next_service_due_date date )\nCREATE TABLE transportation.fuel_logs ( fuel_log_id text PRIMARY KEY, vehicle_id text, trip_id text, log_timestamp timestamp, fuel_type text, quantity numeric, unit text, cost_per_unit numeric, total_cost numeric, odometer_reading int, location_id text )\nCREATE TABLE transportation.bookings ( booking_id text PRIMARY KEY, passenger_id text, trip_id text, seat_number text, booking_time timestamp, status text, fare numeric, payment_transaction_id text, special_requests text )\n"}
{"conversations": [{"role": "user", "content": "List lawyers who have any unbilled time entries. Show their first name, last name, and the count of their unbilled entries."}, {"role": "assistant", "content": "SELECT T1.first_name, T1.last_name, COUNT(T2.entry_id) FROM lawyers AS T1 JOIN time_entries AS T2 ON T1.lawyer_id = T2.lawyer_id WHERE T2.is_billed = false GROUP BY T1.lawyer_id, T1.first_name, T1.last_name;"}, {"role": "user", "content": "Modify that query to only include entries marked as billable, and instead show the total hours spent rather than the count."}, {"role": "assistant", "content": "SELECT T1.first_name, T1.last_name, SUM(T2.hours_spent) FROM lawyers AS T1 JOIN time_entries AS T2 ON T1.lawyer_id = T2.lawyer_id WHERE T2.is_billed = false AND T2.is_billable = true GROUP BY T1.lawyer_id, T1.first_name, T1.last_name;"}, {"role": "user", "content": "Now, only show lawyers with more than 10 unbilled billable hours in total, and sort the results by the total hours descending."}, {"role": "assistant", "content": "SELECT T1.first_name, T1.last_name, SUM(T2.hours_spent) FROM lawyers AS T1 JOIN time_entries AS T2 ON T1.lawyer_id = T2.lawyer_id WHERE T2.is_billed = false AND T2.is_billable = true GROUP BY T1.lawyer_id, T1.first_name, T1.last_name HAVING SUM(T2.hours_spent) > 10 ORDER BY SUM(T2.hours_spent) DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.lawyers ( lawyer_id text PRIMARY KEY, first_name text, last_name text, bar_number text UNIQUE, firm_id text, email text UNIQUE, phone text, specialization text, hire_date timestamp, is_partner bool )\nCREATE TABLE legal_services.law_firms ( firm_id text PRIMARY KEY, firm_name text, address text, phone text, website text, founded_date date, managing_partner_id text )\nCREATE TABLE legal_services.documents ( document_id text PRIMARY KEY, case_id text, document_name text, document_type text, storage_path text, uploaded_by_lawyer_id text, upload_timestamp timestamp, version int, description text )\nCREATE TABLE legal_services.time_entries ( entry_id text PRIMARY KEY, case_id text, lawyer_id text, date_worked date, hours_spent numeric, billing_rate numeric, description text, is_billable bool, is_billed bool, invoice_id text, created_at timestamp )\nCREATE TABLE legal_services.invoices ( invoice_id text PRIMARY KEY, invoice_number text UNIQUE, client_id text, case_id text, issue_date date, due_date date, total_amount numeric, amount_paid numeric, status text, payment_date timestamp, notes text, created_at timestamp )\nCREATE TABLE legal_services.appointments ( appointment_id text PRIMARY KEY, client_id text, lawyer_id text, case_id text, start_time timestamp, end_time timestamp, location text, subject text, notes text, status text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Which vehicles have a total maintenance cost exceeding 10000 across all their maintenance logs?"}, {"role": "assistant", "content": "SELECT vehicle_id, SUM(cost) AS total_maintenance_cost FROM transportation.maintenance_logs GROUP BY vehicle_id HAVING SUM(cost) > 10000;"}, {"role": "user", "content": "For these vehicles, also show the count of maintenance logs and the average cost per log."}, {"role": "assistant", "content": "SELECT vehicle_id, COUNT(log_id) AS maintenance_log_count, AVG(cost) AS average_maintenance_cost FROM transportation.maintenance_logs GROUP BY vehicle_id HAVING SUM(cost) > 10000;"}], "system": "You are an SQL statement expert. Given the table structure 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.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) )\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": "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": "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": "Could you list all pairs of developers that are based in the same country and share the same website domain?"}, {"role": "assistant", "content": "SELECT\n  d1.name AS developer1_name,\n  d2.name AS developer2_name,\n  d1.country,\n  d1.website\nFROM\n  gaming_technology.developers AS d1\nJOIN\n  gaming_technology.developers AS d2 ON d1.country = d2.country\n  AND d1.website = d2.website\n  AND d1.developer_id < d2.developer_id\nWHERE\n  d1.country IS NOT NULL\n  AND d1.website IS NOT NULL AND d1.website != '';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.developers (\n    developer_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the developer studio\n    name character varying(150) NOT NULL UNIQUE, -- name of the development studio\n    country character varying(100), -- country where the studio is based\n    founded_year integer, -- year the studio was founded\n    website character varying(255), -- developer's official website\n    created_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP,\n    PRIMARY KEY (developer_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List all users whose email contains the word 'block', along with their username and registration timestamp."}, {"role": "assistant", "content": "SELECT user_id, username, email, created_at\nFROM web3.users\nWHERE email ILIKE '%block%';"}, {"role": "user", "content": "Can you also include the total number of such users in the result?"}, {"role": "assistant", "content": "SELECT user_id, username, email, created_at, COUNT(*) OVER() AS total_matching_users\nFROM web3.users\nWHERE email ILIKE '%block%';"}], "system": "You are an SQL statement expert. Given the table structure 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": "How many participants are there in each conversation? Return conversation_id and participant_count."}, {"role": "assistant", "content": "SELECT conversation_id,\n       COUNT(*) AS participant_count\nFROM social_media.conversation_participants\nGROUP BY conversation_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.conversation_participants ( participant_id text, conversation_id text, user_id text, joined_at timestamp, last_read_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "What is the average difficulty and the maximum nonce value for all blocks recorded?"}, {"role": "assistant", "content": "SELECT AVG(difficulty), MAX(nonce) FROM blockchain.blocks"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nCREATE TABLE blockchain.blocks ( block_id text, previous_block_id text, timestamp timestamp, nonce integer, merkle_root text, difficulty integer )\n"}
{"conversations": [{"role": "user", "content": "List all loans (loan_id, loan_type, principal_amount) that have a current principal balance less than 25% of the original principal amount, along with their account_id and the difference between principal_amount and current_principal_balance."}, {"role": "assistant", "content": "SELECT loan_id, loan_type, principal_amount, account_id, (principal_amount - current_principal_balance) AS amount_paid FROM financial_services.loans WHERE current_principal_balance < (0.25 * 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 text, account_id text, loan_type text, principal_amount numeric, current_principal_balance numeric, interest_rate numeric, term_months integer, origination_date date, maturity_date date, monthly_payment numeric, collateral_description text, status text )\n"}
{"conversations": [{"role": "user", "content": "List all medication names, their manufacturers, and NDC codes."}, {"role": "assistant", "content": "SELECT medication_name, manufacturer, ndc_code\nFROM healthcare.medications;"}, {"role": "user", "content": "Now restrict to only those entries where generic_name is missing and sort by medication_name ascending."}, {"role": "assistant", "content": "SELECT medication_name, manufacturer, ndc_code\nFROM healthcare.medications\nWHERE generic_name IS NULL\nORDER BY medication_name ASC;"}, {"role": "user", "content": "Finally, for each manufacturer, list pairs of distinct medications produced by that manufacturer (med1 and med2)."}, {"role": "assistant", "content": "SELECT m1.medication_name AS med1, m2.medication_name AS med2, m1.manufacturer\nFROM healthcare.medications m1\nJOIN healthcare.medications m2\n  ON m1.manufacturer = m2.manufacturer\n AND m1.medication_id < m2.medication_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.medications ( medication_id character varying(64) NOT NULL, medication_name character varying(255) NOT NULL, generic_name character varying(255), manufacturer character varying(100), ndc_code character varying(20) UNIQUE, description text, PRIMARY KEY (medication_id) )\n"}
{"conversations": [{"role": "user", "content": "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 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 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 all business center services (category = 'Business Center') along with their property IDs and descriptions, where the service is available."}, {"role": "assistant", "content": "SELECT service_name, property_id, description FROM hospitality_technology.services WHERE category = 'Business Center' AND is_available = true;"}, {"role": "user", "content": "Now, join this with another query to include the property names from the properties table (assuming properties table has property_id and property_name columns)."}, {"role": "assistant", "content": "SELECT s.service_name, s.property_id, s.description, p.property_name FROM hospitality_technology.services s JOIN hospitality_technology.properties p ON s.property_id = p.property_id WHERE s.category = 'Business Center' AND s.is_available = true;"}, {"role": "user", "content": "The query is missing the price information. Can you include that as well?"}, {"role": "assistant", "content": "SELECT s.service_name, s.property_id, s.description, p.property_name, s.price FROM hospitality_technology.services s JOIN hospitality_technology.properties p ON s.property_id = p.property_id WHERE s.category = 'Business Center' AND s.is_available = true;"}, {"role": "user", "content": "Actually, I need to see only services priced per hour (unit = 'Per Hour'), and order them by property name in alphabetical order."}, {"role": "assistant", "content": "SELECT s.service_name, s.property_id, s.description, p.property_name, s.price FROM hospitality_technology.services s JOIN hospitality_technology.properties p ON s.property_id = p.property_id WHERE s.category = 'Business Center' AND s.is_available = true AND s.unit = 'Per Hour' ORDER BY p.property_name ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.services (\n    service_id character varying(64) NOT NULL, -- unique identifier for a chargeable service\n    property_id character varying(64) NOT NULL, -- FK to properties table\n    service_name character varying(150) NOT NULL, -- e.g., Room Service - Burger, Spa - Massage 60min, Laundry - Shirt\n    description text,\n    category character varying(100), -- e.g., Food & Beverage, Wellness, Business Center, Activities\n    price numeric(10, 2) NOT NULL, -- price per unit/instance\n    unit character varying(30), -- e.g., Per Item, Per Hour, Per Day\n    is_available boolean NOT NULL DEFAULT true, -- is the service currently offered?\n    department character varying(100), -- department responsible (e.g., F&B, Spa, Housekeeping)\n    PRIMARY KEY (service_id),\n    FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id)\n)\n"}
{"conversations": [{"role": "user", "content": "What is the average ROI for smart money addresses on the Ethereum chain?"}, {"role": "assistant", "content": "SELECT AVG(roi) FROM smart_money_token_performance WHERE chain = 'Ethereum';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\n \"CREATE TABLE project_fundraising_record (\",\n    \"id character varying(32) NOT NULL,  -- fundraising record id\",\n    \"project_id character varying(32) NOT NULL, -- the invested project's id\",\n    \"project_name character varying(128) NOT NULL, -- name of the invested project\",\n    \"rounds_name character varying(32), -- name of the fundraising round\",\n    \"investment_value numeric(38,14), -- amount of the fundraising in USD\",\n    \"investment_date character varying(128), -- the date of the investment happened\",\n    \"introduction character varying(128), -- the introduction of the invested project\",\n    \"valuation numeric(38,14), -- the valuation of the project in USD when invested\",\n\n \"CREATE TABLE token_basic_info (\",\n    \"coin_id character varying(100) NOT NULL, -- the id of the token\",\n    \"token_name character varying(100) NOT NULL, -- the token's name\",\n    \"token_symbol character varying(100) NOT NULL, -- the token's symbol\",\n    \"token_address character varying(100) NOT NULL, -- the token's address\",\n    \"chain text, -- the chain that the token resides\",\n    \"price double precision, -- the current price of the token\",\n    \"price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour\",\n    \"price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours\",\n    \"price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days\",\n    \"highest_price_24h double precision, -- the highest price of the token in 24 hours\",\n    \"lowest_price_24h double precision,  -- the lowest price of the token in 24 hours\",\n    \"market_cap double precision, -- the market cap of the token\",\n    \"market_cap_rank bigint, -- the rank of the token market cap in desc\",\n    \"market_cap_change_percentage_24h text, -- the percentage of market cap changes in 24 hours\",\n    \"total_volume text, -- the trade volum of the token both in decentralized exchange(DEX) and centralized exchange(CEX)\",    \n    \"narrative text, -- the category or narrative of the token\",\n    \"trend_rank biging, -- the trending rank of the token, value 1 expresses the most popular token.\",\n    \",PRIMARY KEY (coin_id, chain));\",\n\n \"CREATE TABLE narrative_info (\",\n    \"narrative character varying(512) NOT NULL, -- the id of narrative\",\n    \"top_3_coins text, -- the top 3 tokens in the narrative\",\n    \"price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour in the narrative\",\n    \"price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours in the narrative\",\n    \"price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days in the narrative\",\n    \"market_cap double precision, -- the market cap of the narrative\",\n    \"volume_24h double precision, -- the trade volume of the narrative\",\n    \"trend_rank bigint, -- the trending rank of the narrative, value 1 expresses the most popular narrative\",\n    \"token_num bigint, -- total token number in the narrative\",\n    \",PRIMARY KEY (narrative));\"\n\n  \"CREATE TABLE cex_token_balance (\",\n    \"snapshot_time character varying(32) NOT NULL,  -- the snapshot time of record, converted from original timestamp\",\n    \"chain character varying(128) NOT NULL, -- the chain that the token resides\",\n    \"address character varying(128) NOT NULL, -- the address that holds the assets, owned by a CEX\",\n    \"exchange character varying(512) NOT NULL, -- a centralized exchange name\",\n    \"token_address character varying(128) NOT NULL, -- token contract address\",\n    \"token_symbol character varying(512), --token symbol\",\n    \"balance numeric(38,10), -- token balance\",\n    \"usd_value numeric(38,14), -- value of the token held in USD\",\n    \"price double precision, --price of the token in USD\",\n    \",PRIMARY KEY (snapshot_time, exchange, address, chain, token_address));\"\n\n  \"CREATE TABLE smart_money_token_performance (\",\n    \"token_address character varying(100) NOT NULL, -- the token's address\",\n    \"token_symbol character varying(100), -- the tokens's symbol\",\n    \"pnl numeric(38,2), -- the profit users made on this token\",\n    \"net_flow numeric(38,2), -- the netflow of the token, means the money user spent minus the the money user sold of this token\",\n    \"avg_cost numeric(38,16), -- the average cost price of user spent on this token\",\n    \"price double precision, -- the current price of the token\",\n    \"realized_ratio numeric(10,2), -- the ratio user sold of the token\",\n    \"roi numeric(10,2), -- the roi users made of this token\",\n    \"chain character varying(100), -- the chain that the token resides\",\n    \"PRIMARY KEY (token_address, chain));\",\n\n"}
{"conversations": [{"role": "user", "content": "Show the IDs and registration dates of all verified citizens who could be eligible for at least one active service. Display the citizen ID and registration date."}, {"role": "assistant", "content": "SELECT DISTINCT c.citizen_id, c.registration_date\nFROM government_services.citizens c\nJOIN government_services.services s ON s.is_active = true\nWHERE c.is_verified = true;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id character varying(64) NOT NULL, national_id_number character varying(128) NOT NULL UNIQUE, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, gender character varying(20), primary_address text NOT NULL, contact_email character varying(128) UNIQUE, contact_phone character varying(32), registration_date timestamp NOT NULL, is_verified boolean DEFAULT false, PRIMARY KEY (citizen_id) )\nCREATE TABLE government_services.services ( service_id.text, agency_id.text, service_name.text, description.text, category.text, eligibility_criteria.text, standard_fee.numeric, average_processing_time_days.integer, is_active.boolean, online_application_url.text )\n"}
{"conversations": [{"role": "user", "content": "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": "For each NFT collection deployed on Ethereum, count the number of distinct wallets that have ever held any token from that collection."}, {"role": "assistant", "content": "SELECT\n  nc.contract_address,\n  nc.name,\n  COUNT(DISTINCT nh.wallet_address) AS holder_count\nFROM nft_collections nc\nJOIN nft_holder_historical nh\n  ON nc.contract_address = nh.contract_address\nWHERE nc.blockchain = 'Ethereum'\nGROUP BY nc.contract_address, nc.name;"}, {"role": "user", "content": "Include each collection's token_count and floor_price from nft_collections."}, {"role": "assistant", "content": "SELECT\n  nc.contract_address,\n  nc.name,\n  nc.token_count,\n  nc.floor_price,\n  COUNT(DISTINCT nh.wallet_address) AS holder_count\nFROM nft_collections nc\nJOIN nft_holder_historical nh\n  ON nc.contract_address = nh.contract_address\nWHERE nc.blockchain = 'Ethereum'\nGROUP BY\n  nc.contract_address,\n  nc.name,\n  nc.token_count,\n  nc.floor_price;"}], "system": "You are an SQL statement expert. Given the table structure 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.text, wallet_address.text, amount.text, pk.text )\nCREATE TABLE nft_holder_historical ( block_number.bigint, contract_address.text, wallet_address.text, token_id.text, contract_type.text, amount.text, pk.integer )\nCREATE TABLE sui_coins_metadata ( object_id 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_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 varchar, 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 text, log_index integer, contract_address text, pk integer )\nCREATE TABLE token_info (\n    block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n    block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n    tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n    tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n    tick varchar NOT NULL, -- Token tick\n    max_supply decimal(38,0) NOT NULL, -- Max supply\n    lim decimal(38,0) NOT NULL, -- Limit of each mint\n    wlim decimal(38,0) NOT NULL, -- Limit of each address can maximum mint\n    dec integer NOT NULL, -- Decimal for minimum divie\n    creator varchar(42) NOT NULL  -- Address originating the inscription (matches from_address in transactions table)\n)\nCREATE TABLE token_balances_bitcoin ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply varchar, amount 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, block_timestamp timestamp, tick text, wallet_address text, total_supply decimal, amount decimal )\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 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": "Show me all token transfers where the from_address is the same as the to_address, indicating self-transfers, along with the token_id and value."}, {"role": "assistant", "content": "SELECT transfer_id, token_id, from_address, to_address, value, transaction_id FROM web3.token_transfers WHERE from_address = to_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, token_id.text, from_address.text, to_address.text, value.numeric, transaction_id.text, log_index.integer )\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": "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": "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": "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": "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": "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": "What is the total USD value held across all wallets for the ERC20 token with symbol 'DAI'?"}, {"role": "assistant", "content": "SELECT SUM((eb.amount::numeric / POWER(10, tm.decimals)) * tpl.price) AS total_usd\nFROM erc20_balances eb\nJOIN token_metas tm ON eb.contract_address = tm.contract_address AND tm.symbol = 'DAI'\nJOIN token_prices_latest tpl ON tm.contract_address = tpl.address AND tpl.blockchain = 'Ethereum';"}, {"role": "user", "content": "Could you break it down to show the top 5 wallets by USD value for this token?"}, {"role": "assistant", "content": "SELECT eb.wallet_address,\n       SUM((eb.amount::numeric / POWER(10, tm.decimals)) * tpl.price) AS usd_value\nFROM erc20_balances eb\nJOIN token_metas tm ON eb.contract_address = tm.contract_address AND tm.symbol = 'DAI'\nJOIN token_prices_latest tpl ON tm.contract_address = tpl.address AND tpl.blockchain = 'Ethereum'\nGROUP BY eb.wallet_address\nORDER BY usd_value DESC\nLIMIT 5;"}, {"role": "user", "content": "I received a type error because amount is stored as text. Can you cast the fields to numeric explicitly in the query?"}, {"role": "assistant", "content": "SELECT eb.wallet_address,\n       SUM((CAST(eb.amount AS numeric) / POWER(10, tm.decimals)) * CAST(tpl.price AS numeric)) AS usd_value\nFROM erc20_balances eb\nJOIN token_metas tm ON eb.contract_address = tm.contract_address AND tm.symbol = 'DAI'\nJOIN token_prices_latest tpl ON tm.contract_address = tpl.address AND tpl.blockchain = 'Ethereum'\nGROUP BY eb.wallet_address\nORDER BY usd_value DESC\nLIMIT 5;"}, {"role": "user", "content": "Also include the latest price timestamp alongside the USD value for each wallet."}, {"role": "assistant", "content": "SELECT eb.wallet_address,\n       SUM((CAST(eb.amount AS numeric) / POWER(10, tm.decimals)) * tpl.price) AS usd_value,\n       MAX(tpl.timestamp) AS price_timestamp\nFROM erc20_balances eb\nJOIN token_metas tm ON eb.contract_address = tm.contract_address AND tm.symbol = 'DAI'\nJOIN token_prices_latest tpl ON tm.contract_address = tpl.address AND tpl.blockchain = 'Ethereum'\nGROUP BY eb.wallet_address\nORDER BY usd_value 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 varchar, transaction_index bigint, from_address varchar, contract_address varchar, symbol varchar, total_supply varchar, name varchar, decimals bigint, is_erc20 integer, is_erc721 integer, is_erc1155 integer, is_proxy integer, extra_info varchar, pk integer )\nCREATE TABLE erc1155_approval_for_all ( block_number bigint 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, contract_address.text, wallet_address.text, amount.text, pk.text )\nCREATE TABLE erc20_balances_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\n    amount varchar NOT NULL, -- Wallet's on-chain balance at the corresponding block height\n    pk integer NOT NULL  -- Partition key for the table(floor(block_number / 7200))\n)\nCREATE TABLE nft_holder_historical ( block_number.bigint, contract_address.text, wallet_address.text, token_id.text, contract_type.text, amount.text, pk.integer )\nCREATE TABLE sui_coins_metadata ( object_id varchar, coin_type varchar, status varchar, decimals bigint, description varchar, icon_url varchar, symbol varchar, name varchar )\nCREATE TABLE nft_metadata ( blockchain 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 (\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 varchar, blockchain varchar, address varchar, decimals bigint, symbol varchar, 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, block_timestamp timestamp, transaction_index integer, transaction_hash text, log_index integer, contract_address text, pk integer )\nCREATE TABLE token_info (\n    block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n    block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n    tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n    tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n    tick varchar NOT NULL, -- Token tick\n    max_supply decimal(38,0) NOT NULL, -- Max supply\n    lim decimal(38,0) NOT NULL, -- Limit of each mint\n    wlim decimal(38,0) NOT NULL, -- Limit of each address can maximum mint\n    dec integer NOT NULL, -- Decimal for minimum divie\n    creator varchar(42) NOT NULL  -- Address originating the inscription (matches from_address in transactions table)\n)\nCREATE TABLE token_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_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": "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": "List all patients who have a medical record with a chief complaint containing the word 'headache'. Show patient ID, first name, last name, and date of birth."}, {"role": "assistant", "content": "SELECT DISTINCT\n  p.patient_id,\n  p.first_name,\n  p.last_name,\n  p.date_of_birth\nFROM healthcare.patients AS p\nJOIN healthcare.medical_records AS mr\n  ON p.patient_id = mr.patient_id\nWHERE\n  mr.chief_complaint ILIKE '%headache%';"}, {"role": "user", "content": "Refine the query to only include records created in the year 2024."}, {"role": "assistant", "content": "SELECT DISTINCT\n  p.patient_id,\n  p.first_name,\n  p.last_name,\n  p.date_of_birth\nFROM healthcare.patients AS p\nJOIN healthcare.medical_records AS mr\n  ON p.patient_id = mr.patient_id\nWHERE\n  mr.chief_complaint ILIKE '%headache%' AND mr.record_date >= '2024-01-01 00:00:00' AND mr.record_date < '2025-01-01 00:00:00';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id text, first_name text, last_name text, date_of_birth date, gender text, address text, phone_number text, email text, emergency_contact_name text, emergency_contact_phone text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.doctors ( doctor_id text, first_name text, last_name text, specialty text, license_number text, phone_number text, email text, hospital_affiliation_id text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.appointments ( appointment_id text, patient_id text, doctor_id text, appointment_time timestamp, duration_minutes integer, reason text, status text, location_id text, notes text, created_at timestamp )\nCREATE TABLE healthcare.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.medications ( medication_id text, medication_name text, generic_name text, manufacturer text, ndc_code text, description text )\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": "Give me each server's name, the region, and the maximum number of players that have been connected at once."}, {"role": "assistant", "content": "SELECT s.server_id, s.server_name, s.region, MAX(s.current_players) AS max_players_seen\nFROM gaming_technology.servers s\nGROUP BY s.server_id, s.server_name, s.region;"}, {"role": "user", "content": "Could you also include the associated game title for each server?"}, {"role": "assistant", "content": "SELECT s.server_id, s.server_name, s.region, g.title AS game_title, MAX(s.current_players) AS max_players_seen\nFROM gaming_technology.servers s\nJOIN gaming_technology.games g ON s.game_id = g.game_id\nGROUP BY s.server_id, s.server_name, s.region, g.title;"}, {"role": "user", "content": "Now, can you show only servers where the max number of players ever connected exceeded 20?"}, {"role": "assistant", "content": "SELECT s.server_id, s.server_name, s.region, g.title AS game_title, MAX(s.current_players) AS max_players_seen\nFROM gaming_technology.servers s\nJOIN gaming_technology.games g ON s.game_id = g.game_id\nGROUP BY s.server_id, s.server_name, s.region, g.title\nHAVING MAX(s.current_players) > 20;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.players ( player_id uuid PRIMARY KEY, username text, email text, password_hash text, registration_date timestamptz, last_login timestamptz, country_code text, status text, profile_data jsonb )\nCREATE TABLE gaming_technology.games ( game_id uuid PRIMARY KEY, title text, developer_id uuid, publisher_id uuid, genre text, release_date date, description text, platform text, engine text, website text )\nCREATE TABLE gaming_technology.game_sessions ( session_id uuid PRIMARY KEY, player_id uuid, game_id uuid, server_id uuid, start_time timestamptz, end_time timestamptz, duration_seconds int, score int, session_data jsonb )\nCREATE TABLE gaming_technology.servers (\n    server_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game server instance\n    game_id uuid NOT NULL, -- FK linking to the game this server hosts\n    server_name character varying(150), -- display name for the server\n    region character varying(50) NOT NULL, -- geographical region (e.g., us-east-1, eu-west-2)\n    ip_address character varying(45), -- IP address (IPv4 or IPv6)\n    port integer, -- network port number\n    current_players integer NOT NULL DEFAULT 0, -- number of players currently connected\n    max_players integer NOT NULL, -- maximum player capacity\n    status character varying(30) NOT NULL DEFAULT 'offline', -- server status (e.g., online, offline, maintenance)\n    last_heartbeat timestamp with time zone, -- last time the server reported its status\n    PRIMARY KEY (server_id)\n    -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id)\n)\nCREATE TABLE gaming_technology.achievements ( achievement_id.uuid, game_id.uuid, name.text, description.text, icon_url.text, points.integer, hidden.boolean )\nCREATE TABLE gaming_technology.player_achievements ( player_achievement_id.uuid, player_id.uuid, achievement_id.uuid, unlocked_at.timestamptz )\nCREATE TABLE gaming_technology.in_game_items ( item_id uuid NOT NULL DEFAULT gen_random_uuid(), game_id uuid NOT NULL, item_name character varying(150) NOT NULL, item_type character varying(50) NOT NULL, description text, rarity character varying(30), cost_currency character varying(10), cost_amount numeric(12, 2), attributes jsonb, PRIMARY KEY (item_id) )\nCREATE TABLE gaming_technology.player_inventory ( inventory_id uuid NOT NULL DEFAULT gen_random_uuid(), player_id uuid NOT NULL, item_id uuid NOT NULL, quantity integer NOT NULL DEFAULT 1, acquired_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, instance_data jsonb, PRIMARY KEY (inventory_id) )\n"}
{"conversations": [{"role": "user", "content": "Show me the top 5 narratives by market cap, along with their 24-hour trading volume and 7-day price change percentage."}, {"role": "assistant", "content": "SELECT narrative.text, volume_24h.numeric, price_change_percentage_7d.numeric FROM narrative_info ORDER BY market_cap.numeric DESC LIMIT 5;"}, {"role": "user", "content": "Can you also include the top 3 coins for each of these narratives?"}, {"role": "assistant", "content": "SELECT narrative.text, volume_24h.numeric, price_change_percentage_7d.numeric, top_3_coins.text FROM narrative_info ORDER BY market_cap.numeric DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE narrative_info ( narrative.text, top_3_coins.text, price_change_percentage_1h.numeric, price_change_percentage_24h.numeric, price_change_percentage_7d.numeric, market_cap.numeric, volume_24h.numeric, trend_rank.numeric, token_num.numeric )\n"}
