{"conversations": [{"role": "user", "content": "Show me the top 5 users who have the highest total order quantity, along with their order type and the average price they paid."}, {"role": "assistant", "content": "SELECT user_id, order_type, SUM(quantity) as total_quantity, AVG(price) as avg_price FROM trading_platform.orders GROUP BY user_id, order_type ORDER BY total_quantity DESC LIMIT 5;"}, {"role": "user", "content": "Now modify the query to only include completed orders and show the count of orders for each user."}, {"role": "assistant", "content": "SELECT user_id, order_type, SUM(quantity) as total_quantity, AVG(price) as avg_price, COUNT(order_id) as order_count FROM trading_platform.orders WHERE status = 'completed' GROUP BY user_id, order_type ORDER BY total_quantity DESC LIMIT 5;"}, {"role": "user", "content": "Actually, I want to see the results grouped by asset_id instead of user_id, showing the top 5 most ordered assets by quantity."}, {"role": "assistant", "content": "SELECT asset_id, SUM(quantity) as total_quantity, AVG(price) as avg_price, COUNT(order_id) as order_count FROM trading_platform.orders WHERE status = 'completed' GROUP BY asset_id ORDER BY total_quantity 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.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.kyc_audit ( kyc_audit_id text PRIMARY KEY, user_id text, status text, reviewed_at timestamp )\nCREATE TABLE trading_platform.logs ( log_id text PRIMARY KEY, user_id text, action text, details text, logged_at timestamp )\nCREATE TABLE trading_platform.notifications ( notification_id text PRIMARY KEY, user_id text, message text, sent_at timestamp, read_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show me all cryptocurrency assets that have been traded more than 50 times but have never been traded in quantities greater than 100, along with their average trade price."}, {"role": "assistant", "content": "SELECT a.asset_id, a.name, a.symbol, COUNT(t.trade_id) AS trade_count, AVG(t.price) AS avg_price FROM trading_platform.assets a JOIN trading_platform.trades t ON a.asset_id = t.asset_id WHERE a.type = 'cryptocurrency' GROUP BY a.asset_id, a.name, a.symbol HAVING COUNT(t.trade_id) > 50 AND MAX(t.quantity) <= 100;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.users ( user_id character varying(64) NOT NULL, username character varying(128) NOT NULL, email character varying(128) NOT NULL, password_hash text NOT NULL, created_at timestamp NOT NULL, PRIMARY KEY (user_id) )\nCREATE TABLE trading_platform.wallets ( wallet_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, address character varying(128) NOT NULL, private_key text NOT NULL, created_at timestamp NOT NULL, PRIMARY KEY (wallet_id) )\nCREATE TABLE trading_platform.orders ( order_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, wallet_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, order_type character varying(32) NOT NULL, quantity numeric(38,14) NOT NULL, price numeric(38,14) NOT NULL, status character varying(32) NOT NULL, created_at timestamp NOT NULL, PRIMARY KEY (order_id) )\nCREATE TABLE trading_platform.trades ( trade_id character varying(64) NOT NULL, order_id character varying(64) NOT NULL, buyer_id character varying(64) NOT NULL, seller_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, quantity numeric(38,14) NOT NULL, price numeric(38,14) NOT NULL, traded_at timestamp NOT NULL, PRIMARY KEY (trade_id) )\nCREATE TABLE trading_platform.assets ( asset_id character varying(64) NOT NULL, name character varying(128) NOT NULL, symbol character varying(32) NOT NULL, type character varying(32) NOT NULL, PRIMARY KEY (asset_id) )\nCREATE TABLE trading_platform.utxos ( utxo_id character varying(64) NOT NULL, transaction_id character varying(64) NOT NULL, output_index integer NOT NULL, address character varying(128) NOT NULL, amount numeric(38,14) NOT NULL, spent boolean NOT NULL, PRIMARY KEY (utxo_id) )\nCREATE TABLE trading_platform.dapps ( dapp_id character varying(64) NOT NULL, name character varying(128) NOT NULL, description text NOT NULL, url character varying(256) NOT NULL, PRIMARY KEY (dapp_id) )\nCREATE TABLE trading_platform.peers ( peer_id character varying(64) NOT NULL, ip_address character varying(15) NOT NULL, port integer NOT NULL, last_seen timestamp NOT NULL, PRIMARY KEY (peer_id) )\nCREATE TABLE trading_platform.metadata ( metadata_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, key character varying(128) NOT NULL, value text NOT NULL, PRIMARY KEY (metadata_id) )\nCREATE TABLE trading_platform.kyc_audit ( kyc_audit_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, status character varying(32) NOT NULL, reviewed_at timestamp NOT NULL, PRIMARY KEY (kyc_audit_id) )\nCREATE TABLE trading_platform.notifications ( notification_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, message text NOT NULL, sent_at timestamp NOT NULL, read_at timestamp, PRIMARY KEY (notification_id) )\n"}
{"conversations": [{"role": "user", "content": "List the product ID, name, and creation date for all insurance products created in 2024."}, {"role": "assistant", "content": "SELECT product_id, product_name, created_at\nFROM insurance.insurance_products\nWHERE created_at >= '2024-01-01' AND created_at < '2025-01-01';"}, {"role": "user", "content": "Actually, can you also include the product type and base premium in the results?"}, {"role": "assistant", "content": "SELECT product_id, product_name, product_type, base_premium, created_at\nFROM insurance.insurance_products\nWHERE created_at >= '2024-01-01' AND created_at < '2025-01-01';"}, {"role": "user", "content": "I only want to see those products with a base premium below 1000."}, {"role": "assistant", "content": "SELECT product_id, product_name, product_type, base_premium, created_at\nFROM insurance.insurance_products\nWHERE created_at >= '2024-01-01' AND created_at < '2025-01-01'\n  AND base_premium < 1000;"}, {"role": "user", "content": "Also, sort the result by product name in ascending order."}, {"role": "assistant", "content": "SELECT product_id, product_name, product_type, base_premium, created_at\nFROM insurance.insurance_products\nWHERE created_at >= '2024-01-01' AND created_at < '2025-01-01'\n  AND base_premium < 1000\nORDER BY product_name ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.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)\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 medical record entries where the treatment_plan mentions a medication name. Return patient_id, record_id, and the matching medication_name."}, {"role": "assistant", "content": "SELECT mr.patient_id,\n       mr.record_id,\n       m.medication_name\nFROM healthcare.medical_records AS mr\nJOIN healthcare.medications AS m\n  ON mr.treatment_plan ILIKE '%' || m.medication_name || '%';"}, {"role": "user", "content": "Actually, only include medications manufactured by 'Pfizer'."}, {"role": "assistant", "content": "SELECT mr.patient_id,\n       mr.record_id,\n       m.medication_name\nFROM healthcare.medical_records AS mr\nJOIN healthcare.medications AS m\n  ON mr.treatment_plan ILIKE '%' || m.medication_name || '%'\nWHERE m.manufacturer = 'Pfizer';"}, {"role": "user", "content": "Also sort the results by record_date descending."}, {"role": "assistant", "content": "SELECT mr.patient_id,\n       mr.record_id,\n       m.medication_name\nFROM healthcare.medical_records AS mr\nJOIN healthcare.medications AS m\n  ON mr.treatment_plan ILIKE '%' || m.medication_name || '%'\nWHERE m.manufacturer = 'Pfizer'\nORDER BY mr.record_date DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients (\n    patient_id character varying(64) NOT NULL,  -- unique identifier for the patient\n    first_name character varying(100) NOT NULL, -- patient's first name\n    last_name character varying(100) NOT NULL, -- patient's last name\n    date_of_birth date NOT NULL, -- patient's date of birth\n    gender character varying(10), -- patient's gender (e.g., Male, Female, Other)\n    address text, -- patient's home address\n    phone_number character varying(20), -- patient's phone number\n    email character varying(128) UNIQUE, -- patient's email address\n    emergency_contact_name character varying(200), -- name of emergency contact\n    emergency_contact_phone character varying(20), -- phone number of emergency contact\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, -- record creation time\n    updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, -- record last update time\n    PRIMARY KEY (patient_id)\n)\nCREATE TABLE healthcare.doctors (\n    doctor_id character varying(64) NOT NULL,  -- unique identifier for the doctor\n    first_name character varying(100) NOT NULL, -- doctor's first name\n    last_name character varying(100) NOT NULL, -- doctor's last name\n    specialty character varying(100) NOT NULL, -- doctor's medical specialty\n    license_number character varying(50) UNIQUE NOT NULL, -- doctor's medical license number\n    phone_number character varying(20), -- doctor's contact phone\n    email character varying(128) UNIQUE, -- doctor's contact email\n    hospital_affiliation_id character varying(64), -- FK to hospitals table (optional)\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (doctor_id)\n)\nCREATE TABLE healthcare.appointments (\n    appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    doctor_id character varying(64) NOT NULL, -- FK to doctors table\n    appointment_time timestamp with time zone NOT NULL, -- date and time of the appointment\n    duration_minutes integer NOT NULL, -- expected duration in minutes\n    reason text, -- reason for the visit\n    status character varying(32) NOT NULL, -- e.g., Scheduled, Completed, Cancelled, No-show\n    location_id character varying(64), -- FK to a potential locations/clinics table\n    notes text, -- notes related to scheduling\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (appointment_id)\n)\nCREATE TABLE healthcare.medical_records (\n    record_id character varying(64) NOT NULL,  -- unique identifier for the medical record entry\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    appointment_id character varying(64) UNIQUE, -- FK to appointments table (can be null if record not tied to specific appt)\n    doctor_id character varying(64) NOT NULL, -- FK to doctors table (doctor creating the record)\n    record_date timestamp with time zone NOT NULL, -- date the record/observation was made\n    chief_complaint text, -- patient's primary reason for visit\n    present_illness_history text, -- detailed history of the current issue\n    past_medical_history text, -- relevant past conditions/surgeries\n    physical_examination_notes text, -- findings from the physical exam\n    assessment text, -- doctor's assessment/diagnosis summary\n    treatment_plan text, -- planned course of action\n    vitals jsonb, -- store vitals like BP, HR, Temp as structured JSON\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (record_id)\n)\nCREATE TABLE healthcare.medications (\n    medication_id character varying(64) NOT NULL, -- unique identifier for the medication type\n    medication_name character varying(255) NOT NULL, -- common or brand name\n    generic_name character varying(255), -- generic chemical name\n    manufacturer character varying(100), -- drug manufacturer\n    ndc_code character varying(20) UNIQUE, -- National Drug Code (optional but useful)\n    description text, -- description of the medication\n    PRIMARY KEY (medication_id)\n)\nCREATE TABLE healthcare.insurance_plans (\n    plan_id character varying(64) NOT NULL, -- unique identifier for the insurance plan\n    plan_name character varying(200) NOT NULL, -- name of the insurance plan\n    insurance_provider character varying(100) NOT NULL, -- name of the insurance company\n    plan_type character varying(50), -- e.g., PPO, HMO, EPO\n    contact_phone character varying(20), -- provider contact number\n    website character varying(255), -- provider website\n    PRIMARY KEY (plan_id)\n)\nCREATE TABLE healthcare.patient_insurance (\n    patient_insurance_id character varying(64) NOT NULL, -- unique identifier for this patient-plan link\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    plan_id character varying(64) NOT NULL, -- FK to insurance_plans table\n    policy_number character varying(100) NOT NULL, -- patient's policy number\n    group_number character varying(100), -- group number, if applicable\n    subscriber_name character varying(200), -- name of the primary policy holder\n    effective_date date NOT NULL, -- date the coverage begins\n    expiration_date date, -- date the coverage ends (if known)\n    is_primary boolean NOT NULL DEFAULT true, -- indicates if this is the primary insurance\n    PRIMARY KEY (patient_insurance_id),\n    UNIQUE (patient_id, plan_id, policy_number) -- ensure a patient doesn't have the same policy twice\n)\n"}
{"conversations": [{"role": "user", "content": "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": "Provide a count of servers per game status."}, {"role": "assistant", "content": "SELECT status, COUNT(*) AS server_count FROM gaming_technology.servers GROUP BY status;"}, {"role": "user", "content": "Filter the list to only show statuses that have more than 2 servers."}, {"role": "assistant", "content": "SELECT status, COUNT(*) AS server_count FROM gaming_technology.servers GROUP BY status HAVING COUNT(*) > 2;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.game_sessions ( session_id.uuid, player_id.uuid, game_id.uuid, server_id.uuid, start_time.timestamptz, end_time.timestamptz, duration_seconds.integer, score.integer, session_data.jsonb )\nCREATE TABLE gaming_technology.servers ( server_id.uuid, game_id.uuid, server_name.text, region.text, ip_address.text, port.integer, current_players.integer, max_players.integer, status.text, last_heartbeat.timestamptz )\nCREATE TABLE gaming_technology.achievements ( achievement_id.uuid, game_id.uuid, name.text, description.text, icon_url.text, points.integer, hidden.boolean )\nCREATE TABLE gaming_technology.in_game_items ( item_id.uuid, game_id.uuid, item_name.text, item_type.text, description.text, rarity.text, cost_currency.text, cost_amount.numeric, attributes.jsonb )\nCREATE TABLE gaming_technology.player_inventory ( inventory_id.uuid, player_id.uuid, item_id.uuid, quantity.integer, acquired_at.timestamptz, instance_data.jsonb )\n"}
{"conversations": [{"role": "user", "content": "Find pairs of token transfers within the same transaction and for the same token, where the value of one transfer is exactly twice the value of the other. Show the transaction ID, token ID, and both transfer IDs and their values."}, {"role": "assistant", "content": "SELECT\n  t1.transaction_id,\n  t1.token_id,\n  t1.transfer_id AS transfer_id_1,\n  t1.value AS value_1,\n  t2.transfer_id AS transfer_id_2,\n  t2.value AS value_2\nFROM web3.token_transfers AS t1\nJOIN web3.token_transfers AS t2\n  ON t1.transaction_id = t2.transaction_id\n  AND t1.token_id = t2.token_id\n  AND t1.transfer_id < t2.transfer_id\nWHERE\n  t1.value = 2 * t2.value\n  OR t2.value = 2 * t1.value;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.token_transfers (\n    transfer_id character varying(64) NOT NULL,  -- unique identifier for the transfer\n    token_id character varying(64) NOT NULL, -- identifier of the token being transferred\n    from_address character varying(128) NOT NULL, -- address of the sender\n    to_address character varying(128) NOT NULL, -- address of the receiver\n    value numeric(38,14) NOT NULL, -- amount of tokens transferred\n    transaction_id character varying(64) NOT NULL, -- identifier of the transaction containing the transfer\n    log_index integer NOT NULL, -- index of the transfer log in the transaction\n    PRIMARY KEY (transfer_id)\n)\n"}
{"conversations": [{"role": "user", "content": "For each guest who has left at least one review, show their full name, the total number of reviews they have submitted, and the most recent review_date."}, {"role": "assistant", "content": "SELECT g.first_name, g.last_name, COUNT(r.review_id) AS review_count, MAX(r.review_date) AS most_recent_review\nFROM hospitality_technology.guests g\nJOIN hospitality_technology.reviews r ON g.guest_id = r.guest_id\nGROUP BY g.guest_id, g.first_name, g.last_name;"}, {"role": "user", "content": "Actually, can you also include the average overall rating they've given in their reviews?"}, {"role": "assistant", "content": "SELECT g.first_name, g.last_name, COUNT(r.review_id) AS review_count, MAX(r.review_date) AS most_recent_review, AVG(r.rating_overall) AS avg_overall_rating\nFROM hospitality_technology.guests g\nJOIN hospitality_technology.reviews r ON g.guest_id = r.guest_id\nGROUP BY g.guest_id, g.first_name, g.last_name;"}, {"role": "user", "content": "Please add the name of the property for the most recent review each guest submitted."}, {"role": "assistant", "content": "WITH recent_reviews AS (\n  SELECT r.guest_id, r.property_id, r.review_date,\n         ROW_NUMBER() OVER (PARTITION BY r.guest_id ORDER BY r.review_date DESC) as rn\n  FROM hospitality_technology.reviews r\n)\nSELECT g.first_name, g.last_name, COUNT(r.review_id) AS review_count, MAX(r.review_date) AS most_recent_review, AVG(r.rating_overall) AS avg_overall_rating, p.property_name AS most_recent_property\nFROM hospitality_technology.guests g\nJOIN hospitality_technology.reviews r ON g.guest_id = r.guest_id\nLEFT JOIN recent_reviews rr ON g.guest_id = rr.guest_id AND rr.rn = 1\nLEFT JOIN hospitality_technology.properties p ON rr.property_id = p.property_id\nGROUP BY g.guest_id, g.first_name, g.last_name, p.property_name;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.properties ( property_id text, property_name text, address_line1 text, address_line2 text, city text, state_province text, postal_code text, country_code text, phone_number text, email_address text, property_type text, star_rating numeric, timezone text, manager_staff_id text, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.rooms ( room_id text, property_id text, room_number text, room_type_id text, floor integer, status text, is_smoking boolean, features text, current_condition text, last_cleaned_at timestamp )\nCREATE TABLE hospitality_technology.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.reviews ( review_id text, property_id text, reservation_id text, guest_id text, rating_overall integer, rating_cleanliness integer, rating_service integer, rating_location integer, rating_value integer, comment text, review_source text, review_date timestamp, is_public boolean, staff_response text, response_staff_id text, response_date timestamp )\n"}
{"conversations": [{"role": "user", "content": "For each transaction, find the next transaction initiated by the same sender. List the original transaction_id, the next transaction_id, the sender address, and the time difference in hours between them."}, {"role": "assistant", "content": "SELECT t1.transaction_id AS original_tx,\n       t2.transaction_id AS next_tx,\n       t1.from_address,\n       EXTRACT(EPOCH FROM (t2.timestamp - t1.timestamp)) / 3600 AS hours_diff\nFROM transactions t1\nJOIN transactions t2\n  ON t1.from_address = t2.from_address\n AND t2.timestamp = (\n       SELECT MIN(timestamp)\n       FROM transactions t3\n       WHERE t3.from_address = t1.from_address\n         AND t3.timestamp > t1.timestamp\n   );"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.transactions ( transaction_id text, from_address text, to_address text, value numeric, gas_used integer, gas_price numeric, block_number integer, timestamp timestamp, input_data text, status text, nonce integer )\n"}
{"conversations": [{"role": "user", "content": "Get me all unbilled billable time entries with their entry_id, case_id, lawyer_id, hours_spent, and billing_rate."}, {"role": "assistant", "content": "SELECT entry_id,\n       case_id,\n       lawyer_id,\n       hours_spent,\n       billing_rate\nFROM legal_services.time_entries\nWHERE is_billable = TRUE\n  AND is_billed = FALSE;"}, {"role": "user", "content": "Actually, I only want entries for lawyer 'lawyer_123'."}, {"role": "assistant", "content": "SELECT entry_id,\n       case_id,\n       lawyer_id,\n       hours_spent,\n       billing_rate\nFROM legal_services.time_entries\nWHERE is_billable = TRUE\n  AND is_billed = FALSE\n  AND lawyer_id = 'lawyer_123';"}, {"role": "user", "content": "Also, sort the results by hours_spent in descending order."}, {"role": "assistant", "content": "SELECT entry_id,\n       case_id,\n       lawyer_id,\n       hours_spent,\n       billing_rate\nFROM legal_services.time_entries\nWHERE is_billable = TRUE\n  AND is_billed = FALSE\n  AND lawyer_id = 'lawyer_123'\nORDER BY hours_spent DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.time_entries (\n    entry_id character varying(64) NOT NULL,  -- unique identifier for the time entry\n    case_id character varying(64) NOT NULL, -- FK to cases table\n    lawyer_id character varying(64) NOT NULL, -- FK to lawyers table (who performed the work)\n    date_worked date NOT NULL, -- date the work was performed\n    hours_spent numeric(5, 2) NOT NULL CHECK (hours_spent > 0), -- duration of work in hours (e.g., 1.5 for 1h 30m)\n    billing_rate numeric(10, 2) NOT NULL, -- hourly rate applied for this entry\n    description text NOT NULL, -- detailed description of the work performed\n    is_billable boolean DEFAULT true, -- whether this time entry is billable to the client\n    is_billed boolean DEFAULT false, -- whether this entry has been included in an invoice\n    invoice_id character varying(64), -- FK to invoices table (once billed)\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the entry was recorded\n    PRIMARY KEY (entry_id)\n)\n"}
{"conversations": [{"role": "user", "content": "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 cryptocurrency assets that have been traded at least 50 times, 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 HAVING COUNT(t.trade_id) >= 50 ORDER BY trade_count DESC;"}, {"role": "user", "content": "Now filter these results to only show assets where the average trade price is above $100."}, {"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 HAVING COUNT(t.trade_id) >= 50 AND AVG(t.price) > 100 ORDER BY avg_price DESC;"}, {"role": "user", "content": "Can you also include the most recent trade timestamp for each asset?"}, {"role": "assistant", "content": "SELECT a.asset_id, a.name, a.symbol, COUNT(t.trade_id) AS trade_count, AVG(t.price) AS avg_price, MAX(t.traded_at) AS last_trade 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 HAVING COUNT(t.trade_id) >= 50 AND AVG(t.price) > 100 ORDER BY avg_price DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.users (\n    user_id character varying(64) NOT NULL,  -- unique identifier for the user\n    username character varying(128) NOT NULL, -- username of the user\n    email character varying(128) NOT NULL, -- email address of the user\n    password_hash text NOT NULL, -- hashed password of the user\n    created_at timestamp NOT NULL, -- time when the user account was created\n    PRIMARY KEY (user_id)\n)\nCREATE TABLE trading_platform.wallets (\n    wallet_id character varying(64) NOT NULL,  -- unique identifier for the wallet\n    user_id character varying(64) NOT NULL, -- identifier of the user owning the wallet\n    address character varying(128) NOT NULL, -- address of the wallet\n    private_key text NOT NULL, -- private key of the wallet\n    created_at timestamp NOT NULL, -- time when the wallet was created\n    PRIMARY KEY (wallet_id)\n)\nCREATE TABLE trading_platform.orders (\n    order_id character varying(64) NOT NULL,  -- unique identifier for the order\n    user_id character varying(64) NOT NULL, -- identifier of the user placing the order\n    wallet_id character varying(64) NOT NULL, -- identifier of the wallet used for the order\n    asset_id character varying(64) NOT NULL, -- identifier of the asset being traded\n    order_type character varying(32) NOT NULL, -- type of the order (e.g., buy, sell)\n    quantity numeric(38,14) NOT NULL, -- quantity of the asset in the order\n    price numeric(38,14) NOT NULL, -- price per unit of the asset\n    status character varying(32) NOT NULL, -- status of the order (e.g., open, filled, canceled)\n    created_at timestamp NOT NULL, -- time when the order was created\n    PRIMARY KEY (order_id)\n)\nCREATE TABLE trading_platform.trades (\n    trade_id character varying(64) NOT NULL,  -- unique identifier for the trade\n    order_id character varying(64) NOT NULL, -- identifier of the order that led to the trade\n    buyer_id character varying(64) NOT NULL, -- identifier of the buyer\n    seller_id character varying(64) NOT NULL, -- identifier of the seller\n    asset_id character varying(64) NOT NULL, -- identifier of the asset being traded\n    quantity numeric(38,14) NOT NULL, -- quantity of the asset in the trade\n    price numeric(38,14) NOT NULL, -- price per unit of the asset\n    traded_at timestamp NOT NULL, -- time when the trade was executed\n    PRIMARY KEY (trade_id)\n)\nCREATE TABLE trading_platform.assets (\n    asset_id character varying(64) NOT NULL,  -- unique identifier for the asset\n    name character varying(128) NOT NULL, -- name of the asset\n    symbol character varying(32) NOT NULL, -- symbol of the asset\n    type character varying(32) NOT NULL, -- type of the asset (e.g., cryptocurrency, stock)\n    PRIMARY KEY (asset_id)\n)\nCREATE TABLE trading_platform.dapps (\n    dapp_id character varying(64) NOT NULL,  -- unique identifier for the DApp\n    name character varying(128) NOT NULL, -- name of the DApp\n    description text NOT NULL, -- description of the DApp\n    url character varying(256) NOT NULL, -- URL of the DApp\n    PRIMARY KEY (dapp_id)\n)\nCREATE TABLE trading_platform.peers (\n    peer_id character varying(64) NOT NULL,  -- unique identifier for the peer\n    ip_address character varying(15) NOT NULL, -- IP address of the peer\n    port integer NOT NULL, -- port number of the peer\n    last_seen timestamp NOT NULL, -- last time the peer was active\n    PRIMARY KEY (peer_id)\n)\nCREATE TABLE trading_platform.metadata (\n    metadata_id character varying(64) NOT NULL,  -- unique identifier for the metadata\n    asset_id character varying(64) NOT NULL, -- identifier of the asset the metadata is associated with\n    key character varying(128) NOT NULL, -- key of the metadata\n    value text NOT NULL, -- value of the metadata\n    PRIMARY KEY (metadata_id)\n)\nCREATE TABLE trading_platform.kyc_audit (\n    kyc_audit_id character varying(64) NOT NULL,  -- unique identifier for the KYC audit\n    user_id character varying(64) NOT NULL, -- identifier of the user being audited\n    status character varying(32) NOT NULL, -- status of the KYC audit (e.g., pending, approved, rejected)\n    reviewed_at timestamp NOT NULL, -- time when the KYC audit was reviewed\n    PRIMARY KEY (kyc_audit_id)\n)\nCREATE TABLE trading_platform.logs (\n    log_id character varying(64) NOT NULL,  -- unique identifier for the log entry\n    user_id character varying(64), -- identifier of the user associated with the log entry\n    action character varying(128) NOT NULL, -- action performed\n    details text NOT NULL, -- details of the action\n    logged_at timestamp NOT NULL, -- time when the log entry was created\n    PRIMARY KEY (log_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Show me all room types with a base rate over $200 and max occupancy of at least 4, along with their property IDs and amenities."}, {"role": "assistant", "content": "SELECT room_type_id, property_id, type_name, base_rate, max_occupancy, amenities FROM hospitality_technology.room_types WHERE base_rate > 200 AND max_occupancy >= 4;"}, {"role": "user", "content": "Now, join this with the guests table to show only room types from properties where the guest's country code is 'USA'."}, {"role": "assistant", "content": "SELECT rt.room_type_id, rt.property_id, rt.type_name, rt.base_rate, rt.max_occupancy, rt.amenities FROM hospitality_technology.room_types rt JOIN hospitality_technology.guests g ON rt.property_id = g.property_id WHERE rt.base_rate > 200 AND rt.max_occupancy >= 4 AND g.country_code = 'USA';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.room_types ( room_type_id text PRIMARY KEY, property_id text, type_name text, description text, base_rate numeric, max_occupancy int, bed_type text, area_sqft numeric, amenities text )\nCREATE TABLE hospitality_technology.guests ( guest_id text, first_name text, last_name text, email text, phone_number text, date_of_birth date, address_line1 text, city text, state_province text, postal_code text, country_code text, preferences text, loyalty_member_id text, communication_consent boolean, created_at timestamp, updated_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show me all contracts deployed on the 'ethereum' network along with their deployer addresses and deployment timestamps, sorted by the most recent deployments first."}, {"role": "assistant", "content": "SELECT address, deployer_address, deployed_at FROM web3.contracts WHERE network_id = 'ethereum' ORDER BY deployed_at DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.contracts ( contract_id text, address text, abi text, bytecode text, deployer_address text, deployed_at timestamp, network_id text, status text )\n"}
{"conversations": [{"role": "user", "content": "Show me the top 5 projects by valuation that completed fundraising rounds in the last 6 months, along with their narrative information if available."}, {"role": "assistant", "content": "SELECT pfr.project_name, pfr.rounds_name, pfr.valuation, pfr.investment_date, ni.narrative, ni.trend_rank\nFROM project_fundraising_record pfr\nLEFT JOIN narrative_info ni ON pfr.project_name = ni.narrative\nWHERE pfr.investment_date >= date_sub(now(), interval 6 month)\nORDER BY pfr.valuation DESC\nLIMIT 5;"}, {"role": "user", "content": "Can you filter these results to only include projects with valuation over $50 million and add their 24-hour trading volume from the narrative?"}, {"role": "assistant", "content": "SELECT pfr.project_name, pfr.rounds_name, pfr.valuation, ni.volume_24h\nFROM project_fundraising_record pfr\nLEFT JOIN narrative_info ni ON pfr.project_name = ni.narrative\nWHERE pfr.investment_date >= date_sub(now(), interval 6 month)\nAND pfr.valuation > 50000000\nORDER BY pfr.valuation 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 project_fundraising_record ( id character varying(32) NOT NULL,  -- fundraising record id project_id character varying(32) NOT NULL, -- the invested project's id project_name character varying(128) NOT NULL, -- name of the invested project rounds_name character varying(32), -- name of the fundraising round investment_value numeric(38,14), -- amount of the fundraising in USD investment_date character varying(128), -- the date of the investment happened introduction character varying(128), -- the introduction of the invested project valuation numeric(38,14), -- the valuation of the project in USD when invested )\nCREATE TABLE narrative_info ( narrative character varying(512) NOT NULL, -- the id of narrative top_3_coins text, -- the top 3 tokens in the narrative price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour in the narrative price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours in the narrative price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days in the narrative market_cap double precision, -- the market cap of the narrative volume_24h double precision, -- the trade volume of the narrative trend_rank bigint, -- the trending rank of the narrative, value 1 expresses the most popular narrative token_num bigint, -- total token number in the narrative ,PRIMARY KEY (narrative) )\nCREATE TABLE smart_money_profit ( address character varying(100) NOT NULL, -- the user's address rank INT, -- the rank of the address in trade performance, value 1 expresses the best address. profit numeric(38,6), -- the profit user made in a month roi numeric(38,2), -- the roi of the user in a month realized_ratio numeric(38,2), -- the percentage of the user's realized profit most_profit_token character varying(100), -- the token symbol of the user's most profitable trade last_trade_time character varying(100), -- the last trade time of the user chain character varying(100), -- the chain that the address resides PRIMARY KEY (address, chain) )\n"}