{"conversations": [{"role": "user", "content": "Show me the list of hashtags that have been used, along with the time they were first used."}, {"role": "assistant", "content": "SELECT tag_name, created_at \nFROM social_media.hashtags;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users (\n    user_id character varying(64) NOT NULL,  -- unique identifier for the user\n    username character varying(50) NOT NULL UNIQUE, -- user's unique handle\n    email character varying(128) NOT NULL UNIQUE, -- user's email address\n    password_hash text NOT NULL, -- hashed password\n    full_name character varying(100), -- user's full name\n    profile_picture_url text, -- URL to the profile picture\n    bio text, -- short user biography\n    location character varying(100), -- user's location\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of account creation\n    updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last profile update\n    is_verified boolean NOT NULL DEFAULT false, -- verification status\n    PRIMARY KEY (user_id)\n)\nCREATE TABLE social_media.comments (\n    comment_id character varying(64) NOT NULL, -- unique identifier for the comment\n    post_id character varying(64) NOT NULL, -- identifier of the post being commented on (FK to posts.post_id)\n    user_id character varying(64) NOT NULL, -- identifier of the user who made the comment (FK to users.user_id)\n    parent_comment_id character varying(64), -- identifier of the parent comment if it's a reply (FK to comments.comment_id)\n    content text NOT NULL, -- textual content of the comment\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of comment creation\n    updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last comment edit\n    PRIMARY KEY (comment_id)\n)\nCREATE TABLE social_media.likes (\n    like_id character varying(64) NOT NULL, -- unique identifier for the like\n    user_id character varying(64) NOT NULL, -- identifier of the user who liked (FK to users.user_id)\n    post_id character varying(64), -- identifier of the post being liked (FK to posts.post_id, nullable)\n    comment_id character varying(64), -- identifier of the comment being liked (FK to comments.comment_id, nullable)\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of when the like occurred\n    PRIMARY KEY (like_id),\n    CONSTRAINT unique_user_like UNIQUE (user_id, post_id, comment_id), -- prevent duplicate likes\n    CONSTRAINT check_like_target CHECK (post_id IS NOT NULL OR comment_id IS NOT NULL) -- ensure it likes something\n)\nCREATE TABLE social_media.follows (\n    follow_id character varying(64) NOT NULL, -- unique identifier for the follow relationship\n    follower_user_id character varying(64) NOT NULL, -- identifier of the user who is following (FK to users.user_id)\n    following_user_id character varying(64) NOT NULL, -- identifier of the user being followed (FK to users.user_id)\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of when the follow started\n    PRIMARY KEY (follow_id),\n    CONSTRAINT unique_follow UNIQUE (follower_user_id, following_user_id) -- prevent duplicate follows\n)\nCREATE TABLE social_media.hashtags (\n    hashtag_id character varying(64) NOT NULL, -- unique identifier for the hashtag\n    tag_name character varying(100) NOT NULL UNIQUE, -- the actual hashtag text (without '#')\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when the hashtag was first used\n    PRIMARY KEY (hashtag_id)\n)\nCREATE TABLE social_media.post_hashtags (\n    post_hashtag_id character varying(64) NOT NULL, -- unique identifier for the post-hashtag link\n    post_id character varying(64) NOT NULL, -- identifier of the post (FK to posts.post_id)\n    hashtag_id character varying(64) NOT NULL, -- identifier of the hashtag (FK to hashtags.hashtag_id)\n    PRIMARY KEY (post_hashtag_id),\n    CONSTRAINT unique_post_hashtag UNIQUE (post_id, hashtag_id) -- prevent duplicate tags on a post\n)\nCREATE TABLE social_media.messages (\n    message_id character varying(64) NOT NULL, -- unique identifier for the message\n    conversation_id character varying(64) NOT NULL, -- identifier for the conversation thread (FK to conversations.conversation_id)\n    sender_user_id character varying(64) NOT NULL, -- identifier of the sender (FK to users.user_id)\n    content text, -- textual content of the message\n    media_url text, -- URL to attached media (image/video)\n    media_type character varying(20), -- type of media ('image', 'video', null)\n    sent_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when message was sent\n    read_at timestamp, -- timestamp when message was read by recipient(s)\n    PRIMARY KEY (message_id)\n)\nCREATE TABLE social_media.conversations (\n    conversation_id character varying(64) NOT NULL, -- unique identifier for the conversation\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when conversation was initiated\n    last_message_at timestamp, -- timestamp of the last message in the conversation\n    is_group_chat boolean NOT NULL DEFAULT false, -- indicates if it's a group chat or direct message\n    group_name character varying(100), -- name of the group chat (if applicable)\n    PRIMARY KEY (conversation_id)\n)\nCREATE TABLE social_media.conversation_participants (\n    participant_id character varying(64) NOT NULL, -- unique identifier for the participant entry\n    conversation_id character varying(64) NOT NULL, -- identifier of the conversation (FK to conversations.conversation_id)\n    user_id character varying(64) NOT NULL, -- identifier of the user in the conversation (FK to users.user_id)\n    joined_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when user joined the conversation\n    last_read_at timestamp, -- timestamp indicating up to when the user has read messages\n    PRIMARY KEY (participant_id),\n    CONSTRAINT unique_user_conversation UNIQUE (conversation_id, user_id) -- prevent user being added multiple times\n)\nCREATE TABLE social_media.notifications (\n    notification_id character varying(64) NOT NULL, -- unique identifier for the notification\n    recipient_user_id character varying(64) NOT NULL, -- user receiving the notification (FK to users.user_id)\n    sender_user_id character varying(64), -- user triggering the notification (FK to users.user_id, can be null for system notifications)\n    notification_type character varying(30) NOT NULL, -- type of notification ('like', 'comment', 'follow', 'mention', 'message')\n    target_entity_id character varying(64), -- ID of the related entity (post_id, comment_id, user_id, conversation_id)\n    target_entity_type character varying(20), -- type of the related entity ('post', 'comment', 'user', 'conversation')\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp notification was created\n    read_at timestamp, -- timestamp notification was marked as read\n    PRIMARY KEY (notification_id)\n)\nCREATE TABLE social_media.user_settings (\n    setting_id character varying(64) NOT NULL, -- unique identifier for the setting entry\n    user_id character varying(64) NOT NULL UNIQUE, -- user the settings belong to (FK to users.user_id)\n    theme character varying(20) DEFAULT 'light', -- UI theme ('light', 'dark')\n    email_notifications_enabled boolean DEFAULT true, -- enable/disable email notifications\n    push_notifications_enabled boolean DEFAULT true, -- enable/disable push notifications\n    private_profile boolean DEFAULT false, -- is the user profile private\n    updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last setting change\n    PRIMARY KEY (setting_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List the names of agencies and their established dates, but only for agencies that offer at least one service."}, {"role": "assistant", "content": "SELECT DISTINCT T1.agency_name ,  T1.established_date FROM government_services.agencies AS T1 JOIN government_services.services AS T2 ON T1.agency_id  =  T2.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 character varying(64) NOT NULL, national_id_number character varying(128) NOT NULL UNIQUE, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, gender character varying(20), primary_address text NOT NULL, contact_email character varying(128) UNIQUE, contact_phone character varying(32), registration_date timestamp NOT NULL, is_verified boolean DEFAULT false, PRIMARY KEY (citizen_id) )\nCREATE TABLE government_services.agencies ( agency_id character varying(64) NOT NULL, agency_name character varying(255) NOT NULL, jurisdiction_level character varying(50) NOT NULL, primary_contact_email character varying(128), main_phone_number character varying(32), website_url character varying(255), established_date date, parent_agency_id character varying(64), PRIMARY KEY (agency_id) )\nCREATE TABLE government_services.services ( service_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, service_name character varying(255) NOT NULL, description text, category character varying(100), eligibility_criteria text, standard_fee numeric(10, 2) DEFAULT 0.00, average_processing_time_days integer, is_active boolean DEFAULT true, online_application_url character varying(255), PRIMARY KEY (service_id) )\nCREATE TABLE government_services.applications ( application_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, service_id character varying(64) NOT NULL, submitted_at timestamp NOT NULL, status character varying(50) NOT NULL, last_updated_at timestamp NOT NULL, assigned_employee_id character varying(64), decision_date date, notes text, reference_number character varying(100) UNIQUE, PRIMARY KEY (application_id) )\nCREATE TABLE government_services.payments ( payment_id character varying(64) NOT NULL, application_id character varying(64), citizen_id character varying(64) NOT NULL, service_id character varying(64), amount numeric(12, 2) NOT NULL, currency character varying(3) NOT NULL DEFAULT 'USD', payment_method character varying(50), payment_provider_reference character varying(128), payment_timestamp timestamp NOT NULL, status character varying(30) NOT NULL, notes text, PRIMARY KEY (payment_id) )\nCREATE TABLE government_services.employees ( employee_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, job_title character varying(150) NOT NULL, department character varying(100), work_email character varying(128) NOT NULL UNIQUE, work_phone character varying(32), hire_date date NOT NULL, termination_date date, access_level character varying(50), manager_employee_id character varying(64), PRIMARY KEY (employee_id) )\nCREATE TABLE government_services.service_locations ( location_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, location_name character varying(200), address text NOT NULL, city character varying(100), state character varying(50), postal_code character varying(20), latitude numeric(9, 6), longitude numeric(9, 6), operating_hours text, contact_phone character varying(32), is_accessible boolean, PRIMARY KEY (location_id) )\nCREATE TABLE government_services.appointments ( appointment_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, employee_id character varying(64), location_id character varying(64), service_id character varying(64), scheduled_start_time timestamp NOT NULL, scheduled_end_time timestamp, purpose text NOT NULL, status character varying(30) NOT NULL, booking_method character varying(50), created_at timestamp NOT NULL, notes text, PRIMARY KEY (appointment_id) )\nCREATE TABLE government_services.notifications ( notification_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, application_id character varying(64), message_subject character varying(255), message_body text NOT NULL, channel character varying(30) NOT NULL, sent_at timestamp NOT NULL, status character varying(30) NOT NULL, related_entity_type character varying(50), related_entity_id character varying(64), PRIMARY KEY (notification_id) )\n"}
{"conversations": [{"role": "user", "content": "List pairs of wallet IDs owned by the same user where the creation dates are more than one year apart. Show the user ID and the wallet IDs of both wallets."}, {"role": "assistant", "content": "SELECT w1.user_id, w1.wallet_id AS wallet_id_1, w2.wallet_id AS wallet_id_2 FROM web3.wallets w1 JOIN web3.wallets w2 ON w1.user_id = w2.user_id AND w2.created_at > w1.created_at + INTERVAL '1 year' ORDER BY w1.user_id, w1.created_at;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.wallets ( wallet_id text PRIMARY KEY, user_id text, address text, private_key text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Find transactions that triggered events and whose to_address matches the contract_id of the emitted event. List the transaction ID, the to_address, and the count of such events for that transaction."}, {"role": "assistant", "content": "SELECT t.transaction_id, t.to_address, COUNT(e.event_id) AS matching_event_count FROM web3.transactions t JOIN web3.events e ON t.transaction_id = e.transaction_id WHERE t.to_address IS NOT NULL AND t.to_address = e.contract_id GROUP BY t.transaction_id, t.to_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.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.token_transfers ( transfer_id text, token_id text, from_address text, to_address text, value numeric, transaction_id text, log_index integer )\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": "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": "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": "How many employees work in each department? List the department name and the count."}, {"role": "assistant", "content": "SELECT department, COUNT(*) FROM government_services.employees GROUP BY department"}, {"role": "user", "content": "Only show departments with more than 5 employees."}, {"role": "assistant", "content": "SELECT department, COUNT(*) FROM government_services.employees GROUP BY department HAVING COUNT(*) > 5"}, {"role": "user", "content": "For these departments, also list the job titles present."}, {"role": "assistant", "content": "SELECT department, COUNT(*), STRING_AGG(DISTINCT job_title, ', ') FROM government_services.employees GROUP BY department HAVING COUNT(*) > 5"}, {"role": "user", "content": "Add the total number of employees hired in 2023 for each of these departments."}, {"role": "assistant", "content": "SELECT department, COUNT(*), STRING_AGG(DISTINCT job_title, ', '), SUM(CASE WHEN EXTRACT(YEAR FROM hire_date) = 2023 THEN 1 ELSE 0 END) AS employees_hired_in_2023 FROM government_services.employees GROUP BY department HAVING COUNT(*) > 5"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id text, national_id_number text, first_name text, last_name text, date_of_birth date, gender text, primary_address text, contact_email text, contact_phone text, registration_date timestamp, is_verified boolean )\nCREATE TABLE government_services.agencies ( agency_id text, agency_name text, jurisdiction_level text, primary_contact_email text, main_phone_number text, website_url text, established_date date, parent_agency_id text )\nCREATE TABLE government_services.services (\n    service_id character varying(64) NOT NULL, -- unique identifier for the service\n    agency_id character varying(64) NOT NULL, -- FK to agencies table\n    service_name character varying(255) NOT NULL, -- name of the service (e.g., Driver's License Renewal)\n    description text,\n    category character varying(100), -- e.g., Licensing, Benefits, Taxation, Permits\n    eligibility_criteria text, -- description of who is eligible\n    standard_fee numeric(10, 2) DEFAULT 0.00, -- typical fee for the service\n    average_processing_time_days integer, -- estimated processing time\n    is_active boolean DEFAULT true, -- whether the service is currently offered\n    online_application_url character varying(255),\n    PRIMARY KEY (service_id)\n)\nCREATE TABLE government_services.employees ( employee_id text, agency_id text, first_name text, last_name text, job_title text, department text, work_email text, work_phone text, hire_date date, termination_date date, access_level text, manager_employee_id text )\nCREATE TABLE government_services.service_locations ( location_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, location_name character varying(200), address text NOT NULL, city character varying(100), state character varying(50), postal_code character varying(20), latitude numeric(9, 6), longitude numeric(9, 6), operating_hours text, contact_phone character varying(32), is_accessible boolean, PRIMARY KEY (location_id) )\nCREATE TABLE government_services.appointments ( appointment_id.text, citizen_id.text, employee_id.text, location_id.text, service_id.text, scheduled_start_time.timestamp, scheduled_end_time.timestamp, purpose.text, status.text, booking_method.text, created_at.timestamp, notes.text )\n"}
{"conversations": [{"role": "user", "content": "Show me all pairs of time entries that are associated with the same invoice, including their entry IDs, lawyer IDs, and the shared invoice ID."}, {"role": "assistant", "content": "SELECT te1.entry_id AS entry1_id,\n       te2.entry_id AS entry2_id,\n       te1.lawyer_id,\n       te1.invoice_id\nFROM legal_services.time_entries te1\nJOIN legal_services.time_entries te2\n  ON te1.invoice_id = te2.invoice_id\n AND te1.entry_id < te2.entry_id\nWHERE te1.invoice_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 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": "Show me the document name and the date worked for time entries logged by the same lawyer."}, {"role": "assistant", "content": "SELECT T1.document_name ,  T2.date_worked FROM documents AS T1 JOIN time_entries AS T2 ON T1.uploaded_by_lawyer_id  =  T2.lawyer_id"}, {"role": "user", "content": "Only show pairs where the time entry is billable."}, {"role": "assistant", "content": "SELECT T1.document_name ,  T2.date_worked FROM documents AS T1 JOIN time_entries AS T2 ON T1.uploaded_by_lawyer_id  =  T2.lawyer_id WHERE T2.is_billable  =  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 legal_services.documents ( document_id text, case_id text, document_name text, document_type text, storage_path text, uploaded_by_lawyer_id text, upload_timestamp timestamp, version integer, description text )\nCREATE TABLE legal_services.time_entries (\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": "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": "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": "List the appointment ID, subject, and duration in minutes for all completed appointments."}, {"role": "assistant", "content": "SELECT appointment_id, subject, EXTRACT(EPOCH FROM (end_time - start_time))/60 AS duration_minutes FROM legal_services.appointments WHERE status = 'Completed';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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": "I need a report of total maintenance cost per vehicle type."}, {"role": "assistant", "content": "SELECT v.type AS vehicle_type,\n       SUM(m.cost) AS total_maintenance_cost\nFROM transportation.vehicles v\nJOIN transportation.maintenance_logs m ON v.vehicle_id = m.vehicle_id\nGROUP BY v.type;"}, {"role": "user", "content": "Only include types where total maintenance cost is greater than 10000."}, {"role": "assistant", "content": "SELECT v.type AS vehicle_type,\n       SUM(m.cost) AS total_maintenance_cost\nFROM transportation.vehicles v\nJOIN transportation.maintenance_logs m ON v.vehicle_id = m.vehicle_id\nGROUP BY v.type\nHAVING SUM(m.cost) > 10000;"}, {"role": "user", "content": "Also include the number of maintenance events per vehicle type."}, {"role": "assistant", "content": "SELECT v.type AS vehicle_type,\n       SUM(m.cost) AS total_maintenance_cost,\n       COUNT(m.log_id) AS maintenance_event_count\nFROM transportation.vehicles v\nJOIN transportation.maintenance_logs m ON v.vehicle_id = m.vehicle_id\nGROUP BY v.type\nHAVING SUM(m.cost) > 10000;"}, {"role": "user", "content": "Sort the results by average cost per event in descending order."}, {"role": "assistant", "content": "SELECT v.type AS vehicle_type,\n       SUM(m.cost) AS total_maintenance_cost,\n       COUNT(m.log_id) AS maintenance_event_count,\n       AVG(m.cost) AS average_cost_per_event\nFROM transportation.vehicles v\nJOIN transportation.maintenance_logs m ON v.vehicle_id = m.vehicle_id\nGROUP BY v.type\nHAVING SUM(m.cost) > 10000\nORDER BY AVG(m.cost) DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles (\n    vehicle_id character varying(64) NOT NULL,  -- unique identifier for the vehicle\n    license_plate character varying(32) NOT NULL UNIQUE, -- vehicle license plate\n    vin character varying(17) UNIQUE, -- vehicle identification number\n    make character varying(64) NOT NULL, -- manufacturer of the vehicle\n    model character varying(64) NOT NULL, -- model of the vehicle\n    year integer NOT NULL, -- manufacturing year\n    type character varying(32) NOT NULL, -- type of vehicle (e.g., Bus, Train, Truck, Car, Van)\n    capacity integer, -- passenger or cargo capacity\n    fuel_type character varying(32) NOT NULL, -- e.g., Diesel, Gasoline, Electric, Hydrogen\n    status character varying(32) NOT NULL, -- e.g., Active, Maintenance, Decommissioned\n    depot_id character varying(64), -- identifier of the home depot/base\n    acquisition_date date, -- date the vehicle was acquired\n    PRIMARY KEY (vehicle_id)\n)\nCREATE TABLE transportation.drivers ( driver_id character varying(64) NOT NULL, employee_id character varying(64) NOT NULL UNIQUE, first_name character varying(128) NOT NULL, last_name character varying(128) NOT NULL, license_number character varying(64) NOT NULL UNIQUE, license_expiry_date date NOT NULL, contact_number character varying(32), email character varying(128) UNIQUE, hire_date date NOT NULL, status character varying(32) NOT NULL, PRIMARY KEY (driver_id) )\nCREATE TABLE transportation.routes ( route_id text, route_number text, description text, origin_location_id text, destination_location_id text, distance_km numeric, estimated_duration_minutes integer, type text )\nCREATE TABLE transportation.trips (\n    trip_id character varying(64) NOT NULL,  -- unique identifier for a specific trip instance\n    route_id character varying(64), -- identifier of the route being followed (can be null for ad-hoc trips)\n    vehicle_id character varying(64) NOT NULL, -- identifier of the vehicle used\n    driver_id character varying(64) NOT NULL, -- identifier of the driver operating\n    scheduled_departure timestamp with time zone NOT NULL, -- planned departure time\n    actual_departure timestamp with time zone, -- actual departure time\n    scheduled_arrival timestamp with time zone NOT NULL, -- planned arrival time\n    actual_arrival timestamp with time zone, -- actual arrival time\n    origin_location_id character varying(64) NOT NULL, -- actual starting location (could differ from route origin)\n    destination_location_id character varying(64) NOT NULL, -- actual ending location (could differ from route destination)\n    status character varying(32) NOT NULL, -- e.g., Scheduled, In Progress, Completed, Delayed, Cancelled\n    passenger_count integer, -- number of passengers (if applicable)\n    cargo_manifest_id character varying(64), -- link to cargo details (if applicable)\n    PRIMARY KEY (trip_id)\n)\nCREATE TABLE transportation.locations ( location_id.text, name.text, type.text, address_line1.text, city.text, state_province.text, postal_code.text, country.text, latitude.numeric, longitude.numeric, timezone.text )\nCREATE TABLE transportation.maintenance_logs ( log_id character varying(64) NOT NULL, vehicle_id character varying(64) NOT NULL, service_date date NOT NULL, odometer_reading integer, service_type character varying(128) NOT NULL, description text NOT NULL, cost numeric(10, 2), mechanic_name character varying(128), next_service_due_date date, PRIMARY KEY (log_id) )\nCREATE TABLE transportation.fuel_logs ( fuel_log_id text PRIMARY KEY, vehicle_id text, trip_id text, log_timestamp timestamp, fuel_type text, quantity numeric, unit text, cost_per_unit numeric, total_cost numeric, odometer_reading int, location_id text )\nCREATE TABLE transportation.passengers ( passenger_id text PRIMARY KEY, first_name text, last_name text, email text, phone_number text, date_of_birth date, loyalty_program_id text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "List each guest’s full name and the total number of service orders they have placed, ordered by order count descending."}, {"role": "assistant", "content": "SELECT g.guest_id,\n       g.first_name || ' ' || g.last_name AS full_name,\n       COUNT(so.order_id) AS order_count\nFROM hospitality_technology.guests g\nLEFT JOIN hospitality_technology.service_orders so\n  ON g.guest_id = so.guest_id\nGROUP BY g.guest_id, full_name\nORDER 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.guests ( guest_id text PRIMARY KEY, first_name text, last_name text, email text, phone_number text, date_of_birth date, address_line1 text, city text, state_province text, postal_code text, country_code text, preferences text, loyalty_member_id text, communication_consent boolean, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.reservations ( reservation_id text, property_id text, guest_id text, room_id text, room_type_id text, check_in_date date, check_out_date date, actual_check_in_ts timestamp, actual_check_out_ts timestamp, num_adults integer, num_children integer, status text, booking_source text, rate_plan_id text, total_amount numeric, amount_paid numeric, special_requests text, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.service_orders ( order_id.text, reservation_id.text, guest_id.text, service_id.text, staff_id_ordered.text, staff_id_delivered.text, order_timestamp.timestamp, delivery_timestamp.timestamp, quantity.integer, unit_price.numeric, total_price.numeric, status.text, notes.text, bill_id.text )\nCREATE TABLE hospitality_technology.reviews ( review_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, reservation_id character varying(64) UNIQUE, guest_id character varying(64) NOT NULL, rating_overall integer, rating_cleanliness integer, rating_service integer, rating_location integer, rating_value integer, comment text, review_source character varying(100), review_date timestamp with time zone NOT NULL DEFAULT current_timestamp, is_public boolean DEFAULT true, staff_response text, response_staff_id character varying(64), response_date timestamp with time zone, PRIMARY KEY (review_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (response_staff_id) REFERENCES hospitality_technology.staff(staff_id) )\n"}
{"conversations": [{"role": "user", "content": "Show each user's username along with their KYC status and the date of their latest KYC review."}, {"role": "assistant", "content": "SELECT u.username, ka.status, ka.reviewed_at AS latest_review\nFROM trading_platform.users u\nJOIN trading_platform.kyc_audit ka ON u.user_id = ka.user_id\nWHERE ka.reviewed_at = (\n  SELECT MAX(reviewed_at)\n  FROM trading_platform.kyc_audit\n  WHERE user_id = u.user_id\n);"}, {"role": "user", "content": "Also filter to only include those whose latest status is 'approved'."}, {"role": "assistant", "content": "SELECT u.username, ka.status, ka.reviewed_at AS latest_review\nFROM trading_platform.users u\nJOIN trading_platform.kyc_audit ka ON u.user_id = ka.user_id\nWHERE ka.reviewed_at = (\n  SELECT MAX(reviewed_at)\n  FROM trading_platform.kyc_audit\n  WHERE user_id = u.user_id\n)\n  AND ka.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 trading_platform.users ( user_id.text, username.text, email.text, password_hash.text, created_at.timestamp )\nCREATE TABLE trading_platform.assets ( asset_id text, name text, symbol text, type text )\nCREATE TABLE trading_platform.utxos ( utxo_id text PRIMARY KEY, transaction_id text, output_index int, address text, amount numeric, spent boolean )\nCREATE TABLE trading_platform.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": "Count how many users have not specified a value for their bio."}, {"role": "assistant", "content": "SELECT COUNT(*) FROM social_media.users WHERE bio IS NULL OR 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": "Which customers have policies that expired in the last month? Please show the customer ID, policy number, and expiration date."}, {"role": "assistant", "content": "SELECT c.customer_id, p.policy_number, p.end_date\nFROM insurance.customers c\nJOIN insurance.policies p ON c.customer_id = p.customer_id\nWHERE p.end_date >= (CURRENT_DATE - INTERVAL '1 month') AND p.end_date < CURRENT_DATE;"}, {"role": "user", "content": "Add the customer's email to the results."}, {"role": "assistant", "content": "SELECT c.customer_id, c.email, p.policy_number, p.end_date\nFROM insurance.customers c\nJOIN insurance.policies p ON c.customer_id = p.customer_id\nWHERE p.end_date >= (CURRENT_DATE - INTERVAL '1 month') AND p.end_date < CURRENT_DATE;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.customers ( customer_id text, first_name text, last_name text, date_of_birth date, ssn_hash text, address_line1 text, address_line2 text, city text, state text, zip_code text, country text, phone_number text, email text, created_at timestamp, updated_at timestamp, status text )\nCREATE TABLE insurance.policies ( policy_id text, customer_id text, product_id text, agent_id text, policy_number text, start_date date, end_date date, premium_amount numeric, coverage_limit numeric, deductible numeric, status text, issued_at timestamp, cancellation_date date, cancellation_reason text )\nCREATE TABLE insurance.claims ( claim_id text, policy_id text, customer_id text, incident_date timestamp, reported_date timestamp, description text, estimated_loss numeric, status text, settlement_amount numeric, settlement_date date, claim_handler_id text, police_report_number text )\nCREATE TABLE insurance.insurance_products ( product_id text, product_name text, product_type text, description text, base_premium numeric, coverage_details text, underwriting_rules text, is_active boolean, created_at timestamp, updated_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show the symbol, name, and total supply for all SUI coins with status 'active'."}, {"role": "assistant", "content": "SELECT scm.symbol, scm.name, scm.coin_type, scm.total_supply\nFROM sui_coins_metadata scm\nWHERE scm.status = 'active';"}, {"role": "user", "content": "I received an error that column 'total_supply' doesn't exist in sui_coins_metadata."}, {"role": "assistant", "content": "SELECT scm.symbol, scm.name, scm.coin_type\nFROM sui_coins_metadata scm\nWHERE scm.status = 'active';"}, {"role": "user", "content": "Now, join with sui_coins to add up the total balance across all owners for each coin_type."}, {"role": "assistant", "content": "SELECT scm.symbol, scm.name, scm.coin_type, SUM(CAST(sc.balance AS NUMERIC)) AS total_balance\nFROM sui_coins_metadata scm\nJOIN sui_coins sc ON scm.coin_type = sc.coin_type\nWHERE scm.status = 'active'\nGROUP BY scm.symbol, scm.name, scm.coin_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 token_metas ( block_timestamp timestamp, block_number bigint, transaction_hash text, transaction_index bigint, from_address text, contract_address text, symbol text, total_supply text, name text, decimals bigint, is_erc20 integer, is_erc721 integer, is_erc1155 integer, is_proxy integer, extra_info text, pk integer )\nCREATE TABLE erc1155_approval_for_all ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash text, log_index integer, contract_address text )\nCREATE TABLE erc20_balances ( block_number bigint, contract_address text, wallet_address text, amount text, pk text )\nCREATE TABLE erc20_balances_historical ( block_number bigint, contract_address text, wallet_address text, amount text, pk integer )\nCREATE TABLE nft_holders ( block_number bigint, contract_address text, wallet_address text, token_id text, contract_type text, amount text, pk text )\nCREATE TABLE nft_holder_historical ( block_number bigint, contract_address text, wallet_address text, token_id text, contract_type text, amount text, pk integer )\nCREATE TABLE sui_coins ( object_id text, status text, coin_type text, balance text, owner text )\nCREATE TABLE sui_coins_metadata ( object_id text, coin_type text, status text, decimals bigint, description text, icon_url text, symbol text, name text )\nCREATE TABLE sui_nfts ( object_id text, status text, collection_type text, package_id text, previous_transaction text, display text, owner text, name text )\nCREATE TABLE nft_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_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 )\n"}
{"conversations": [{"role": "user", "content": "Find all NFTs with a rarity rank less than 100 and show their name and the name of their collection."}, {"role": "assistant", "content": "SELECT nm.name AS nft_name, nc.name AS collection_name FROM nft_metadata nm JOIN nft_collections nc ON nm.contract_address = nc.contract_address WHERE nm.rarity_rank < 100;"}, {"role": "user", "content": "Filter that further to only include NFTs from collections named 'Bored Ape Yacht Club'."}, {"role": "assistant", "content": "SELECT nm.name AS nft_name, nc.name AS collection_name FROM nft_metadata nm JOIN nft_collections nc ON nm.contract_address = nc.contract_address WHERE nm.rarity_rank < 100 AND nc.name = 'Bored Ape Yacht Club';"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nCREATE TABLE token_metas ( block_timestamp timestamp, block_number bigint, transaction_hash varchar, transaction_index bigint, from_address varchar, contract_address varchar, symbol varchar, total_supply varchar, name varchar, decimals bigint, is_erc20 integer, is_erc721 integer, is_erc1155 integer, is_proxy integer, extra_info varchar, pk integer )\nCREATE TABLE erc1155_approval_for_all ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash varchar, log_index integer, contract_address varchar )\nCREATE TABLE erc20_balances ( block_number bigint, contract_address varchar, wallet_address varchar, amount varchar, pk varchar )\nCREATE TABLE nft_holders ( block_number bigint, contract_address varchar, wallet_address varchar, token_id varchar, contract_type varchar, amount varchar, pk varchar )\nCREATE TABLE nft_holder_historical ( block_number bigint, contract_address varchar, wallet_address varchar, token_id varchar, contract_type varchar, amount varchar, pk integer )\nCREATE TABLE sui_coins ( object_id varchar, status varchar, coin_type varchar, balance varchar, owner varchar )\nCREATE TABLE sui_nfts ( object_id varchar, status varchar, collection_type varchar, package_id varchar, previous_transaction varchar, display varchar, owner varchar, name varchar )\nCREATE TABLE nft_metadata ( blockchain varchar, contract_address varchar, token_id varchar, contract_name varchar, erc_type varchar, amount bigint, minter varchar, owner varchar, mint_block_number bigint, mint_time bigint, mint_transaction_hash varchar, mint_price varchar, token_uri varchar, metadata varchar, name varchar, image_uri varchar, traits varchar, updated_at bigint, status varchar, rarity_score real, rarity_rank integer, unique_attribute_count integer, pk integer )\nCREATE TABLE nft_collections ( blockchain varchar, contract_address varchar, name varchar, symbol varchar, deploy_block_number bigint, deploy_block_time bigint, erc_type varchar, owner varchar, traits varchar, description varchar, slug varchar, media_info varchar, image_url varchar, banner_image_url varchar, updated_at bigint, banner varchar, token_count bigint, floor_price varchar, floor_price_symbol varchar, floor_price_contract varchar, pk integer )\nCREATE TABLE token_prices ( uuid varchar, blockchain varchar, address varchar, decimals bigint, symbol varchar, price real, timestamp timestamp )\nCREATE TABLE token_prices_latest ( blockchain varchar, address varchar, decimals bigint, symbol varchar, price real, timestamp timestamp )\nCREATE TABLE erc20_approval ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash varchar, log_index integer, contract_address varchar, pk integer )\nCREATE TABLE token_balances ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply decimal, amount decimal )\nCREATE TABLE token_info ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar )\nCREATE TABLE token_activities ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\nCREATE TABLE mud_holesky_redstone ( address varchar, table_id varchar, key_bytes varchar, key0 varchar, key1 varchar, static_data varchar, encoded_lengths varchar, dynamic_data varchar, is_deleted boolean, block_number bigint, log_index bigint )\nCREATE TABLE token_balances_bitcoin ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply varchar, amount varchar )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\nCREATE TABLE token_balances_avalanche ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply decimal, amount decimal )\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id varchar )\n"}
{"conversations": [{"role": "user", "content": "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": "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": "Can you help me fetch the inventory details for components associated with a specific aircraft build, including the batch number, quantity, and warehouse location?"}, {"role": "assistant", "content": "MATCH (ab:AircraftBuild {build_id: 'specific_build_id'})-[:IS_MODEL]->(am:AircraftModel),\n(ib:InventoryBatch)-[:IS_INSTANCE_OF]->(c:Component)\nRETURN ib.inventory_record_id, ib.batch_number, ib.quantity, ib.location_warehouse"}, {"role": "user", "content": "Can you modify this to show only inventory batches received after a specific date, say June 1, 2023?"}, {"role": "assistant", "content": "MATCH (ab:AircraftBuild {build_id: 'specific_build_id'})-[:IS_MODEL]->(am:AircraftModel),\n(ib:InventoryBatch)-[:IS_INSTANCE_OF]->(c:Component)\nWHERE ib.received_date > datetime('2023-06-01')\nRETURN ib.inventory_record_id, ib.batch_number, ib.quantity, ib.location_warehouse"}, {"role": "user", "content": "What if I also want to exclude batches with quantities less than 10?"}, {"role": "assistant", "content": "MATCH (ab:AircraftBuild {build_id: 'specific_build_id'})-[:IS_MODEL]->(am:AircraftModel),\n(ib:InventoryBatch)-[:IS_INSTANCE_OF]->(c:Component)\nWHERE ib.received_date > datetime('2023-06-01') AND ib.quantity >= 10\nRETURN ib.inventory_record_id, ib.batch_number, ib.quantity, ib.location_warehouse"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nNode Label ':AircraftModel'. Properties: { model_id: String (Constraint: UNIQUE), model_name: String, manufacturer: String, passenger_capacity: Integer, max_range_km: Integer, engine_type: String, wingspan_m: Float, status: String, first_flight_date: Date }. Index on model_id.\nNode Label ':Material'. Properties: { material_id: String (Constraint: UNIQUE), material_name: String, specification: String, description: String, density_kg_m3: Float, tensile_strength_mpa: Integer }. Index on material_id.\nNode Label ':AssemblyLine'. Properties: { line_id: String (Constraint: UNIQUE), line_name: String, location_building: String, location_area: String, capacity_units_per_month: Integer, status: String }. Relationship: (:AssemblyLine)-[:BUILDS_MODEL]->(:AircraftModel {model_id}). Index on line_id.\nNode Label ':AssemblyStep'. Properties: { step_id: String (Constraint: UNIQUE), step_number: Integer, step_name: String, description: String, standard_duration_hours: Float, required_skill_level: String, workstation: String }. Relationship: (:AssemblyLine {line_id})-[:HAS_STEP {sequence: <step_number>}]->(:AssemblyStep). Index on step_id.\nNode Label ':AircraftBuild'. Properties: { build_id: String (Constraint: UNIQUE), serial_number: String (Constraint: UNIQUE), build_start_date: Datetime, estimated_completion_date: Date, actual_completion_date: Datetime, current_status: String, customer_order_id: String }. Relationships: (:AircraftBuild)-[:IS_MODEL]->(:AircraftModel {model_id}), (:AircraftBuild)-[:ASSEMBLED_ON]->(:AssemblyLine {line_id}). Index on build_id, serial_number, current_status.\nNode Label ':Employee'. Properties: { employee_id: String (Constraint: UNIQUE), first_name: String, last_name: String, job_title: String, skill_certifications: String[], hire_date: Date, employment_status: String }. Relationships: (:Employee)-[:ASSIGNED_TO]->(:AssemblyLine {line_id}), (:Employee)-[:REPORTS_TO]->(:Employee {employee_id as supervisor_id}). Index on employee_id.\nNode Label ':InventoryBatch'. Properties: { inventory_record_id: String (Constraint: UNIQUE), quantity: Integer, location_warehouse: String, location_bin: String, received_date: Datetime, expiry_date: Date, batch_number: String, last_updated: Datetime }. Relationship: (:InventoryBatch)-[:IS_INSTANCE_OF]->(:Component {component_id}). Index on inventory_record_id, component_id.\n"}
{"conversations": [{"role": "user", "content": "How many tokens had a net positive flow according to smart_money_token_performance, and what is their average ROI?"}, {"role": "assistant", "content": "SELECT COUNT(*) AS token_count, AVG(roi) AS avg_roi\nFROM smart_money_token_performance\nWHERE net_flow > 0;"}, {"role": "user", "content": "Now, break this down by chain, and order the results by avg_roi descending."}, {"role": "assistant", "content": "SELECT chain, COUNT(*) AS token_count, AVG(roi) AS avg_roi\nFROM smart_money_token_performance\nWHERE net_flow > 0\nGROUP BY chain\nORDER BY avg_roi DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE project_fundraising_record ( id character varying(32) NOT NULL, project_id character varying(32) NOT NULL, project_name character varying(128) NOT NULL, rounds_name character varying(32), investment_value numeric(38,14), investment_date character varying(128), introduction character varying(128), valuation numeric(38,14) )\nCREATE TABLE 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": "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": "Show the number of active agents in each license state."}, {"role": "assistant", "content": "SELECT license_state,\n       COUNT(*) AS active_agent_count\nFROM insurance.agents\nWHERE status = 'active'\nGROUP BY license_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.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": "Return the number of top-level comments and the number of replies in the comments table."}, {"role": "assistant", "content": "SELECT\n  SUM(CASE WHEN parent_comment_id IS NULL THEN 1 ELSE 0 END) AS top_level_comments,\n  SUM(CASE WHEN parent_comment_id IS NOT NULL THEN 1 ELSE 0 END) AS reply_comments\nFROM social_media.comments;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id text, username text, email text, password_hash text, full_name text, profile_picture_url text, bio text, location text, created_at timestamp, updated_at timestamp, is_verified boolean )\nCREATE TABLE social_media.posts ( post_id text, user_id text, content text, media_url text, media_type text, created_at timestamp, updated_at timestamp, visibility text, location_lat numeric, location_lon numeric )\nCREATE TABLE social_media.comments ( comment_id text, post_id text, user_id text, parent_comment_id text, content text, created_at timestamp, updated_at timestamp )\nCREATE TABLE social_media.follows ( follow_id text, follower_user_id text, following_user_id text, created_at timestamp )\nCREATE TABLE social_media.post_hashtags ( post_hashtag_id text, post_id text, hashtag_id text )\nCREATE TABLE social_media.conversations ( conversation_id text, created_at timestamp, last_message_at timestamp, is_group_chat boolean, group_name text )\nCREATE TABLE social_media.notifications ( notification_id text, recipient_user_id text, sender_user_id text, notification_type text, target_entity_id text, target_entity_type text, created_at timestamp, read_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Find any two policies for the same customer whose coverage dates overlap. Return the customer ID, both policy numbers, and their start and end dates."}, {"role": "assistant", "content": "SELECT p1.customer_id,\n       p1.policy_number AS policy1_number,\n       p1.start_date   AS policy1_start,\n       p1.end_date     AS policy1_end,\n       p2.policy_number AS policy2_number,\n       p2.start_date   AS policy2_start,\n       p2.end_date     AS policy2_end\nFROM insurance.policies p1\nJOIN insurance.policies p2\n  ON p1.customer_id = p2.customer_id\n AND p1.policy_id   <  p2.policy_id\n AND p1.start_date  <= p2.end_date\n 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 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": "How many beneficiaries has each unique relationship type? List relationship and the count."}, {"role": "assistant", "content": "SELECT relationship, COUNT(*) AS beneficiary_count\nFROM insurance.policy_beneficiaries\nGROUP 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.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": "For each asset, I want to know how many orders have the status 'filled', showing the asset symbol."}, {"role": "assistant", "content": "SELECT m.value AS asset_symbol,\n       COUNT(*) AS filled_order_count\nFROM trading_platform.orders o\nJOIN trading_platform.metadata m\n  ON o.asset_id = m.asset_id\n AND m.key = 'symbol'\nWHERE o.status = 'filled'\nGROUP BY m.value;"}, {"role": "user", "content": "Include assets that have zero filled orders, showing filled_order_count as 0."}, {"role": "assistant", "content": "WITH asset_symbols AS (\n  SELECT DISTINCT asset_id,\n         value AS asset_symbol\n  FROM trading_platform.metadata\n  WHERE key = 'symbol'\n)\nSELECT a.asset_symbol,\n       COALESCE(f.filled_order_count, 0) AS filled_order_count\nFROM asset_symbols a\nLEFT JOIN (\n  SELECT asset_id,\n         COUNT(*) AS filled_order_count\n  FROM trading_platform.orders\n  WHERE status = 'filled'\n  GROUP BY asset_id\n) f\n  ON a.asset_id = f.asset_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.users (\n    user_id character varying(64) NOT NULL,  -- unique identifier for the user\n    username character varying(128) NOT NULL, -- username of the user\n    email character varying(128) NOT NULL, -- email address of the user\n    password_hash text NOT NULL, -- hashed password of the user\n    created_at timestamp NOT NULL, -- time when the user account was created\n    PRIMARY KEY (user_id)\n)\nCREATE TABLE trading_platform.orders (\n    order_id character varying(64) NOT NULL,  -- unique identifier for the order\n    user_id character varying(64) NOT NULL, -- identifier of the user placing the order\n    wallet_id character varying(64) NOT NULL, -- identifier of the wallet used for the order\n    asset_id character varying(64) NOT NULL, -- identifier of the asset being traded\n    order_type character varying(32) NOT NULL, -- type of the order (e.g., buy, sell)\n    quantity numeric(38,14) NOT NULL, -- quantity of the asset in the order\n    price numeric(38,14) NOT NULL, -- price per unit of the asset\n    status character varying(32) NOT NULL, -- status of the order (e.g., open, filled, canceled)\n    created_at timestamp NOT NULL, -- time when the order was created\n    PRIMARY KEY (order_id)\n)\nCREATE TABLE trading_platform.dapps (\n    dapp_id character varying(64) NOT NULL,  -- unique identifier for the DApp\n    name character varying(128) NOT NULL, -- name of the DApp\n    description text NOT NULL, -- description of the DApp\n    url character varying(256) NOT NULL, -- URL of the DApp\n    PRIMARY KEY (dapp_id)\n)\nCREATE TABLE trading_platform.peers (\n    peer_id character varying(64) NOT NULL,  -- unique identifier for the peer\n    ip_address character varying(15) NOT NULL, -- IP address of the peer\n    port integer NOT NULL, -- port number of the peer\n    last_seen timestamp NOT NULL, -- last time the peer was active\n    PRIMARY KEY (peer_id)\n)\nCREATE TABLE trading_platform.metadata (\n    metadata_id character varying(64) NOT NULL,  -- unique identifier for the metadata\n    asset_id character varying(64) NOT NULL, -- identifier of the asset the metadata is associated with\n    key character varying(128) NOT NULL, -- key of the metadata\n    value text NOT NULL, -- value of the metadata\n    PRIMARY KEY (metadata_id)\n)\nCREATE TABLE trading_platform.logs (\n    log_id character varying(64) NOT NULL,  -- unique identifier for the log entry\n    user_id character varying(64), -- identifier of the user associated with the log entry\n    action character varying(128) NOT NULL, -- action performed\n    details text NOT NULL, -- details of the action\n    logged_at timestamp NOT NULL, -- time when the log entry was created\n    PRIMARY KEY (log_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Which law firms were founded in the same year and share the same managing partner? Show the firm names, founding year, and managing partner ID."}, {"role": "assistant", "content": "SELECT f1.firm_name AS firm_name_1, f2.firm_name AS firm_name_2, EXTRACT(YEAR FROM f1.founded_date) AS founding_year, f1.managing_partner_id\nFROM legal_services.law_firms f1\nJOIN legal_services.law_firms f2\n  ON f1.firm_id <> f2.firm_id\n  AND EXTRACT(YEAR FROM f1.founded_date) = EXTRACT(YEAR FROM f2.founded_date)\n  AND f1.managing_partner_id = f2.managing_partner_id\nORDER BY founding_year, f1.firm_name, f2.firm_name;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.law_firms ( firm_id text PRIMARY KEY, firm_name text, address text, phone text, website text, founded_date date, managing_partner_id text )\n"}
{"conversations": [{"role": "user", "content": "For each player, count the total number of achievements they've unlocked."}, {"role": "assistant", "content": "SELECT player_id,\n       COUNT(*) AS total_achievements\nFROM gaming_technology.player_achievements\nGROUP BY player_id;"}, {"role": "user", "content": "Exclude players with fewer than 10 achievements."}, {"role": "assistant", "content": "SELECT player_id,\n       COUNT(*) AS total_achievements\nFROM gaming_technology.player_achievements\nGROUP BY player_id\nHAVING COUNT(*) >= 10;"}, {"role": "user", "content": "Additionally, provide the month when they achieved their 10th achievement. Show player_id, total_achievements, and the month of the 10th unlock."}, {"role": "assistant", "content": "WITH ranked AS (\n  SELECT player_id,\n         unlocked_at,\n         ROW_NUMBER() OVER (PARTITION BY player_id ORDER BY unlocked_at) AS rn\n  FROM gaming_technology.player_achievements\n),\ncounts AS (\n  SELECT player_id,\n         COUNT(*) AS total_achievements\n  FROM gaming_technology.player_achievements\n  GROUP BY player_id\n  HAVING COUNT(*) >= 10\n)\nSELECT c.player_id,\n       c.total_achievements,\n       EXTRACT(MONTH FROM r.unlocked_at) AS tenth_achievement_month\nFROM counts c\nJOIN ranked r\n  ON c.player_id = r.player_id\n AND r.rn = 10;"}, {"role": "user", "content": "Finally, order by total_achievements descending."}, {"role": "assistant", "content": "WITH ranked AS (\n  SELECT player_id,\n         unlocked_at,\n         ROW_NUMBER() OVER (PARTITION BY player_id ORDER BY unlocked_at) AS rn\n  FROM gaming_technology.player_achievements\n),\ncounts AS (\n  SELECT player_id,\n         COUNT(*) AS total_achievements\n  FROM gaming_technology.player_achievements\n  GROUP BY player_id\n  HAVING COUNT(*) >= 10\n)\nSELECT c.player_id,\n       c.total_achievements,\n       EXTRACT(MONTH FROM r.unlocked_at) AS tenth_achievement_month\nFROM counts c\nJOIN ranked r\n  ON c.player_id = r.player_id\n AND r.rn = 10\nORDER BY c.total_achievements DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.player_achievements (\n    player_achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for this unlock instance\n    player_id uuid NOT NULL, -- FK linking to the player who unlocked it\n    achievement_id uuid NOT NULL, -- FK linking to the achievement definition\n    unlocked_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the achievement was unlocked\n    PRIMARY KEY (player_achievement_id),\n    UNIQUE (player_id, achievement_id) -- Ensure a player can only unlock an achievement once\n    -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n    -- FOREIGN KEY (achievement_id) REFERENCES gaming_technology.achievements(achievement_id)\n)\n"}
{"conversations": [{"role": "user", "content": "For each vehicle, count how many maintenance logs exist."}, {"role": "assistant", "content": "SELECT v.vehicle_id, v.make, v.model, COUNT(ml.log_id) AS maintenance_log_count FROM transportation.vehicles v JOIN transportation.maintenance_logs ml ON v.vehicle_id = ml.vehicle_id GROUP BY v.vehicle_id, v.make, v.model ORDER BY maintenance_log_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.drivers ( driver_id character varying(64) NOT NULL, employee_id character varying(64) NOT NULL UNIQUE, first_name character varying(128) NOT NULL, last_name character varying(128) NOT NULL, license_number character varying(64) NOT NULL UNIQUE, license_expiry_date date NOT NULL, contact_number character varying(32), email character varying(128) UNIQUE, hire_date date NOT NULL, status character varying(32) NOT NULL, PRIMARY KEY (driver_id) )\nCREATE TABLE transportation.trips ( trip_id character varying(64) NOT NULL, route_id character varying(64), vehicle_id character varying(64) NOT NULL, driver_id character varying(64) NOT NULL, scheduled_departure timestamp with time zone NOT NULL, actual_departure timestamp with time zone, scheduled_arrival timestamp with time zone NOT NULL, actual_arrival timestamp with time zone, origin_location_id character varying(64) NOT NULL, destination_location_id character varying(64) NOT NULL, status character varying(32) NOT NULL, passenger_count integer, cargo_manifest_id character varying(64), PRIMARY KEY (trip_id) )\nCREATE TABLE transportation.locations ( location_id character varying(64) NOT NULL, name character varying(255) NOT NULL, type character varying(64) NOT NULL, address_line1 character varying(255), city character varying(128), state_province character varying(128), postal_code character varying(32), country character varying(64) NOT NULL, latitude numeric(9, 6), longitude numeric(9, 6), timezone character varying(64), PRIMARY KEY (location_id) )\nCREATE TABLE transportation.maintenance_logs ( log_id character varying(64) NOT NULL, vehicle_id character varying(64) NOT NULL, service_date date NOT NULL, odometer_reading integer, service_type character varying(128) NOT NULL, description text NOT NULL, cost numeric(10, 2), mechanic_name character varying(128), next_service_due_date date, PRIMARY KEY (log_id) )\nCREATE TABLE transportation.passengers ( passenger_id character varying(64) NOT NULL, first_name character varying(128) NOT NULL, last_name character varying(128) NOT NULL, email character varying(128) UNIQUE, phone_number character varying(32) UNIQUE, date_of_birth date, loyalty_program_id character varying(64), created_at timestamp with time zone NOT NULL, PRIMARY KEY (passenger_id) )\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 me all policies that expired in the last 60 days, along with their product IDs and premium amounts."}, {"role": "assistant", "content": "SELECT policy_id, product_id, premium_amount FROM insurance.policies WHERE status = 'expired' AND end_date >= CURRENT_DATE - INTERVAL '60 days' AND end_date <= CURRENT_DATE;"}, {"role": "user", "content": "Now include only policies that had a deductible of $1000 or more."}, {"role": "assistant", "content": "SELECT policy_id, product_id, premium_amount, deductible FROM insurance.policies WHERE status = 'expired' AND end_date >= CURRENT_DATE - INTERVAL '60 days' AND end_date <= CURRENT_DATE AND deductible >= 1000;"}, {"role": "user", "content": "I also want to see the count of such expired policies per product ID."}, {"role": "assistant", "content": "SELECT product_id, COUNT(*) as policy_count FROM insurance.policies WHERE status = 'expired' AND end_date >= CURRENT_DATE - INTERVAL '60 days' AND end_date <= CURRENT_DATE AND deductible >= 1000 GROUP BY product_id ORDER BY policy_count DESC;"}, {"role": "user", "content": "Finally, show me the average premium amount for these expired high-deductible policies grouped by product ID."}, {"role": "assistant", "content": "SELECT product_id, AVG(premium_amount) as avg_premium FROM insurance.policies WHERE status = 'expired' AND end_date >= CURRENT_DATE - INTERVAL '60 days' AND end_date <= CURRENT_DATE AND deductible >= 1000 GROUP BY product_id ORDER BY avg_premium DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.policies ( policy_id text PRIMARY KEY, customer_id text, product_id text, agent_id text, policy_number text, start_date date, end_date date, premium_amount numeric, coverage_limit numeric, deductible numeric, status text, issued_at timestamp, cancellation_date date, cancellation_reason text )\n"}
{"conversations": [{"role": "user", "content": "Show the names of all insurance plans and the number of patients enrolled in each plan."}, {"role": "assistant", "content": "SELECT ip.plan_name, COUNT(pi.patient_id) AS enrolled_patients FROM healthcare.insurance_plans ip JOIN healthcare.patient_insurance pi ON ip.plan_id = pi.plan_id GROUP BY ip.plan_name;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, gender character varying(10), address text, phone_number character varying(20), email character varying(128) UNIQUE, emergency_contact_name character varying(200), emergency_contact_phone character varying(20), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (patient_id) )\nCREATE TABLE healthcare.appointments ( appointment_id.text, patient_id.text, doctor_id.text, appointment_time.timestamp, duration_minutes.integer, reason.text, status.text, location_id.text, notes.text, created_at.timestamp )\nCREATE TABLE healthcare.diagnoses (\n    diagnosis_id character varying(64) NOT NULL, -- unique identifier for the diagnosis entry\n    record_id character varying(64) NOT NULL, -- FK linking to the specific medical record entry\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    doctor_id character varying(64) NOT NULL, -- FK to doctors table (diagnosing doctor)\n    diagnosis_code character varying(20) NOT NULL, -- standard code (e.g., ICD-10)\n    code_type character varying(10) NOT NULL DEFAULT 'ICD-10', -- type of code used\n    description text, -- textual description of the diagnosis\n    diagnosis_date date NOT NULL, -- date the diagnosis was made\n    status character varying(32) NOT NULL, -- e.g., Active, Resolved, Ruled Out\n    is_chronic boolean DEFAULT false, -- flag for chronic conditions\n    PRIMARY KEY (diagnosis_id)\n)\nCREATE TABLE healthcare.prescriptions ( prescription_id text, record_id text, patient_id text, doctor_id text, medication_id text, dosage text, frequency text, route text, start_date date, end_date date, quantity_dispensed numeric, refills_allowed integer, prescription_date timestamp )\nCREATE TABLE healthcare.insurance_plans ( plan_id text, plan_name text, insurance_provider text, plan_type text, contact_phone text, website text )\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id.text, patient_id.text, plan_id.text, policy_number.text, group_number.text, subscriber_name.text, effective_date.date, expiration_date.date, is_primary.boolean )\n"}
{"conversations": [{"role": "user", "content": "What is the current market cap and 7-day price change percentage for the top 3 narratives by trend rank?"}, {"role": "assistant", "content": "SELECT narrative, market_cap, price_change_percentage_7d FROM narrative_info ORDER BY trend_rank ASC LIMIT 3;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\n \"CREATE TABLE token_basic_info (\",\n    \"coin_id character varying(100) NOT NULL, -- the id of the token\",\n    \"token_name character varying(100) NOT NULL, -- the token's name\",\n    \"token_symbol character varying(100) NOT NULL, -- the token's symbol\",\n    \"token_address character varying(100) NOT NULL, -- the token's address\",\n    \"chain text, -- the chain that the token resides\",\n    \"price double precision, -- the current price of the token\",\n    \"price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour\",\n    \"price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours\",\n    \"price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days\",\n    \"highest_price_24h double precision, -- the highest price of the token in 24 hours\",\n    \"lowest_price_24h double precision,  -- the lowest price of the token in 24 hours\",\n    \"market_cap double precision, -- the market cap of the token\",\n    \"market_cap_rank bigint, -- the rank of the token market cap in desc\",\n    \"market_cap_change_percentage_24h text, -- the percentage of market cap changes in 24 hours\",\n    \"total_volume text, -- the trade volum of the token both in decentralized exchange(DEX) and centralized exchange(CEX)\",    \n    \"narrative text, -- the category or narrative of the token\",\n    \"trend_rank biging, -- the trending rank of the token, value 1 expresses the most popular token.\",\n    \",PRIMARY KEY (coin_id, chain));\",\n\n \"CREATE TABLE narrative_info (\",\n    \"narrative character varying(512) NOT NULL, -- the id of narrative\",\n    \"top_3_coins text, -- the top 3 tokens in the narrative\",\n    \"price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour in the narrative\",\n    \"price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours in the narrative\",\n    \"price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days in the narrative\",\n    \"market_cap double precision, -- the market cap of the narrative\",\n    \"volume_24h double precision, -- the trade volume of the narrative\",\n    \"trend_rank bigint, -- the trending rank of the narrative, value 1 expresses the most popular narrative\",\n    \"token_num bigint, -- total token number in the narrative\",\n    \",PRIMARY KEY (narrative));\"\n\n  \"CREATE TABLE cex_token_balance (\",\n    \"snapshot_time character varying(32) NOT NULL,  -- the snapshot time of record, converted from original timestamp\",\n    \"chain character varying(128) NOT NULL, -- the chain that the token resides\",\n    \"address character varying(128) NOT NULL, -- the address that holds the assets, owned by a CEX\",\n    \"exchange character varying(512) NOT NULL, -- a centralized exchange name\",\n    \"token_address character varying(128) NOT NULL, -- token contract address\",\n    \"token_symbol character varying(512), --token symbol\",\n    \"balance numeric(38,10), -- token balance\",\n    \"usd_value numeric(38,14), -- value of the token held in USD\",\n    \"price double precision, --price of the token in USD\",\n    \",PRIMARY KEY (snapshot_time, exchange, address, chain, token_address));\"\n\n  \"CREATE TABLE smart_money_profit (\",\n    \"address character varying(100) NOT NULL, -- the user's address\",\n    \"rank INT, -- the rank of the address in trade performance, value 1 expresses the best address.\",\n    \"profit numeric(38,6), -- the profit user made in a month\",\n    \"roi numeric(38,2), -- the roi of the user in a month\",\n    \"realized_ratio numeric(38,2), -- the percentage of the user's realized profit\",\n    \"most_profit_token character varying(100), -- the token symbol of the user's most profitable trade\",\n    \"last_trade_time character varying(100), -- the last trade time of the user\",\n    \"chain character varying(100), -- the chain that the address resides\",\n    \"PRIMARY KEY (address, chain));\",\n\n  \"CREATE TABLE smart_money_token_performance (\",\n    \"token_address character varying(100) NOT NULL, -- the token's address\",\n    \"token_symbol character varying(100), -- the tokens's symbol\",\n    \"pnl numeric(38,2), -- the profit users made on this token\",\n    \"net_flow numeric(38,2), -- the netflow of the token, means the money user spent minus the the money user sold of this token\",\n    \"avg_cost numeric(38,16), -- the average cost price of user spent on this token\",\n    \"price double precision, -- the current price of the token\",\n    \"realized_ratio numeric(10,2), -- the ratio user sold of the token\",\n    \"roi numeric(10,2), -- the roi users made of this token\",\n    \"chain character varying(100), -- the chain that the token resides\",\n    \"PRIMARY KEY (token_address, chain));\",\n\n  \"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 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": "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": "How many unique IP addresses are there in the nodes table?"}, {"role": "assistant", "content": "SELECT COUNT(DISTINCT ip_address) FROM blockchain.nodes;"}, {"role": "user", "content": "Can you break this down by port numbers, showing the count of nodes for each port?"}, {"role": "assistant", "content": "SELECT port, COUNT(node_id) as node_count FROM blockchain.nodes GROUP BY port;"}, {"role": "user", "content": "Now, order these results by node_count in descending order."}, {"role": "assistant", "content": "SELECT port, COUNT(node_id) as node_count FROM blockchain.nodes GROUP BY port ORDER BY node_count DESC;"}, {"role": "user", "content": "Actually, I only want to see ports that have more than 5 nodes."}, {"role": "assistant", "content": "SELECT port, COUNT(node_id) as node_count FROM blockchain.nodes GROUP BY port HAVING COUNT(node_id) > 5 ORDER BY node_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 blockchain.nodes ( node_id text PRIMARY KEY, ip_address text, port int, last_seen timestamp )\n"}
{"conversations": [{"role": "user", "content": "Retrieve the agency name and the most recent notification sent date for each agency, considering only notifications related to agencies."}, {"role": "assistant", "content": "SELECT a.agency_name, MAX(n.sent_at) AS last_notification_date\nFROM government_services.agencies a\nJOIN government_services.notifications n\n  ON n.related_entity_type = 'Agency'\n  AND n.related_entity_id = a.agency_id\nGROUP BY a.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 character varying(64) NOT NULL, agency_name character varying(255) NOT NULL, jurisdiction_level character varying(50) NOT NULL, primary_contact_email character varying(128), main_phone_number character varying(32), website_url character varying(255), established_date date, parent_agency_id character varying(64), PRIMARY KEY (agency_id) )\nCREATE TABLE government_services.notifications (\n    notification_id character varying(64) NOT NULL, -- unique identifier for the notification\n    citizen_id character varying(64) NOT NULL, -- FK to citizens table\n    application_id character varying(64), -- FK to applications table (optional)\n    message_subject character varying(255),\n    message_body text NOT NULL,\n    channel character varying(30) NOT NULL, -- e.g., Email, SMS, Portal Message, Mail\n    sent_at timestamp NOT NULL,\n    status character varying(30) NOT NULL, -- e.g., Queued, Sent, Delivered, Failed, Read\n    related_entity_type character varying(50), -- e.g., Application, Appointment, Document Request\n    related_entity_id character varying(64), -- ID of the related entity\n    PRIMARY KEY (notification_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Show the usernames and email addresses of all users who have never created a post."}, {"role": "assistant", "content": "SELECT u.username, u.email\nFROM social_media.users u\nLEFT JOIN social_media.posts p ON u.user_id = p.user_id\nWHERE p.post_id IS NULL;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id text, username text, email text, password_hash text, full_name text, profile_picture_url text, bio text, location text, created_at timestamp, updated_at timestamp, is_verified boolean )\nCREATE TABLE social_media.posts ( post_id.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.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.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)\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 t.name, t.symbol, t.address FROM token_prices_latest t WHERE t.price BETWEEN 1 AND 10;"}, {"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, tpl.address, tpl.price FROM token_prices_latest tpl JOIN sui_coins_metadata scm ON tpl.address = scm.coin_type 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, tpl.address, tpl.price FROM token_prices_latest tpl JOIN sui_coins_metadata scm ON tpl.address = scm.coin_type 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 ( block_number.bigint, block_timestamp.timestamp, transaction_index.integer, transaction_hash.text, log_index.integer, contract_address.text )\nCREATE TABLE erc20_balances_historical ( block_number.bigint, contract_address.text, wallet_address.text, amount.text, pk.integer )\nCREATE TABLE nft_holders ( block_number.bigint, contract_address.text, wallet_address.text, token_id.text, contract_type.text, amount.text, pk.text )\nCREATE TABLE 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 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_activities ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\nCREATE TABLE token_balances_bitcoin ( block_number.bigint, block_timestamp.timestamp, tick.text, wallet_address.text, total_supply.text, amount.text )\nCREATE TABLE token_info_bitcoin ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, tick.text, max_supply.decimal, lim.decimal, wlim.decimal, dec.integer, creator.text )\nCREATE TABLE token_activities_bitcoin ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\nCREATE TABLE token_activities_avalanche ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\nCREATE TABLE token_balances_avalanche ( block_number.bigint, block_timestamp.timestamp, tick.text, wallet_address.text, total_supply.decimal, amount.decimal )\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": "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": "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 citizen who has made at least one payment, show the citizen's full name, number of payments, and total amount paid, grouped by currency."}, {"role": "assistant", "content": "SELECT\n  c.first_name || ' ' || c.last_name AS full_name,\n  p.currency,\n  COUNT(*) AS payment_count,\n  SUM(p.amount) AS total_amount\nFROM government_services.citizens c\nJOIN government_services.payments p ON c.citizen_id = p.citizen_id\nGROUP BY full_name, p.currency;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id character varying(64) NOT NULL, national_id_number character varying(128) NOT NULL UNIQUE, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, gender character varying(20), primary_address text NOT NULL, contact_email character varying(128) UNIQUE, contact_phone character varying(32), registration_date timestamp NOT NULL, is_verified boolean DEFAULT false, PRIMARY KEY (citizen_id) )\nCREATE TABLE government_services.payments ( payment_id character varying(64) NOT NULL, application_id character varying(64), citizen_id character varying(64) NOT NULL, service_id character varying(64), amount numeric(12, 2) NOT NULL, currency character varying(3) NOT NULL DEFAULT 'USD', payment_method character varying(50), payment_provider_reference character varying(128), payment_timestamp timestamp NOT NULL, status character varying(30) NOT NULL, notes text, PRIMARY KEY (payment_id) )\nCREATE TABLE government_services.employees ( employee_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, job_title character varying(150) NOT NULL, department character varying(100), work_email character varying(128) NOT NULL UNIQUE, work_phone character varying(32), hire_date date NOT NULL, termination_date date, access_level character varying(50), manager_employee_id character varying(64), PRIMARY KEY (employee_id) )\nCREATE TABLE government_services.service_locations ( location_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, location_name character varying(200), address text NOT NULL, city character varying(100), state character varying(50), postal_code character varying(20), latitude numeric(9, 6), longitude numeric(9, 6), operating_hours text, contact_phone character varying(32), is_accessible boolean, PRIMARY KEY (location_id) )\nCREATE TABLE government_services.appointments ( appointment_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, employee_id character varying(64), location_id character varying(64), service_id character varying(64), scheduled_start_time timestamp NOT NULL, scheduled_end_time timestamp, purpose text NOT NULL, status character varying(30) NOT NULL, booking_method character varying(50), created_at timestamp NOT NULL, notes text, PRIMARY KEY (appointment_id) )\nCREATE TABLE government_services.notifications ( notification_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, application_id character varying(64), message_subject character varying(255), message_body text NOT NULL, channel character varying(30) NOT NULL, sent_at timestamp NOT NULL, status character varying(30) NOT NULL, related_entity_type character varying(50), related_entity_id character varying(64), PRIMARY KEY (notification_id) )\n"}