{"conversations": [{"role": "user", "content": "List service orders placed in the last 7 days, showing order_id, service_name, guest full name, and order_timestamp."}, {"role": "assistant", "content": "SELECT so.order_id, s.service_name, g.first_name || ' ' || g.last_name AS guest_name, so.order_timestamp\nFROM hospitality_technology.service_orders so\nJOIN hospitality_technology.services s ON so.service_id = s.service_id\nJOIN hospitality_technology.guests g ON so.guest_id = g.guest_id\nWHERE so.order_timestamp >= current_date - INTERVAL '7 days';"}, {"role": "user", "content": "Filter to only those orders with status 'Delivered' and sort by delivery_timestamp ascending."}, {"role": "assistant", "content": "SELECT so.order_id, s.service_name, g.first_name || ' ' || g.last_name AS guest_name, so.order_timestamp, so.delivery_timestamp\nFROM hospitality_technology.service_orders so\nJOIN hospitality_technology.services s ON so.service_id = s.service_id\nJOIN hospitality_technology.guests g ON so.guest_id = g.guest_id\nWHERE so.order_timestamp >= current_date - INTERVAL '7 days'\n  AND so.status = 'Delivered'\nORDER BY so.delivery_timestamp ASC;"}, {"role": "user", "content": "Also include the staff member who delivered the service as delivered_by (full name) and limit to 10 records."}, {"role": "assistant", "content": "SELECT so.order_id, s.service_name, g.first_name || ' ' || g.last_name AS guest_name, so.order_timestamp, so.delivery_timestamp, st.first_name || ' ' || st.last_name AS delivered_by\nFROM hospitality_technology.service_orders so\nJOIN hospitality_technology.services s ON so.service_id = s.service_id\nJOIN hospitality_technology.guests g ON so.guest_id = g.guest_id\nJOIN hospitality_technology.staff st ON so.staff_id_delivered = st.staff_id\nWHERE so.order_timestamp >= current_date - INTERVAL '7 days'\n  AND so.status = 'Delivered'\nORDER BY so.delivery_timestamp ASC\nLIMIT 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.rooms ( room_id.text, property_id.text, room_number.text, room_type_id.text, floor.integer, status.text, is_smoking.boolean, features.text, current_condition.text, last_cleaned_at.timestamp )\nCREATE TABLE hospitality_technology.room_types ( room_type_id.text, property_id.text, type_name.text, description.text, base_rate.numeric, max_occupancy.integer, bed_type.text, area_sqft.numeric, amenities.text )\nCREATE TABLE hospitality_technology.guests ( guest_id.text, first_name.text, last_name.text, email.text, phone_number.text, date_of_birth.date, address_line1.text, city.text, state_province.text, postal_code.text, country_code.text, preferences.text, loyalty_member_id.text, communication_consent.boolean, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE hospitality_technology.reservations ( reservation_id.text, property_id.text, guest_id.text, room_id.text, room_type_id.text, check_in_date.date, check_out_date.date, actual_check_in_ts.timestamp, actual_check_out_ts.timestamp, num_adults.integer, num_children.integer, status.text, booking_source.text, rate_plan_id.text, total_amount.numeric, amount_paid.numeric, special_requests.text, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE hospitality_technology.staff ( staff_id.text, property_id.text, first_name.text, last_name.text, position.text, work_email.text, work_phone.text, hire_date.date, termination_date.date, is_active.boolean, access_level.integer, manager_id.text, created_at.timestamp )\nCREATE TABLE hospitality_technology.services ( service_id.text, property_id.text, service_name.text, description.text, category.text, price.numeric, unit.text, is_available.boolean, department.text )\nCREATE TABLE hospitality_technology.service_orders ( order_id.text, reservation_id.text, guest_id.text, service_id.text, staff_id_ordered.text, staff_id_delivered.text, order_timestamp.timestamp, delivery_timestamp.timestamp, quantity.integer, unit_price.numeric, total_price.numeric, status.text, notes.text, bill_id.text )\nCREATE TABLE hospitality_technology.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": "Count the number of completed premium payments grouped by payment_method."}, {"role": "assistant", "content": "SELECT payment_method,\n       COUNT(*) AS payment_count\nFROM insurance.premium_payments\nWHERE status = 'Completed'\nGROUP BY payment_method;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.premium_payments ( payment_id text PRIMARY KEY, policy_id text, customer_id text, payment_date timestamp, amount_paid numeric, payment_method text, transaction_reference text, due_date date, payment_period_start date, payment_period_end date, status text )\n"}
{"conversations": [{"role": "user", "content": "What is the total transaction amount for each transaction_type in the last 30 days?"}, {"role": "assistant", "content": "SELECT transaction_type, SUM(amount) AS total_amount FROM financial_services.transactions WHERE transaction_date >= CURRENT_DATE - INTERVAL '30 days' GROUP BY transaction_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.customers ( customer_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, ssn_hash character varying(128), address text NOT NULL, city character varying(100) NOT NULL, state character varying(50) NOT NULL, zip_code character varying(20) NOT NULL, country character varying(50) NOT NULL, email character varying(128) UNIQUE, phone_number character varying(32), created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, status character varying(32) NOT NULL, risk_profile character varying(50), PRIMARY KEY (customer_id) )\nCREATE TABLE financial_services.accounts ( account_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, account_number character varying(128) NOT NULL UNIQUE, account_type character varying(50) NOT NULL, balance numeric(19, 4) NOT NULL DEFAULT 0.00, currency character varying(3) NOT NULL, opened_date date NOT NULL, status character varying(32) NOT NULL, interest_rate numeric(5, 4), last_updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (account_id), FOREIGN KEY (customer_id) REFERENCES financial_services.customers(customer_id) )\nCREATE TABLE financial_services.transactions ( transaction_id character varying(64) NOT NULL, account_id character varying(64) NOT NULL, related_account_id character varying(64), transaction_type character varying(50) NOT NULL, amount numeric(19, 4) NOT NULL, currency character varying(3) NOT NULL, transaction_date timestamp NOT NULL, effective_date date NOT NULL, description text, status character varying(32) NOT NULL, reference_number character varying(128), PRIMARY KEY (transaction_id), FOREIGN KEY (account_id) REFERENCES financial_services.accounts(account_id), FOREIGN KEY (related_account_id) REFERENCES financial_services.accounts(account_id) )\nCREATE TABLE financial_services.securities ( security_id character varying(64) NOT NULL, ticker_symbol character varying(20) NOT NULL UNIQUE, isin_code character varying(12) UNIQUE, cusip_code character varying(9) UNIQUE, security_name text NOT NULL, security_type character varying(50) NOT NULL, exchange character varying(50), currency character varying(3) NOT NULL, issuer_name character varying(255), sector character varying(100), last_updated timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (security_id) )\nCREATE TABLE financial_services.trades ( trade_id character varying(64) NOT NULL, account_id character varying(64) NOT NULL, security_id character varying(64) NOT NULL, order_id character varying(64), trade_type character varying(10) NOT NULL, quantity numeric(19, 8) NOT NULL, price_per_unit numeric(19, 8) NOT NULL, total_amount numeric(19, 4) NOT NULL, commission numeric(10, 4), trade_timestamp timestamp NOT NULL, settlement_date date, status character varying(32) NOT NULL, execution_venue character varying(100), PRIMARY KEY (trade_id), FOREIGN KEY (account_id) REFERENCES financial_services.accounts(account_id), FOREIGN KEY (security_id) REFERENCES financial_services.securities(security_id) )\n"}
{"conversations": [{"role": "user", "content": "Show me the count of notifications sent for each channel for applications submitted after January 1, 2024."}, {"role": "assistant", "content": "SELECT n.channel, COUNT(*) AS notification_count\nFROM government_services.notifications n\nJOIN government_services.applications a ON n.application_id = a.application_id\nWHERE a.submitted_at > '2024-01-01'\nGROUP BY n.channel;"}, {"role": "user", "content": "Now, only include channels that have sent more than 10 notifications."}, {"role": "assistant", "content": "SELECT n.channel, COUNT(*) AS notification_count\nFROM government_services.notifications n\nJOIN government_services.applications a ON n.application_id = a.application_id\nWHERE a.submitted_at > '2024-01-01'\nGROUP BY n.channel\nHAVING COUNT(*) > 10;"}, {"role": "user", "content": "Exclude notifications with the status 'Failed'."}, {"role": "assistant", "content": "SELECT n.channel, COUNT(*) AS notification_count\nFROM government_services.notifications n\nJOIN government_services.applications a ON n.application_id = a.application_id\nWHERE a.submitted_at > '2024-01-01' AND n.status != 'Failed'\nGROUP BY n.channel\nHAVING COUNT(*) > 10;"}, {"role": "user", "content": "Show for 2023 instead of 2024."}, {"role": "assistant", "content": "SELECT n.channel, COUNT(*) AS notification_count\nFROM government_services.notifications n\nJOIN government_services.applications a ON n.application_id = a.application_id\nWHERE a.submitted_at >= '2023-01-01' AND a.submitted_at < '2024-01-01' AND n.status != 'Failed'\nGROUP BY n.channel\nHAVING COUNT(*) > 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.applications ( application_id text, citizen_id text, service_id text, submitted_at timestamp, status text, last_updated_at timestamp, assigned_employee_id text, decision_date date, notes text, reference_number text )\nCREATE TABLE government_services.notifications ( notification_id text, citizen_id text, application_id text, message_subject text, message_body text, channel text, sent_at timestamp, status text, related_entity_type text, related_entity_id text )\n"}
{"conversations": [{"role": "user", "content": "Show me all home loans (loan_id, principal_amount, interest_rate) where the current principal balance is more than 75% of the original principal amount, along with the account_id and employee details (first_name, last_name) of the employee who processed the loan application."}, {"role": "assistant", "content": "SELECT l.loan_id, l.principal_amount, l.interest_rate, l.account_id, e.first_name, e.last_name FROM financial_services.loans l JOIN financial_services.employees e ON l.account_id = e.employee_id WHERE l.loan_type = 'Home' AND l.current_principal_balance > (l.principal_amount * 0.75)"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.transactions ( transaction_id.text, account_id.text, related_account_id.text, transaction_type.text, amount.numeric, currency.text, transaction_date.timestamp, effective_date.date, description.text, status.text, reference_number.text )\nCREATE TABLE financial_services.securities ( security_id.text, ticker_symbol.text, isin_code.text, cusip_code.text, security_name.text, security_type.text, exchange.text, currency.text, issuer_name.text, sector.text, last_updated.timestamp )\nCREATE TABLE financial_services.market_data ( data_point_id.bigint, security_id.text, data_timestamp.timestamp, open_price.numeric, high_price.numeric, low_price.numeric, close_price.numeric, adjusted_close_price.numeric, volume.bigint, source.text )\nCREATE TABLE financial_services.employees ( employee_id.text, first_name.text, last_name.text, job_title.text, department.text, branch_id.text, email.text, phone_extension.text, hire_date.date, termination_date.date, manager_id.text, status.text )\nCREATE TABLE financial_services.loans ( loan_id.text, account_id.text, loan_type.text, principal_amount.numeric, current_principal_balance.numeric, interest_rate.numeric, term_months.integer, origination_date.date, maturity_date.date, monthly_payment.numeric, collateral_description.text, status.text )\n"}
{"conversations": [{"role": "user", "content": "Show me all properties in California with a star rating above 4.0, along with their room types and base rates."}, {"role": "assistant", "content": "SELECT p.property_name, p.star_rating, rt.type_name, rt.base_rate FROM hospitality_technology.properties p JOIN hospitality_technology.room_types rt ON p.property_id = rt.property_id WHERE p.state_province = 'California' AND p.star_rating > 4.0 ORDER BY p.star_rating DESC;"}, {"role": "user", "content": "Now, filter the results to only include room types with a max occupancy of at least 4 people and a base rate below $300."}, {"role": "assistant", "content": "SELECT p.property_name, p.star_rating, rt.type_name, rt.base_rate, rt.max_occupancy FROM hospitality_technology.properties p JOIN hospitality_technology.room_types rt ON p.property_id = rt.property_id WHERE p.state_province = 'California' AND p.star_rating > 4.0 AND rt.max_occupancy >= 4 AND rt.base_rate < 300 ORDER BY p.star_rating DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.properties ( property_id character varying(64) NOT NULL, property_name character varying(255) NOT NULL, address_line1 character varying(255) NOT NULL, address_line2 character varying(255), city character varying(100) NOT NULL, state_province character varying(100), postal_code character varying(20) NOT NULL, country_code character varying(3) NOT NULL, phone_number character varying(30), email_address character varying(255), property_type character varying(50) NOT NULL, star_rating numeric(2,1), timezone character varying(64) NOT NULL, manager_staff_id character varying(64), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (property_id) )\nCREATE TABLE hospitality_technology.rooms ( room_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, room_number character varying(10) NOT NULL, room_type_id character varying(64) NOT NULL, floor integer, status character varying(50) NOT NULL, is_smoking boolean NOT NULL DEFAULT false, features text, current_condition text, last_cleaned_at timestamp with time zone, PRIMARY KEY (room_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id) )\nCREATE TABLE hospitality_technology.room_types ( room_type_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, type_name character varying(100) NOT NULL, description text, base_rate numeric(10, 2) NOT NULL, max_occupancy integer NOT NULL, bed_type character varying(50), area_sqft numeric(8,2), amenities text, PRIMARY KEY (room_type_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id) )\nCREATE TABLE hospitality_technology.guests ( guest_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, email character varying(255) UNIQUE, phone_number character varying(30), date_of_birth date, address_line1 character varying(255), city character varying(100), state_province character varying(100), postal_code character varying(20), country_code character varying(3), preferences text, loyalty_member_id character varying(64) UNIQUE, communication_consent boolean DEFAULT true, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (guest_id) )\nCREATE TABLE hospitality_technology.reservations ( reservation_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, guest_id character varying(64) NOT NULL, room_id character varying(64), room_type_id character varying(64) NOT NULL, check_in_date date NOT NULL, check_out_date date NOT NULL, actual_check_in_ts timestamp with time zone, actual_check_out_ts timestamp with time zone, num_adults integer NOT NULL, num_children integer DEFAULT 0, status character varying(50) NOT NULL, booking_source character varying(100), rate_plan_id character varying(64), total_amount numeric(12, 2), amount_paid numeric(12, 2) DEFAULT 0.00, special_requests text, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (reservation_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (room_id) REFERENCES hospitality_technology.rooms(room_id), FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id) )\nCREATE TABLE hospitality_technology.services ( service_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, service_name character varying(150) NOT NULL, description text, category character varying(100), price numeric(10, 2) NOT NULL, unit character varying(30), is_available boolean NOT NULL DEFAULT true, department character varying(100), PRIMARY KEY (service_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id) )\nCREATE TABLE hospitality_technology.service_orders ( order_id character varying(64) NOT NULL, reservation_id character varying(64), guest_id character varying(64) NOT NULL, service_id character varying(64) NOT NULL, staff_id_ordered character varying(64), staff_id_delivered character varying(64), order_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, delivery_timestamp timestamp with time zone, quantity integer NOT NULL DEFAULT 1, unit_price numeric(10, 2) NOT NULL, total_price numeric(12, 2) NOT NULL, status character varying(50) NOT NULL, notes text, bill_id character varying(64), PRIMARY KEY (order_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (service_id) REFERENCES hospitality_technology.services(service_id), FOREIGN KEY (staff_id_ordered) REFERENCES hospitality_technology.staff(staff_id), FOREIGN KEY (staff_id_delivered) REFERENCES hospitality_technology.staff(staff_id) )\nCREATE TABLE hospitality_technology.payments ( payment_id character varying(64) NOT NULL, reservation_id character varying(64), guest_id character varying(64) NOT NULL, bill_id character varying(64), amount numeric(12,2) NOT NULL, currency_code character varying(3) NOT NULL, payment_method character varying(50) NOT NULL, card_type character varying(50), card_last_four character varying(4), transaction_ref character varying(128), payment_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, status character varying(50) NOT NULL, staff_id_processed character varying(64), notes text, PRIMARY KEY (payment_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (staff_id_processed) REFERENCES hospitality_technology.staff(staff_id) )\nCREATE TABLE hospitality_technology.reviews ( review_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, reservation_id character varying(64) UNIQUE, guest_id character varying(64) NOT NULL, rating_overall integer, rating_cleanliness integer, rating_service integer, rating_location integer, rating_value integer, comment text, review_source character varying(100), review_date timestamp with time zone NOT NULL DEFAULT current_timestamp, is_public boolean DEFAULT true, staff_response text, response_staff_id character varying(64), response_date timestamp with time zone, PRIMARY KEY (review_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (response_staff_id) REFERENCES hospitality_technology.staff(staff_id) )\n"}