{"conversations": [{"role": "user", "content": "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": "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": "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": "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": "List all claim documents that are police reports and were uploaded in the last 30 days, along with their file sizes."}, {"role": "assistant", "content": "SELECT cd.document_id, cd.claim_id, cd.file_size_bytes FROM insurance.claim_documents cd WHERE cd.document_type = 'Police Report' AND cd.uploaded_at >= CURRENT_DATE - INTERVAL '30 days';"}, {"role": "user", "content": "Now include only documents that are larger than 1MB and sort them by file size in descending order."}, {"role": "assistant", "content": "SELECT cd.document_id, cd.claim_id, cd.file_size_bytes FROM insurance.claim_documents cd WHERE cd.document_type = 'Police Report' AND cd.uploaded_at >= CURRENT_DATE - INTERVAL '30 days' AND cd.file_size_bytes > 1000000 ORDER BY cd.file_size_bytes 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 character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, product_id character varying(64) NOT NULL, agent_id character varying(64), policy_number character varying(100) NOT NULL UNIQUE, start_date date NOT NULL, end_date date NOT NULL, premium_amount numeric(12, 2) NOT NULL, coverage_limit numeric(15, 2) NOT NULL, deductible numeric(10, 2) NOT NULL, status character varying(30) NOT NULL, issued_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, cancellation_date date, cancellation_reason text, PRIMARY KEY (policy_id) )\nCREATE TABLE insurance.claims ( claim_id character varying(64) NOT NULL, policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, incident_date timestamp NOT NULL, reported_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, description text NOT NULL, estimated_loss numeric(15, 2), status character varying(30) NOT NULL, settlement_amount numeric(15, 2), settlement_date date, claim_handler_id character varying(64), police_report_number character varying(100), PRIMARY KEY (claim_id) )\nCREATE TABLE insurance.agents ( agent_id 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) )\nCREATE TABLE insurance.premium_payments ( payment_id character varying(64) NOT NULL, policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, payment_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, amount_paid numeric(12, 2) NOT NULL, payment_method character varying(50), transaction_reference character varying(128) UNIQUE, due_date date, payment_period_start date, payment_period_end date, status character varying(30) NOT NULL DEFAULT 'Completed', PRIMARY KEY (payment_id) )\nCREATE TABLE insurance.claim_documents ( document_id 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) )\nCREATE TABLE insurance.policy_beneficiaries ( beneficiary_id character varying(64) NOT NULL, policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, relationship character varying(50) NOT NULL, percentage_share numeric(5, 2) NOT NULL CHECK (percentage_share > 0 AND percentage_share <= 100), contact_info text, added_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (beneficiary_id), UNIQUE (policy_id, customer_id) )\n"}
{"conversations": [{"role": "user", "content": "For all chains, which token held by centralized exchanges (CEX) has the highest ROI according to smart money token performance? Show token symbol, chain, exchange, total USD value held on CEX, and the smart money ROI."}, {"role": "assistant", "content": "SELECT c.token_symbol, c.chain, c.exchange, SUM(c.usd_value) AS total_usd_value, s.roi\nFROM cex_token_balance c\nJOIN smart_money_token_performance s ON c.token_symbol = s.token_symbol AND c.chain = s.chain\nGROUP BY c.token_symbol, c.chain, c.exchange, s.roi\nORDER BY s.roi DESC\nLIMIT 1;"}, {"role": "user", "content": "Instead of just the top one, show the top 3 tokens by ROI, and only include cases where the total USD value held on CEX is greater than $2,000,000."}, {"role": "assistant", "content": "SELECT c.token_symbol, c.chain, c.exchange, SUM(c.usd_value) AS total_usd_value, s.roi\nFROM cex_token_balance c\nJOIN smart_money_token_performance s ON c.token_symbol = s.token_symbol AND c.chain = s.chain\nGROUP BY c.token_symbol, c.chain, c.exchange, s.roi\nHAVING SUM(c.usd_value) > 2000000\nORDER BY s.roi DESC\nLIMIT 3;"}, {"role": "user", "content": "Add the last recorded price for each token, and sort by total_usd_value in descending order."}, {"role": "assistant", "content": "SELECT c.token_symbol, c.chain, c.exchange, SUM(c.usd_value) AS total_usd_value, s.roi, MAX(c.price) AS last_price\nFROM cex_token_balance c\nJOIN smart_money_token_performance s ON c.token_symbol = s.token_symbol AND c.chain = s.chain\nGROUP BY c.token_symbol, c.chain, c.exchange, s.roi\nHAVING SUM(c.usd_value) > 2000000\nORDER BY total_usd_value DESC\nLIMIT 3;"}, {"role": "user", "content": "I got duplicate tokens across exchanges. Can you show only the top exchange (with the greatest USD value) per token and chain combination?"}, {"role": "assistant", "content": "WITH cex_totals AS (\n  SELECT c.token_symbol, c.chain, c.exchange, SUM(c.usd_value) AS total_usd_value, s.roi, MAX(c.price) AS last_price,\n         ROW_NUMBER() OVER (PARTITION BY c.token_symbol, c.chain ORDER BY SUM(c.usd_value) DESC) as rn\n  FROM cex_token_balance c\n  JOIN smart_money_token_performance s ON c.token_symbol = s.token_symbol AND c.chain = s.chain\n  GROUP BY c.token_symbol, c.chain, c.exchange, s.roi\n  HAVING SUM(c.usd_value) > 2000000\n)\nSELECT token_symbol, chain, exchange, total_usd_value, roi, last_price\nFROM cex_totals\nWHERE rn = 1\nORDER BY total_usd_value 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, 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 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 a list of cases, including the case number, case name, and the full name of the client associated with each case that has at least one appointment."}, {"role": "assistant", "content": "SELECT DISTINCT T1.case_number, T1.case_name, T2.first_name, T2.last_name FROM cases AS T1 JOIN clients AS T2 ON T1.client_id = T2.client_id JOIN appointments AS T3 ON T1.case_id = T3.case_id;"}, {"role": "user", "content": "Additionally, for each of these cases, include the subject and start time of the related appointments. Show all appointments, not just distinct cases."}, {"role": "assistant", "content": "SELECT T1.case_number, T1.case_name, T2.first_name, T2.last_name, T3.subject, T3.start_time FROM cases AS T1 JOIN clients AS T2 ON T1.client_id = T2.client_id JOIN appointments AS T3 ON T1.case_id = T3.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.clients ( client_id text, first_name text, last_name text, company_name text, email text, phone text, address text, date_registered timestamp, status text )\nCREATE TABLE legal_services.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.law_firms ( firm_id text, firm_name text, address text, phone text, website text, founded_date date, managing_partner_id text )\nCREATE TABLE legal_services.documents ( document_id text, case_id text, document_name text, document_type text, storage_path text, uploaded_by_lawyer_id text, upload_timestamp timestamp, version integer, description text )\nCREATE TABLE legal_services.time_entries ( entry_id text, case_id text, lawyer_id text, date_worked date, hours_spent numeric, billing_rate numeric, description text, is_billable boolean, is_billed boolean, invoice_id text, created_at timestamp )\nCREATE TABLE legal_services.appointments ( appointment_id text, client_id text, lawyer_id text, case_id text, start_time timestamp, end_time timestamp, location text, subject text, notes text, status text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "List all 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": "List the first_name, last_name, and email of all clients whose email domain is 'gmail.com'."}, {"role": "assistant", "content": "SELECT first_name, last_name, email FROM legal_services.clients WHERE SUBSTRING(email FROM POSITION('@' IN email) + 1) = 'gmail.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 legal_services.clients ( client_id text, first_name text, last_name text, company_name text, email text, phone text, address text, date_registered timestamp, status text )\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 me the top 5 users with the most wallet addresses, along with the count of their wallets."}, {"role": "assistant", "content": "SELECT user_id, COUNT(wallet_id) AS wallet_count FROM blockchain.wallets WHERE user_id IS NOT NULL GROUP BY user_id ORDER BY wallet_count DESC LIMIT 5;"}, {"role": "user", "content": "Now include the earliest created wallet address for each of these top 5 users."}, {"role": "assistant", "content": "Note: The wallets table doesn't have a creation timestamp column. Without this information, we cannot determine the earliest created wallet. Please provide a table with creation timestamps if you need this analysis."}, {"role": "user", "content": "Then just show me these top 5 users with their wallet counts and the first wallet_id alphabetically for each user."}, {"role": "assistant", "content": "SELECT user_id, COUNT(wallet_id) AS wallet_count, MIN(wallet_id) AS first_wallet_id FROM blockchain.wallets WHERE user_id IS NOT NULL GROUP BY user_id ORDER BY wallet_count DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE blockchain.wallets ( wallet_id text, user_id text, address_id text, private_key text )\n"}
{"conversations": [{"role": "user", "content": "Show me all claims along with the related customer's full name and the policy number for incidents that occurred in 2024."}, {"role": "assistant", "content": "SELECT c.claim_id, c.incident_date, c.description, cu.first_name || ' ' || cu.last_name AS customer_full_name, p.policy_number\nFROM insurance.claims c\nJOIN insurance.customers cu ON c.customer_id = cu.customer_id\nJOIN insurance.policies p ON c.policy_id = p.policy_id\nWHERE EXTRACT(YEAR FROM c.incident_date) = 2024;"}, {"role": "user", "content": "Include the settlement amount and status of each claim in the results."}, {"role": "assistant", "content": "SELECT c.claim_id, c.incident_date, c.description, cu.first_name || ' ' || cu.last_name AS customer_full_name, p.policy_number, c.settlement_amount, c.status\nFROM insurance.claims c\nJOIN insurance.customers cu ON c.customer_id = cu.customer_id\nJOIN insurance.policies p ON c.policy_id = p.policy_id\nWHERE EXTRACT(YEAR FROM c.incident_date) = 2024;"}, {"role": "user", "content": "Actually, please filter only those claims with a settlement_amount that is not null."}, {"role": "assistant", "content": "SELECT c.claim_id, c.incident_date, c.description, cu.first_name || ' ' || cu.last_name AS customer_full_name, p.policy_number, c.settlement_amount, c.status\nFROM insurance.claims c\nJOIN insurance.customers cu ON c.customer_id = cu.customer_id\nJOIN insurance.policies p ON c.policy_id = p.policy_id\nWHERE EXTRACT(YEAR FROM c.incident_date) = 2024\n  AND c.settlement_amount IS NOT NULL;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.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)\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.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.premium_payments ( payment_id text, 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 )\n"}
{"conversations": [{"role": "user", "content": "List all peer logs, showing the user_id and the action taken, ordered by the most recent log entry."}, {"role": "assistant", "content": "SELECT user_id, action, logged_at\nFROM trading_platform.logs\nORDER BY logged_at DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.users ( 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.assets ( asset_id text, name text, symbol text, type text )\nCREATE TABLE trading_platform.utxos ( utxo_id text PRIMARY KEY, transaction_id text, output_index int, address text, amount numeric, spent boolean )\nCREATE TABLE trading_platform.dapps ( dapp_id text, name text, description text, url text )\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": "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": "List each patient's first_name, last_name, and the plan_name and policy_number of their primary insurance plan."}, {"role": "assistant", "content": "SELECT p.first_name,\n       p.last_name,\n       ip.plan_name,\n       pi.policy_number\nFROM healthcare.patients p\nJOIN healthcare.patient_insurance pi ON p.patient_id = pi.patient_id AND pi.is_primary = TRUE\nJOIN healthcare.insurance_plans ip ON pi.plan_id = ip.plan_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id text, 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.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 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)\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id text PRIMARY KEY, patient_id text, plan_id text, policy_number text, group_number text, subscriber_name text, effective_date date, expiration_date date, is_primary boolean )\n"}
{"conversations": [{"role": "user", "content": "Show me all doctors who have prescribed medications with a dosage greater than 200mg, along with their specialties and the count of such prescriptions per doctor."}, {"role": "assistant", "content": "SELECT d.doctor_id, d.first_name, d.last_name, d.specialty, COUNT(p.prescription_id) AS prescription_count FROM healthcare.doctors d JOIN healthcare.prescriptions p ON d.doctor_id = p.doctor_id WHERE CAST(SUBSTRING(p.dosage FROM '[0-9]+') AS INTEGER) > 200 GROUP BY d.doctor_id, d.first_name, d.last_name, d.specialty ORDER BY prescription_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.doctors ( doctor_id.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.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.patient_insurance ( patient_insurance_id.text, patient_id.text, plan_id.text, policy_number.text, group_number.text, subscriber_name.text, effective_date.date, expiration_date.date, is_primary.boolean )\n"}
{"conversations": [{"role": "user", "content": "List the first name, last name, and hire date of all lawyers who are partners."}, {"role": "assistant", "content": "SELECT first_name ,  last_name ,  hire_date FROM legal_services.lawyers WHERE is_partner  =  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 legal_services.lawyers (\n    lawyer_id character varying(64) NOT NULL,  -- unique identifier for the lawyer\n    first_name character varying(100) NOT NULL, -- lawyer's first name\n    last_name character varying(100) NOT NULL, -- lawyer's last name\n    bar_number character varying(64) UNIQUE NOT NULL, -- lawyer's bar association number\n    firm_id character varying(64), -- FK to law_firms table\n    email character varying(128) UNIQUE NOT NULL, -- lawyer's professional email\n    phone character varying(32), -- lawyer's contact phone number\n    specialization text, -- areas of legal expertise\n    hire_date timestamp NOT NULL, -- date the lawyer was hired or joined\n    is_partner boolean DEFAULT false, -- flag indicating if the lawyer is a partner\n    PRIMARY KEY (lawyer_id)\n)\n"}
{"conversations": [{"role": "user", "content": "What is the number of guests per country, grouped by country_code?"}, {"role": "assistant", "content": "SELECT country_code,\n       COUNT(*) AS guest_count\nFROM hospitality_technology.guests\nGROUP BY country_code;"}, {"role": "user", "content": "Only include countries that have at least 5 guests."}, {"role": "assistant", "content": "SELECT country_code,\n       COUNT(*) AS guest_count\nFROM hospitality_technology.guests\nGROUP BY country_code\nHAVING COUNT(*) >= 5;"}, {"role": "user", "content": "Also include the most recently registered guest in each of those countries, showing their full name and created_at."}, {"role": "assistant", "content": "WITH country_counts AS (\n  SELECT country_code,\n         COUNT(*) AS guest_count,\n         MAX(created_at) AS last_reg\n  FROM hospitality_technology.guests\n  GROUP BY country_code\n  HAVING COUNT(*) >= 5\n)\nSELECT cc.country_code,\n       cc.guest_count,\n       g.first_name || ' ' || g.last_name AS last_guest_name,\n       g.created_at          AS last_registration\nFROM country_counts cc\nJOIN hospitality_technology.guests g\n  ON g.country_code = cc.country_code\n AND g.created_at = cc.last_reg;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.guests ( guest_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, email character varying(255) UNIQUE, phone_number character varying(30), date_of_birth date, address_line1 character varying(255), city character varying(100), state_province character varying(100), postal_code character varying(20), country_code character varying(3), preferences text, loyalty_member_id character varying(64) UNIQUE, communication_consent boolean DEFAULT true, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (guest_id) )\n"}
{"conversations": [{"role": "user", "content": "List each wallet that has received tokens of more than one distinct token type. Show wallet_id, address, the number of distinct tokens received as distinct_token_count, and the total received value, ordered by total_received_value descending."}, {"role": "assistant", "content": "SELECT w.wallet_id,\n       w.address,\n       COUNT(DISTINCT t.token_id) AS distinct_token_count,\n       SUM(tt.value)            AS total_received_value\nFROM web3.wallets w\nJOIN web3.token_transfers tt\n  ON w.address = tt.to_address\nJOIN web3.tokens t\n  ON tt.token_id = t.token_id\nGROUP BY w.wallet_id, w.address\nHAVING COUNT(DISTINCT t.token_id) > 1\nORDER BY total_received_value DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.tokens (\n    token_id character varying(64) NOT NULL,  -- unique identifier for the token\n    contract_address character varying(128) NOT NULL, -- address of the token contract\n    token_name character varying(128) NOT NULL, -- name of the token\n    token_symbol character varying(32) NOT NULL, -- symbol of the token\n    decimals integer NOT NULL, -- number of decimals for the token\n    total_supply numeric(38,14) NOT NULL, -- total supply of the token\n    PRIMARY KEY (token_id)\n)\nCREATE TABLE web3.token_transfers (\n    transfer_id character varying(64) NOT NULL,  -- unique identifier for the transfer\n    token_id character varying(64) NOT NULL, -- identifier of the token being transferred\n    from_address character varying(128) NOT NULL, -- address of the sender\n    to_address character varying(128) NOT NULL, -- address of the receiver\n    value numeric(38,14) NOT NULL, -- amount of tokens transferred\n    transaction_id character varying(64) NOT NULL, -- identifier of the transaction containing the transfer\n    log_index integer NOT NULL, -- index of the transfer log in the transaction\n    PRIMARY KEY (transfer_id)\n)\nCREATE TABLE web3.wallets (\n    wallet_id character varying(64) NOT NULL,  -- unique identifier for the wallet\n    user_id character varying(64) NOT NULL, -- identifier of the user owning the wallet\n    address character varying(128) NOT NULL, -- address of the wallet\n    private_key text NOT NULL, -- private key of the wallet\n    created_at timestamp NOT NULL, -- time when the wallet was created\n    PRIMARY KEY (wallet_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Show me the top 3 tokens by 24-hour trading volume in the 'NFT' narrative, along with their price and market cap."}, {"role": "assistant", "content": "SELECT token_name, token_symbol, total_volume, price, market_cap FROM token_basic_info WHERE narrative = 'NFT' ORDER BY CAST(total_volume AS double precision) DESC LIMIT 3;"}, {"role": "user", "content": "Can you also include their 7-day price change percentage and filter for tokens with a market cap over $100 million?"}, {"role": "assistant", "content": "SELECT token_name, token_symbol, total_volume, price, market_cap, price_change_percentage_7d FROM token_basic_info WHERE narrative = 'NFT' AND market_cap > 100000000 ORDER BY CAST(total_volume AS double precision) DESC LIMIT 3;"}, {"role": "user", "content": "Actually, I want to see tokens with positive 7-day price changes and order by market cap instead."}, {"role": "assistant", "content": "SELECT token_name, token_symbol, total_volume, price, market_cap, price_change_percentage_7d FROM token_basic_info WHERE narrative = 'NFT' AND market_cap > 100000000 AND price_change_percentage_7d > 0 ORDER BY market_cap DESC LIMIT 3;"}, {"role": "user", "content": "Now include their highest and lowest prices in the last 24 hours as well."}, {"role": "assistant", "content": "SELECT token_name, token_symbol, total_volume, price, market_cap, price_change_percentage_7d, highest_price_24h, lowest_price_24h FROM token_basic_info WHERE narrative = 'NFT' AND market_cap > 100000000 AND price_change_percentage_7d > 0 ORDER BY market_cap DESC LIMIT 3;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_basic_info ( coin_id character varying(100) NOT NULL, token_name character varying(100) NOT NULL, token_symbol character varying(100) NOT NULL, token_address character varying(100) NOT NULL, chain text, price double precision, price_change_percentage_1h double precision, price_change_percentage_24h double precision, price_change_percentage_7d double precision, highest_price_24h double precision, lowest_price_24h double precision, market_cap double precision, market_cap_rank bigint, market_cap_change_percentage_24h text, total_volume text, narrative text, trend_rank bigint )\n"}
{"conversations": [{"role": "user", "content": "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 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": "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": "Show me all wallet addresses that hold more than 1000 of any ERC1155 token, along with the token ID and amount."}, {"role": "assistant", "content": "SELECT wallet_address, token_id, amount FROM nft_holders WHERE contract_type = 'ERC1155' AND CAST(amount AS decimal) > 1000;"}, {"role": "user", "content": "Can you join this with the nft_metadata table to include the name and image URI of each token?"}, {"role": "assistant", "content": "SELECT nh.wallet_address, nh.token_id, nh.amount, nm.name, nm.image_uri FROM nft_holders nh JOIN nft_metadata nm ON nh.contract_address = nm.contract_address AND nh.token_id = nm.token_id WHERE nh.contract_type = 'ERC1155' AND CAST(nh.amount AS decimal) > 1000;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE erc1155_approval_for_all (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the transaction\n    transaction_index integer NOT NULL, -- Index of the transaction within the block\n    transaction_hash varchar(66) NOT NULL, -- Transaction hash\n    log_index integer NOT NULL, -- Log index\n    contract_address varchar(42) NOT NULL  -- Event contract address\n)\nCREATE TABLE erc20_balances ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE erc20_balances_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_holders (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    contract_address varchar NOT NULL, -- Event contract address\n    wallet_address varchar NOT NULL, -- The wallet address for the contract(with bloom filter)\n    token_id varchar NOT NULL, -- NFT token id\n    contract_type varchar NOT NULL, -- NFT contract type\n    amount varchar NOT NULL, -- Number of held NFTs\n    pk varchar NOT NULL  -- The last string partition of the contract.\n)\nCREATE TABLE nft_holder_historical ( block_number bigint, contract_address text, wallet_address text, token_id text, contract_type text, amount text, pk integer )\nCREATE TABLE sui_coins_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 varchar, contract_address varchar, name varchar, symbol varchar, deploy_block_number bigint, deploy_block_time bigint, erc_type varchar, owner varchar, traits varchar, description varchar, slug varchar, media_info varchar, image_url varchar, banner_image_url varchar, updated_at bigint, banner varchar, token_count bigint, floor_price varchar, floor_price_symbol varchar, floor_price_contract varchar, pk integer )\nCREATE TABLE token_prices ( uuid.text, blockchain.text, address.text, decimals.bigint, symbol.text, price.real, timestamp.timestamp )\nCREATE TABLE erc20_approval ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash text, log_index integer, contract_address text, pk integer )\nCREATE TABLE token_balances ( block_number.bigint, block_timestamp.timestamp, tick.text, wallet_address.text, total_supply.decimal, amount.decimal )\nCREATE TABLE token_info (\n    block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n    block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n    tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n    tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n    tick varchar NOT NULL, -- Token tick\n    max_supply decimal(38,0) NOT NULL, -- Max supply\n    lim decimal(38,0) NOT NULL, -- Limit of each mint\n    wlim decimal(38,0) NOT NULL, -- Limit of each address can maximum mint\n    dec integer NOT NULL, -- Decimal for minimum divie\n    creator varchar(42) NOT NULL  -- Address originating the inscription (matches from_address in transactions table)\n)\nCREATE TABLE token_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(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, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_balances_avalanche ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar(20) NOT NULL, wallet_address varchar(42) NOT NULL, total_supply decimal(38,0) NOT NULL, amount decimal(38,0) NOT NULL )\n"}
{"conversations": [{"role": "user", "content": "What is the total USD value held by all centralized exchanges (CEX) for the token with the symbol 'BTC'?"}, {"role": "assistant", "content": "SELECT SUM(usd_value) AS total_btc_cex_value FROM cex_token_balance WHERE token_symbol = 'BTC';"}, {"role": "user", "content": "Can you break down the total USD value for 'BTC' held by CEXes by chain?"}, {"role": "assistant", "content": "SELECT chain, SUM(usd_value) AS total_btc_cex_value FROM cex_token_balance WHERE token_symbol = 'BTC' GROUP BY chain ORDER BY total_btc_cex_value DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE project_fundraising_record ( id character varying(32) NOT NULL,  -- fundraising record id project_id character varying(32) NOT NULL, -- the invested project's id project_name character varying(128) NOT NULL, -- name of the invested project rounds_name character varying(32), -- name of the fundraising round investment_value numeric(38,14), -- amount of the fundraising in USD investment_date character varying(128), -- the date of the investment happened introduction character varying(128), -- the introduction of the invested project valuation numeric(38,14), -- the valuation of the project in USD when invested )\nCREATE TABLE token_basic_info ( coin_id character varying(100) NOT NULL, -- the id of the token token_name character varying(100) NOT NULL, -- the token's name token_symbol character varying(100) NOT NULL, -- the token's symbol token_address character varying(100) NOT NULL, -- the token's address chain text, -- the chain that the token resides price double precision, -- the current price of the token price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days highest_price_24h double precision, -- the highest price of the token in 24 hours lowest_price_24h double precision,  -- the lowest price of the token in 24 hours market_cap double precision, -- the market cap of the token market_cap_rank bigint, -- the rank of the token market cap in desc market_cap_change_percentage_24h text, -- the percentage of market cap changes in 24 hours total_volume text, -- the trade volum of the token both in decentralized exchange(DEX) and centralized exchange(CEX) narrative text, -- the category or narrative of the token trend_rank biging, -- the trending rank of the token, value 1 expresses the most popular token. ,PRIMARY KEY (coin_id, chain) )\nCREATE TABLE 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 character varying(32) NOT NULL,  -- the snapshot time of record, converted from original timestamp chain character varying(128) NOT NULL, -- the chain that the token resides address character varying(128) NOT NULL, -- the address that holds the assets, owned by a CEX exchange character varying(512) NOT NULL, -- a centralized exchange name token_address character varying(128) NOT NULL, -- token contract address token_symbol character varying(512), --token symbol balance numeric(38,10), -- token balance usd_value numeric(38,14), -- value of the token held in USD price double precision, --price of the token in USD ,PRIMARY KEY (snapshot_time, exchange, address, chain, token_address) )\nCREATE TABLE smart_money_profit ( address text, rank numeric, profit numeric, roi numeric, realized_ratio numeric, most_profit_token text, last_trade_time text, chain text )\nCREATE TABLE smart_money_token_performance ( token_address.text, token_symbol.text, pnl.numeric, net_flow.numeric, avg_cost.numeric, price.numeric, realized_ratio.numeric, roi.numeric, chain.text )\nCREATE TABLE smart_money_token_inflow ( token_address.text, token_symbol.text, token_amount.numeric, usd_value.numeric, avg_price.numeric, type.numeric, address_amount.numeric, narrative.text, chain.text )\n"}
{"conversations": [{"role": "user", "content": "List 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 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": "Find the most recent verified document for each application, showing application_id, document_id, and verification_timestamp."}, {"role": "assistant", "content": "SELECT d.document_id, d.application_id, d.verification_timestamp\nFROM government_services.documents d\nJOIN (\n  SELECT application_id, MAX(verification_timestamp) AS latest_ts\n  FROM government_services.documents\n  WHERE verification_status = 'Verified'\n  GROUP BY application_id\n) m ON d.application_id = m.application_id\n    AND d.verification_timestamp = m.latest_ts;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.documents ( document_id text PRIMARY KEY, application_id text, citizen_id text, document_type text, file_reference text, upload_timestamp timestamp, expiry_date date, verification_status text, verified_by_employee_id text, verification_timestamp timestamp )\n"}
{"conversations": [{"role": "user", "content": "List all users who have never followed anyone, showing their username, full name, email, and account creation date."}, {"role": "assistant", "content": "SELECT u.username,\n       u.full_name,\n       u.email,\n       u.created_at\nFROM social_media.users AS u\nLEFT JOIN social_media.follows AS f\n  ON u.user_id = f.follower_user_id\nWHERE f.follow_id IS NULL;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id text, username text, email text, password_hash text, full_name text, profile_picture_url text, bio text, location text, created_at timestamp, updated_at timestamp, is_verified boolean )\nCREATE TABLE social_media.posts ( post_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, content text, media_url text, media_type character varying(20), created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, visibility character varying(20) NOT NULL DEFAULT 'public', location_lat numeric(9,6), location_lon numeric(9,6), PRIMARY KEY (post_id) )\nCREATE TABLE social_media.comments ( comment_id.text, post_id.text, user_id.text, parent_comment_id.text, content.text, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE social_media.likes ( like_id text PRIMARY KEY, user_id text, post_id text, comment_id text, created_at timestamp )\nCREATE TABLE social_media.follows (\n    follow_id character varying(64) NOT NULL, -- unique identifier for the follow relationship\n    follower_user_id character varying(64) NOT NULL, -- identifier of the user who is following (FK to users.user_id)\n    following_user_id character varying(64) NOT NULL, -- identifier of the user being followed (FK to users.user_id)\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of when the follow started\n    PRIMARY KEY (follow_id),\n    CONSTRAINT unique_follow UNIQUE (follower_user_id, following_user_id) -- prevent duplicate follows\n)\nCREATE TABLE social_media.hashtags ( hashtag_id character varying(64) NOT NULL, tag_name character varying(100) NOT NULL UNIQUE, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (hashtag_id) )\nCREATE TABLE social_media.post_hashtags ( post_hashtag_id text PRIMARY KEY, post_id text, hashtag_id text )\nCREATE TABLE social_media.conversations ( conversation_id.text, created_at.timestamp, last_message_at.timestamp, is_group_chat.boolean, group_name.text )\nCREATE TABLE social_media.conversation_participants ( participant_id.text, conversation_id.text, user_id.text, joined_at.timestamp, last_read_at.timestamp )\nCREATE TABLE social_media.notifications ( notification_id.text, recipient_user_id.text, sender_user_id.text, notification_type.text, target_entity_id.text, target_entity_type.text, created_at.timestamp, read_at.timestamp )\nCREATE TABLE social_media.user_settings ( setting_id.text, user_id.text, theme.text, email_notifications_enabled.boolean, push_notifications_enabled.boolean, private_profile.boolean, updated_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "List all rooms that have a 'Jacuzzi' feature, including the room_number, property_id, type_name, and base_rate."}, {"role": "assistant", "content": "SELECT r.room_number,\n       r.property_id,\n       rt.type_name,\n       rt.base_rate\nFROM hospitality_technology.rooms AS r\nJOIN hospitality_technology.room_types AS rt\n  ON r.room_type_id = rt.room_type_id\n AND r.property_id = rt.property_id\nWHERE r.features ILIKE '%Jacuzzi%';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.rooms ( room_id.text, property_id.text, room_number.text, room_type_id.text, floor.integer, status.text, is_smoking.boolean, features.text, current_condition.text, last_cleaned_at.timestamp )\nCREATE TABLE hospitality_technology.room_types ( room_type_id.text, property_id.text, type_name.text, description.text, base_rate.numeric, max_occupancy.integer, bed_type.text, area_sqft.numeric, amenities.text )\nCREATE TABLE hospitality_technology.guests ( guest_id.text, first_name.text, last_name.text, email.text, phone_number.text, date_of_birth.date, address_line1.text, city.text, state_province.text, postal_code.text, country_code.text, preferences.text, loyalty_member_id.text, communication_consent.boolean, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE hospitality_technology.staff ( staff_id.text, property_id.text, first_name.text, last_name.text, position.text, work_email.text, work_phone.text, hire_date.date, termination_date.date, is_active.boolean, access_level.integer, manager_id.text, created_at.timestamp )\nCREATE TABLE hospitality_technology.service_orders ( order_id.text, reservation_id.text, guest_id.text, service_id.text, staff_id_ordered.text, staff_id_delivered.text, order_timestamp.timestamp, delivery_timestamp.timestamp, quantity.integer, unit_price.numeric, total_price.numeric, status.text, notes.text, bill_id.text )\nCREATE TABLE hospitality_technology.payments ( payment_id.text, reservation_id.text, guest_id.text, bill_id.text, amount.numeric, currency_code.text, payment_method.text, card_type.text, card_last_four.text, transaction_ref.text, payment_timestamp.timestamp, status.text, staff_id_processed.text, notes.text )\nCREATE TABLE hospitality_technology.reviews ( review_id.text, property_id.text, reservation_id.text, guest_id.text, rating_overall.integer, rating_cleanliness.integer, rating_service.integer, rating_location.integer, rating_value.integer, comment.text, review_source.text, review_date.timestamp, is_public.boolean, staff_response.text, response_staff_id.text, response_date.timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show me the username and email of all users who own at least one wallet."}, {"role": "assistant", "content": "SELECT DISTINCT T1.username, T1.email FROM blockchain.users AS T1 JOIN blockchain.wallets AS T2 ON T1.user_id = T2.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.wallets ( wallet_id.text, user_id.text, address_id.text, private_key.text )\nCREATE TABLE blockchain.users ( user_id.text, username.text, email.text, password_hash.text )\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": "List all guests from California who are loyalty members and have provided their email addresses, ordered by last name."}, {"role": "assistant", "content": "SELECT guest_id, first_name, last_name, email, phone_number FROM hospitality_technology.guests WHERE state_province = 'California' AND loyalty_member_id IS NOT NULL AND email IS NOT NULL ORDER BY last_name;"}, {"role": "user", "content": "Now, include only guests who have communication consent and were created in the last year."}, {"role": "assistant", "content": "SELECT guest_id, first_name, last_name, email, phone_number, created_at FROM hospitality_technology.guests WHERE state_province = 'California' AND loyalty_member_id IS NOT NULL AND email IS NOT NULL AND communication_consent = true AND created_at >= DATE_SUB(CURRENT_DATE, INTERVAL 1 YEAR) ORDER BY last_name;"}, {"role": "user", "content": "The query is missing their loyalty member IDs. Can you include that as well?"}, {"role": "assistant", "content": "SELECT guest_id, first_name, last_name, email, phone_number, loyalty_member_id, created_at FROM hospitality_technology.guests WHERE state_province = 'California' AND loyalty_member_id IS NOT NULL AND email IS NOT NULL AND communication_consent = true AND created_at >= DATE_SUB(CURRENT_DATE, INTERVAL 1 YEAR) ORDER BY last_name;"}, {"role": "user", "content": "Actually, I only need guests from Los Angeles and San Francisco, and order by created date from newest to oldest."}, {"role": "assistant", "content": "SELECT guest_id, first_name, last_name, email, phone_number, loyalty_member_id, created_at FROM hospitality_technology.guests WHERE state_province = 'California' AND city IN ('Los Angeles', 'San Francisco') AND loyalty_member_id IS NOT NULL AND email IS NOT NULL AND communication_consent = true AND created_at >= DATE_SUB(CURRENT_DATE, INTERVAL 1 YEAR) ORDER BY created_at DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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.service_orders ( order_id.text, reservation_id.text, guest_id.text, service_id.text, staff_id_ordered.text, staff_id_delivered.text, order_timestamp.timestamp, delivery_timestamp.timestamp, quantity.integer, unit_price.numeric, total_price.numeric, status.text, notes.text, bill_id.text )\n"}
{"conversations": [{"role": "user", "content": "Show me the top 5 games by number of online servers in European regions. I want the game title and the server count."}, {"role": "assistant", "content": "SELECT g.title, COUNT(s.server_id) AS server_count\nFROM gaming_technology.games g\nJOIN gaming_technology.servers s ON g.game_id = s.game_id\nWHERE s.region ILIKE 'eu%' AND s.status = 'online'\nGROUP BY g.title\nORDER BY server_count DESC\nLIMIT 5;"}, {"role": "user", "content": "Now include only those games whose average current_players per online server exceeds 100."}, {"role": "assistant", "content": "SELECT g.title,\n       COUNT(s.server_id) AS server_count,\n       AVG(s.current_players)::numeric(10,2) AS avg_players\nFROM gaming_technology.games g\nJOIN gaming_technology.servers s ON g.game_id = s.game_id\nWHERE s.region ILIKE 'eu%' AND s.status = 'online'\nGROUP BY g.title\nHAVING AVG(s.current_players) > 100\nORDER BY server_count DESC\nLIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.players ( player_id uuid PRIMARY KEY, username text, email text, password_hash text, registration_date timestamptz, last_login timestamptz, country_code text, status text, profile_data jsonb )\nCREATE TABLE gaming_technology.games ( game_id uuid PRIMARY KEY, title text, developer_id uuid, publisher_id uuid, genre text, release_date date, description text, platform text, engine text, website text )\nCREATE TABLE gaming_technology.servers ( server_id uuid PRIMARY KEY, game_id uuid, server_name text, region text, ip_address text, port int, current_players int, max_players int, status text, last_heartbeat timestamptz )\nCREATE TABLE gaming_technology.achievements ( achievement_id uuid PRIMARY KEY, game_id uuid, name text, description text, icon_url text, points int, hidden boolean )\nCREATE TABLE gaming_technology.player_achievements ( player_achievement_id uuid PRIMARY KEY, player_id uuid, achievement_id uuid, unlocked_at timestamptz )\nCREATE TABLE gaming_technology.in_game_items ( item_id uuid PRIMARY KEY, game_id uuid, item_name text, item_type text, description text, rarity text, cost_currency text, cost_amount numeric, attributes jsonb )\nCREATE TABLE gaming_technology.player_inventory ( inventory_id uuid PRIMARY KEY, player_id uuid, item_id uuid, quantity int, acquired_at timestamptz, instance_data jsonb )\n"}
{"conversations": [{"role": "user", "content": "For each user, list all pairs of read and unread notifications, showing the recipient_user_id, the unread notification_id and type, and the read notification_id and type."}, {"role": "assistant", "content": "SELECT\n  n_unread.recipient_user_id,\n  n_unread.notification_id   AS unread_id,\n  n_unread.notification_type AS unread_type,\n  n_read.notification_id     AS read_id,\n  n_read.notification_type   AS read_type\nFROM social_media.notifications n_unread\nJOIN social_media.notifications n_read\n  ON n_unread.recipient_user_id = n_read.recipient_user_id\nWHERE n_unread.read_at IS NULL\n  AND n_read.read_at IS NOT NULL;"}, {"role": "user", "content": "Actually, only include pairs where the unread notification_type is 'message'."}, {"role": "assistant", "content": "SELECT\n  n_unread.recipient_user_id,\n  n_unread.notification_id   AS unread_id,\n  n_unread.notification_type AS unread_type,\n  n_read.notification_id     AS read_id,\n  n_read.notification_type   AS read_type\nFROM social_media.notifications n_unread\nJOIN social_media.notifications n_read\n  ON n_unread.recipient_user_id = n_read.recipient_user_id\nWHERE n_unread.read_at IS NULL\n  AND n_read.read_at IS NOT NULL\n  AND n_unread.notification_type = 'message';"}], "system": "You are an SQL statement expert. Given the table structure 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.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) )\n"}
{"conversations": [{"role": "user", "content": "List all applications that have at least one document with a verification status of 'Verified'. Show the application reference number and the name of the service associated with the application."}, {"role": "assistant", "content": "SELECT\n  T1.reference_number,\n  T2.service_name\nFROM government_services.applications AS T1\nINNER JOIN government_services.services AS T2\n  ON T1.service_id = T2.service_id\nWHERE EXISTS (\n  SELECT\n    1\n  FROM government_services.documents AS T3\n  WHERE\n    T3.application_id = T1.application_id AND T3.verification_status = 'Verified'\n);"}, {"role": "user", "content": "Now, only include applications that were submitted in the year 2024."}, {"role": "assistant", "content": "SELECT\n  T1.reference_number,\n  T2.service_name\nFROM government_services.applications AS T1\nINNER JOIN government_services.services AS T2\n  ON T1.service_id = T2.service_id\nWHERE EXISTS (\n  SELECT\n    1\n  FROM government_services.documents AS T3\n  WHERE\n    T3.application_id = T1.application_id AND T3.verification_status = 'Verified'\n)\nAND EXTRACT(YEAR FROM T1.submitted_at) = 2024;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens (\n    citizen_id character varying(64) NOT NULL,  -- unique identifier for the citizen\n    national_id_number character varying(128) NOT NULL UNIQUE, -- official national identification number\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    date_of_birth date NOT NULL,\n    gender character varying(20),\n    primary_address text NOT NULL, -- full primary residential address\n    contact_email character varying(128) UNIQUE,\n    contact_phone character varying(32),\n    registration_date timestamp NOT NULL, -- when the citizen profile was created\n    is_verified boolean DEFAULT false, -- whether identity has been officially verified\n    PRIMARY KEY (citizen_id)\n)\nCREATE TABLE government_services.agencies (\n    agency_id character varying(64) NOT NULL, -- unique identifier for the agency\n    agency_name character varying(255) NOT NULL, -- full name of the government agency\n    jurisdiction_level character varying(50) NOT NULL, -- e.g., Federal, State, County, City\n    primary_contact_email character varying(128),\n    main_phone_number character varying(32),\n    website_url character varying(255),\n    established_date date,\n    parent_agency_id character varying(64), -- FK to self for hierarchical structure\n    PRIMARY KEY (agency_id)\n)\nCREATE TABLE government_services.services (\n    service_id character varying(64) NOT NULL, -- unique identifier for the service\n    agency_id character varying(64) NOT NULL, -- FK to agencies table\n    service_name character varying(255) NOT NULL, -- name of the service (e.g., Driver's License Renewal)\n    description text,\n    category character varying(100), -- e.g., Licensing, Benefits, Taxation, Permits\n    eligibility_criteria text, -- description of who is eligible\n    standard_fee numeric(10, 2) DEFAULT 0.00, -- typical fee for the service\n    average_processing_time_days integer, -- estimated processing time\n    is_active boolean DEFAULT true, -- whether the service is currently offered\n    online_application_url character varying(255),\n    PRIMARY KEY (service_id)\n)\nCREATE TABLE government_services.documents (\n    document_id character varying(64) NOT NULL, -- unique identifier for the document instance\n    application_id character varying(64), -- FK to applications table (optional, could be linked to citizen directly)\n    citizen_id character varying(64) NOT NULL, -- FK to citizens table\n    document_type character varying(100) NOT NULL, -- e.g., Passport Scan, Proof of Address, Birth Certificate\n    file_reference text NOT NULL, -- reference to the stored file (e.g., S3 URL, internal path)\n    upload_timestamp timestamp NOT NULL,\n    expiry_date date,\n    verification_status character varying(30) DEFAULT 'Pending', -- e.g., Pending, Verified, Rejected\n    verified_by_employee_id character varying(64), -- FK to employees table\n    verification_timestamp timestamp,\n    PRIMARY KEY (document_id)\n)\nCREATE TABLE government_services.appointments (\n    appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment\n    citizen_id character varying(64) NOT NULL, -- FK to citizens table\n    employee_id character varying(64), -- FK to employees table (optional, if assigned)\n    location_id character varying(64), -- FK to service_locations table (if physical)\n    service_id character varying(64), -- FK to services table (optional, if related to specific service)\n    scheduled_start_time timestamp NOT NULL,\n    scheduled_end_time timestamp,\n    purpose text NOT NULL, -- reason for the appointment\n    status character varying(30) NOT NULL, -- e.g., Scheduled, Completed, Cancelled, No-Show\n    booking_method character varying(50), -- e.g., Online, Phone, In-Person\n    created_at timestamp NOT NULL, -- when the appointment was booked\n    notes text,\n    PRIMARY KEY (appointment_id)\n)\nCREATE TABLE government_services.notifications (\n    notification_id character varying(64) NOT NULL, -- unique identifier for the notification\n    citizen_id character varying(64) NOT NULL, -- FK to citizens table\n    application_id character varying(64), -- FK to applications table (optional)\n    message_subject character varying(255),\n    message_body text NOT NULL,\n    channel character varying(30) NOT NULL, -- e.g., Email, SMS, Portal Message, Mail\n    sent_at timestamp NOT NULL,\n    status character varying(30) NOT NULL, -- e.g., Queued, Sent, Delivered, Failed, Read\n    related_entity_type character varying(50), -- e.g., Application, Appointment, Document Request\n    related_entity_id character varying(64), -- ID of the related entity\n    PRIMARY KEY (notification_id)\n)\n"}
{"conversations": [{"role": "user", "content": "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": "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 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": "For each route, show the route_number, origin and destination location names with their cities, and the average departure delay (in minutes) for trips where actual_departure was later than scheduled_departure."}, {"role": "assistant", "content": "SELECT r.route_number,\n       lo.name       AS origin_name,\n       lo.city       AS origin_city,\n       ld.name       AS destination_name,\n       ld.city       AS destination_city,\n       AVG(EXTRACT(EPOCH FROM (t.actual_departure - t.scheduled_departure)) / 60) AS avg_delay_minutes\nFROM transportation.routes r\nJOIN transportation.trips t\n  ON r.route_id = t.route_id\nJOIN transportation.locations lo\n  ON r.origin_location_id = lo.location_id\nJOIN transportation.locations ld\n  ON r.destination_location_id = ld.location_id\nWHERE t.actual_departure > t.scheduled_departure\nGROUP BY r.route_number, origin_name, origin_city, destination_name, destination_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.vehicles (\n    vehicle_id character varying(64) NOT NULL,  -- unique identifier for the vehicle\n    license_plate character varying(32) NOT NULL UNIQUE, -- vehicle license plate\n    vin character varying(17) UNIQUE, -- vehicle identification number\n    make character varying(64) NOT NULL, -- manufacturer of the vehicle\n    model character varying(64) NOT NULL, -- model of the vehicle\n    year integer NOT NULL, -- manufacturing year\n    type character varying(32) NOT NULL, -- type of vehicle (e.g., Bus, Train, Truck, Car, Van)\n    capacity integer, -- passenger or cargo capacity\n    fuel_type character varying(32) NOT NULL, -- e.g., Diesel, Gasoline, Electric, Hydrogen\n    status character varying(32) NOT NULL, -- e.g., Active, Maintenance, Decommissioned\n    depot_id character varying(64), -- identifier of the home depot/base\n    acquisition_date date, -- date the vehicle was acquired\n    PRIMARY KEY (vehicle_id)\n)\nCREATE TABLE transportation.drivers ( driver_id character varying(64) NOT NULL, employee_id character varying(64) NOT NULL UNIQUE, first_name character varying(128) NOT NULL, last_name character varying(128) NOT NULL, license_number character varying(64) NOT NULL UNIQUE, license_expiry_date date NOT NULL, contact_number character varying(32), email character varying(128) UNIQUE, hire_date date NOT NULL, status character varying(32) NOT NULL, PRIMARY KEY (driver_id) )\nCREATE TABLE transportation.routes ( route_id text, route_number text, description text, origin_location_id text, destination_location_id text, distance_km numeric, estimated_duration_minutes integer, type text )\nCREATE TABLE transportation.trips (\n    trip_id character varying(64) NOT NULL,  -- unique identifier for a specific trip instance\n    route_id character varying(64), -- identifier of the route being followed (can be null for ad-hoc trips)\n    vehicle_id character varying(64) NOT NULL, -- identifier of the vehicle used\n    driver_id character varying(64) NOT NULL, -- identifier of the driver operating\n    scheduled_departure timestamp with time zone NOT NULL, -- planned departure time\n    actual_departure timestamp with time zone, -- actual departure time\n    scheduled_arrival timestamp with time zone NOT NULL, -- planned arrival time\n    actual_arrival timestamp with time zone, -- actual arrival time\n    origin_location_id character varying(64) NOT NULL, -- actual starting location (could differ from route origin)\n    destination_location_id character varying(64) NOT NULL, -- actual ending location (could differ from route destination)\n    status character varying(32) NOT NULL, -- e.g., Scheduled, In Progress, Completed, Delayed, Cancelled\n    passenger_count integer, -- number of passengers (if applicable)\n    cargo_manifest_id character varying(64), -- link to cargo details (if applicable)\n    PRIMARY KEY (trip_id)\n)\nCREATE TABLE transportation.locations ( location_id.text, name.text, type.text, address_line1.text, city.text, state_province.text, postal_code.text, country.text, latitude.numeric, longitude.numeric, timezone.text )\nCREATE TABLE transportation.passengers ( passenger_id text PRIMARY KEY, first_name text, last_name text, email text, phone_number text, date_of_birth date, loyalty_program_id text, created_at timestamp )\nCREATE TABLE transportation.bookings (\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 WHERE tm.is_erc20 = 1 ORDER BY CAST(tm.total_supply AS decimal) DESC LIMIT 5;"}, {"role": "user", "content": "I think there's a typo in your query - it should be 'total_supply' not 'total_supply'. Also, can you join this with the token_prices_latest table to include the current price of each token?"}, {"role": "assistant", "content": "SELECT tm.name, tm.contract_address, tm.total_supply, tpl.price FROM token_metas tm JOIN token_prices_latest tpl ON tm.contract_address = tpl.address WHERE tm.is_erc20 = 1 AND tpl.price > 0.10 ORDER BY CAST(tm.total_supply AS decimal) DESC LIMIT 5;"}, {"role": "user", "content": "The token_prices_latest table isn't in the schema. Can you modify the query to use the erc20_balances table instead to show the total balance held across all wallets for each token?"}, {"role": "assistant", "content": "SELECT tm.name, tm.contract_address, tm.total_supply, SUM(CAST(eb.amount AS decimal)) AS total_balance FROM token_metas tm JOIN erc20_balances eb ON tm.contract_address = eb.contract_address WHERE tm.is_erc20 = 1 GROUP BY tm.name, tm.contract_address, tm.total_supply ORDER BY CAST(tm.total_supply AS decimal) DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas (\n    block_timestamp timestamp(6) NOT NULL,  -- Timestamp of the block when token metadata was recorded\n    block_number bigint NOT NULL, -- Block number uniquely identifying the block\n    transaction_hash varchar NOT NULL, -- Hash value of the transaction\n    transaction_index bigint NOT NULL, -- Index of the transaction within the block\n    from_address varchar NOT NULL, -- Address from which the transaction originated\n    contract_address varchar NOT NULL, -- Address of the token contract\n    symbol varchar NOT NULL, -- Symbol of the token\n    total_supply varchar NOT NULL, -- erc20 contract total supply\n    name varchar NOT NULL, -- Name of the token\n    decimals bigint NOT NULL, -- Number of decimal places for the token\n    is_erc20 integer NOT NULL, -- Flag indicating if the token is an ERC-20 token (0 or 1)\n    is_erc721 integer NOT NULL, -- Flag indicating if the token is an ERC-721 token (0 or 1)\n    is_erc1155 integer NOT NULL, -- Flag indicating if the token is an ERC-1155 token (0 or 1)\n    is_proxy integer NOT NULL, -- Flag indicating if the token is a proxy (0 or 1)\n    extra_info varchar NOT NULL, -- Additional information about the token\n    pk integer NOT NULL  -- Partition key for the table(floor(block_number / 5760))\n)\nCREATE TABLE erc1155_approval_for_all (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the transaction\n    transaction_index integer NOT NULL, -- Index of the transaction within the block\n    transaction_hash varchar(66) NOT NULL, -- Transaction hash\n    log_index integer NOT NULL, -- Log index\n    contract_address varchar(42) NOT NULL  -- Event contract address\n)\nCREATE TABLE erc20_balances ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE erc20_balances_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_holders (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    contract_address varchar NOT NULL, -- Event contract address\n    wallet_address varchar NOT NULL, -- The wallet address for the contract(with bloom filter)\n    token_id varchar NOT NULL, -- NFT token id\n    contract_type varchar NOT NULL, -- NFT contract type\n    amount varchar NOT NULL, -- Number of held NFTs\n    pk varchar NOT NULL  -- The last string partition of the contract.\n)\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_nfts ( object_id text, status text, collection_type text, package_id text, previous_transaction text, display text, owner text, name text )\nCREATE TABLE nft_metadata ( blockchain text, contract_address text, token_id text, contract_name text, erc_type text, amount bigint, minter text, owner text, mint_block_number bigint, mint_time bigint, mint_transaction_hash text, mint_price text, token_uri text, metadata text, name text, image_uri text, traits text, updated_at bigint, status text, rarity_score real, rarity_rank integer, unique_attribute_count integer, pk integer )\nCREATE TABLE erc20_approval ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash text, log_index integer, contract_address text, pk integer )\nCREATE TABLE token_info (\n    block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n    block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n    tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n    tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n    tick varchar NOT NULL, -- Token tick\n    max_supply decimal(38,0) NOT NULL, -- Max supply\n    lim decimal(38,0) NOT NULL, -- Limit of each mint\n    wlim decimal(38,0) NOT NULL, -- Limit of each address can maximum mint\n    dec integer NOT NULL, -- Decimal for minimum divie\n    creator varchar(42) NOT NULL  -- Address originating the inscription (matches from_address in transactions table)\n)\nCREATE TABLE token_activities (\n    block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n    block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n    tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n    tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n    log_index integer NOT NULL, -- Index of the log within the transaction\n    type varchar NOT NULL, -- mint | transfer | burn\n    tick varchar NOT NULL, -- Token tick\n    id varchar(255) NOT NULL, -- Unique identifier of the inscription\n    amt decimal(38,0) NOT NULL, -- Mint amount\n    from_address varchar(42) NOT NULL, -- Address sending the inscription (matches from_address in transactions table)\n    to_address varchar(42) NOT NULL  -- Address receiving the inscription (match to_address in transactions table)\n)\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_activities_avalanche ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\n"}
{"conversations": [{"role": "user", "content": "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": "I want to find total PNL and average ROI of smart money token performance for each narrative category. Only include narratives with average ROI greater than 0.5."}, {"role": "assistant", "content": "SELECT bi.narrative,\n       SUM(smtp.pnl)       AS total_pnl,\n       AVG(smtp.roi)       AS avg_roi\nFROM smart_money_token_performance AS smtp\nJOIN token_basic_info AS bi\n  ON smtp.token_symbol = bi.token_symbol\nGROUP BY bi.narrative\nHAVING AVG(smtp.roi) > 0.5;"}, {"role": "user", "content": "Exclude narratives with total net_flow below zero and show only the top 3 narratives by total PNL."}, {"role": "assistant", "content": "SELECT bi.narrative,\n       SUM(smtp.pnl)       AS total_pnl,\n       AVG(smtp.roi)       AS avg_roi,\n       SUM(smtp.net_flow)  AS total_net_flow\nFROM smart_money_token_performance AS smtp\nJOIN token_basic_info AS bi\n  ON smtp.token_symbol = bi.token_symbol\nGROUP BY bi.narrative\nHAVING AVG(smtp.roi) > 0.5\n   AND SUM(smtp.net_flow) >= 0\nORDER BY total_pnl DESC\nLIMIT 3;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE project_fundraising_record ( id.text, project_id.text, project_name.text, rounds_name.text, investment_value.numeric, investment_date.text, introduction.text, valuation.numeric )\nCREATE TABLE token_basic_info ( coin_id.text, token_name.text, token_symbol.text, token_address.text, chain.text, price.numeric, price_change_percentage_1h.numeric, price_change_percentage_24h.numeric, price_change_percentage_7d.numeric, highest_price_24h.numeric, lowest_price_24h.numeric, market_cap.numeric, market_cap_rank.numeric, market_cap_change_percentage_24h.text, total_volume.text, narrative.text, trend_rank.numeric )\nCREATE TABLE token_dexpool_info ( pair_address.text, token_name.text, token_symbol.text, chain.text, price.numeric, price_change_percentage_1h.numeric, price_change_percentage_6h.numeric, price_change_percentage_24h.numeric, makers_24h.numeric, volume_24h.numeric, liquidity.numeric, market_cap.numeric, trend_rank.numeric )\nCREATE TABLE cex_token_balance ( snapshot_time.text, chain.text, address.text, exchange.text, token_address.text, token_symbol.text, balance.numeric, usd_value.numeric, price.numeric )\nCREATE TABLE smart_money_token_performance ( token_address.text, token_symbol.text, pnl.numeric, net_flow.numeric, avg_cost.numeric, price.numeric, realized_ratio.numeric, roi.numeric, chain.text )\n"}
{"conversations": [{"role": "user", "content": "I want to list all insurance plans along with the number of medical records that have a record_date in 2024. Display plan_id, plan_name, and the total medical records."}, {"role": "assistant", "content": "SELECT ip.plan_id, ip.plan_name, COUNT(mr.record_id) AS total_medical_records\nFROM healthcare.insurance_plans ip\nLEFT JOIN healthcare.medical_records mr ON 1=0 -- there is no direct relationship in schema, so no records will be counted\nWHERE mr.record_date >= '2024-01-01' AND mr.record_date < '2025-01-01'\nGROUP BY ip.plan_id, ip.plan_name;"}, {"role": "user", "content": "Since there's no direct relationship, can you adjust it to just show all insurance plans of type 'EPO' with their plan_id and plan_name?"}, {"role": "assistant", "content": "SELECT plan_id, plan_name\nFROM healthcare.insurance_plans\nWHERE plan_type = 'EPO';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.medical_records (\n    record_id character varying(64) NOT NULL,  -- unique identifier for the medical record entry\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    appointment_id character varying(64) UNIQUE, -- FK to appointments table (can be null if record not tied to specific appt)\n    doctor_id character varying(64) NOT NULL, -- FK to doctors table (doctor creating the record)\n    record_date timestamp with time zone NOT NULL, -- date the record/observation was made\n    chief_complaint text, -- patient's primary reason for visit\n    present_illness_history text, -- detailed history of the current issue\n    past_medical_history text, -- relevant past conditions/surgeries\n    physical_examination_notes text, -- findings from the physical exam\n    assessment text, -- doctor's assessment/diagnosis summary\n    treatment_plan text, -- planned course of action\n    vitals jsonb, -- store vitals like BP, HR, Temp as structured JSON\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (record_id)\n)\nCREATE TABLE healthcare.insurance_plans ( plan_id text, plan_name text, insurance_provider text, plan_type text, contact_phone text, website text )\n"}