{"conversations": [{"role": "user", "content": "Show the number of employees in each department."}, {"role": "assistant", "content": "SELECT department, COUNT(*) AS employee_count\nFROM financial_services.employees\ngroup BY department;"}, {"role": "user", "content": "Exclude departments that have less than 3 employees."}, {"role": "assistant", "content": "SELECT department, COUNT(*) AS employee_count\nFROM financial_services.employees\ngroup BY department\nHAVING COUNT(*) >= 3;"}, {"role": "user", "content": "Can you also show the average hire_date for employees in each department?"}, {"role": "assistant", "content": "SELECT department, COUNT(*) AS employee_count, AVG(hire_date) AS average_hire_date\nFROM financial_services.employees\ngroup BY department\nHAVING COUNT(*) >= 3;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.accounts ( account_id text PRIMARY KEY, customer_id text, account_number text, account_type text, balance numeric, currency text, opened_date date, status text, interest_rate numeric, last_updated_at timestamp )\nCREATE TABLE financial_services.transactions ( transaction_id text PRIMARY KEY, account_id text, related_account_id text, transaction_type text, amount numeric, currency text, transaction_date timestamp, effective_date date, description text, status text, reference_number text )\nCREATE TABLE financial_services.trades ( trade_id text PRIMARY KEY, account_id text, security_id text, order_id text, trade_type text, quantity numeric, price_per_unit numeric, total_amount numeric, commission numeric, trade_timestamp timestamp, settlement_date date, status text, execution_venue text )\nCREATE TABLE financial_services.market_data ( data_point_id bigserial PRIMARY KEY, security_id text, data_timestamp timestamp, open_price numeric, high_price numeric, low_price numeric, close_price numeric, adjusted_close_price numeric, volume bigint, source text )\nCREATE TABLE financial_services.employees ( employee_id text PRIMARY KEY, first_name text, last_name text, job_title text, department text, branch_id text, email text, phone_extension text, hire_date date, termination_date date, manager_id text, status text )\n"}
{"conversations": [{"role": "user", "content": "Find all pairs of lawyers from the same firm who have the same specialization."}, {"role": "assistant", "content": "SELECT a.lawyer_id AS lawyer_id_1, a.first_name AS first_name_1, a.last_name AS last_name_1, b.lawyer_id AS lawyer_id_2, b.first_name AS first_name_2, b.last_name AS last_name_2, a.specialization FROM legal_services.lawyers a JOIN legal_services.lawyers b ON a.firm_id = b.firm_id AND a.specialization = b.specialization AND a.lawyer_id < b.lawyer_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.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 )\n"}
{"conversations": [{"role": "user", "content": "Provide a report of each user with their username and the count of all log entries from the last 30 days."}, {"role": "assistant", "content": "SELECT u.user_id, u.username, COUNT(l.log_id) AS log_count\nFROM trading_platform.users u\nLEFT JOIN trading_platform.logs l\n  ON u.user_id = l.user_id\n  AND l.logged_at >= CURRENT_DATE - INTERVAL '30 days'\nGROUP BY u.user_id, u.username;"}, {"role": "user", "content": "Actually, show only logs where the action includes the word 'trade'."}, {"role": "assistant", "content": "SELECT u.user_id, u.username, COUNT(l.log_id) AS log_count\nFROM trading_platform.users u\nJOIN trading_platform.logs l\n  ON u.user_id = l.user_id\nWHERE l.logged_at >= CURRENT_DATE - INTERVAL '30 days'\n  AND l.action ILIKE '%trade%'\nGROUP BY u.user_id, u.username;"}, {"role": "user", "content": "Also include the earliest log date for each user in that period."}, {"role": "assistant", "content": "SELECT u.user_id,\n       u.username,\n       COUNT(l.log_id) AS log_count,\n       MIN(l.logged_at) AS first_log_date\nFROM trading_platform.users u\nJOIN trading_platform.logs l\n  ON u.user_id = l.user_id\nWHERE l.logged_at >= CURRENT_DATE - INTERVAL '30 days'\n  AND l.action ILIKE '%trade%'\nGROUP BY u.user_id, u.username;"}, {"role": "user", "content": "Finally, sort the results by log_count descending and limit to the top 5 users."}, {"role": "assistant", "content": "SELECT u.user_id,\n       u.username,\n       COUNT(l.log_id) AS log_count,\n       MIN(l.logged_at) AS first_log_date\nFROM trading_platform.users u\nJOIN trading_platform.logs l\n  ON u.user_id = l.user_id\nWHERE l.logged_at >= CURRENT_DATE - INTERVAL '30 days'\n  AND l.action ILIKE '%trade%'\nGROUP BY u.user_id, u.username\nORDER BY log_count DESC\nLIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.users (\n    user_id character varying(64) NOT NULL,  -- unique identifier for the user\n    username character varying(128) NOT NULL, -- username of the user\n    email character varying(128) NOT NULL, -- email address of the user\n    password_hash text NOT NULL, -- hashed password of the user\n    created_at timestamp NOT NULL, -- time when the user account was created\n    PRIMARY KEY (user_id)\n)\nCREATE TABLE trading_platform.orders (\n    order_id character varying(64) NOT NULL,  -- unique identifier for the order\n    user_id character varying(64) NOT NULL, -- identifier of the user placing the order\n    wallet_id character varying(64) NOT NULL, -- identifier of the wallet used for the order\n    asset_id character varying(64) NOT NULL, -- identifier of the asset being traded\n    order_type character varying(32) NOT NULL, -- type of the order (e.g., buy, sell)\n    quantity numeric(38,14) NOT NULL, -- quantity of the asset in the order\n    price numeric(38,14) NOT NULL, -- price per unit of the asset\n    status character varying(32) NOT NULL, -- status of the order (e.g., open, filled, canceled)\n    created_at timestamp NOT NULL, -- time when the order was created\n    PRIMARY KEY (order_id)\n)\nCREATE TABLE trading_platform.utxos (\n    utxo_id character varying(64) NOT NULL,  -- unique identifier for the UTXO\n    transaction_id character varying(64) NOT NULL, -- identifier of the transaction that created the UTXO\n    output_index integer NOT NULL, -- index of the output in the transaction\n    address character varying(128) NOT NULL, -- address that can spend the UTXO\n    amount numeric(38,14) NOT NULL, -- amount of the asset in the UTXO\n    spent boolean NOT NULL, -- whether the UTXO has been spent\n    PRIMARY KEY (utxo_id)\n)\nCREATE TABLE trading_platform.dapps (\n    dapp_id character varying(64) NOT NULL,  -- unique identifier for the DApp\n    name character varying(128) NOT NULL, -- name of the DApp\n    description text NOT NULL, -- description of the DApp\n    url character varying(256) NOT NULL, -- URL of the DApp\n    PRIMARY KEY (dapp_id)\n)\nCREATE TABLE trading_platform.peers (\n    peer_id character varying(64) NOT NULL,  -- unique identifier for the peer\n    ip_address character varying(15) NOT NULL, -- IP address of the peer\n    port integer NOT NULL, -- port number of the peer\n    last_seen timestamp NOT NULL, -- last time the peer was active\n    PRIMARY KEY (peer_id)\n)\nCREATE TABLE trading_platform.logs (\n    log_id character varying(64) NOT NULL,  -- unique identifier for the log entry\n    user_id character varying(64), -- identifier of the user associated with the log entry\n    action character varying(128) NOT NULL, -- action performed\n    details text NOT NULL, -- details of the action\n    logged_at timestamp NOT NULL, -- time when the log entry was created\n    PRIMARY KEY (log_id)\n)\n"}
{"conversations": [{"role": "user", "content": "What is the average price of tokens held by Binance exchange across all chains in the cex_token_balance table?"}, {"role": "assistant", "content": "SELECT AVG(price) AS average_price FROM cex_token_balance WHERE exchange = 'Binance';"}], "system": "You are an SQL statement expert. Given the 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) )\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"}
{"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 a list of all game developers with their name and founded year."}, {"role": "assistant", "content": "SELECT\n  name,\n  founded_year\nFROM gaming_technology.developers;"}, {"role": "user", "content": "Please filter the list to only include developers founded in the year 1998."}, {"role": "assistant", "content": "SELECT\n  name,\n  founded_year\nFROM gaming_technology.developers\nWHERE\n  founded_year = 1998;"}, {"role": "user", "content": "Can you also include the number of games each of these developers has released?"}, {"role": "assistant", "content": "SELECT\n  T1.name,\n  T1.founded_year,\n  COUNT(T2.game_id) AS game_count\nFROM gaming_technology.developers AS T1\nLEFT JOIN gaming_technology.games AS T2\n  ON T1.developer_id = T2.developer_id\nWHERE\n  T1.founded_year = 1998\nGROUP BY\n  T1.developer_id,\n  T1.name,\n  T1.founded_year;"}, {"role": "user", "content": "Now, only show the developers who have released exactly 2 games."}, {"role": "assistant", "content": "SELECT\n  T1.name,\n  T1.founded_year,\n  COUNT(T2.game_id) AS game_count\nFROM gaming_technology.developers AS T1\nJOIN gaming_technology.games AS T2\n  ON T1.developer_id = T2.developer_id\nWHERE\n  T1.founded_year = 1998\nGROUP BY\n  T1.developer_id,\n  T1.name,\n  T1.founded_year\nHAVING\n  COUNT(T2.game_id) = 2;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.players (\n    player_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the player\n    username character varying(100) NOT NULL UNIQUE, -- player's chosen display name\n    email character varying(255) NOT NULL UNIQUE, -- player's email address for login/recovery\n    password_hash text NOT NULL, -- securely hashed password\n    registration_date timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the player account was created\n    last_login timestamp with time zone, -- timestamp of the last successful login\n    country_code character(2), -- player's country (ISO 3166-1 alpha-2)\n    status character varying(20) NOT NULL DEFAULT 'active', -- account status (e.g., active, banned, suspended)\n    profile_data jsonb, -- flexible field for avatar url, bio, preferences etc.\n    PRIMARY KEY (player_id)\n)\nCREATE TABLE gaming_technology.games (\n    game_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game\n    title character varying(200) NOT NULL, -- official title of the game\n    developer_id uuid NOT NULL, -- FK linking to the developers table\n    publisher_id uuid, -- FK linking to a potential publishers table (optional)\n    genre character varying(100), -- primary genre (e.g., RPG, FPS, Strategy)\n    release_date date, -- official release date\n    description text, -- short description or synopsis of the game\n    platform character varying(50) NOT NULL, -- primary platform (e.g., PC, PlayStation 5, Xbox Series X, Mobile)\n    engine character varying(100), -- game engine used (e.g., Unreal Engine 5, Unity)\n    website character varying(255), -- official website URL\n    PRIMARY KEY (game_id)\n    -- FOREIGN KEY (developer_id) REFERENCES gaming_technology.developers(developer_id) -- Example FK constraint\n)\nCREATE TABLE gaming_technology.developers (\n    developer_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the developer studio\n    name character varying(150) NOT NULL UNIQUE, -- name of the development studio\n    country character varying(100), -- country where the studio is based\n    founded_year integer, -- year the studio was founded\n    website character varying(255), -- developer's official website\n    created_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP,\n    PRIMARY KEY (developer_id)\n)\nCREATE TABLE gaming_technology.game_sessions (\n    session_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game session\n    player_id uuid NOT NULL, -- FK linking to the players table\n    game_id uuid NOT NULL, -- FK linking to the games table\n    server_id uuid, -- FK linking to the servers table (nullable for single-player)\n    start_time timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the session began\n    end_time timestamp with time zone, -- when the session ended (null if ongoing)\n    duration_seconds integer, -- calculated duration of the session in seconds\n    score integer, -- player's score for the session, if applicable\n    session_data jsonb, -- flexible field for session-specific info (e.g., map played, character used)\n    PRIMARY KEY (session_id)\n    -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n    -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id),\n    -- FOREIGN KEY (server_id) REFERENCES gaming_technology.servers(server_id)\n)\nCREATE TABLE gaming_technology.servers (\n    server_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game server instance\n    game_id uuid NOT NULL, -- FK linking to the game this server hosts\n    server_name character varying(150), -- display name for the server\n    region character varying(50) NOT NULL, -- geographical region (e.g., us-east-1, eu-west-2)\n    ip_address character varying(45), -- IP address (IPv4 or IPv6)\n    port integer, -- network port number\n    current_players integer NOT NULL DEFAULT 0, -- number of players currently connected\n    max_players integer NOT NULL, -- maximum player capacity\n    status character varying(30) NOT NULL DEFAULT 'offline', -- server status (e.g., online, offline, maintenance)\n    last_heartbeat timestamp with time zone, -- last time the server reported its status\n    PRIMARY KEY (server_id)\n    -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id)\n)\nCREATE TABLE gaming_technology.achievements (\n    achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for an achievement definition\n    game_id uuid NOT NULL, -- FK linking to the game the achievement belongs to\n    name character varying(150) NOT NULL, -- name of the achievement\n    description text NOT NULL, -- how to unlock the achievement\n    icon_url character varying(255), -- URL for the achievement's icon\n    points integer DEFAULT 0, -- points awarded for unlocking (optional)\n    hidden boolean DEFAULT false, -- whether the achievement details are hidden until unlocked\n    PRIMARY KEY (achievement_id)\n    -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id)\n)\nCREATE TABLE gaming_technology.player_achievements (\n    player_achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for this unlock instance\n    player_id uuid NOT NULL, -- FK linking to the player who unlocked it\n    achievement_id uuid NOT NULL, -- FK linking to the achievement definition\n    unlocked_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the achievement was unlocked\n    PRIMARY KEY (player_achievement_id),\n    UNIQUE (player_id, achievement_id) -- Ensure a player can only unlock an achievement once\n    -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n    -- FOREIGN KEY (achievement_id) REFERENCES gaming_technology.achievements(achievement_id)\n)\n"}
{"conversations": [{"role": "user", "content": "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": "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": "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": "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": "What is the current job satisfaction level or feedback from staff members working at a specific train station?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information on job satisfaction levels or feedback from staff members as this data is not included in the staff table."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.staff ( staff_id.text, first_name.text, last_name.text, role.text, primary_station_id.text, employee_number.text, hire_date.date, contact_email.text, contact_phone.text, is_active.boolean )\n"}
{"conversations": [{"role": "user", "content": "Which route numbers connect locations with a distance less than 80 km and more than 5 words in their description? Include the route type in the results."}, {"role": "assistant", "content": "SELECT route_number, type FROM transportation.routes WHERE distance_km < 80 AND array_length(regexp_split_to_array(description, '\\s+'), 1) > 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.routes ( route_id text, route_number text, description text, origin_location_id text, destination_location_id text, distance_km numeric, estimated_duration_minutes integer, type text )\n"}