{"conversations": [{"role": "user", "content": "For each user, show their username and the timestamp of their most recent notification. Include users who have never received notifications."}, {"role": "assistant", "content": "SELECT T1.username, max(T2.sent_at) FROM users AS T1 LEFT JOIN trading_platform.notifications AS T2 ON T1.user_id = T2.user_id GROUP BY T1.username"}, {"role": "user", "content": "Could you also include the total number of notifications for each user?"}, {"role": "assistant", "content": "SELECT T1.username, count(T2.notification_id), max(T2.sent_at) FROM users AS T1 LEFT JOIN trading_platform.notifications AS T2 ON T1.user_id = T2.user_id GROUP BY T1.username"}, {"role": "user", "content": "Actually, only show users whose latest notification is unread."}, {"role": "assistant", "content": "WITH LatestNotification AS ( SELECT user_id, sent_at, read_at, ROW_NUMBER() OVER(PARTITION BY user_id ORDER BY sent_at DESC) AS rn FROM trading_platform.notifications ) SELECT T1.username, T2.sent_at FROM users AS T1 JOIN LatestNotification AS T2 ON T1.user_id = T2.user_id WHERE T2.rn = 1 AND T2.read_at IS NULL"}, {"role": "user", "content": "Also, include the count of unread notifications for these users."}, {"role": "assistant", "content": "WITH LatestNotification AS ( SELECT user_id, sent_at, read_at, ROW_NUMBER() OVER(PARTITION BY user_id ORDER BY sent_at DESC) AS rn FROM trading_platform.notifications ) SELECT T1.username, count(CASE WHEN T3.read_at IS NULL THEN T3.notification_id ELSE NULL END), T2.sent_at FROM users AS T1 JOIN LatestNotification AS T2 ON T1.user_id = T2.user_id AND T2.rn = 1 AND T2.read_at IS NULL JOIN trading_platform.notifications AS T3 ON T1.user_id = T3.user_id GROUP BY T1.username, T2.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, user_id.text, message.text, sent_at.timestamp, read_at.timestamp )\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": "How many events were emitted on each date? List the date and the count of events."}, {"role": "assistant", "content": "SELECT DATE(emitted_at) AS emit_date,\n       COUNT(*) AS event_count\nFROM web3.events\nGROUP BY DATE(emitted_at);"}, {"role": "user", "content": "Actually, only include dates where more than 10 events were emitted."}, {"role": "assistant", "content": "SELECT DATE(emitted_at) AS emit_date,\n       COUNT(*) AS event_count\nFROM web3.events\nGROUP BY DATE(emitted_at)\nHAVING COUNT(*) > 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.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": "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": "List all pairs of contracts that were deployed on the same calendar day but on different network IDs. Show the deployment date, the contract addresses, and the network IDs for both contracts in each pair."}, {"role": "assistant", "content": "SELECT DATE(c1.deployed_at) AS deployment_date, c1.address AS contract1_address, c2.address AS contract2_address, c1.network_id AS contract1_network, c2.network_id AS contract2_network FROM web3.contracts c1 JOIN web3.contracts c2 ON DATE(c1.deployed_at) = DATE(c2.deployed_at) AND c1.network_id != c2.network_id WHERE c1.contract_id < c2.contract_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.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": "Could you provide a summary of the total balance for each account type?"}, {"role": "assistant", "content": "SELECT account_type, SUM(balance) FROM financial_services.accounts GROUP BY account_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 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.trades ( trade_id text, account_id text, security_id text, order_id text, trade_type text, quantity numeric, price_per_unit numeric, total_amount numeric, commission numeric, trade_timestamp timestamp, settlement_date date, status text, execution_venue text )\n"}
{"conversations": [{"role": "user", "content": "Show the name of each agency and whether it operates at least one service location marked as accessible."}, {"role": "assistant", "content": "SELECT T1.agency_name FROM government_services.agencies AS T1 JOIN government_services.service_locations AS T2 ON T1.agency_id = T2.agency_id WHERE T2.is_accessible = TRUE GROUP BY T1.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 (\n    agency_id character varying(64) NOT NULL, -- unique identifier for the agency\n    agency_name character varying(255) NOT NULL, -- full name of the government agency\n    jurisdiction_level character varying(50) NOT NULL, -- e.g., Federal, State, County, City\n    primary_contact_email character varying(128),\n    main_phone_number character varying(32),\n    website_url character varying(255),\n    established_date date,\n    parent_agency_id character varying(64), -- FK to self for hierarchical structure\n    PRIMARY KEY (agency_id)\n)\nCREATE TABLE government_services.services (\n    service_id character varying(64) NOT NULL, -- unique identifier for the service\n    agency_id character varying(64) NOT NULL, -- FK to agencies table\n    service_name character varying(255) NOT NULL, -- name of the service (e.g., Driver's License Renewal)\n    description text,\n    category character varying(100), -- e.g., Licensing, Benefits, Taxation, Permits\n    eligibility_criteria text, -- description of who is eligible\n    standard_fee numeric(10, 2) DEFAULT 0.00, -- typical fee for the service\n    average_processing_time_days integer, -- estimated processing time\n    is_active boolean DEFAULT true, -- whether the service is currently offered\n    online_application_url character varying(255),\n    PRIMARY KEY (service_id)\n)\nCREATE TABLE government_services.service_locations (\n    location_id character varying(64) NOT NULL, -- unique identifier for the physical location\n    agency_id character varying(64) NOT NULL, -- FK to agencies table\n    location_name character varying(200), -- e.g., Downtown DMV Office\n    address text NOT NULL,\n    city character varying(100),\n    state character varying(50),\n    postal_code character varying(20),\n    latitude numeric(9, 6),\n    longitude numeric(9, 6),\n    operating_hours text, -- description of opening times\n    contact_phone character varying(32),\n    is_accessible boolean, -- accessibility information (e.g., wheelchair access)\n    PRIMARY KEY (location_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Could you list the name, type, and rarity for all in-game items that belong to games released on or after January 1st, 2022?"}, {"role": "assistant", "content": "SELECT ii.item_name, ii.item_type, ii.rarity FROM gaming_technology.in_game_items AS ii JOIN gaming_technology.games AS g ON ii.game_id = g.game_id WHERE g.release_date >= '2022-01-01';"}, {"role": "user", "content": "Now, only include items that have a 'Epic' or 'Legendary' rarity."}, {"role": "assistant", "content": "SELECT ii.item_name, ii.item_type, ii.rarity FROM gaming_technology.in_game_items AS ii JOIN gaming_technology.games AS g ON ii.game_id = g.game_id WHERE g.release_date >= '2022-01-01' AND ii.rarity IN ('Epic', 'Legendary');"}, {"role": "user", "content": "Please also include the title of the game for each item and order the list by rarity ascending, then by item name ascending."}, {"role": "assistant", "content": "SELECT ii.item_name, ii.item_type, ii.rarity, g.title AS game_title FROM gaming_technology.in_game_items AS ii JOIN gaming_technology.games AS g ON ii.game_id = g.game_id WHERE g.release_date >= '2022-01-01' AND ii.rarity IN ('Epic', 'Legendary') ORDER BY ii.rarity ASC, ii.item_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": "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": "Return the count of comments for each hashtag."}, {"role": "assistant", "content": "SELECT ph.hashtag_id,\n       h.tag_name,\n       COUNT(c.comment_id) AS comment_count\nFROM social_media.post_hashtags ph\nJOIN social_media.hashtags h\n  ON ph.hashtag_id = h.hashtag_id\nJOIN social_media.comments c\n  ON ph.post_id = c.post_id\nGROUP BY ph.hashtag_id, h.tag_name;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id text 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 PRIMARY KEY, user_id text, content text, media_url text, media_type text, created_at timestamp, updated_at timestamp, visibility text, location_lat numeric, location_lon numeric )\nCREATE TABLE social_media.comments ( comment_id text PRIMARY KEY, post_id text, user_id text, parent_comment_id text, content text, created_at timestamp, updated_at timestamp )\nCREATE TABLE social_media.likes ( like_id text PRIMARY KEY, user_id text, post_id text, comment_id text, created_at timestamp )\nCREATE TABLE social_media.hashtags ( hashtag_id text PRIMARY KEY, tag_name text, created_at timestamp )\nCREATE TABLE social_media.post_hashtags ( post_hashtag_id text PRIMARY KEY, post_id text, hashtag_id text )\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 PRIMARY KEY, created_at timestamp, last_message_at timestamp, is_group_chat bool, group_name text )\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 PRIMARY KEY, 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 PRIMARY KEY, user_id text, theme text, email_notifications_enabled bool, push_notifications_enabled bool, private_profile bool, updated_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "List all clients along with their case_number and case_type for cases that are currently 'Open'."}, {"role": "assistant", "content": "SELECT c.first_name, c.last_name, c.email, cs.case_number, cs.case_type\nFROM legal_services.clients AS c\nJOIN legal_services.cases AS cs\n  ON c.client_id = cs.client_id\nWHERE cs.status = 'Open';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.clients ( client_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, company_name character varying(200), email character varying(128) UNIQUE NOT NULL, phone character varying(32), address text, date_registered timestamp NOT NULL, status character varying(32) NOT NULL, PRIMARY KEY (client_id) )\nCREATE TABLE legal_services.lawyers ( lawyer_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, bar_number character varying(64) UNIQUE NOT NULL, firm_id character varying(64), email character varying(128) UNIQUE NOT NULL, phone character varying(32), specialization text, hire_date timestamp NOT NULL, is_partner boolean DEFAULT false, PRIMARY KEY (lawyer_id) )\nCREATE TABLE legal_services.law_firms ( firm_id character varying(64) NOT NULL, firm_name character varying(200) NOT NULL, address text NOT NULL, phone character varying(32), website character varying(255), founded_date date, managing_partner_id character varying(64), PRIMARY KEY (firm_id) )\nCREATE TABLE legal_services.cases ( case_id character varying(64) NOT NULL, case_number character varying(100) UNIQUE, case_name text NOT NULL, client_id character varying(64) NOT NULL, lead_lawyer_id character varying(64) NOT NULL, case_type character varying(100) NOT NULL, status character varying(50) NOT NULL, date_opened timestamp NOT NULL, date_closed timestamp, description text, court_jurisdiction character varying(128), PRIMARY KEY (case_id) )\nCREATE TABLE legal_services.documents ( document_id character varying(64) NOT NULL, case_id character varying(64) NOT NULL, document_name character varying(255) NOT NULL, document_type character varying(100), storage_path text NOT NULL, uploaded_by_lawyer_id character varying(64), upload_timestamp timestamp NOT NULL, version integer DEFAULT 1, description text, PRIMARY KEY (document_id) )\nCREATE TABLE legal_services.time_entries ( entry_id character varying(64) NOT NULL, case_id character varying(64) NOT NULL, lawyer_id character varying(64) NOT NULL, date_worked date NOT NULL, hours_spent numeric(5, 2) NOT NULL CHECK (hours_spent > 0), billing_rate numeric(10, 2) NOT NULL, description text NOT NULL, is_billable boolean DEFAULT true, is_billed boolean DEFAULT false, invoice_id character varying(64), created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (entry_id) )\nCREATE TABLE legal_services.appointments ( appointment_id character varying(64) NOT NULL, client_id character varying(64) NOT NULL, lawyer_id character varying(64) NOT NULL, case_id character varying(64), start_time timestamp NOT NULL, end_time timestamp NOT NULL, location text, subject character varying(255), notes text, status character varying(50) NOT NULL, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (appointment_id) )\n"}
{"conversations": [{"role": "user", "content": "Count the number of events for each hour of the day based on the emitted_at timestamp."}, {"role": "assistant", "content": "SELECT EXTRACT(HOUR FROM emitted_at) AS event_hour, COUNT(*) AS event_count FROM web3.events GROUP BY event_hour ORDER BY event_hour;"}, {"role": "user", "content": "Actually, only show hours with more than 100 events."}, {"role": "assistant", "content": "SELECT EXTRACT(HOUR FROM emitted_at) AS event_hour, COUNT(*) AS event_count FROM web3.events GROUP BY event_hour HAVING COUNT(*) > 100 ORDER BY event_hour;"}], "system": "You are an SQL statement expert. Given the table structure 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": "Which NFTs minted in the past 14 days on Ethereum have a rarity_score above 70? For each, show contract address, token ID, name, and minter."}, {"role": "assistant", "content": "SELECT contract_address, token_id, name, minter\nFROM nft_metadata\nWHERE blockchain = 'Ethereum'\n  AND mint_time >= (extract(epoch from now()) - 14*24*60*60)\n  AND rarity_score > 70;"}, {"role": "user", "content": "For these NFTs, can you also include the collection name and symbol by joining with the nft_collections table?"}, {"role": "assistant", "content": "SELECT nm.contract_address, nm.token_id, nm.name, nm.minter, nc.name AS collection_name, nc.symbol\nFROM nft_metadata nm\nJOIN nft_collections nc\n  ON nm.blockchain = nc.blockchain AND nm.contract_address = nc.contract_address\nWHERE nm.blockchain = 'Ethereum'\n  AND nm.mint_time >= (extract(epoch from now()) - 14*24*60*60)\n  AND nm.rarity_score > 70;"}, {"role": "user", "content": "Can you filter only those collections where the erc_type is 'ERC1155'?"}, {"role": "assistant", "content": "SELECT nm.contract_address, nm.token_id, nm.name, nm.minter, nc.name AS collection_name, nc.symbol\nFROM nft_metadata nm\nJOIN nft_collections nc\n  ON nm.blockchain = nc.blockchain AND nm.contract_address = nc.contract_address\nWHERE nm.blockchain = 'Ethereum'\n  AND nm.mint_time >= (extract(epoch from now()) - 14*24*60*60)\n  AND nm.rarity_score > 70\n  AND nc.erc_type = 'ERC1155';"}, {"role": "user", "content": "Now, also include the owner for each NFT, and order the results by rarity_rank ascending."}, {"role": "assistant", "content": "SELECT nm.contract_address, nm.token_id, nm.name, nm.minter, nm.owner, nc.name AS collection_name, nc.symbol\nFROM nft_metadata nm\nJOIN nft_collections nc\n  ON nm.blockchain = nc.blockchain AND nm.contract_address = nc.contract_address\nWHERE nm.blockchain = 'Ethereum'\n  AND nm.mint_time >= (extract(epoch from now()) - 14*24*60*60)\n  AND nm.rarity_score > 70\n  AND nc.erc_type = 'ERC1155'\nORDER BY nm.rarity_rank ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE nft_holders ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, token_id varchar NOT NULL, contract_type varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_coins_metadata (\n    object_id varchar NOT NULL, -- object id of the coin metadata object\n    coin_type varchar NOT NULL, -- coin type, eg. 0x...66::reap_token::REAP_TOKEN\n    status varchar NOT NULL, -- coin status, eg. exists, deleted\n    decimals bigint NOT NULL, -- decimals of the coin\n    description varchar NOT NULL, -- description of the coin\n    icon_url varchar NOT NULL, -- icon url of the coin\n    symbol varchar NOT NULL, -- symbol of the coin\n    name varchar NOT NULL  -- name of the coin\n)\nCREATE TABLE sui_nfts ( object_id text, status text, collection_type text, package_id text, previous_transaction text, display text, owner text, name text )\nCREATE TABLE nft_metadata ( blockchain text, contract_address text, token_id text, contract_name text, erc_type text, amount bigint, minter text, owner text, mint_block_number bigint, mint_time bigint, mint_transaction_hash text, mint_price text, token_uri text, metadata text, name text, image_uri text, traits text, updated_at bigint, status text, rarity_score real, rarity_rank integer, unique_attribute_count integer, pk integer )\nCREATE TABLE nft_collections ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, name varchar NOT NULL, symbol varchar NOT NULL, deploy_block_number bigint NOT NULL, deploy_block_time bigint NOT NULL, erc_type varchar NOT NULL, owner varchar NOT NULL, traits varchar NOT NULL, description varchar NOT NULL, slug varchar NOT NULL, media_info varchar NOT NULL, image_url varchar NOT NULL, banner_image_url varchar NOT NULL, updated_at bigint NOT NULL, banner varchar NOT NULL, token_count bigint NOT NULL, floor_price varchar NOT NULL, floor_price_symbol varchar NOT NULL, floor_price_contract varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_prices ( uuid text, blockchain text, address text, decimals bigint, symbol text, price real, timestamp timestamp )\nCREATE TABLE token_prices_latest (\n    blockchain varchar(36) NOT NULL, -- blockchain fields for the functionType  in contract\n    address varchar(42) NOT NULL, -- address fields for the functionType  in contract\n    decimals bigint NOT NULL, -- decimals fields for the functionType  in contract\n    symbol varchar(36) NOT NULL, -- symbol fields for the functionType  in contract\n    price real NOT NULL, -- price fields for the functionType  in contract\n    timestamp timestamp(6) NOT NULL  -- timestamp fields for the functionType  in contract\n)\nCREATE TABLE erc20_approval ( block_number bigint NOT NULL, block_timestamp timestamp(6) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar NOT NULL, log_index integer NOT NULL, contract_address varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_balances ( block_number.bigint, block_timestamp.timestamp, tick.text, wallet_address.text, total_supply.decimal, amount.decimal )\nCREATE TABLE token_info (\n    block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n    block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n    tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n    tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n    tick varchar NOT NULL, -- Token tick\n    max_supply decimal(38,0) NOT NULL, -- Max supply\n    lim decimal(38,0) NOT NULL, -- Limit of each mint\n    wlim decimal(38,0) NOT NULL, -- Limit of each address can maximum mint\n    dec integer NOT NULL, -- Decimal for minimum divie\n    creator varchar(42) NOT NULL  -- Address originating the inscription (matches from_address in transactions table)\n)\nCREATE TABLE mud_holesky_redstone (\n    address varchar NOT NULL, -- address fields for the functionType  in contract\n    table_id varchar NOT NULL, -- table_id fields for the functionType  in contract\n    key_bytes varchar NOT NULL, -- key_bytes fields for the functionType  in contract\n    key0 varchar NOT NULL, -- key0 fields for the functionType  in contract\n    key1 varchar NOT NULL, -- key1 fields for the functionType  in contract\n    static_data varchar NOT NULL, -- static_data fields for the functionType  in contract\n    encoded_lengths varchar NOT NULL, -- encoded_lengths fields for the functionType  in contract\n    dynamic_data varchar NOT NULL, -- dynamic_data fields for the functionType  in contract\n    is_deleted boolean NOT NULL, -- is_deleted fields for the functionType  in contract\n    block_number bigint NOT NULL, -- Block number uniquely identifying the block\n    log_index bigint NOT NULL  -- Index of the log within the transaction\n)\nCREATE TABLE token_info_bitcoin ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, tick.text, max_supply.decimal, lim.decimal, wlim.decimal, dec.integer, creator.text )\nCREATE TABLE token_activities_avalanche (\n    block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n    block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n    tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n    tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n    log_index integer NOT NULL, -- Index of the log within the transaction\n    type varchar(20) NOT NULL, -- Operation: Type of event (deploy, mint, transfer, list)\n    tick varchar(255) NOT NULL, -- Ticker: Identifier of the inscription\n    id varchar(255) NOT NULL, -- Unique identifier of the inscription\n    amt decimal(38,0) NOT NULL, -- Amount to mint: States the amount of the inscription to operation. When operation is mint, has to be less or equal to \"lim\"\n    from_address varchar(42) NOT NULL, -- Address sending the inscription\n    to_address varchar(42) NOT NULL  -- Address receiving the inscription\n)\nCREATE TABLE token_balances_avalanche ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply decimal, amount decimal )\n"}
{"conversations": [{"role": "user", "content": "For each diagnosis, show the diagnosis code, description, and the full name of the doctor who made the diagnosis."}, {"role": "assistant", "content": "SELECT dgn.diagnosis_code, dgn.description, doc.first_name AS doctor_first_name, doc.last_name AS doctor_last_name\nFROM healthcare.diagnoses dgn\nJOIN healthcare.doctors doc ON dgn.doctor_id = doc.doctor_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients (\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.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 (\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 in-game items that have a 'mana_cost' attribute in their attributes JSON. Show the item ID, item name, and the value of the 'mana_cost'."}, {"role": "assistant", "content": "SELECT item_id, item_name, attributes ->> 'mana_cost' AS mana_cost FROM gaming_technology.in_game_items WHERE attributes ? 'mana_cost'"}, {"role": "user", "content": "Now, only include items where the 'mana_cost' is greater than 50."}, {"role": "assistant", "content": "SELECT item_id, item_name, attributes ->> 'mana_cost' AS mana_cost FROM gaming_technology.in_game_items WHERE attributes ? 'mana_cost' AND (attributes ->> 'mana_cost')::int > 50"}, {"role": "user", "content": "Add the item's rarity and the title of the game it belongs to in the output."}, {"role": "assistant", "content": "SELECT t1.item_id, t1.item_name, t1.rarity, t2.title, t1.attributes ->> 'mana_cost' AS mana_cost FROM gaming_technology.in_game_items AS t1 JOIN gaming_technology.games AS t2 ON t1.game_id = t2.game_id WHERE t1.attributes ? 'mana_cost' AND (t1.attributes ->> 'mana_cost')::int > 50"}, {"role": "user", "content": "Filter the results to only include items from games in the 'Fantasy' genre."}, {"role": "assistant", "content": "SELECT t1.item_id, t1.item_name, t1.rarity, t2.title, t1.attributes ->> 'mana_cost' AS mana_cost FROM gaming_technology.in_game_items AS t1 JOIN gaming_technology.games AS t2 ON t1.game_id = t2.game_id WHERE t1.attributes ? 'mana_cost' AND (t1.attributes ->> 'mana_cost')::int > 50 AND t2.genre = 'Fantasy'"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.games ( game_id uuid PRIMARY KEY, title text, developer_id uuid, publisher_id uuid, genre text, release_date date, description text, platform text, engine text, website text )\nCREATE TABLE gaming_technology.developers ( developer_id uuid PRIMARY KEY, name text, country text, founded_year int, website text, created_at timestamptz )\nCREATE TABLE gaming_technology.game_sessions ( session_id uuid PRIMARY KEY, player_id uuid, game_id uuid, server_id uuid, start_time timestamptz, end_time timestamptz, duration_seconds int, score int, session_data jsonb )\nCREATE TABLE gaming_technology.servers ( server_id uuid PRIMARY KEY, game_id uuid, server_name text, region text, ip_address text, port int, current_players int, max_players int, status text, last_heartbeat timestamptz )\nCREATE TABLE gaming_technology.achievements ( achievement_id uuid PRIMARY KEY, game_id uuid, name text, description text, icon_url text, points int, hidden boolean )\nCREATE TABLE gaming_technology.player_achievements ( player_achievement_id uuid PRIMARY KEY, player_id uuid, achievement_id uuid, unlocked_at timestamptz )\nCREATE TABLE gaming_technology.in_game_items ( item_id uuid PRIMARY KEY, game_id uuid, item_name text, item_type text, description text, rarity text, cost_currency text, cost_amount numeric, attributes jsonb )\nCREATE TABLE gaming_technology.player_inventory ( inventory_id uuid PRIMARY KEY, player_id uuid, item_id uuid, quantity int, acquired_at timestamptz, instance_data jsonb )\n"}
{"conversations": [{"role": "user", "content": "For each chain, which token had the highest number of smart money addresses buying it this week? Show the token symbol and narrative too."}, {"role": "assistant", "content": "SELECT chain, token_symbol, narrative, MAX(address_amount) AS max_buyers FROM smart_money_token_inflow WHERE type = 1 AND DATE_TRUNC('week', CURRENT_DATE) = DATE_TRUNC('week', CURRENT_DATE) GROUP BY chain, token_symbol, narrative;"}, {"role": "user", "content": "I got an error, I think the filter for the week may be wrong. Please revise the query so that it only counts buys from the current week."}, {"role": "assistant", "content": "SELECT chain, token_symbol, narrative, address_amount AS buyers FROM smart_money_token_inflow WHERE type = 1 AND EXTRACT(week FROM CURRENT_DATE) = EXTRACT(week FROM CURRENT_DATE) AND EXTRACT(year FROM CURRENT_DATE) = EXTRACT(year FROM CURRENT_DATE) ORDER BY chain, buyers DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE smart_money_token_inflow ( token_address character varying(100) NOT NULL, -- the token's address token_symbol character varying(100), -- the tokens's symbol token_amount numeric(38,2), -- the absolute value of the amount if user bought minus  the amount user sold of this token usd_value numeric(38,2), -- the absolute usd value of the bought token minus sold token avg_price numeric(38,6), -- the average cost price of user spent on this token type int, -- the direction of the trade on this token. 1 means buying, 2 means selling address_amount integer, -- the amount of the user bought this token narrative character varying(100), -- the category or narrative of the token chain character varying(100), -- the chain that the token resides ,PRIMARY KEY (token_address, chain) )\n"}
{"conversations": [{"role": "user", "content": "What is the average ROI for smart money addresses on the Ethereum chain with a realized profit ratio above 50%?"}, {"role": "assistant", "content": "SELECT AVG(roi) AS average_roi FROM smart_money_profit WHERE chain = 'Ethereum' AND realized_ratio > 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\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": "I need to identify pairs of verified documents submitted by the same citizen. For each pair, display the citizen_id, the earlier document_id with its verification timestamp, and the later document_id with its verification timestamp."}, {"role": "assistant", "content": "SELECT\n  d1.citizen_id,\n  d1.document_id AS earlier_document_id,\n  d1.verification_timestamp AS earlier_verification,\n  d2.document_id AS later_document_id,\n  d2.verification_timestamp AS later_verification\nFROM government_services.documents d1\nJOIN government_services.documents d2\n  ON d1.citizen_id = d2.citizen_id\n  AND d1.verification_timestamp < d2.verification_timestamp\nWHERE d1.verification_status = 'Verified'\n  AND d2.verification_status = 'Verified';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.documents ( document_id character varying(64) NOT NULL, application_id character varying(64), citizen_id character varying(64) NOT NULL, document_type character varying(100) NOT NULL, file_reference text NOT NULL, upload_timestamp timestamp NOT NULL, expiry_date date, verification_status character varying(30) DEFAULT 'Pending', verified_by_employee_id character varying(64), verification_timestamp timestamp, PRIMARY KEY (document_id) )\n"}
{"conversations": [{"role": "user", "content": "Find currently employed employees whose direct manager has been terminated. Display the employee's full name, hire date, manager's full name, and manager's termination date."}, {"role": "assistant", "content": "SELECT e.employee_id,\n       CONCAT(e.first_name, ' ', e.last_name) AS employee_full_name,\n       e.hire_date,\n       CONCAT(m.first_name, ' ', m.last_name) AS manager_full_name,\n       m.termination_date\nFROM government_services.employees e\nJOIN government_services.employees m ON e.manager_employee_id = m.employee_id\nWHERE e.termination_date IS NULL\n  AND m.termination_date 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 ( citizen_id text, national_id_number text, first_name text, last_name text, date_of_birth date, gender text, primary_address text, contact_email text, contact_phone text, registration_date timestamp, is_verified boolean )\nCREATE TABLE government_services.agencies ( agency_id character varying(64) NOT NULL, agency_name character varying(255) NOT NULL, jurisdiction_level character varying(50) NOT NULL, primary_contact_email character varying(128), main_phone_number character varying(32), website_url character varying(255), established_date date, parent_agency_id character varying(64), PRIMARY KEY (agency_id) )\nCREATE TABLE government_services.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 (\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.service_locations ( location_id text PRIMARY KEY, agency_id text, location_name text, address text, city text, state text, postal_code text, latitude numeric, longitude numeric, operating_hours text, contact_phone text, is_accessible boolean )\nCREATE TABLE government_services.appointments ( appointment_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, employee_id character varying(64), location_id character varying(64), service_id character varying(64), scheduled_start_time timestamp NOT NULL, scheduled_end_time timestamp, purpose text NOT NULL, status character varying(30) NOT NULL, booking_method character varying(50), created_at timestamp NOT NULL, notes text, PRIMARY KEY (appointment_id) )\nCREATE TABLE government_services.notifications ( notification_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, application_id character varying(64), message_subject character varying(255), message_body text NOT NULL, channel character varying(30) NOT NULL, sent_at timestamp NOT NULL, status character varying(30) NOT NULL, related_entity_type character varying(50), related_entity_id character varying(64), PRIMARY KEY (notification_id) )\n"}