{"conversations": [{"role": "user", "content": "List the ERC20 tokens (from token_metas) with exactly 6 decimals. Show their symbol, contract_address, and name."}, {"role": "assistant", "content": "SELECT symbol, contract_address, name FROM token_metas WHERE is_erc20 = 1 AND decimals = 6;"}, {"role": "user", "content": "Can you also include the total current supply for each token?"}, {"role": "assistant", "content": "SELECT symbol, contract_address, name, total_supply FROM token_metas WHERE is_erc20 = 1 AND decimals = 6;"}, {"role": "user", "content": "Now, join with token_prices_latest to also include the latest price for each token."}, {"role": "assistant", "content": "SELECT tm.symbol, tm.contract_address, tm.name, tm.total_supply, tpl.price AS latest_price\nFROM token_metas tm\nJOIN token_prices_latest tpl ON tm.contract_address = tpl.address AND tpl.blockchain = 'Ethereum'\nWHERE tm.is_erc20 = 1 AND tm.decimals = 6;"}, {"role": "user", "content": "Only include tokens where the latest price is between 0.5 and 2.0 USD, and limit the result to the top 5 tokens by price descending."}, {"role": "assistant", "content": "SELECT tm.symbol, tm.contract_address, tm.name, tm.total_supply, tpl.price AS latest_price\nFROM token_metas tm\nJOIN token_prices_latest tpl ON tm.contract_address = tpl.address AND tpl.blockchain = 'Ethereum'\nWHERE tm.is_erc20 = 1 AND tm.decimals = 6 AND tpl.price BETWEEN 0.5 AND 2.0\nORDER BY tpl.price DESC\nLIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp.timestamp, block_number.bigint, transaction_hash.text, transaction_index.bigint, from_address.text, contract_address.text, symbol.text, total_supply.text, name.text, decimals.bigint, is_erc20.integer, is_erc721.integer, is_erc1155.integer, is_proxy.integer, extra_info.text, pk.integer )\nCREATE TABLE erc1155_approval_for_all (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the transaction\n    transaction_index integer NOT NULL, -- Index of the transaction within the block\n    transaction_hash varchar(66) NOT NULL, -- Transaction hash\n    log_index integer NOT NULL, -- Log index\n    contract_address varchar(42) NOT NULL  -- Event contract address\n)\nCREATE TABLE erc20_balances ( block_number bigint, contract_address varchar, wallet_address varchar, amount varchar, pk varchar )\nCREATE TABLE erc20_balances_historical ( block_number bigint, contract_address text, wallet_address text, amount text, pk integer )\nCREATE TABLE nft_holders ( block_number.bigint, contract_address.text, wallet_address.text, token_id.text, contract_type.text, amount.text, pk.text )\nCREATE TABLE nft_holder_historical (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    contract_address varchar NOT NULL, -- Event contract address\n    wallet_address varchar NOT NULL, -- The wallet address for the contract(with bloom filter)\n    token_id varchar NOT NULL, -- NFT token id\n    contract_type varchar NOT NULL, -- NFT contract type\n    amount varchar NOT NULL, -- The quantity held in the wallet\n    pk integer NOT NULL  -- Partition key for the table(floor(block_number / 7200))\n)\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_coins_metadata (\n    object_id varchar NOT NULL, -- object id of the coin metadata object\n    coin_type varchar NOT NULL, -- coin type, eg. 0x...66::reap_token::REAP_TOKEN\n    status varchar NOT NULL, -- coin status, eg. exists, deleted\n    decimals bigint NOT NULL, -- decimals of the coin\n    description varchar NOT NULL, -- description of the coin\n    icon_url varchar NOT NULL, -- icon url of the coin\n    symbol varchar NOT NULL, -- symbol of the coin\n    name varchar NOT NULL  -- name of the coin\n)\nCREATE TABLE sui_nfts ( object_id.text, status.text, collection_type.text, package_id.text, previous_transaction.text, display.text, owner.text, name.text )\nCREATE TABLE nft_metadata ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, token_id varchar NOT NULL, contract_name varchar NOT NULL, erc_type varchar NOT NULL, amount bigint NOT NULL, minter varchar NOT NULL, owner varchar NOT NULL, mint_block_number bigint NOT NULL, mint_time bigint NOT NULL, mint_transaction_hash varchar NOT NULL, mint_price varchar NOT NULL, token_uri varchar NOT NULL, metadata varchar NOT NULL, name varchar NOT NULL, image_uri varchar NOT NULL, traits varchar NOT NULL, updated_at bigint NOT NULL, status varchar NOT NULL, rarity_score real NOT NULL, rarity_rank integer NOT NULL, unique_attribute_count integer NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_prices ( uuid.text, blockchain.text, address.text, decimals.bigint, symbol.text, price.real, timestamp.timestamp )\nCREATE TABLE token_prices_latest ( blockchain.text, address.text, decimals.bigint, symbol.text, price.real, timestamp.timestamp )\nCREATE TABLE erc20_approval ( block_number.bigint, block_timestamp.timestamp, transaction_index.integer, transaction_hash.text, log_index.integer, contract_address.text, pk.integer )\nCREATE TABLE token_balances (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n    tick varchar NOT NULL, -- Token tick\n    wallet_address varchar(42) NOT NULL, -- Address of owner\n    total_supply decimal(38,0) NOT NULL, -- Max supply\n    amount decimal(38,0) NOT NULL  -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE token_activities ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\nCREATE TABLE mud_holesky_redstone ( address text, table_id text, key_bytes text, key0 text, key1 text, static_data text, encoded_lengths text, dynamic_data text, is_deleted boolean, block_number bigint, log_index bigint )\nCREATE TABLE token_balances_bitcoin (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n    tick varchar(255) NOT NULL, -- Ticker: Identifier of the inscription\n    wallet_address varchar(42) NOT NULL, -- Address of owner\n    total_supply varchar NOT NULL, -- Max supply: Set max supply of the inscription\n    amount varchar NOT NULL  -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\nCREATE TABLE token_balances_avalanche (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n    tick varchar(20) NOT NULL, -- Ticker: Identifier of the inscription\n    wallet_address varchar(42) NOT NULL, -- Address of owner\n    total_supply decimal(38,0) NOT NULL, -- Max supply: Set max supply of the inscription\n    amount decimal(38,0) NOT NULL  -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id varchar )\n"}
{"conversations": [{"role": "user", "content": "For each state, count the number of customers and display state as state and the count as customer_count, ordered by customer_count descending."}, {"role": "assistant", "content": "SELECT state,\n       COUNT(*) AS customer_count\nFROM insurance.customers\nGROUP BY state\nORDER BY customer_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.customers ( customer_id text PRIMARY KEY, first_name text, last_name text, date_of_birth date, ssn_hash text, address_line1 text, address_line2 text, city text, state text, zip_code text, country text, phone_number text, email text, created_at timestamp, updated_at timestamp, status text )\n"}
{"conversations": [{"role": "user", "content": "Show me all securities (security_id, ticker_symbol, security_name) that are traded on the NASDAQ exchange and have a daily trading volume exceeding 1 million shares, along with the employee details (employee_id, first_name, last_name) who last updated these securities."}, {"role": "assistant", "content": "SELECT s.security_id, s.ticker_symbol, s.security_name, e.employee_id, e.first_name, e.last_name FROM financial_services.securities s JOIN financial_services.employees e ON s.last_updated = e.employee_id WHERE s.exchange = 'NASDAQ' AND s.security_id IN (SELECT security_id FROM financial_services.market_data WHERE volume > 1000000);"}, {"role": "user", "content": "Now modify the query to only include securities from the 'Technology' sector and sort them by ticker_symbol in ascending order."}, {"role": "assistant", "content": "SELECT s.security_id, s.ticker_symbol, s.security_name, e.employee_id, e.first_name, e.last_name FROM financial_services.securities s JOIN financial_services.employees e ON s.last_updated = e.employee_id WHERE s.exchange = 'NASDAQ' AND s.sector = 'Technology' AND s.security_id IN (SELECT security_id FROM financial_services.market_data WHERE volume > 1000000) ORDER BY s.ticker_symbol ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.accounts ( account_id text PRIMARY KEY, customer_id text, account_number text, account_type text, balance numeric, currency text, opened_date date, status text, interest_rate numeric, last_updated_at timestamp )\nCREATE TABLE financial_services.securities ( security_id text PRIMARY KEY, ticker_symbol text, isin_code text, cusip_code text, security_name text, security_type text, exchange text, currency text, issuer_name text, sector text, last_updated timestamp )\nCREATE TABLE financial_services.trades ( trade_id text PRIMARY KEY, account_id text, security_id text, order_id text, trade_type text, quantity numeric, price_per_unit numeric, total_amount numeric, commission numeric, trade_timestamp timestamp, settlement_date date, status text, execution_venue text )\nCREATE TABLE financial_services.market_data ( data_point_id bigserial PRIMARY KEY, security_id text, data_timestamp timestamp, open_price numeric, high_price numeric, low_price numeric, close_price numeric, adjusted_close_price numeric, volume bigint, source text )\nCREATE TABLE financial_services.employees ( employee_id text PRIMARY KEY, first_name text, last_name text, job_title text, department text, branch_id text, email text, phone_extension text, hire_date date, termination_date date, manager_id text, status text )\n"}
{"conversations": [{"role": "user", "content": "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": "What is the total amount paid across all premium payments for payments marked as 'Failed'?"}, {"role": "assistant", "content": "SELECT sum(amount_paid) FROM insurance.premium_payments WHERE status = 'Failed';"}], "system": "You are an SQL statement expert. Given the table structure 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.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 )\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 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": "Show me all events emitted by contracts where the event name contains 'Approval', along with the contract ID and transaction ID, sorted by emitted timestamp in descending order."}, {"role": "assistant", "content": "SELECT event_id, contract_id, event_name, transaction_id, emitted_at FROM web3.events WHERE event_name LIKE '%Approval%' ORDER BY emitted_at DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.events (\n    event_id character varying(64) NOT NULL,  -- unique identifier for the event\n    contract_id character varying(64) NOT NULL, -- identifier of the contract emitting the event\n    event_name character varying(128) NOT NULL, -- name of the event\n    data text NOT NULL, -- data payload of the event\n    emitted_at timestamp NOT NULL, -- time when the event was emitted\n    transaction_id character varying(64) NOT NULL, -- identifier of the transaction that triggered the event\n    log_index integer NOT NULL, -- index of the event log in the transaction\n    PRIMARY KEY (event_id)\n)\n"}
{"conversations": [{"role": "user", "content": "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": "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 names of service locations where services categorized as 'Licensing' have had appointments scheduled."}, {"role": "assistant", "content": "SELECT DISTINCT T1.location_name FROM service_locations AS T1 JOIN appointments AS T2 ON T1.location_id = T2.location_id JOIN services AS T3 ON T2.service_id = T3.service_id WHERE T3.category = 'Licensing';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.services (\n    service_id character varying(64) NOT NULL, -- unique identifier for the service\n    agency_id character varying(64) NOT NULL, -- FK to agencies table\n    service_name character varying(255) NOT NULL, -- name of the service (e.g., Driver's License Renewal)\n    description text,\n    category character varying(100), -- e.g., Licensing, Benefits, Taxation, Permits\n    eligibility_criteria text, -- description of who is eligible\n    standard_fee numeric(10, 2) DEFAULT 0.00, -- typical fee for the service\n    average_processing_time_days integer, -- estimated processing time\n    is_active boolean DEFAULT true, -- whether the service is currently offered\n    online_application_url character varying(255),\n    PRIMARY KEY (service_id)\n)\nCREATE TABLE government_services.service_locations (\n    location_id character varying(64) NOT NULL, -- unique identifier for the physical location\n    agency_id character varying(64) NOT NULL, -- FK to agencies table\n    location_name character varying(200), -- e.g., Downtown DMV Office\n    address text NOT NULL,\n    city character varying(100),\n    state character varying(50),\n    postal_code character varying(20),\n    latitude numeric(9, 6),\n    longitude numeric(9, 6),\n    operating_hours text, -- description of opening times\n    contact_phone character varying(32),\n    is_accessible boolean, -- accessibility information (e.g., wheelchair access)\n    PRIMARY KEY (location_id)\n)\nCREATE TABLE government_services.appointments (\n    appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment\n    citizen_id character varying(64) NOT NULL, -- FK to citizens table\n    employee_id character varying(64), -- FK to employees table (optional, if assigned)\n    location_id character varying(64), -- FK to service_locations table (if physical)\n    service_id character varying(64), -- FK to services table (optional, if related to specific service)\n    scheduled_start_time timestamp NOT NULL,\n    scheduled_end_time timestamp,\n    purpose text NOT NULL, -- reason for the appointment\n    status character varying(30) NOT NULL, -- e.g., Scheduled, Completed, Cancelled, No-Show\n    booking_method character varying(50), -- e.g., Online, Phone, In-Person\n    created_at timestamp NOT NULL, -- when the appointment was booked\n    notes text,\n    PRIMARY KEY (appointment_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List all managers (employees who have other employees reporting to them) along with the count of their direct reports, showing only those with more than 5 reports."}, {"role": "assistant", "content": "SELECT e.employee_id, e.first_name, e.last_name, COUNT(r.employee_id) as direct_reports_count FROM financial_services.employees e JOIN financial_services.employees r ON e.employee_id = r.manager_id WHERE e.status = 'Active' GROUP BY e.employee_id, e.first_name, e.last_name HAVING COUNT(r.employee_id) > 5 ORDER BY direct_reports_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.employees ( employee_id text PRIMARY KEY, first_name text, last_name text, job_title text, department text, branch_id text, email text, phone_extension text, hire_date date, termination_date date, manager_id text, status text )\n"}
{"conversations": [{"role": "user", "content": "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": "I want a list of game_id and the count of hidden achievements for each game."}, {"role": "assistant", "content": "SELECT game_id, COUNT(*) AS hidden_achievement_count\nFROM gaming_technology.achievements\nWHERE hidden = TRUE\nGROUP BY game_id;"}, {"role": "user", "content": "Now only include games where the hidden_achievement_count is greater than 5."}, {"role": "assistant", "content": "SELECT game_id, COUNT(*) AS hidden_achievement_count\nFROM gaming_technology.achievements\nWHERE hidden = TRUE\nGROUP BY game_id\nHAVING COUNT(*) > 5;"}, {"role": "user", "content": "Also order the results by hidden_achievement_count in descending order."}, {"role": "assistant", "content": "SELECT game_id, COUNT(*) AS hidden_achievement_count\nFROM gaming_technology.achievements\nWHERE hidden = TRUE\nGROUP BY game_id\nHAVING COUNT(*) > 5\nORDER BY hidden_achievement_count DESC;"}, {"role": "user", "content": "Finally, include the average points of those hidden achievements as avg_hidden_points."}, {"role": "assistant", "content": "SELECT game_id,\n       COUNT(*) AS hidden_achievement_count,\n       AVG(points) AS avg_hidden_points\nFROM gaming_technology.achievements\nWHERE hidden = TRUE\nGROUP BY game_id\nHAVING COUNT(*) > 5\nORDER BY hidden_achievement_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.players ( player_id uuid NOT NULL DEFAULT gen_random_uuid(), username character varying(100) NOT NULL UNIQUE, email character varying(255) NOT NULL UNIQUE, password_hash text NOT NULL, registration_date timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, last_login timestamp with time zone, country_code character(2), status character varying(20) NOT NULL DEFAULT 'active', profile_data jsonb, PRIMARY KEY (player_id) )\nCREATE TABLE gaming_technology.games ( game_id uuid PRIMARY KEY, title text, developer_id uuid, publisher_id uuid, genre text, release_date date, description text, platform text, engine text, website text )\nCREATE TABLE gaming_technology.game_sessions ( session_id uuid NOT NULL DEFAULT gen_random_uuid(), player_id uuid NOT NULL, game_id uuid NOT NULL, server_id uuid, start_time timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, end_time timestamp with time zone, duration_seconds integer, score integer, session_data jsonb, PRIMARY KEY (session_id) )\nCREATE TABLE gaming_technology.servers ( server_id uuid PRIMARY KEY, game_id uuid, server_name text, region text, ip_address text, port int, current_players int, max_players int, status text, last_heartbeat timestamptz )\nCREATE TABLE gaming_technology.achievements ( achievement_id.uuid, game_id.uuid, name.text, description.text, icon_url.text, points.integer, hidden.boolean )\nCREATE TABLE gaming_technology.player_achievements ( player_achievement_id uuid PRIMARY KEY, player_id uuid, achievement_id uuid, unlocked_at timestamptz )\nCREATE TABLE gaming_technology.in_game_items ( item_id uuid PRIMARY KEY, game_id uuid, item_name text, item_type text, description text, rarity text, cost_currency text, cost_amount numeric, attributes jsonb )\nCREATE TABLE gaming_technology.player_inventory ( inventory_id uuid PRIMARY KEY, player_id uuid, item_id uuid, quantity int, acquired_at timestamptz, instance_data jsonb )\n"}