{"conversations": [{"role": "user", "content": "Show me the top 5 token balances by amount for wallet '0xabc123abcdef' in the erc20_balances table."}, {"role": "assistant", "content": "SELECT contract_address, amount\nFROM erc20_balances\nWHERE wallet_address = '0xabc123abcdef'\nORDER BY CAST(amount AS numeric) DESC\nLIMIT 5;"}, {"role": "user", "content": "Include token symbol and decimals from token_prices_latest by joining on contract_address = address."}, {"role": "assistant", "content": "SELECT eb.contract_address, eb.amount, tpl.symbol, tpl.decimals\nFROM erc20_balances eb\nJOIN token_prices_latest tpl ON eb.contract_address = tpl.address\nWHERE eb.wallet_address = '0xabc123abcdef'\nORDER BY CAST(eb.amount AS numeric) DESC\nLIMIT 5;"}, {"role": "user", "content": "Filter to tokens where the latest price is greater than 1.0."}, {"role": "assistant", "content": "SELECT eb.contract_address, eb.amount, tpl.symbol, tpl.decimals\nFROM erc20_balances eb\nJOIN token_prices_latest tpl ON eb.contract_address = tpl.address\nWHERE eb.wallet_address = '0xabc123abcdef'\n  AND tpl.price > 1.0\nORDER BY CAST(eb.amount AS numeric) DESC\nLIMIT 5;"}, {"role": "user", "content": "Add a computed column usd_value as amount * price."}, {"role": "assistant", "content": "SELECT eb.contract_address,\n       eb.amount,\n       tpl.symbol,\n       tpl.decimals,\n       tpl.price,\n       CAST(eb.amount AS numeric) * tpl.price AS usd_value\nFROM erc20_balances eb\nJOIN token_prices_latest tpl ON eb.contract_address = tpl.address\nWHERE eb.wallet_address = '0xabc123abcdef'\n  AND tpl.price > 1.0\nORDER BY CAST(eb.amount AS numeric) 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 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": "Show me claim_id, incident_date, policy_number, and customer full name for all claims where settlement_amount is null."}, {"role": "assistant", "content": "SELECT c.claim_id, c.incident_date, p.policy_number, cu.first_name || ' ' || cu.last_name AS customer_full_name\nFROM insurance.claims c\nJOIN insurance.policies p ON c.policy_id = p.policy_id\nJOIN insurance.customers cu ON c.customer_id = cu.customer_id\nWHERE c.settlement_amount IS NULL;"}, {"role": "user", "content": "The query should only include claims reported in 2024."}, {"role": "assistant", "content": "SELECT c.claim_id, c.incident_date, p.policy_number, cu.first_name || ' ' || cu.last_name AS customer_full_name\nFROM insurance.claims c\nJOIN insurance.policies p ON c.policy_id = p.policy_id\nJOIN insurance.customers cu ON c.customer_id = cu.customer_id\nWHERE c.settlement_amount IS NULL\n  AND c.incident_date >= '2024-01-01'\n  AND c.incident_date < '2025-01-01';"}, {"role": "user", "content": "Also order the results by incident_date descending and limit the output to the top 10."}, {"role": "assistant", "content": "SELECT c.claim_id, c.incident_date, p.policy_number, cu.first_name || ' ' || cu.last_name AS customer_full_name\nFROM insurance.claims c\nJOIN insurance.policies p ON c.policy_id = p.policy_id\nJOIN insurance.customers cu ON c.customer_id = cu.customer_id\nWHERE c.settlement_amount IS NULL\n  AND c.incident_date >= '2024-01-01'\n  AND c.incident_date < '2025-01-01'\nORDER BY c.incident_date DESC\nLIMIT 10;"}, {"role": "user", "content": "Actually, I need to include the agent_id who sold each policy in the output as well."}, {"role": "assistant", "content": "SELECT c.claim_id, c.incident_date, p.policy_number, cu.first_name || ' ' || cu.last_name AS customer_full_name, p.agent_id\nFROM insurance.claims c\nJOIN insurance.policies p ON c.policy_id = p.policy_id\nJOIN insurance.customers cu ON c.customer_id = cu.customer_id\nWHERE c.settlement_amount IS NULL\n  AND c.incident_date >= '2024-01-01'\n  AND c.incident_date < '2025-01-01'\nORDER BY c.incident_date 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 insurance.customers ( customer_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, ssn_hash character varying(128), address_line1 character varying(255) NOT NULL, address_line2 character varying(255), city character varying(100) NOT NULL, state character varying(50) NOT NULL, zip_code character varying(20) NOT NULL, country character varying(50) NOT NULL DEFAULT 'USA', phone_number character varying(30), email character varying(128) UNIQUE, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, updated_at timestamp, status character varying(20) NOT NULL DEFAULT 'Active', PRIMARY KEY (customer_id) )\nCREATE TABLE insurance.policies ( policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, product_id character varying(64) NOT NULL, agent_id character varying(64), policy_number character varying(100) NOT NULL UNIQUE, start_date date NOT NULL, end_date date NOT NULL, premium_amount numeric(12, 2) NOT NULL, coverage_limit numeric(15, 2) NOT NULL, deductible numeric(10, 2) NOT NULL, status character varying(30) NOT NULL, issued_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, cancellation_date date, cancellation_reason text, PRIMARY KEY (policy_id) )\nCREATE TABLE insurance.claims ( claim_id character varying(64) NOT NULL, policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, incident_date timestamp NOT NULL, reported_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, description text NOT NULL, estimated_loss numeric(15, 2), status character varying(30) NOT NULL, settlement_amount numeric(15, 2), settlement_date date, claim_handler_id character varying(64), police_report_number character varying(100), PRIMARY KEY (claim_id) )\nCREATE TABLE insurance.premium_payments ( payment_id character varying(64) NOT NULL, policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, payment_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, amount_paid numeric(12, 2) NOT NULL, payment_method character varying(50), transaction_reference character varying(128) UNIQUE, due_date date, payment_period_start date, payment_period_end date, status character varying(30) NOT NULL DEFAULT 'Completed', PRIMARY KEY (payment_id) )\nCREATE TABLE insurance.claim_documents ( document_id 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 address, show the total amount contained in UTXOs that have been spent."}, {"role": "assistant", "content": "SELECT address, SUM(amount) FROM utxos WHERE spent = TRUE GROUP BY address;"}, {"role": "user", "content": "Only include addresses where this total spent amount is greater than 500 and order the results by the total amount descending."}, {"role": "assistant", "content": "SELECT address, SUM(amount) FROM utxos WHERE spent = TRUE GROUP BY address HAVING SUM(amount) > 500 ORDER BY SUM(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 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": "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": "Find the product type that has the lowest average base premium among all product types that have at least 5 active products. Display the product type and its average base premium."}, {"role": "assistant", "content": "SELECT product_type, AVG(base_premium) AS average_premium FROM insurance.insurance_products WHERE is_active = TRUE GROUP BY product_type HAVING COUNT(product_id) >= 5 ORDER BY AVG(base_premium) ASC 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 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 individual token holdings by CEX addresses on the 'Arbitrum' chain with a USD value greater than $100,000. Show the exchange, token symbol, and USD value."}, {"role": "assistant", "content": "SELECT exchange, token_symbol, usd_value FROM cex_token_balance WHERE chain = 'Arbitrum' AND usd_value > 100000;"}, {"role": "user", "content": "Can you calculate the total USD value held by all CEXes for *each token* on the 'Arbitrum' chain, considering only holdings greater than $100,000? Show the token symbol and the total USD value."}, {"role": "assistant", "content": "SELECT token_symbol, SUM(usd_value) AS total_usd_value FROM cex_token_balance WHERE chain = 'Arbitrum' AND usd_value > 100000 GROUP BY token_symbol;"}, {"role": "user", "content": "Now, join this with the basic info table to include the token's narrative and its current price."}, {"role": "assistant", "content": "SELECT aggregated_cex.token_symbol, aggregated_cex.total_usd_value, tbi.narrative, tbi.price AS current_price FROM ( SELECT token_symbol, SUM(usd_value) AS total_usd_value FROM cex_token_balance WHERE chain = 'Arbitrum' AND usd_value > 100000 GROUP BY token_symbol ) AS aggregated_cex JOIN token_basic_info AS tbi ON aggregated_cex.token_symbol = tbi.token_symbol AND 'Arbitrum' = tbi.chain;"}, {"role": "user", "content": "Filter these results to only show tokens belonging to the 'DeFi' or 'AI' narratives and order by total USD value descending, showing the top 5."}, {"role": "assistant", "content": "SELECT aggregated_cex.token_symbol, aggregated_cex.total_usd_value, tbi.narrative, tbi.price AS current_price FROM ( SELECT token_symbol, SUM(usd_value) AS total_usd_value FROM cex_token_balance WHERE chain = 'Arbitrum' AND usd_value > 100000 GROUP BY token_symbol ) AS aggregated_cex JOIN token_basic_info AS tbi ON aggregated_cex.token_symbol = tbi.token_symbol AND 'Arbitrum' = tbi.chain WHERE tbi.narrative IN ('DeFi', 'AI') ORDER BY aggregated_cex.total_usd_value DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\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": "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": "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": "Get a count of available rooms per room type across all properties."}, {"role": "assistant", "content": "SELECT T2.type_name, COUNT(T1.room_id) AS available_room_count FROM hospitality_technology.rooms AS T1 INNER JOIN hospitality_technology.room_types AS T2 ON T1.room_type_id = T2.room_type_id WHERE T1.status = 'Available' GROUP BY T2.room_type_id, T2.type_name;"}, {"role": "user", "content": "Filter the results to only include room types with more than 50 available rooms. Also include the average base rate for these types."}, {"role": "assistant", "content": "SELECT T2.type_name, COUNT(T1.room_id) AS available_room_count, AVG(T2.base_rate) AS average_base_rate FROM hospitality_technology.rooms AS T1 INNER JOIN hospitality_technology.room_types AS T2 ON T1.room_type_id = T2.room_type_id WHERE T1.status = 'Available' GROUP BY T2.room_type_id, T2.type_name HAVING COUNT(T1.room_id) > 50;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.properties ( property_id character varying(64) NOT NULL, property_name character varying(255) NOT NULL, address_line1 character varying(255) NOT NULL, address_line2 character varying(255), city character varying(100) NOT NULL, state_province character varying(100), postal_code character varying(20) NOT NULL, country_code character varying(3) NOT NULL, phone_number character varying(30), email_address character varying(255), property_type character varying(50) NOT NULL, star_rating numeric(2,1), timezone character varying(64) NOT NULL, manager_staff_id character varying(64), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (property_id) )\nCREATE TABLE hospitality_technology.rooms ( room_id text, 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 (\n    room_type_id character varying(64) NOT NULL, -- unique identifier for the room type\n    property_id character varying(64) NOT NULL, -- FK to properties table (type might be property-specific)\n    type_name character varying(100) NOT NULL, -- e.g., Standard King, Deluxe Queen, Executive Suite\n    description text, -- description of the room type\n    base_rate numeric(10, 2) NOT NULL, -- standard price per night\n    max_occupancy integer NOT NULL, -- maximum number of guests\n    bed_type character varying(50), -- e.g., King, Queen, 2 Doubles, Twin\n    area_sqft numeric(8,2), -- size of the room in square feet\n    amenities text, -- comma-separated list or JSON of amenities\n    PRIMARY KEY (room_type_id),\n    FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id)\n)\nCREATE TABLE hospitality_technology.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 ( staff_id text, property_id text, first_name text, last_name text, position text, work_email text, work_phone text, hire_date date, termination_date date, is_active boolean, access_level integer, manager_id text, created_at timestamp )\nCREATE TABLE hospitality_technology.services ( service_id 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.text, reservation_id.text, guest_id.text, service_id.text, staff_id_ordered.text, staff_id_delivered.text, order_timestamp.timestamp, delivery_timestamp.timestamp, quantity.integer, unit_price.numeric, total_price.numeric, status.text, notes.text, bill_id.text )\nCREATE TABLE hospitality_technology.payments ( payment_id 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) )\n"}
{"conversations": [{"role": "user", "content": "List the first name, last name, email, and phone number of all clients who have a case of type 'Bankruptcy', along with the name of the case."}, {"role": "assistant", "content": "SELECT T1.first_name ,  T1.last_name ,  T1.email ,  T1.phone ,  T2.case_name FROM legal_services.clients AS T1 JOIN legal_services.cases AS T2 ON T1.client_id  =  T2.client_id WHERE T2.case_type  =  'Bankruptcy'"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.clients ( client_id text PRIMARY KEY, first_name text, last_name text, company_name text, email text UNIQUE, phone text, address text, date_registered timestamp, status text )\nCREATE TABLE legal_services.law_firms (\n    firm_id character varying(64) NOT NULL,  -- unique identifier for the law firm\n    firm_name character varying(200) NOT NULL, -- official name of the law firm\n    address text NOT NULL, -- primary address of the firm\n    phone character varying(32), -- firm's main phone number\n    website character varying(255), -- firm's website URL\n    founded_date date, -- date the firm was established\n    managing_partner_id character varying(64), -- FK to lawyers table (optional)\n    PRIMARY KEY (firm_id)\n)\nCREATE TABLE legal_services.cases ( case_id text, case_number text, case_name text, client_id text, lead_lawyer_id text, case_type text, status text, date_opened timestamp, date_closed timestamp, description text, court_jurisdiction text )\nCREATE TABLE legal_services.time_entries ( entry_id text PRIMARY KEY, case_id text, lawyer_id text, date_worked date, hours_spent numeric, billing_rate numeric, description text, is_billable bool, is_billed bool, invoice_id text, created_at timestamp )\nCREATE TABLE legal_services.appointments ( appointment_id.text, client_id.text, lawyer_id.text, case_id.text, start_time.timestamp, end_time.timestamp, location.text, subject.text, notes.text, status.text, created_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "特定の職種の従業員情報を取得したいです。従業員ID、名前、職種、雇用日を表示してください。"}, {"role": "assistant", "content": "db.employees.find(\n    { job_title: '<specific_job_title>' },\n    { employee_id: 1, first_name: 1, last_name: 1, job_title: 1, hire_date: 1, _id: 0 }\n).sort({ hire_date: -1 })"}, {"role": "user", "content": "雇用日が2020年1月1日以降の従業員だけに絞り込むことはできますか？"}, {"role": "assistant", "content": "db.employees.find(\n    { \n        job_title: '<specific_job_title>',\n        hire_date: { $gte: ISODate('2020-01-01') }\n    },\n    { employee_id: 1, first_name: 1, last_name: 1, job_title: 1, hire_date: 1, _id: 0 }\n).sort({ hire_date: -1 })"}, {"role": "user", "content": "雇用ステータスが「Active」の従業員だけをさらに条件に加えられますか？"}, {"role": "assistant", "content": "db.employees.find(\n    { \n        job_title: '<specific_job_title>',\n        hire_date: { $gte: ISODate('2020-01-01') },\n        employment_status: 'Active'\n    },\n    { employee_id: 1, first_name: 1, last_name: 1, job_title: 1, hire_date: 1, _id: 0 }\n).sort({ hire_date: -1 })"}, {"role": "user", "content": "スキル認定情報も結果に含めてください。"}, {"role": "assistant", "content": "db.employees.find(\n    { \n        job_title: '<specific_job_title>',\n        hire_date: { $gte: ISODate('2020-01-01') },\n        employment_status: 'Active'\n    },\n    { employee_id: 1, first_name: 1, last_name: 1, job_title: 1, hire_date: 1, skill_certifications: 1, _id: 0 }\n).sort({ hire_date: -1 })"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nCollection 'assembly_steps'. Document structure: { _id: <ObjectId (or step_id)>, step_id: String, line_id: String (reference), step_number: NumberInt, step_name: String, description: String, standard_duration_hours: Decimal128, required_skill_level: String, workstation: String }. Required: step_id, line_id, step_number, step_name. Index on line_id, step_number.\nCollection 'employees'. Document structure: { _id: <ObjectId (or employee_id)>, employee_id: String, first_name: String, last_name: String, job_title: String, skill_certifications: [String], hire_date: ISODate, assigned_line_id: String (reference, optional), employment_status: String, supervisor_employee_id: String (reference, optional) }. Required: employee_id, first_name, last_name, job_title, hire_date, employment_status.\n"}
{"conversations": [{"role": "user", "content": "Provide a count of notifications, separated by whether they have been read or not."}, {"role": "assistant", "content": "SELECT CASE WHEN T1.read_at IS NULL THEN 'Unread' ELSE 'Read' END, count(T1.notification_id) FROM trading_platform.notifications AS T1 GROUP BY CASE WHEN T1.read_at IS NULL THEN 'Unread' ELSE 'Read' END"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.notifications ( notification_id.text, user_id.text, message.text, sent_at.timestamp, read_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show me the top 5 addresses with the highest balances, along with their public keys."}, {"role": "assistant", "content": "SELECT address_id, public_key, balance FROM blockchain.addresses ORDER BY balance DESC LIMIT 5;"}, {"role": "user", "content": "Now, join this with another query to show the difference between each address's balance and the average balance of all addresses."}, {"role": "assistant", "content": "SELECT a.address_id, a.public_key, a.balance, (a.balance - (SELECT AVG(balance) FROM blockchain.addresses)) as balance_diff FROM blockchain.addresses a ORDER BY a.balance DESC LIMIT 5;"}, {"role": "user", "content": "Can you modify this to show the percentage difference instead of absolute difference?"}, {"role": "assistant", "content": "SELECT a.address_id, a.public_key, a.balance, ((a.balance - (SELECT AVG(balance) FROM blockchain.addresses))/(SELECT AVG(balance) FROM blockchain.addresses)*100 as balance_pct_diff FROM blockchain.addresses a ORDER BY a.balance DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE blockchain.addresses ( address_id.text, public_key.text, balance.numeric )\n"}
{"conversations": [{"role": "user", "content": "How many distinct ports have been used by peers in the system?"}, {"role": "assistant", "content": "SELECT COUNT(DISTINCT port) AS distinct_port_count\nFROM trading_platform.peers;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.users ( user_id text PRIMARY KEY, username text, email text, password_hash text, created_at timestamp )\nCREATE TABLE trading_platform.wallets (\n    wallet_id character varying(64) NOT NULL,  -- unique identifier for the wallet\n    user_id character varying(64) NOT NULL, -- identifier of the user owning the wallet\n    address character varying(128) NOT NULL, -- address of the wallet\n    private_key text NOT NULL, -- private key of the wallet\n    created_at timestamp NOT NULL, -- time when the wallet was created\n    PRIMARY KEY (wallet_id)\n)\nCREATE TABLE trading_platform.orders ( order_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, wallet_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, order_type character varying(32) NOT NULL, quantity numeric(38,14) NOT NULL, price numeric(38,14) NOT NULL, status character varying(32) NOT NULL, created_at timestamp NOT NULL, PRIMARY KEY (order_id) )\nCREATE TABLE trading_platform.assets (\n    asset_id character varying(64) NOT NULL,  -- unique identifier for the asset\n    name character varying(128) NOT NULL, -- name of the asset\n    symbol character varying(32) NOT NULL, -- symbol of the asset\n    type character varying(32) NOT NULL, -- type of the asset (e.g., cryptocurrency, stock)\n    PRIMARY KEY (asset_id)\n)\nCREATE TABLE trading_platform.utxos (\n    utxo_id character varying(64) NOT NULL,  -- unique identifier for the UTXO\n    transaction_id character varying(64) NOT NULL, -- identifier of the transaction that created the UTXO\n    output_index integer NOT NULL, -- index of the output in the transaction\n    address character varying(128) NOT NULL, -- address that can spend the UTXO\n    amount numeric(38,14) NOT NULL, -- amount of the asset in the UTXO\n    spent boolean NOT NULL, -- whether the UTXO has been spent\n    PRIMARY KEY (utxo_id)\n)\nCREATE TABLE trading_platform.dapps ( dapp_id.text, name.text, description.text, url.text )\nCREATE TABLE trading_platform.peers ( peer_id character varying(64) NOT NULL, ip_address character varying(15) NOT NULL, port integer NOT NULL, last_seen timestamp NOT NULL, PRIMARY KEY (peer_id) )\nCREATE TABLE trading_platform.metadata (\n    metadata_id character varying(64) NOT NULL,  -- unique identifier for the metadata\n    asset_id character varying(64) NOT NULL, -- identifier of the asset the metadata is associated with\n    key character varying(128) NOT NULL, -- key of the metadata\n    value text NOT NULL, -- value of the metadata\n    PRIMARY KEY (metadata_id)\n)\nCREATE TABLE trading_platform.kyc_audit ( kyc_audit_id.text, user_id.text, status.text, reviewed_at.timestamp )\nCREATE TABLE trading_platform.logs (\n    log_id character varying(64) NOT NULL,  -- unique identifier for the log entry\n    user_id character varying(64), -- identifier of the user associated with the log entry\n    action character varying(128) NOT NULL, -- action performed\n    details text NOT NULL, -- details of the action\n    logged_at timestamp NOT NULL, -- time when the log entry was created\n    PRIMARY KEY (log_id)\n)\nCREATE TABLE trading_platform.notifications ( notification_id.text, user_id.text, message.text, sent_at.timestamp, read_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "Find pairs of BUY and SELL trades from the trades table for the same account that occurred on the same settlement_date and had matching quantities."}, {"role": "assistant", "content": "SELECT\n  a.trade_id AS buy_trade_id,\n  b.trade_id AS sell_trade_id,\n  a.account_id,\n  a.settlement_date,\n  a.quantity\nFROM financial_services.trades a\nJOIN financial_services.trades b\n  ON a.account_id = b.account_id\n  AND a.settlement_date = b.settlement_date\n  AND a.quantity = b.quantity\nWHERE a.trade_type = 'BUY'\n  AND b.trade_type = 'SELL';"}, {"role": "user", "content": "Only include pairs where the execution_venue is different between the two trades."}, {"role": "assistant", "content": "SELECT\n  a.trade_id AS buy_trade_id,\n  b.trade_id AS sell_trade_id,\n  a.account_id,\n  a.settlement_date,\n  a.quantity\nFROM financial_services.trades a\nJOIN financial_services.trades b\n  ON a.account_id = b.account_id\n  AND a.settlement_date = b.settlement_date\n  AND a.quantity = b.quantity\nWHERE a.trade_type = 'BUY'\n  AND b.trade_type = 'SELL'\n  AND a.execution_venue <> b.execution_venue;"}, {"role": "user", "content": "Sort the results by account_id ascending and settlement_date descending."}, {"role": "assistant", "content": "SELECT\n  a.trade_id AS buy_trade_id,\n  b.trade_id AS sell_trade_id,\n  a.account_id,\n  a.settlement_date,\n  a.quantity\nFROM financial_services.trades a\nJOIN financial_services.trades b\n  ON a.account_id = b.account_id\n  AND a.settlement_date = b.settlement_date\n  AND a.quantity = b.quantity\nWHERE a.trade_type = 'BUY'\n  AND b.trade_type = 'SELL'\n  AND a.execution_venue <> b.execution_venue\nORDER BY a.account_id ASC, a.settlement_date DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.trades ( trade_id character varying(64) NOT NULL, account_id character varying(64) NOT NULL, security_id character varying(64) NOT NULL, order_id character varying(64), trade_type character varying(10) NOT NULL, quantity numeric(19, 8) NOT NULL, price_per_unit numeric(19, 8) NOT NULL, total_amount numeric(19, 4) NOT NULL, commission numeric(10, 4), trade_timestamp timestamp NOT NULL, settlement_date date, status character varying(32) NOT NULL, execution_venue character varying(100), PRIMARY KEY (trade_id), FOREIGN KEY (account_id) REFERENCES financial_services.accounts(account_id), FOREIGN KEY (security_id) REFERENCES financial_services.securities(security_id) )\nCREATE TABLE financial_services.employees ( employee_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, job_title character varying(100) NOT NULL, department character varying(100), branch_id character varying(64), email character varying(128) NOT NULL UNIQUE, phone_extension character varying(20), hire_date date NOT NULL, termination_date date, manager_id character varying(64), status character varying(32) NOT NULL, PRIMARY KEY (employee_id), FOREIGN KEY (branch_id) REFERENCES financial_services.branches(branch_id), FOREIGN KEY (manager_id) REFERENCES financial_services.employees(employee_id) )\n"}
{"conversations": [{"role": "user", "content": "List all pairs of hashtags that were created on the same date. Show both tag names and the creation date."}, {"role": "assistant", "content": "SELECT a.tag_name AS tag1, b.tag_name AS tag2, a.created_at::date AS created_date\nFROM social_media.hashtags a\nJOIN social_media.hashtags b\n  ON a.created_at::date = b.created_at::date\n  AND a.hashtag_id < b.hashtag_id;"}, {"role": "user", "content": "Actually, only include pairs where both tag names start with the letter 'S'."}, {"role": "assistant", "content": "SELECT a.tag_name AS tag1, b.tag_name AS tag2, a.created_at::date AS created_date\nFROM social_media.hashtags a\nJOIN social_media.hashtags b\n  ON a.created_at::date = b.created_at::date\n  AND a.hashtag_id < b.hashtag_id\nWHERE a.tag_name LIKE 'S%'\n  AND b.tag_name LIKE 'S%';"}], "system": "You are an SQL statement expert. Given the table structure 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.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) )\n"}
{"conversations": [{"role": "user", "content": "Provide a count of how many peers were last seen on each distinct day recorded in the system."}, {"role": "assistant", "content": "SELECT DATE(last_seen), COUNT(*) FROM trading_platform.peers GROUP BY DATE(last_seen) ORDER BY DATE(last_seen);"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.users ( user_id text, username text, email text, password_hash text, created_at timestamp )\nCREATE TABLE trading_platform.wallets ( wallet_id text, user_id text, address text, private_key text, created_at timestamp )\nCREATE TABLE trading_platform.orders ( order_id text, user_id text, wallet_id text, asset_id text, order_type text, quantity numeric, price numeric, status text, created_at timestamp )\nCREATE TABLE trading_platform.trades ( trade_id text, order_id text, buyer_id text, seller_id text, asset_id text, quantity numeric, price numeric, traded_at timestamp )\nCREATE TABLE trading_platform.assets ( asset_id text, name text, symbol text, type text )\nCREATE TABLE trading_platform.utxos ( utxo_id text, transaction_id text, output_index integer, address text, amount numeric, spent boolean )\nCREATE TABLE trading_platform.dapps ( dapp_id text, name text, description text, url text )\nCREATE TABLE trading_platform.peers ( peer_id text, ip_address text, port integer, last_seen timestamp )\nCREATE TABLE trading_platform.kyc_audit ( kyc_audit_id text, user_id text, status text, reviewed_at timestamp )\nCREATE TABLE trading_platform.logs ( log_id text, user_id text, action text, details text, logged_at timestamp )\nCREATE TABLE trading_platform.notifications ( notification_id text, user_id text, message text, sent_at timestamp, read_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "What is the detailed repair history for train number T5678?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide the detailed repair history for train number T5678 as this information is not available in the current database table. The table only includes basic information such as train ID, model, manufacturer, capacity, status, and maintenance dates. For repair history, you may need to consult a different database or 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.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": "Show me all doctors whose first name contains 'an'. Return their doctor ID, full name, and hospital affiliation ID."}, {"role": "assistant", "content": "SELECT doctor_id, first_name, last_name, hospital_affiliation_id\nFROM healthcare.doctors\nWHERE first_name ILIKE '%an%';"}, {"role": "user", "content": "Please also include their specialty, and sort the results by last name and then by doctor ID."}, {"role": "assistant", "content": "SELECT doctor_id, first_name, last_name, hospital_affiliation_id, specialty\nFROM healthcare.doctors\nWHERE first_name ILIKE '%an%'\nORDER BY last_name ASC, doctor_id ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.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 )\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": "Show me the total number of trades and the sum of total_amount for each status in the trades table."}, {"role": "assistant", "content": "SELECT\n  t.status,\n  COUNT(t.trade_id) AS trade_count,\n  SUM(t.total_amount) AS total_amount_by_status\nFROM financial_services.trades t\nGROUP BY t.status;"}, {"role": "user", "content": "Now, only include statuses where trade_count is greater than 100, and restrict to trades executed in the last 30 days."}, {"role": "assistant", "content": "SELECT\n  t.status,\n  COUNT(t.trade_id) AS trade_count,\n  SUM(t.total_amount) AS total_amount_by_status\nFROM financial_services.trades t\nWHERE t.trade_timestamp >= CURRENT_DATE - INTERVAL '30 days'\nGROUP BY t.status\nHAVING COUNT(t.trade_id) > 100;"}, {"role": "user", "content": "Exclude any statuses where the sum of commission is null or less than 1000."}, {"role": "assistant", "content": "SELECT\n  t.status,\n  COUNT(t.trade_id) AS trade_count,\n  SUM(t.total_amount) AS total_amount_by_status,\n  SUM(t.commission) AS total_commission\nFROM financial_services.trades t\nWHERE t.trade_timestamp >= CURRENT_DATE - INTERVAL '30 days'\nGROUP BY t.status\nHAVING COUNT(t.trade_id) > 100\n   AND SUM(t.commission) >= 1000;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.trades ( trade_id character varying(64) NOT NULL, account_id character varying(64) NOT NULL, security_id character varying(64) NOT NULL, order_id character varying(64), trade_type character varying(10) NOT NULL, quantity numeric(19, 8) NOT NULL, price_per_unit numeric(19, 8) NOT NULL, total_amount numeric(19, 4) NOT NULL, commission numeric(10, 4), trade_timestamp timestamp NOT NULL, settlement_date date, status character varying(32) NOT NULL, execution_venue character varying(100), PRIMARY KEY (trade_id), FOREIGN KEY (account_id) REFERENCES financial_services.accounts(account_id), FOREIGN KEY (security_id) REFERENCES financial_services.securities(security_id) )\nCREATE TABLE financial_services.employees ( employee_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, job_title character varying(100) NOT NULL, department character varying(100), branch_id character varying(64), email character varying(128) NOT NULL UNIQUE, phone_extension character varying(20), hire_date date NOT NULL, termination_date date, manager_id character varying(64), status character varying(32) NOT NULL, PRIMARY KEY (employee_id), FOREIGN KEY (branch_id) REFERENCES financial_services.branches(branch_id), FOREIGN KEY (manager_id) REFERENCES financial_services.employees(employee_id) )\n"}
{"conversations": [{"role": "user", "content": "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": "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 each service's name along with the total number of appointments scheduled and the number of unique locations these appointments are scheduled at."}, {"role": "assistant", "content": "SELECT s.service_name, COUNT(a.application_id) AS appointment_count, COUNT(DISTINCT ap.location_id) AS unique_location_count\nFROM government_services.services s\nJOIN government_services.applications a ON s.service_id = a.service_id\nJOIN government_services.appointments ap ON a.application_id = ap.application_id\nGROUP BY s.service_name;"}, {"role": "user", "content": "I got an error: relation 'appointments' does not exist."}, {"role": "assistant", "content": "-- The appointments table is not present in the provided schema. If you want to count by another join, perhaps by documents or payments, please specify.\n-- Alternatively, do you want appointment information replaced with application submissions per service and their associated location from service_locations?\nSELECT s.service_name, COUNT(a.application_id) AS application_count, COUNT(DISTINCT sl.location_id) AS unique_location_count\nFROM government_services.services s\nJOIN government_services.applications a ON s.service_id = a.service_id\nJOIN government_services.service_locations sl ON s.agency_id = sl.agency_id\nGROUP BY s.service_name;"}, {"role": "user", "content": "Show only those services where application_count is greater than 50."}, {"role": "assistant", "content": "SELECT s.service_name, COUNT(a.application_id) AS application_count, COUNT(DISTINCT sl.location_id) AS unique_location_count\nFROM government_services.services s\nJOIN government_services.applications a ON s.service_id = a.service_id\nJOIN government_services.service_locations sl ON s.agency_id = sl.agency_id\nGROUP BY s.service_name\nHAVING COUNT(a.application_id) > 50;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens (\n    citizen_id character varying(64) NOT NULL,  -- unique identifier for the citizen\n    national_id_number character varying(128) NOT NULL UNIQUE, -- official national identification number\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    date_of_birth date NOT NULL,\n    gender character varying(20),\n    primary_address text NOT NULL, -- full primary residential address\n    contact_email character varying(128) UNIQUE,\n    contact_phone character varying(32),\n    registration_date timestamp NOT NULL, -- when the citizen profile was created\n    is_verified boolean DEFAULT false, -- whether identity has been officially verified\n    PRIMARY KEY (citizen_id)\n)\nCREATE TABLE government_services.agencies ( agency_id.text, agency_name.text, jurisdiction_level.text, primary_contact_email.text, main_phone_number.text, website_url.text, established_date.date, parent_agency_id.text )\nCREATE TABLE government_services.services ( service_id text PRIMARY KEY, agency_id text, service_name text, description text, category text, eligibility_criteria text, standard_fee numeric, average_processing_time_days int, is_active boolean, online_application_url text )\nCREATE TABLE government_services.applications ( application_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, service_id character varying(64) NOT NULL, submitted_at timestamp NOT NULL, status character varying(50) NOT NULL, last_updated_at timestamp NOT NULL, assigned_employee_id character varying(64), decision_date date, notes text, reference_number character varying(100) UNIQUE, PRIMARY KEY (application_id) )\nCREATE TABLE government_services.documents ( document_id.text, application_id.text, citizen_id.text, document_type.text, file_reference.text, upload_timestamp.timestamp, expiry_date.date, verification_status.text, verified_by_employee_id.text, verification_timestamp.timestamp )\nCREATE TABLE government_services.payments ( payment_id text, application_id text, citizen_id text, service_id text, amount numeric, currency text, payment_method text, payment_provider_reference text, payment_timestamp timestamp, status text, notes text )\nCREATE TABLE government_services.service_locations (\n    location_id character varying(64) NOT NULL, -- unique identifier for the physical location\n    agency_id character varying(64) NOT NULL, -- FK to agencies table\n    location_name character varying(200), -- e.g., Downtown DMV Office\n    address text NOT NULL,\n    city character varying(100),\n    state character varying(50),\n    postal_code character varying(20),\n    latitude numeric(9, 6),\n    longitude numeric(9, 6),\n    operating_hours text, -- description of opening times\n    contact_phone character varying(32),\n    is_accessible boolean, -- accessibility information (e.g., wheelchair access)\n    PRIMARY KEY (location_id)\n)\nCREATE TABLE government_services.notifications ( notification_id text PRIMARY KEY, citizen_id text, application_id text, message_subject text, message_body text, channel text, sent_at timestamp, status text, related_entity_type text, related_entity_id text )\n"}