{"conversations": [{"role": "user", "content": "List the first and last names of all doctors whose email address ends with '@hospital.org'."}, {"role": "assistant", "content": "SELECT first_name, last_name FROM healthcare.doctors WHERE email LIKE '%@hospital.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.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": "How many lawyers who are partners were hired in each year? Show the hire year and the count."}, {"role": "assistant", "content": "SELECT strftime('%Y', hire_date) AS hire_year ,  count(lawyer_id) FROM legal_services.lawyers WHERE is_partner  =  true GROUP BY hire_year"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.lawyers (\n    lawyer_id character varying(64) NOT NULL,  -- unique identifier for the lawyer\n    first_name character varying(100) NOT NULL, -- lawyer's first name\n    last_name character varying(100) NOT NULL, -- lawyer's last name\n    bar_number character varying(64) UNIQUE NOT NULL, -- lawyer's bar association number\n    firm_id character varying(64), -- FK to law_firms table\n    email character varying(128) UNIQUE NOT NULL, -- lawyer's professional email\n    phone character varying(32), -- lawyer's contact phone number\n    specialization text, -- areas of legal expertise\n    hire_date timestamp NOT NULL, -- date the lawyer was hired or joined\n    is_partner boolean DEFAULT false, -- flag indicating if the lawyer is a partner\n    PRIMARY KEY (lawyer_id)\n)\n"}
{"conversations": [{"role": "user", "content": "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 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": "Show me all customers (customer_id, first_name, last_name) who have both a personal loan (loan_type = 'Personal') and a high risk profile (risk_profile = 'High'), along with their loan details (loan_id, principal_amount)."}, {"role": "assistant", "content": "SELECT c.customer_id, c.first_name, c.last_name, l.loan_id, l.principal_amount FROM financial_services.customers c JOIN financial_services.loans l ON c.customer_id = l.account_id WHERE c.risk_profile = 'High' AND l.loan_type = 'Personal';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.customers ( customer_id text PRIMARY KEY, first_name text, last_name text, date_of_birth date, ssn_hash text, address text, city text, state text, zip_code text, country text, email text, phone_number text, created_at timestamp, status text, risk_profile text )\nCREATE TABLE financial_services.securities ( security_id text, ticker_symbol text, isin_code text, cusip_code text, security_name text, security_type text, exchange text, currency text, issuer_name text, sector text, last_updated timestamp )\nCREATE TABLE financial_services.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 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": "List the conversation IDs and user IDs for participants who have email notifications enabled."}, {"role": "assistant", "content": "SELECT cp.conversation_id, cp.user_id FROM social_media.conversation_participants AS cp JOIN social_media.user_settings AS us ON cp.user_id = us.user_id WHERE us.email_notifications_enabled = TRUE;"}, {"role": "user", "content": "Now, only include those users whose profile is set to private."}, {"role": "assistant", "content": "SELECT cp.conversation_id, cp.user_id FROM social_media.conversation_participants AS cp JOIN social_media.user_settings AS us ON cp.user_id = us.user_id WHERE us.email_notifications_enabled = TRUE AND us.private_profile = TRUE;"}, {"role": "user", "content": "Also, filter the results to include only participants who joined after a specific date, say '2023-01-01'."}, {"role": "assistant", "content": "SELECT cp.conversation_id, cp.user_id FROM social_media.conversation_participants AS cp JOIN social_media.user_settings AS us ON cp.user_id = us.user_id WHERE us.email_notifications_enabled = TRUE AND us.private_profile = TRUE AND cp.joined_at > '2023-01-01';"}, {"role": "user", "content": "Instead of user ID, can you show their theme setting and order the results by the join date ascending?"}, {"role": "assistant", "content": "SELECT cp.conversation_id, us.theme, cp.joined_at FROM social_media.conversation_participants AS cp JOIN social_media.user_settings AS us ON cp.user_id = us.user_id WHERE us.email_notifications_enabled = TRUE AND us.private_profile = TRUE AND cp.joined_at > '2023-01-01' ORDER BY cp.joined_at 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 (\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.conversation_participants ( participant_id text, conversation_id text, user_id text, joined_at timestamp, last_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": "Give me the total number of reservations and the sum of total_amount by month for the year 2023."}, {"role": "assistant", "content": "SELECT DATE_TRUNC('month', check_in_date) AS month,\n       COUNT(*)                         AS reservation_count,\n       SUM(total_amount)               AS total_revenue\nFROM hospitality_technology.reservations\nWHERE EXTRACT(YEAR FROM check_in_date) = 2023\nGROUP BY DATE_TRUNC('month', check_in_date)\nORDER BY month;"}, {"role": "user", "content": "Actually, I only want reservations with status 'CheckedOut' or 'Completed'."}, {"role": "assistant", "content": "SELECT DATE_TRUNC('month', check_in_date) AS month,\n       COUNT(*)                         AS reservation_count,\n       SUM(total_amount)               AS total_revenue\nFROM hospitality_technology.reservations\nWHERE EXTRACT(YEAR FROM check_in_date) = 2023\n  AND status IN ('CheckedOut', 'Completed')\nGROUP BY DATE_TRUNC('month', check_in_date)\nORDER BY month;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.reservations ( reservation_id text PRIMARY KEY, 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 int, num_children int, status text, booking_source text, rate_plan_id text, total_amount numeric, amount_paid numeric, special_requests text, created_at timestamp, updated_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "List all agencies that do not have a website URL specified. Return their agency_id, agency_name, and main_phone_number."}, {"role": "assistant", "content": "SELECT agency_id, agency_name, main_phone_number FROM government_services.agencies WHERE website_url IS NULL OR website_url = '';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.agencies ( agency_id character varying(64) NOT NULL, agency_name character varying(255) NOT NULL, jurisdiction_level character varying(50) NOT NULL, primary_contact_email character varying(128), main_phone_number character varying(32), website_url character varying(255), established_date date, parent_agency_id character varying(64), PRIMARY KEY (agency_id) )\n"}
{"conversations": [{"role": "user", "content": "List all wallets that were created during the hour of the day which saw the highest number of wallet creations. Show the wallet ID, user ID, address, and creation timestamp."}, {"role": "assistant", "content": "WITH HourlyCounts AS (\n    SELECT EXTRACT(HOUR FROM created_at) AS hour, COUNT(*) AS wallet_count\n    FROM web3.wallets\n    GROUP BY 1\n),\nMaxHour AS (\n    SELECT hour\n    FROM HourlyCounts\n    ORDER BY wallet_count DESC\n    LIMIT 1\n)\nSELECT wallet_id, user_id, address, created_at\nFROM web3.wallets\nWHERE EXTRACT(HOUR FROM created_at) = (SELECT hour FROM MaxHour);"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.wallets ( wallet_id text PRIMARY KEY, user_id text, address text, private_key text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show me all policies that expired in the last 60 days, along with their product IDs and premium amounts."}, {"role": "assistant", "content": "SELECT policy_id, product_id, premium_amount FROM insurance.policies WHERE status = 'expired' AND end_date >= CURRENT_DATE - INTERVAL '60 days' AND end_date <= CURRENT_DATE;"}, {"role": "user", "content": "Now include only policies that had a deductible of $1000 or more."}, {"role": "assistant", "content": "SELECT policy_id, product_id, premium_amount, deductible FROM insurance.policies WHERE status = 'expired' AND end_date >= CURRENT_DATE - INTERVAL '60 days' AND end_date <= CURRENT_DATE AND deductible >= 1000;"}, {"role": "user", "content": "I also want to see the count of such expired policies per product ID."}, {"role": "assistant", "content": "SELECT product_id, COUNT(*) as policy_count FROM insurance.policies WHERE status = 'expired' AND end_date >= CURRENT_DATE - INTERVAL '60 days' AND end_date <= CURRENT_DATE AND deductible >= 1000 GROUP BY product_id ORDER BY policy_count DESC;"}, {"role": "user", "content": "Finally, show me the average premium amount for these expired high-deductible policies grouped by product ID."}, {"role": "assistant", "content": "SELECT product_id, AVG(premium_amount) as avg_premium FROM insurance.policies WHERE status = 'expired' AND end_date >= CURRENT_DATE - INTERVAL '60 days' AND end_date <= CURRENT_DATE AND deductible >= 1000 GROUP BY product_id ORDER BY avg_premium DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.policies ( policy_id text PRIMARY KEY, customer_id text, product_id text, agent_id text, policy_number text, start_date date, end_date date, premium_amount numeric, coverage_limit numeric, deductible numeric, status text, issued_at timestamp, cancellation_date date, cancellation_reason text )\n"}
{"conversations": [{"role": "user", "content": "List the top 5 tokens by net_flow, showing token_symbol, net_flow, pnl, and price."}, {"role": "assistant", "content": "SELECT token_symbol,\n       net_flow,\n       pnl,\n       price\nFROM smart_money_token_performance\nORDER BY net_flow DESC\nLIMIT 5;"}, {"role": "user", "content": "Now join this result back to the full table to include the chain for each of these tokens."}, {"role": "assistant", "content": "WITH top5 AS (\n  SELECT token_symbol\n  FROM smart_money_token_performance\n  ORDER BY net_flow DESC\n  LIMIT 5\n)\nSELECT t.token_symbol,\n       t.chain,\n       t.net_flow,\n       t.pnl,\n       t.price\nFROM smart_money_token_performance t\nJOIN top5 ON t.token_symbol = top5.token_symbol;"}, {"role": "user", "content": "Filter these joined results to only include tokens with realized_ratio greater than 0.1."}, {"role": "assistant", "content": "WITH top5 AS (\n  SELECT token_symbol\n  FROM smart_money_token_performance\n  ORDER BY net_flow DESC\n  LIMIT 5\n)\nSELECT t.token_symbol,\n       t.chain,\n       t.net_flow,\n       t.pnl,\n       t.price,\n       t.realized_ratio\nFROM smart_money_token_performance t\nJOIN top5 ON t.token_symbol = top5.token_symbol\nWHERE t.realized_ratio > 0.1;"}, {"role": "user", "content": "Sort the final output by realized_ratio in descending order."}, {"role": "assistant", "content": "WITH top5 AS (\n  SELECT token_symbol\n  FROM smart_money_token_performance\n  ORDER BY net_flow DESC\n  LIMIT 5\n)\nSELECT t.token_symbol,\n       t.chain,\n       t.net_flow,\n       t.pnl,\n       t.price,\n       t.realized_ratio\nFROM smart_money_token_performance t\nJOIN top5 ON t.token_symbol = top5.token_symbol\nWHERE t.realized_ratio > 0.1\nORDER BY t.realized_ratio 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_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 claim, show the corresponding product_type of the insurance product for the related policy."}, {"role": "assistant", "content": "SELECT cl.claim_id, ip.product_type\nFROM insurance.claims cl\nJOIN insurance.policies p ON cl.policy_id = p.policy_id\nJOIN insurance.insurance_products ip ON p.product_id = ip.product_id;"}, {"role": "user", "content": "Sorry, there is no policies table, I got an error. Can you try joining claims to insurance_products another way?"}, {"role": "assistant", "content": "-- Unable to join directly since there is no 'policies' table connecting claims to insurance_products. If policy_id equals product_id, you may try:\nSELECT claim_id, policy_id, product_type\nFROM insurance.claims\nJOIN insurance.insurance_products ON claims.policy_id = insurance_products.product_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.customers ( customer_id.text, first_name.text, last_name.text, date_of_birth.date, ssn_hash.text, address_line1.text, address_line2.text, city.text, state.text, zip_code.text, country.text, phone_number.text, email.text, created_at.timestamp, updated_at.timestamp, status.text )\nCREATE TABLE insurance.claims ( claim_id.text, policy_id.text, customer_id.text, incident_date.timestamp, reported_date.timestamp, description.text, estimated_loss.numeric, status.text, settlement_amount.numeric, settlement_date.date, claim_handler_id.text, police_report_number.text )\nCREATE TABLE insurance.insurance_products ( product_id.text, product_name.text, product_type.text, description.text, base_premium.numeric, coverage_details.text, underwriting_rules.text, is_active.boolean, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE insurance.claim_documents ( document_id.text, claim_id.text, document_type.text, file_name.text, file_path.text, file_size_bytes.integer, mime_type.text, uploaded_by.text, uploaded_at.timestamp, description.text )\n"}
{"conversations": [{"role": "user", "content": "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": "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": "For each claim handler, count the number of documents uploaded for the claims they handled. Return claim_handler_id and document_count."}, {"role": "assistant", "content": "SELECT c.claim_handler_id,\n       COUNT(d.document_id) AS document_count\nFROM insurance.claims AS c\nJOIN insurance.claim_documents AS d\n  ON c.claim_id = d.claim_id\nGROUP BY c.claim_handler_id;"}, {"role": "user", "content": "Now restrict to handlers who have uploaded more than 10 documents."}, {"role": "assistant", "content": "SELECT c.claim_handler_id,\n       COUNT(d.document_id) AS document_count\nFROM insurance.claims AS c\nJOIN insurance.claim_documents AS d\n  ON c.claim_id = d.claim_id\nGROUP BY c.claim_handler_id\nHAVING COUNT(d.document_id) > 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.claims ( claim_id.text, policy_id.text, customer_id.text, incident_date.timestamp, reported_date.timestamp, description.text, estimated_loss.numeric, status.text, settlement_amount.numeric, settlement_date.date, claim_handler_id.text, police_report_number.text )\nCREATE TABLE insurance.premium_payments ( payment_id character varying(64) NOT NULL, policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, payment_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, amount_paid numeric(12, 2) NOT NULL, payment_method character varying(50), transaction_reference character varying(128) UNIQUE, due_date date, payment_period_start date, payment_period_end date, status character varying(30) NOT NULL DEFAULT 'Completed', PRIMARY KEY (payment_id) )\nCREATE TABLE insurance.claim_documents ( document_id text PRIMARY KEY, claim_id text, document_type text, file_name text, file_path text, file_size_bytes int, mime_type text, uploaded_by text, uploaded_at timestamp, description text )\n"}