{"conversations": [{"role": "user", "content": "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": "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": "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": "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": "List tokens with trend rank 5 or better and a price below $1. Show symbol, price, and trend rank."}, {"role": "assistant", "content": "SELECT token_symbol, price, trend_rank FROM token_dexpool_info WHERE trend_rank IS NOT NULL AND trend_rank <= 5 AND price < 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_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 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 NFT collections where the floor price is greater than 0.5 ETH, including their names and contract addresses."}, {"role": "assistant", "content": "SELECT name, contract_address FROM nft_collections WHERE CAST(floor_price AS decimal) > 0.5 AND floor_price_symbol = 'ETH';"}, {"role": "user", "content": "Can you also include the banner image URL and filter to only show ERC721 collections?"}, {"role": "assistant", "content": "SELECT name, contract_address, banner_image_url FROM nft_collections WHERE CAST(floor_price AS decimal) > 0.5 AND floor_price_symbol = 'ETH' AND erc_type = 'ERC721';"}, {"role": "user", "content": "Now sort these results by floor price in descending order and limit to the top 10."}, {"role": "assistant", "content": "SELECT name, contract_address, banner_image_url FROM nft_collections WHERE CAST(floor_price AS decimal) > 0.5 AND floor_price_symbol = 'ETH' AND erc_type = 'ERC721' ORDER BY CAST(floor_price AS decimal) DESC LIMIT 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( 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 erc20_balances_historical ( block_number bigint, contract_address text, wallet_address text, amount text, pk integer )\nCREATE TABLE sui_coins ( object_id text, status text, coin_type text, balance text, owner text )\nCREATE TABLE sui_coins_metadata ( object_id text, coin_type text, status text, decimals bigint, description text, icon_url text, symbol text, name text )\nCREATE TABLE sui_nfts ( object_id text, status text, collection_type text, package_id text, previous_transaction text, display text, owner text, name text )\nCREATE TABLE nft_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_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_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": "What is the average investment_value and total number of projects for each rounds_name in project_fundraising_record?"}, {"role": "assistant", "content": "SELECT rounds_name,\n       AVG(investment_value) AS avg_investment,\n       COUNT(DISTINCT project_id) AS project_count\nFROM project_fundraising_record\nGROUP BY rounds_name;"}, {"role": "user", "content": "Please show only rounds where project_count > 5, and order by avg_investment descending."}, {"role": "assistant", "content": "SELECT rounds_name,\n       AVG(investment_value) AS avg_investment,\n       COUNT(DISTINCT project_id) AS project_count\nFROM project_fundraising_record\nGROUP BY rounds_name\nHAVING COUNT(DISTINCT project_id) > 5\nORDER BY avg_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 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 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 token_dexpool_info ( pair_address text, token_name text, token_symbol text, chain text, price numeric, price_change_percentage_1h numeric, price_change_percentage_6h numeric, price_change_percentage_24h numeric, makers_24h numeric, volume_24h numeric, liquidity numeric, market_cap numeric, trend_rank numeric )\nCREATE TABLE smart_money_token_performance ( token_address text, token_symbol text, pnl numeric, net_flow numeric, avg_cost numeric, price numeric, realized_ratio numeric, roi numeric, chain text )\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": "List the full names and email addresses of citizens who have submitted an application but have not uploaded any documents for that application. Display the citizen's full name, application_id, and submitted_at."}, {"role": "assistant", "content": "SELECT c.first_name || ' ' || c.last_name AS full_name,\n       c.contact_email,\n       a.application_id,\n       a.submitted_at\nFROM government_services.applications a\nJOIN government_services.citizens c ON a.citizen_id = c.citizen_id\nLEFT JOIN government_services.documents d ON a.application_id = d.application_id\nWHERE d.document_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 government_services.citizens ( citizen_id character varying(64) NOT NULL, national_id_number character varying(128) NOT NULL UNIQUE, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, gender character varying(20), primary_address text NOT NULL, contact_email character varying(128) UNIQUE, contact_phone character varying(32), registration_date timestamp NOT NULL, is_verified boolean DEFAULT false, PRIMARY KEY (citizen_id) )\nCREATE TABLE government_services.agencies ( agency_id 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.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 character varying(64) NOT NULL, application_id character varying(64), citizen_id character varying(64) NOT NULL, document_type character varying(100) NOT NULL, file_reference text NOT NULL, upload_timestamp timestamp NOT NULL, expiry_date date, verification_status character varying(30) DEFAULT 'Pending', verified_by_employee_id character varying(64), verification_timestamp timestamp, PRIMARY KEY (document_id) )\nCREATE TABLE government_services.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": "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 each driver along with the driver_id of the driver who was hired immediately after them."}, {"role": "assistant", "content": "SELECT d1.driver_id AS current_driver_id, d2.driver_id AS next_driver_id FROM transportation.drivers d1 LEFT JOIN transportation.drivers d2 ON d2.hire_date = (SELECT MIN(hire_date) FROM transportation.drivers WHERE hire_date > d1.hire_date);"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.drivers ( driver_id.text, employee_id.text, first_name.text, last_name.text, license_number.text, license_expiry_date.date, contact_number.text, email.text, hire_date.date, status.text )\n"}
{"conversations": [{"role": "user", "content": "Find all medical records where the treatment plan includes 'physical therapy' and the patient has an active primary insurance plan, showing the patient ID, record date, and insurance provider details."}, {"role": "assistant", "content": "SELECT mr.patient_id, mr.record_date, ip.insurance_provider, ip.plan_name, pi.policy_number FROM healthcare.medical_records mr JOIN healthcare.patients p ON mr.patient_id = p.patient_id JOIN healthcare.patient_insurance pi ON p.patient_id = pi.patient_id AND pi.is_primary = true JOIN healthcare.insurance_plans ip ON pi.plan_id = ip.plan_id WHERE mr.treatment_plan LIKE '%physical therapy%' AND (pi.expiration_date IS NULL OR pi.expiration_date > CURRENT_DATE);"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id text, first_name text, last_name text, date_of_birth date, gender text, address text, phone_number text, email text, emergency_contact_name text, emergency_contact_phone text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.appointments ( appointment_id text, patient_id text, doctor_id text, appointment_time timestamp, duration_minutes integer, reason text, status text, location_id text, notes text, created_at timestamp )\nCREATE TABLE healthcare.medical_records ( record_id text PRIMARY KEY, patient_id text, appointment_id text, doctor_id text, record_date timestamp, chief_complaint text, present_illness_history text, past_medical_history text, physical_examination_notes text, assessment text, treatment_plan text, vitals text, created_at timestamp )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id text PRIMARY KEY, record_id text, patient_id text, doctor_id text, diagnosis_code text, code_type text, description text, diagnosis_date date, status text, is_chronic boolean )\nCREATE TABLE healthcare.medications ( medication_id text, medication_name text, generic_name text, manufacturer text, ndc_code text, description text )\nCREATE TABLE healthcare.insurance_plans (\n    plan_id character varying(64) NOT NULL, -- unique identifier for the insurance plan\n    plan_name character varying(200) NOT NULL, -- name of the insurance plan\n    insurance_provider character varying(100) NOT NULL, -- name of the insurance company\n    plan_type character varying(50), -- e.g., PPO, HMO, EPO\n    contact_phone character varying(20), -- provider contact number\n    website character varying(255), -- provider website\n    PRIMARY KEY (plan_id)\n)\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, plan_id character varying(64) NOT NULL, policy_number character varying(100) NOT NULL, group_number character varying(100), subscriber_name character varying(200), effective_date date NOT NULL, expiration_date date, is_primary boolean NOT NULL DEFAULT true, PRIMARY KEY (patient_insurance_id), UNIQUE (patient_id, plan_id, policy_number) )\n"}
{"conversations": [{"role": "user", "content": "For each type of entity a notification can be related to, how many notifications have been successfully sent?"}, {"role": "assistant", "content": "SELECT related_entity_type, COUNT(*) AS sent_notification_count FROM government_services.notifications WHERE status = 'Sent' GROUP BY related_entity_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 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.documents (\n    document_id character varying(64) NOT NULL, -- unique identifier for the document instance\n    application_id character varying(64), -- FK to applications table (optional, could be linked to citizen directly)\n    citizen_id character varying(64) NOT NULL, -- FK to citizens table\n    document_type character varying(100) NOT NULL, -- e.g., Passport Scan, Proof of Address, Birth Certificate\n    file_reference text NOT NULL, -- reference to the stored file (e.g., S3 URL, internal path)\n    upload_timestamp timestamp NOT NULL,\n    expiry_date date,\n    verification_status character varying(30) DEFAULT 'Pending', -- e.g., Pending, Verified, Rejected\n    verified_by_employee_id character varying(64), -- FK to employees table\n    verification_timestamp timestamp,\n    PRIMARY KEY (document_id)\n)\nCREATE TABLE government_services.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 (\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) )\nCREATE TABLE government_services.notifications ( notification_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, application_id character varying(64), message_subject character varying(255), message_body text NOT NULL, channel character varying(30) NOT NULL, sent_at timestamp NOT NULL, status character varying(30) NOT NULL, related_entity_type character varying(50), related_entity_id character varying(64), PRIMARY KEY (notification_id) )\n"}
{"conversations": [{"role": "user", "content": "List each comment_id and the number of likes it has received, but only include comments with at least 5 likes, ordered by like_count ascending."}, {"role": "assistant", "content": "SELECT l.comment_id, COUNT(*) AS like_count\nFROM social_media.likes l\nWHERE l.comment_id IS NOT NULL\nGROUP BY l.comment_id\nHAVING COUNT(*) >= 5\nORDER BY like_count ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.comments ( comment_id text PRIMARY KEY, post_id text, user_id text, parent_comment_id text, content text, created_at timestamp, updated_at timestamp )\nCREATE TABLE social_media.likes ( like_id 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.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 PRIMARY KEY, 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 ticket price for a journey on train number T4321?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to information about ticket prices for specific trains. The data I have is limited to train details such as model, manufacturer, capacity, and maintenance schedules. For ticket pricing, please consult the ticketing office or the official website."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.trains ( train_id text PRIMARY KEY, train_number text UNIQUE, model text, manufacturer text, year_manufactured int, capacity int, status text, last_maintenance_date date, next_maintenance_date date )\n"}
{"conversations": [{"role": "user", "content": "List all pairs of law firms that were founded on the same month and day, showing their names, and the shared founding date. Exclude firms founded on January 1st."}, {"role": "assistant", "content": "SELECT t1.firm_name AS firm1_name, t2.firm_name AS firm2_name, t1.founded_date FROM legal_services.law_firms AS t1 JOIN legal_services.law_firms AS t2 ON MONTH(t1.founded_date) = MONTH(t2.founded_date) AND DAY(t1.founded_date) = DAY(t2.founded_date) AND t1.firm_id < t2.firm_id WHERE MONTH(t1.founded_date) <> 1 OR DAY(t1.founded_date) <> 1;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.law_firms ( firm_id character varying(64) NOT NULL, firm_name character varying(200) NOT NULL, address text NOT NULL, phone character varying(32), website character varying(255), founded_date date, managing_partner_id character varying(64), PRIMARY KEY (firm_id) )\n"}
{"conversations": [{"role": "user", "content": "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": "Show me all time entries, including the case name they are associated with."}, {"role": "assistant", "content": "SELECT T1.*, T2.case_name FROM time_entries AS T1 JOIN cases AS T2 ON T1.case_id = T2.case_id"}, {"role": "user", "content": "Only show me time entries for lawyer with ID 'lawyer_789'."}, {"role": "assistant", "content": "SELECT T1.*, T2.case_name FROM time_entries AS T1 JOIN cases AS T2 ON T1.case_id = T2.case_id WHERE T1.lawyer_id = 'lawyer_789'"}, {"role": "user", "content": "Actually, I only want entries for the date '2024-07-30', and just show the entry description, hours spent, and case name."}, {"role": "assistant", "content": "SELECT T1.description, T1.hours_spent, T2.case_name FROM time_entries AS T1 JOIN cases AS T2 ON T1.case_id = T2.case_id WHERE T1.lawyer_id = 'lawyer_789' AND T1.date_worked = '2024-07-30'"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.cases ( case_id.text, case_number.text, case_name.text, client_id.text, lead_lawyer_id.text, case_type.text, status.text, date_opened.timestamp, date_closed.timestamp, description.text, court_jurisdiction.text )\nCREATE TABLE legal_services.time_entries (\n    entry_id character varying(64) NOT NULL,  -- unique identifier for the time entry\n    case_id character varying(64) NOT NULL, -- FK to cases table\n    lawyer_id character varying(64) NOT NULL, -- FK to lawyers table (who performed the work)\n    date_worked date NOT NULL, -- date the work was performed\n    hours_spent numeric(5, 2) NOT NULL CHECK (hours_spent > 0), -- duration of work in hours (e.g., 1.5 for 1h 30m)\n    billing_rate numeric(10, 2) NOT NULL, -- hourly rate applied for this entry\n    description text NOT NULL, -- detailed description of the work performed\n    is_billable boolean DEFAULT true, -- whether this time entry is billable to the client\n    is_billed boolean DEFAULT false, -- whether this entry has been included in an invoice\n    invoice_id character varying(64), -- FK to invoices table (once billed)\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the entry was recorded\n    PRIMARY KEY (entry_id)\n)\nCREATE TABLE legal_services.appointments (\n    appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment\n    client_id character varying(64) NOT NULL, -- FK to clients table\n    lawyer_id character varying(64) NOT NULL, -- FK to lawyers table\n    case_id character varying(64), -- FK to cases table (optional, if related to a specific case)\n    start_time timestamp NOT NULL, -- scheduled start date and time\n    end_time timestamp NOT NULL, -- scheduled end date and time\n    location text, -- location of the meeting (address or virtual link)\n    subject character varying(255), -- subject or purpose of the appointment\n    notes text, -- additional notes for the appointment\n    status character varying(50) NOT NULL, -- e.g., Scheduled, Completed, Canceled, Rescheduled\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n    PRIMARY KEY (appointment_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List each employee's first and last name along with the count of active services offered by their agency."}, {"role": "assistant", "content": "SELECT e.first_name, e.last_name, COUNT(s.service_id) AS active_service_count\nFROM government_services.employees e\nJOIN government_services.services s ON e.agency_id = s.agency_id AND s.is_active = TRUE\nGROUP BY e.employee_id, e.first_name, e.last_name;"}, {"role": "user", "content": "Actually, only include employees whose service count is greater than 5."}, {"role": "assistant", "content": "SELECT e.first_name, e.last_name, COUNT(s.service_id) AS active_service_count\nFROM government_services.employees e\nJOIN government_services.services s ON e.agency_id = s.agency_id AND s.is_active = TRUE\nGROUP BY e.employee_id, e.first_name, e.last_name\nHAVING COUNT(s.service_id) > 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id character varying(64) NOT NULL, national_id_number character varying(128) NOT NULL UNIQUE, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, gender character varying(20), primary_address text NOT NULL, contact_email character varying(128) UNIQUE, contact_phone character varying(32), registration_date timestamp NOT NULL, is_verified boolean DEFAULT false, PRIMARY KEY (citizen_id) )\nCREATE TABLE government_services.agencies ( agency_id character varying(64) NOT NULL, agency_name character varying(255) NOT NULL, jurisdiction_level character varying(50) NOT NULL, primary_contact_email character varying(128), main_phone_number character varying(32), website_url character varying(255), established_date date, parent_agency_id character varying(64), PRIMARY KEY (agency_id) )\nCREATE TABLE government_services.services ( service_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, service_name character varying(255) NOT NULL, description text, category character varying(100), eligibility_criteria text, standard_fee numeric(10, 2) DEFAULT 0.00, average_processing_time_days integer, is_active boolean DEFAULT true, online_application_url character varying(255), PRIMARY KEY (service_id) )\nCREATE TABLE government_services.applications ( application_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, service_id character varying(64) NOT NULL, submitted_at timestamp NOT NULL, status character varying(50) NOT NULL, last_updated_at timestamp NOT NULL, assigned_employee_id character varying(64), decision_date date, notes text, reference_number character varying(100) UNIQUE, PRIMARY KEY (application_id) )\nCREATE TABLE government_services.payments ( payment_id character varying(64) NOT NULL, application_id character varying(64), citizen_id character varying(64) NOT NULL, service_id character varying(64), amount numeric(12, 2) NOT NULL, currency character varying(3) NOT NULL DEFAULT 'USD', payment_method character varying(50), payment_provider_reference character varying(128), payment_timestamp timestamp NOT NULL, status character varying(30) NOT NULL, notes text, PRIMARY KEY (payment_id) )\nCREATE TABLE government_services.employees ( employee_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, job_title character varying(150) NOT NULL, department character varying(100), work_email character varying(128) NOT NULL UNIQUE, work_phone character varying(32), hire_date date NOT NULL, termination_date date, access_level character varying(50), manager_employee_id character varying(64), PRIMARY KEY (employee_id) )\nCREATE TABLE government_services.service_locations ( location_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, location_name character varying(200), address text NOT NULL, city character varying(100), state character varying(50), postal_code character varying(20), latitude numeric(9, 6), longitude numeric(9, 6), operating_hours text, contact_phone character varying(32), is_accessible boolean, PRIMARY KEY (location_id) )\nCREATE TABLE government_services.appointments ( appointment_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, employee_id character varying(64), location_id character varying(64), service_id character varying(64), scheduled_start_time timestamp NOT NULL, scheduled_end_time timestamp, purpose text NOT NULL, status character varying(30) NOT NULL, booking_method character varying(50), created_at timestamp NOT NULL, notes text, PRIMARY KEY (appointment_id) )\nCREATE TABLE government_services.notifications ( notification_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, application_id character varying(64), message_subject character varying(255), message_body text NOT NULL, channel character varying(30) NOT NULL, sent_at timestamp NOT NULL, status character varying(30) NOT NULL, related_entity_type character varying(50), related_entity_id character varying(64), PRIMARY KEY (notification_id) )\n"}
{"conversations": [{"role": "user", "content": "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": "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": "Show me wallet addresses that hold more than 1000 of any ERC20 token, along with the token symbol and amount."}, {"role": "assistant", "content": "SELECT eb.wallet_address, tm.symbol, eb.amount FROM erc20_balances eb JOIN token_metas tm ON eb.contract_address = tm.contract_address WHERE CAST(eb.amount AS decimal) > 1000;"}, {"role": "user", "content": "Can you join this with the token_prices_latest table to include the current price of each token and sort the results by amount in descending order?"}, {"role": "assistant", "content": "SELECT eb.wallet_address, tm.symbol, eb.amount, tpl.price FROM erc20_balances eb JOIN token_metas tm ON eb.contract_address = tm.contract_address JOIN token_prices_latest tpl ON eb.contract_address = tpl.address WHERE CAST(eb.amount AS decimal) > 1000 ORDER BY CAST(eb.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 token_metas ( block_timestamp timestamp, block_number bigint, transaction_hash varchar, transaction_index bigint, from_address varchar, contract_address varchar, symbol varchar, total_supply varchar, name varchar, decimals bigint, is_erc20 integer, is_erc721 integer, is_erc1155 integer, is_proxy integer, extra_info varchar, pk integer )\nCREATE TABLE erc1155_approval_for_all (\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 (\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\n    amount varchar NOT NULL, -- Wallet's on-chain balance at the corresponding block height\n    pk varchar NOT NULL  -- The last string partition of the contract.\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, contract_address text, wallet_address text, token_id text, contract_type 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 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_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 (\n    uuid varchar(36) NOT NULL, -- uuid fields for the functionType  in contract\n    blockchain varchar(36) NOT NULL, -- blockchain fields for the functionType  in contract\n    address varchar(42) NOT NULL, -- address fields for the functionType  in contract\n    decimals bigint NOT NULL, -- decimals fields for the functionType  in contract\n    symbol varchar(36) NOT NULL, -- symbol fields for the functionType  in contract\n    price real NOT NULL, -- price fields for the functionType  in contract\n    timestamp timestamp(6) NOT NULL  -- timestamp fields for the functionType  in contract\n)\nCREATE TABLE token_prices_latest ( blockchain text, address text, decimals bigint, symbol text, price real, timestamp timestamp )\nCREATE TABLE token_info ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text )\nCREATE TABLE token_activities ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_balances_bitcoin (\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(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 (\n    block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n    block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n    tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n    tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n    log_index integer NOT NULL, -- Index of the log within the transaction\n    type varchar(20) NOT NULL, -- Operation: Type of event (deploy, mint, transfer, list)\n    tick varchar(255) NOT NULL, -- Ticker: Identifier of the inscription\n    id varchar(255) NOT NULL, -- Unique identifier of the inscription\n    amt decimal(38,0) NOT NULL, -- Amount to mint: States the amount of the inscription to operation. When operation is mint, has to be less or equal to \"lim\"\n    from_address varchar(62) NOT NULL, -- Address sending the inscription\n    to_address varchar(62) NOT NULL  -- Address receiving the inscription\n)\nCREATE TABLE token_activities_avalanche ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\nCREATE TABLE token_balances_avalanche ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar(20) NOT NULL, wallet_address varchar(42) NOT NULL, total_supply decimal(38,0) NOT NULL, amount decimal(38,0) NOT NULL )\nCREATE TABLE token_info_avalanche ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, tick.text, max_supply.decimal, lim.decimal, wlim.decimal, dec.integer, creator.text, minted.decimal, holders.decimal, txs.decimal, updated_timestamp.timestamp, completed_timestamp.timestamp, id.text )\n"}
{"conversations": [{"role": "user", "content": "List all active SUI coins with status 'exists' in metadata, showing coin_type, symbol, name, balance, and description."}, {"role": "assistant", "content": "SELECT sc.coin_type, sm.symbol, sm.name, sc.balance, sm.description\nFROM sui_coins sc\nJOIN sui_coins_metadata sm ON sc.coin_type = sm.coin_type\nWHERE sm.status = 'exists';"}, {"role": "user", "content": "Limit to coins where balance > 1000000 and order by balance descending."}, {"role": "assistant", "content": "SELECT sc.coin_type, sm.symbol, sm.name, sc.balance, sm.description\nFROM sui_coins sc\nJOIN sui_coins_metadata sm ON sc.coin_type = sm.coin_type\nWHERE sm.status = 'exists'\n  AND CAST(sc.balance AS numeric) > 1000000\nORDER BY CAST(sc.balance AS numeric) DESC;"}, {"role": "user", "content": "Also include the number of distinct owners per coin_type."}, {"role": "assistant", "content": "SELECT sc.coin_type, sm.symbol, sm.name, sm.description,\n       SUM(CAST(sc.balance AS numeric)) AS total_balance,\n       COUNT(DISTINCT sc.owner) AS owner_count\nFROM sui_coins sc\nJOIN sui_coins_metadata sm ON sc.coin_type = sm.coin_type\nWHERE sm.status = 'exists'\n  AND CAST(sc.balance AS numeric) > 1000000\nGROUP BY sc.coin_type, sm.symbol, sm.name, sm.description\nORDER BY total_balance DESC;"}, {"role": "user", "content": "Only show the top 3 coins by total_balance."}, {"role": "assistant", "content": "SELECT sc.coin_type, sm.symbol, sm.name, sm.description,\n       SUM(CAST(sc.balance AS numeric)) AS total_balance,\n       COUNT(DISTINCT sc.owner) AS owner_count\nFROM sui_coins sc\nJOIN sui_coins_metadata sm ON sc.coin_type = sm.coin_type\nWHERE sm.status = 'exists'\n  AND CAST(sc.balance AS numeric) > 1000000\nGROUP BY sc.coin_type, sm.symbol, sm.name, sm.description\nORDER BY total_balance DESC\nLIMIT 3;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE erc1155_approval_for_all (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the transaction\n    transaction_index integer NOT NULL, -- Index of the transaction within the block\n    transaction_hash varchar(66) NOT NULL, -- Transaction hash\n    log_index integer NOT NULL, -- Log index\n    contract_address varchar(42) NOT NULL  -- Event contract address\n)\nCREATE TABLE erc20_balances ( block_number bigint, contract_address varchar, wallet_address varchar, amount varchar, pk varchar )\nCREATE TABLE erc20_balances_historical ( block_number bigint, contract_address text, wallet_address text, amount text, pk integer )\nCREATE TABLE nft_holders ( block_number.bigint, contract_address.text, wallet_address.text, token_id.text, contract_type.text, amount.text, pk.text )\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_coins_metadata (\n    object_id varchar NOT NULL, -- object id of the coin metadata object\n    coin_type varchar NOT NULL, -- coin type, eg. 0x...66::reap_token::REAP_TOKEN\n    status varchar NOT NULL, -- coin status, eg. exists, deleted\n    decimals bigint NOT NULL, -- decimals of the coin\n    description varchar NOT NULL, -- description of the coin\n    icon_url varchar NOT NULL, -- icon url of the coin\n    symbol varchar NOT NULL, -- symbol of the coin\n    name varchar NOT NULL  -- name of the coin\n)\nCREATE TABLE token_prices_latest ( blockchain.text, address.text, decimals.bigint, symbol.text, price.real, timestamp.timestamp )\nCREATE TABLE erc20_approval ( block_number.bigint, block_timestamp.timestamp, transaction_index.integer, transaction_hash.text, log_index.integer, contract_address.text, pk.integer )\nCREATE TABLE token_activities ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\nCREATE TABLE token_balances_bitcoin (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n    tick varchar(255) NOT NULL, -- Ticker: Identifier of the inscription\n    wallet_address varchar(42) NOT NULL, -- Address of owner\n    total_supply varchar NOT NULL, -- Max supply: Set max supply of the inscription\n    amount varchar NOT NULL  -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id varchar )\n"}
{"conversations": [{"role": "user", "content": "What is the total USD value of smart money token inflows for each chain?"}, {"role": "assistant", "content": "SELECT chain, SUM(usd_value) AS total_usd_inflow FROM smart_money_token_inflow GROUP BY chain ORDER BY total_usd_inflow DESC;"}, {"role": "user", "content": "Now, show me the total USD inflow for each chain, but only for inflows associated with the 'AI' narrative."}, {"role": "assistant", "content": "SELECT chain, SUM(usd_value) AS total_usd_inflow FROM smart_money_token_inflow WHERE narrative = 'AI' GROUP BY chain ORDER BY total_usd_inflow 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 smart_money_token_inflow ( token_address text, token_symbol text, token_amount numeric, usd_value numeric, avg_price numeric, type numeric, address_amount numeric, narrative text, chain text )\n"}
{"conversations": [{"role": "user", "content": "Show me 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": "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": "Show me all wallet addresses and their private keys for users who have more than 3 wallets."}, {"role": "assistant", "content": "SELECT w.address_id, w.private_key FROM blockchain.wallets w WHERE w.user_id IN (SELECT user_id FROM blockchain.wallets GROUP BY user_id HAVING COUNT(*) > 3);"}, {"role": "user", "content": "Now, filter these results to only show wallets where the private_key starts with '0x1'."}, {"role": "assistant", "content": "SELECT w.address_id, w.private_key FROM blockchain.wallets w WHERE w.user_id IN (SELECT user_id FROM blockchain.wallets GROUP BY user_id HAVING COUNT(*) > 3) AND w.private_key LIKE '0x1%';"}], "system": "You are an SQL statement expert. Given the table structure 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 (\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_id character varying(128) NOT NULL, -- identifier of the address associated with the wallet\n    private_key text NOT NULL, -- private key of the wallet\n    PRIMARY KEY (wallet_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List all pairs of diagnoses that belong to the same medical record. Show record_id, diagnosis_id from the first entry as diag1_id, and diagnosis_id from the second entry as diag2_id."}, {"role": "assistant", "content": "SELECT d1.record_id,\n       d1.diagnosis_id AS diag1_id,\n       d2.diagnosis_id AS diag2_id\nFROM healthcare.diagnoses d1\nJOIN healthcare.diagnoses d2\n  ON d1.record_id = d2.record_id\n AND d1.diagnosis_id < d2.diagnosis_id;"}, {"role": "user", "content": "Only include pairs where both diagnoses are chronic."}, {"role": "assistant", "content": "SELECT d1.record_id,\n       d1.diagnosis_id AS diag1_id,\n       d2.diagnosis_id AS diag2_id\nFROM healthcare.diagnoses d1\nJOIN healthcare.diagnoses d2\n  ON d1.record_id = d2.record_id\n AND d1.diagnosis_id < d2.diagnosis_id\nWHERE d1.is_chronic = TRUE\n  AND d2.is_chronic = TRUE;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.diagnoses (\n    diagnosis_id character varying(64) NOT NULL, -- unique identifier for the diagnosis entry\n    record_id character varying(64) NOT NULL, -- FK linking to the specific medical record entry\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    doctor_id character varying(64) NOT NULL, -- FK to doctors table (diagnosing doctor)\n    diagnosis_code character varying(20) NOT NULL, -- standard code (e.g., ICD-10)\n    code_type character varying(10) NOT NULL DEFAULT 'ICD-10', -- type of code used\n    description text, -- textual description of the diagnosis\n    diagnosis_date date NOT NULL, -- date the diagnosis was made\n    status character varying(32) NOT NULL, -- e.g., Active, Resolved, Ruled Out\n    is_chronic boolean DEFAULT false, -- flag for chronic conditions\n    PRIMARY KEY (diagnosis_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Show the total transfer volume and number of transfers for each Avalanche token in the past 7 days, including token tick and its creator."}, {"role": "assistant", "content": "SELECT ta.tick, ti.creator, SUM(ta.amt) AS total_volume, COUNT(*) AS transfer_count\nFROM token_activities ta\nJOIN token_info 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 total_volume > 1000 and sort by total_volume descending."}, {"role": "assistant", "content": "SELECT ta.tick, ti.creator, SUM(ta.amt) AS total_volume, COUNT(*) AS transfer_count\nFROM token_activities ta\nJOIN token_info 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;"}, {"role": "user", "content": "Limit the output to the top 5 tokens."}, {"role": "assistant", "content": "SELECT ta.tick, ti.creator, SUM(ta.amt) AS total_volume, COUNT(*) AS transfer_count\nFROM token_activities ta\nJOIN token_info 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 varchar, transaction_index bigint, from_address varchar, contract_address varchar, symbol varchar, total_supply varchar, name varchar, decimals bigint, is_erc20 integer, is_erc721 integer, is_erc1155 integer, is_proxy integer, extra_info varchar, pk integer )\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_coins_metadata ( object_id.text, coin_type.text, status.text, decimals.bigint, description.text, icon_url.text, symbol.text, name.text )\nCREATE TABLE sui_nfts ( object_id.text, status.text, collection_type.text, package_id.text, previous_transaction.text, display.text, owner.text, name.text )\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 ( 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 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, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\nCREATE TABLE token_balances_avalanche ( block_number bigint 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"}