{"conversations": [{"role": "user", "content": "Which users have sent messages containing media in group chats? List their usernames and the names of the group chats."}, {"role": "assistant", "content": "SELECT DISTINCT u.username, c.group_name\nFROM social_media.messages m\nJOIN social_media.users u ON m.sender_user_id = u.user_id\nJOIN social_media.conversations c ON m.conversation_id = c.conversation_id\nWHERE m.media_url IS NOT NULL AND c.is_group_chat = true;"}, {"role": "user", "content": "Also, show the time when each user first sent a media message in those group chats."}, {"role": "assistant", "content": "SELECT u.username, c.group_name, MIN(m.sent_at) AS first_media_message_time\nFROM social_media.messages m\nJOIN social_media.users u ON m.sender_user_id = u.user_id\nJOIN social_media.conversations c ON m.conversation_id = c.conversation_id\nWHERE m.media_url IS NOT NULL AND c.is_group_chat = true\nGROUP BY u.username, c.group_name;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users (\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 ( 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, 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, user_id.text, post_id.text, comment_id.text, created_at.timestamp )\nCREATE TABLE social_media.hashtags ( hashtag_id character varying(64) NOT NULL, tag_name character varying(100) NOT NULL UNIQUE, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (hashtag_id) )\nCREATE TABLE social_media.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 (\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": "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 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": "Could you provide a count of guests for each country code?"}, {"role": "assistant", "content": "SELECT country_code, COUNT(*) FROM hospitality_technology.guests GROUP BY country_code"}, {"role": "user", "content": "Now show only those countries that have more than 50 guests and order the list by the guest count in descending order."}, {"role": "assistant", "content": "SELECT country_code, COUNT(*) FROM hospitality_technology.guests GROUP BY country_code HAVING COUNT(*) > 50 ORDER BY COUNT(*) DESC"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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 (\n    room_type_id character varying(64) NOT NULL, -- unique identifier for the room type\n    property_id character varying(64) NOT NULL, -- FK to properties table (type might be property-specific)\n    type_name character varying(100) NOT NULL, -- e.g., Standard King, Deluxe Queen, Executive Suite\n    description text, -- description of the room type\n    base_rate numeric(10, 2) NOT NULL, -- standard price per night\n    max_occupancy integer NOT NULL, -- maximum number of guests\n    bed_type character varying(50), -- e.g., King, Queen, 2 Doubles, Twin\n    area_sqft numeric(8,2), -- size of the room in square feet\n    amenities text, -- comma-separated list or JSON of amenities\n    PRIMARY KEY (room_type_id),\n    FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id)\n)\nCREATE TABLE hospitality_technology.guests ( guest_id text, first_name text, last_name text, email text, phone_number text, date_of_birth date, address_line1 text, city text, state_province text, postal_code text, country_code text, preferences text, loyalty_member_id text, communication_consent boolean, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.reservations ( reservation_id.text, property_id.text, guest_id.text, room_id.text, room_type_id.text, check_in_date.date, check_out_date.date, actual_check_in_ts.timestamp, actual_check_out_ts.timestamp, num_adults.integer, num_children.integer, status.text, booking_source.text, rate_plan_id.text, total_amount.numeric, amount_paid.numeric, special_requests.text, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE hospitality_technology.staff ( staff_id text, property_id text, first_name text, last_name text, position text, work_email text, work_phone text, hire_date date, termination_date date, is_active boolean, access_level integer, manager_id text, created_at timestamp )\nCREATE TABLE hospitality_technology.services (\n    service_id character varying(64) NOT NULL, -- unique identifier for a chargeable service\n    property_id character varying(64) NOT NULL, -- FK to properties table\n    service_name character varying(150) NOT NULL, -- e.g., Room Service - Burger, Spa - Massage 60min, Laundry - Shirt\n    description text,\n    category character varying(100), -- e.g., Food & Beverage, Wellness, Business Center, Activities\n    price numeric(10, 2) NOT NULL, -- price per unit/instance\n    unit character varying(30), -- e.g., Per Item, Per Hour, Per Day\n    is_available boolean NOT NULL DEFAULT true, -- is the service currently offered?\n    department character varying(100), -- department responsible (e.g., F&B, Spa, Housekeeping)\n    PRIMARY KEY (service_id),\n    FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id)\n)\nCREATE TABLE hospitality_technology.service_orders ( order_id character varying(64) NOT NULL, reservation_id character varying(64), guest_id character varying(64) NOT NULL, service_id character varying(64) NOT NULL, staff_id_ordered character varying(64), staff_id_delivered character varying(64), order_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, delivery_timestamp timestamp with time zone, quantity integer NOT NULL DEFAULT 1, unit_price numeric(10, 2) NOT NULL, total_price numeric(12, 2) NOT NULL, status character varying(50) NOT NULL, notes text, bill_id character varying(64), PRIMARY KEY (order_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (service_id) REFERENCES hospitality_technology.services(service_id), FOREIGN KEY (staff_id_ordered) REFERENCES hospitality_technology.staff(staff_id), FOREIGN KEY (staff_id_delivered) REFERENCES hospitality_technology.staff(staff_id) )\nCREATE TABLE hospitality_technology.payments (\n    payment_id character varying(64) NOT NULL,  -- unique identifier for the payment transaction\n    reservation_id character varying(64), -- FK to reservations (if payment is for a stay)\n    guest_id character varying(64) NOT NULL, -- FK to guests (who paid)\n    bill_id character varying(64), -- FK to bills/invoices this payment applies to\n    amount numeric(12,2) NOT NULL, -- amount of the payment\n    currency_code character varying(3) NOT NULL, -- ISO currency code (e.g., USD, EUR)\n    payment_method character varying(50) NOT NULL, -- e.g., CreditCard, Cash, BankTransfer, Points, Voucher\n    card_type character varying(50), -- e.g., Visa, MasterCard, Amex (if CC)\n    card_last_four character varying(4), -- last 4 digits of CC (if CC)\n    transaction_ref character varying(128), -- reference ID from payment gateway or processor\n    payment_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, -- when the payment occurred\n    status character varying(50) NOT NULL, -- e.g., Pending, Succeeded, Failed, Refunded, Disputed\n    staff_id_processed character varying(64), -- FK to staff (who processed the payment)\n    notes text, -- notes about the payment\n    PRIMARY KEY (payment_id),\n    FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id),\n    FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id),\n    FOREIGN KEY (staff_id_processed) REFERENCES hospitality_technology.staff(staff_id)\n)\nCREATE TABLE hospitality_technology.reviews ( review_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, reservation_id character varying(64) UNIQUE, guest_id character varying(64) NOT NULL, rating_overall integer, rating_cleanliness integer, rating_service integer, rating_location integer, rating_value integer, comment text, review_source character varying(100), review_date timestamp with time zone NOT NULL DEFAULT current_timestamp, is_public boolean DEFAULT true, staff_response text, response_staff_id character varying(64), response_date timestamp with time zone, PRIMARY KEY (review_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (response_staff_id) REFERENCES hospitality_technology.staff(staff_id) )\n"}
{"conversations": [{"role": "user", "content": "Show all reviews with the guest's ID, review comment, and the full name of the staff member who responded."}, {"role": "assistant", "content": "SELECT r.review_id, r.guest_id, r.comment, s.first_name AS response_staff_first_name, s.last_name AS response_staff_last_name\nFROM hospitality_technology.reviews r\nLEFT JOIN hospitality_technology.staff s ON r.response_staff_id = s.staff_id;"}, {"role": "user", "content": "Can you include the property name as well?"}, {"role": "assistant", "content": "SELECT r.review_id, r.guest_id, r.comment, p.property_name, s.first_name AS response_staff_first_name, s.last_name AS response_staff_last_name\nFROM hospitality_technology.reviews r\nJOIN hospitality_technology.properties p ON r.property_id = p.property_id\nLEFT JOIN hospitality_technology.staff s ON r.response_staff_id = s.staff_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 hospitality_technology.properties ( property_id text PRIMARY KEY, property_name text, address_line1 text, address_line2 text, city text, state_province text, postal_code text, country_code text, phone_number text, email_address text, property_type text, star_rating numeric, timezone text, manager_staff_id text, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.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.reviews ( review_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, reservation_id character varying(64) UNIQUE, guest_id character varying(64) NOT NULL, rating_overall integer, rating_cleanliness integer, rating_service integer, rating_location integer, rating_value integer, comment text, review_source character varying(100), review_date timestamp with time zone NOT NULL DEFAULT current_timestamp, is_public boolean DEFAULT true, staff_response text, response_staff_id character varying(64), response_date timestamp with time zone, PRIMARY KEY (review_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (response_staff_id) REFERENCES hospitality_technology.staff(staff_id) )\n"}
{"conversations": [{"role": "user", "content": "For each 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": "For each event recorded, list its ID, name, and the status and value of the transaction in which it occurred."}, {"role": "assistant", "content": "SELECT E.event_id, E.event_name, E.transaction_id, T.status, T.value FROM web3.events AS E JOIN web3.transactions AS T ON E.transaction_id = T.transaction_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.events (\n    event_id character varying(64) NOT NULL,  -- unique identifier for the event\n    contract_id character varying(64) NOT NULL, -- identifier of the contract emitting the event\n    event_name character varying(128) NOT NULL, -- name of the event\n    data text NOT NULL, -- data payload of the event\n    emitted_at timestamp NOT NULL, -- time when the event was emitted\n    transaction_id character varying(64) NOT NULL, -- identifier of the transaction that triggered the event\n    log_index integer NOT NULL, -- index of the event log in the transaction\n    PRIMARY KEY (event_id)\n)\nCREATE TABLE web3.transactions ( transaction_id character varying(64) NOT NULL, from_address character varying(128) NOT NULL, to_address character varying(128), value numeric(38,14) NOT NULL, gas_used integer NOT NULL, gas_price numeric(38,14) NOT NULL, block_number integer NOT NULL, timestamp timestamp NOT NULL, input_data text, status character varying(32) NOT NULL, nonce integer NOT NULL, PRIMARY KEY (transaction_id) )\nCREATE TABLE web3.tokens ( token_id text PRIMARY KEY, contract_address text, token_name text, token_symbol text, decimals int, total_supply numeric )\nCREATE TABLE web3.wallets ( wallet_id text, user_id text, address text, private_key text, created_at timestamp )\nCREATE TABLE web3.users ( user_id text, username text, email text, password_hash text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show the usernames of users who have liked a comment made by a user they are following."}, {"role": "assistant", "content": "SELECT DISTINCT T1.username FROM social_media.users AS T1 JOIN likes AS T2 ON T1.user_id = T2.user_id JOIN comments AS T3 ON T2.target_entity_id = T3.comment_id JOIN social_media.users AS T4 ON T3.user_id = T4.user_id JOIN follows AS T5 ON T1.user_id = T5.follower_user_id AND T4.user_id = T5.followed_user_id WHERE T2.target_entity_type = 'comment';"}, {"role": "user", "content": "Include the content of the comment and the username of the commenter."}, {"role": "assistant", "content": "SELECT T1.username AS liker_username, T4.username AS commenter_username, T3.content AS comment_content FROM social_media.users AS T1 JOIN likes AS T2 ON T1.user_id = T2.user_id JOIN comments AS T3 ON T2.target_entity_id = T3.comment_id JOIN social_media.users AS T4 ON T3.user_id = T4.user_id JOIN follows AS T5 ON T1.user_id = T5.follower_user_id AND T4.user_id = T5.followed_user_id WHERE T2.target_entity_type = 'comment';"}, {"role": "user", "content": "Filter to only show likes made in June 2024 and order by like creation time descending."}, {"role": "assistant", "content": "SELECT T1.username AS liker_username, T4.username AS commenter_username, T3.content AS comment_content, T2.created_at AS like_time FROM social_media.users AS T1 JOIN likes AS T2 ON T1.user_id = T2.user_id JOIN comments AS T3 ON T2.target_entity_id = T3.comment_id JOIN social_media.users AS T4 ON T3.user_id = T4.user_id JOIN follows AS T5 ON T1.user_id = T5.follower_user_id AND T4.user_id = T5.followed_user_id WHERE T2.target_entity_type = 'comment' AND T2.created_at >= '2024-06-01' AND T2.created_at < '2024-07-01' ORDER BY T2.created_at DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id text PRIMARY KEY, username text, email text, password_hash text, full_name text, profile_picture_url text, bio text, location text, created_at timestamp, updated_at timestamp, is_verified bool )\n"}
{"conversations": [{"role": "user", "content": "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": "For projects that have completed more than one fundraising round, calculate the average investment value across all their recorded rounds. Display the project name and this average value."}, {"role": "assistant", "content": "SELECT project_name, AVG(investment_value) AS average_investment FROM project_fundraising_record GROUP BY project_name HAVING COUNT(*) > 1;"}, {"role": "user", "content": "Can you modify this to only show projects where the average investment value is greater than 10 million USD and order the results by average investment value descending?"}, {"role": "assistant", "content": "SELECT project_name, AVG(investment_value) AS average_investment FROM project_fundraising_record GROUP BY project_name HAVING COUNT(*) > 1 AND AVG(investment_value) > 10000000 ORDER BY average_investment DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE project_fundraising_record ( id character varying(32) NOT NULL,  -- fundraising record id project_id character varying(32) NOT NULL, -- the invested project's id project_name character varying(128) NOT NULL, -- name of the invested project rounds_name character varying(32), -- name of the fundraising round investment_value numeric(38,14), -- amount of the fundraising in USD investment_date character varying(128), -- the date of the investment happened introduction character varying(128), -- the introduction of the invested project valuation numeric(38,14), -- the valuation of the project in USD when invested )\n"}
{"conversations": [{"role": "user", "content": "What are the maintenance costs for a specific aircraft model like the Airbus A320?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to data regarding maintenance costs for specific aircraft models such as the Airbus A320. The information in the database is limited to details like model name, manufacturer, passenger capacity, and technical specifications. For maintenance cost information, you may need to consult with the manufacturer or a maintenance service provider."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE manufacturing.aircraft_models ( model_id character varying(64) NOT NULL, model_name character varying(128) NOT NULL, manufacturer character varying(128) NOT NULL, passenger_capacity integer, max_range_km integer, engine_type character varying(100), wingspan_m numeric(6,2), status character varying(50) NOT NULL, first_flight_date date, PRIMARY KEY (model_id) )\n"}
{"conversations": [{"role": "user", "content": "List the total value and count of transactions for each status, ordered by total value descending."}, {"role": "assistant", "content": "SELECT status, COUNT(*) AS transaction_count, SUM(value) AS total_value\nFROM web3.transactions\nGROUP BY status\nORDER BY total_value DESC;"}, {"role": "user", "content": "Actually, can you also include the average value per transaction for each status?"}, {"role": "assistant", "content": "SELECT status, COUNT(*) AS transaction_count, SUM(value) AS total_value, AVG(value) AS avg_value\nFROM web3.transactions\nGROUP BY status\nORDER BY total_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.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": "Find all medical records where the vitals JSON field contains a blood pressure reading with systolic higher than 140, and show the patient_id, record_date, and vitals."}, {"role": "assistant", "content": "SELECT patient_id, record_date, vitals FROM healthcare.medical_records WHERE (vitals->>'blood_pressure_systolic')::integer > 140;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.medical_records (\n    record_id character varying(64) NOT NULL,  -- unique identifier for the medical record entry\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    appointment_id character varying(64) UNIQUE, -- FK to appointments table (can be null if record not tied to specific appt)\n    doctor_id character varying(64) NOT NULL, -- FK to doctors table (doctor creating the record)\n    record_date timestamp with time zone NOT NULL, -- date the record/observation was made\n    chief_complaint text, -- patient's primary reason for visit\n    present_illness_history text, -- detailed history of the current issue\n    past_medical_history text, -- relevant past conditions/surgeries\n    physical_examination_notes text, -- findings from the physical exam\n    assessment text, -- doctor's assessment/diagnosis summary\n    treatment_plan text, -- planned course of action\n    vitals jsonb, -- store vitals like BP, HR, Temp as structured JSON\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (record_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List all active SUI coins with status 'exists' in metadata, showing coin_type, symbol, name, balance, and description."}, {"role": "assistant", "content": "SELECT sc.coin_type, sm.symbol, sm.name, sc.balance, sm.description\nFROM sui_coins sc\nJOIN sui_coins_metadata sm ON sc.coin_type = sm.coin_type\nWHERE sm.status = 'exists';"}, {"role": "user", "content": "Limit to coins where balance > 1000000 and order by balance descending."}, {"role": "assistant", "content": "SELECT sc.coin_type, sm.symbol, sm.name, sc.balance, sm.description\nFROM sui_coins sc\nJOIN sui_coins_metadata sm ON sc.coin_type = sm.coin_type\nWHERE sm.status = 'exists'\n  AND CAST(sc.balance AS numeric) > 1000000\nORDER BY CAST(sc.balance AS numeric) DESC;"}, {"role": "user", "content": "Also include the number of distinct owners per coin_type."}, {"role": "assistant", "content": "SELECT sc.coin_type, sm.symbol, sm.name, sm.description,\n       SUM(CAST(sc.balance AS numeric)) AS total_balance,\n       COUNT(DISTINCT sc.owner) AS owner_count\nFROM sui_coins sc\nJOIN sui_coins_metadata sm ON sc.coin_type = sm.coin_type\nWHERE sm.status = 'exists'\n  AND CAST(sc.balance AS numeric) > 1000000\nGROUP BY sc.coin_type, sm.symbol, sm.name, sm.description\nORDER BY total_balance DESC;"}, {"role": "user", "content": "Only show the top 3 coins by total_balance."}, {"role": "assistant", "content": "SELECT sc.coin_type, sm.symbol, sm.name, sm.description,\n       SUM(CAST(sc.balance AS numeric)) AS total_balance,\n       COUNT(DISTINCT sc.owner) AS owner_count\nFROM sui_coins sc\nJOIN sui_coins_metadata sm ON sc.coin_type = sm.coin_type\nWHERE sm.status = 'exists'\n  AND CAST(sc.balance AS numeric) > 1000000\nGROUP BY sc.coin_type, sm.symbol, sm.name, sm.description\nORDER BY total_balance DESC\nLIMIT 3;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE erc1155_approval_for_all (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the transaction\n    transaction_index integer NOT NULL, -- Index of the transaction within the block\n    transaction_hash varchar(66) NOT NULL, -- Transaction hash\n    log_index integer NOT NULL, -- Log index\n    contract_address varchar(42) NOT NULL  -- Event contract address\n)\nCREATE TABLE erc20_balances ( block_number bigint, contract_address varchar, wallet_address varchar, amount varchar, pk varchar )\nCREATE TABLE erc20_balances_historical ( block_number bigint, contract_address text, wallet_address text, amount text, pk integer )\nCREATE TABLE nft_holders ( block_number.bigint, contract_address.text, wallet_address.text, token_id.text, contract_type.text, amount.text, pk.text )\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_coins_metadata (\n    object_id varchar NOT NULL, -- object id of the coin metadata object\n    coin_type varchar NOT NULL, -- coin type, eg. 0x...66::reap_token::REAP_TOKEN\n    status varchar NOT NULL, -- coin status, eg. exists, deleted\n    decimals bigint NOT NULL, -- decimals of the coin\n    description varchar NOT NULL, -- description of the coin\n    icon_url varchar NOT NULL, -- icon url of the coin\n    symbol varchar NOT NULL, -- symbol of the coin\n    name varchar NOT NULL  -- name of the coin\n)\nCREATE TABLE token_prices_latest ( blockchain.text, address.text, decimals.bigint, symbol.text, price.real, timestamp.timestamp )\nCREATE TABLE erc20_approval ( block_number.bigint, block_timestamp.timestamp, transaction_index.integer, transaction_hash.text, log_index.integer, contract_address.text, pk.integer )\nCREATE TABLE token_activities ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\nCREATE TABLE token_balances_bitcoin (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n    tick varchar(255) NOT NULL, -- Ticker: Identifier of the inscription\n    wallet_address varchar(42) NOT NULL, -- Address of owner\n    total_supply varchar NOT NULL, -- Max supply: Set max supply of the inscription\n    amount varchar NOT NULL  -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id varchar )\n"}
{"conversations": [{"role": "user", "content": "List all public reviews including the property name, guest full name, overall rating, and comment."}, {"role": "assistant", "content": "SELECT T2.property_name, T3.first_name || ' ' || T3.last_name AS guest_full_name, T1.rating_overall, T1.comment FROM hospitality_technology.reviews AS T1 INNER JOIN hospitality_technology.properties AS T2 ON T1.property_id = T2.property_id INNER JOIN hospitality_technology.guests AS T3 ON T1.guest_id = T3.guest_id WHERE T1.is_public = TRUE;"}, {"role": "user", "content": "Only include reviews with an overall rating of 5."}, {"role": "assistant", "content": "SELECT T2.property_name, T3.first_name || ' ' || T3.last_name AS guest_full_name, T1.rating_overall, T1.comment FROM hospitality_technology.reviews AS T1 INNER JOIN hospitality_technology.properties AS T2 ON T1.property_id = T2.property_id INNER JOIN hospitality_technology.guests AS T3 ON T1.guest_id = T3.guest_id WHERE T1.is_public = TRUE AND T1.rating_overall = 5;"}, {"role": "user", "content": "Also, order the results by review date descending."}, {"role": "assistant", "content": "SELECT T2.property_name, T3.first_name || ' ' || T3.last_name AS guest_full_name, T1.rating_overall, T1.comment FROM hospitality_technology.reviews AS T1 INNER JOIN hospitality_technology.properties AS T2 ON T1.property_id = T2.property_id INNER JOIN hospitality_technology.guests AS T3 ON T1.guest_id = T3.guest_id WHERE T1.is_public = TRUE AND T1.rating_overall = 5 ORDER BY T1.review_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 hospitality_technology.properties ( property_id text PRIMARY KEY, property_name text, address_line1 text, address_line2 text, city text, state_province text, postal_code text, country_code text, phone_number text, email_address text, property_type text, star_rating numeric, timezone text, manager_staff_id text, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.rooms ( room_id text PRIMARY KEY, property_id text, room_number text, room_type_id text, floor int, status text, is_smoking boolean, features text, current_condition text, last_cleaned_at timestamp )\nCREATE TABLE hospitality_technology.room_types ( room_type_id text PRIMARY KEY, property_id text, type_name text, description text, base_rate numeric, max_occupancy int, bed_type text, area_sqft numeric, amenities text )\nCREATE TABLE hospitality_technology.guests ( guest_id text PRIMARY KEY, first_name text, last_name text, email text, phone_number text, date_of_birth date, address_line1 text, city text, state_province text, postal_code text, country_code text, preferences text, loyalty_member_id text, communication_consent boolean, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.reservations ( reservation_id text PRIMARY KEY, 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 int, num_children int, status text, booking_source text, rate_plan_id text, total_amount numeric, amount_paid numeric, special_requests text, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.staff ( staff_id text PRIMARY KEY, property_id text, first_name text, last_name text, position text, work_email text, work_phone text, hire_date date, termination_date date, is_active boolean, access_level int, manager_id text, created_at timestamp )\nCREATE TABLE hospitality_technology.payments ( payment_id text PRIMARY KEY, reservation_id text, guest_id text, bill_id text, amount numeric, currency_code text, payment_method text, card_type text, card_last_four text, transaction_ref text, payment_timestamp timestamp, status text, staff_id_processed text, notes text )\nCREATE TABLE hospitality_technology.reviews ( review_id text PRIMARY KEY, property_id text, reservation_id text, guest_id text, rating_overall int, rating_cleanliness int, rating_service int, rating_location int, rating_value int, comment text, review_source text, review_date timestamp, is_public boolean, staff_response text, response_staff_id text, response_date timestamp )\n"}
{"conversations": [{"role": "user", "content": "Find transactions where the from_address is the same as the to_address (self-transactions) with values greater than 1 ETH (1e18 wei), showing transaction_id and value."}, {"role": "assistant", "content": "SELECT transaction_id, value FROM web3.transactions WHERE from_address = to_address AND value > 1000000000000000000;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.transactions ( transaction_id text PRIMARY KEY, from_address text, to_address text, value numeric, gas_used int, gas_price numeric, block_number int, timestamp timestamp, input_data text, status text, nonce int )\n"}
{"conversations": [{"role": "user", "content": "For each passenger, show their passenger_id, first_name, last_name, the date and time of their earliest booking, and the date and time of their latest booking."}, {"role": "assistant", "content": "SELECT p.passenger_id,\n       p.first_name,\n       p.last_name,\n       MIN(b.booking_time) AS earliest_booking_time,\n       MAX(b.booking_time) AS latest_booking_time\nFROM transportation.passengers p\nLEFT JOIN transportation.bookings b\n  ON p.passenger_id = b.passenger_id\nGROUP BY p.passenger_id,\n         p.first_name,\n         p.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 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.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 (\n    passenger_id character varying(64) NOT NULL,  -- unique identifier for the passenger\n    first_name character varying(128) NOT NULL, -- passenger's first name\n    last_name character varying(128) NOT NULL, -- passenger's last name\n    email character varying(128) UNIQUE, -- email address\n    phone_number character varying(32) UNIQUE, -- phone number\n    date_of_birth date, -- passenger's date of birth\n    loyalty_program_id character varying(64), -- identifier for loyalty program membership\n    created_at timestamp with time zone NOT NULL, -- time when the passenger record was created\n    PRIMARY KEY (passenger_id)\n)\nCREATE TABLE transportation.bookings ( booking_id character varying(64) NOT NULL, passenger_id character varying(64) NOT NULL, trip_id character varying(64) NOT NULL, seat_number character varying(16), booking_time timestamp with time zone NOT NULL, status character varying(32) NOT NULL, fare numeric(10, 2) NOT NULL, payment_transaction_id character varying(128), special_requests text, PRIMARY KEY (booking_id) )\n"}
{"conversations": [{"role": "user", "content": "List all NFT collections from the sui_nfts table where the owner is not null, including their name and collection_type."}, {"role": "assistant", "content": "SELECT name, collection_type FROM sui_nfts WHERE owner IS NOT NULL;"}, {"role": "user", "content": "Can you also include the display field and filter to only show collections with a package_id starting with '0x'?"}, {"role": "assistant", "content": "SELECT name, collection_type, display FROM sui_nfts WHERE owner IS NOT NULL AND package_id LIKE '0x%';"}, {"role": "user", "content": "Now sort these results by name in ascending order."}, {"role": "assistant", "content": "SELECT name, collection_type, display FROM sui_nfts WHERE owner IS NOT NULL AND package_id LIKE '0x%' ORDER BY name ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp timestamp(6) NOT NULL, block_number bigint NOT NULL, transaction_hash varchar NOT NULL, transaction_index bigint NOT NULL, from_address varchar NOT NULL, contract_address varchar NOT NULL, symbol varchar NOT NULL, total_supply varchar NOT NULL, name varchar NOT NULL, decimals bigint NOT NULL, is_erc20 integer NOT NULL, is_erc721 integer NOT NULL, is_erc1155 integer NOT NULL, is_proxy integer NOT NULL, extra_info varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE erc1155_approval_for_all ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar(66) NOT NULL, log_index integer NOT NULL, contract_address varchar(42) NOT NULL )\nCREATE TABLE erc20_balances_historical ( block_number bigint, contract_address text, wallet_address text, amount text, pk integer )\nCREATE TABLE nft_holders ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, token_id varchar NOT NULL, contract_type varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE nft_holder_historical ( block_number.bigint, contract_address.text, wallet_address.text, token_id.text, contract_type.text, amount.text, pk.integer )\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_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 (\n    blockchain varchar NOT NULL, -- blockchain fields for the functionType  in contract\n    contract_address varchar NOT NULL, -- Contract address(with bloom filter)\n    token_id varchar NOT NULL, -- The number of the token\n    contract_name varchar NOT NULL, -- contract_name fields for the functionType  in contract\n    erc_type varchar NOT NULL, -- The type of token\n    amount bigint NOT NULL, -- amount fields for the functionType  in contract\n    minter varchar NOT NULL, -- minter fields for the functionType  in contract\n    owner varchar NOT NULL, -- owner fields for the functionType  in contract\n    mint_block_number bigint NOT NULL, -- mint_block_number fields for the functionType  in contract\n    mint_time bigint NOT NULL, -- mint_time fields for the functionType  in contract\n    mint_transaction_hash varchar NOT NULL, -- mint_transaction_hash fields for the functionType  in contract\n    mint_price varchar NOT NULL, -- mint_price fields for the functionType  in contract\n    token_uri varchar NOT NULL, -- token_uri fields for the functionType  in contract\n    metadata varchar NOT NULL, -- metadata fields for the functionType  in contract\n    name varchar NOT NULL, -- name fields for the functionType  in contract\n    image_uri varchar NOT NULL, -- image_uri fields for the functionType  in contract\n    traits varchar NOT NULL, -- traits fields for the functionType  in contract\n    updated_at bigint NOT NULL, -- updated_at fields for the functionType  in contract\n    status varchar NOT NULL, -- status fields for the functionType  in contract\n    rarity_score real NOT NULL, -- rarity_score fields for the functionType  in contract\n    rarity_rank integer NOT NULL, -- rarity_rank fields for the functionType  in contract\n    unique_attribute_count integer NOT NULL, -- unique_attribute_count fields for the functionType  in contract\n    pk integer NOT NULL  -- Partition key for the table(floor(mint_time / 1000 / 86400 / 30))\n)\nCREATE TABLE token_prices ( uuid 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 varchar, log_index integer, contract_address varchar, pk integer )\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 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_info_bitcoin (\n    block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n    block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n    tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n    tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n    tick varchar(255) NOT NULL, -- Ticker:  Identifier of the inscription\n    max_supply decimal(38,0) NOT NULL, -- Max supply: Set max supply of the inscription\n    lim decimal(38,0) NOT NULL, -- Mint limit: limit per inscription\n    wlim decimal(38,0) NOT NULL, -- Limit of each address can maximum mint\n    dec integer NOT NULL, -- Decimal for minimum divie\n    creator varchar(42) NOT NULL  -- Address originating the inscription (matches from_address in transactions table)\n)\nCREATE TABLE token_activities_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 (\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)\n"}
{"conversations": [{"role": "user", "content": "What is the average commission rate for active agents?"}, {"role": "assistant", "content": "SELECT AVG(commission_rate) FROM insurance.agents WHERE status = 'Active';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.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 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 )\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.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": "List all clients along with their case_number and case_type for cases that are currently 'Open'."}, {"role": "assistant", "content": "SELECT c.first_name, c.last_name, c.email, cs.case_number, cs.case_type\nFROM legal_services.clients AS c\nJOIN legal_services.cases AS cs\n  ON c.client_id = cs.client_id\nWHERE cs.status = 'Open';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.clients ( client_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, company_name character varying(200), email character varying(128) UNIQUE NOT NULL, phone character varying(32), address text, date_registered timestamp NOT NULL, status character varying(32) NOT NULL, PRIMARY KEY (client_id) )\nCREATE TABLE legal_services.lawyers ( lawyer_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, bar_number character varying(64) UNIQUE NOT NULL, firm_id character varying(64), email character varying(128) UNIQUE NOT NULL, phone character varying(32), specialization text, hire_date timestamp NOT NULL, is_partner boolean DEFAULT false, PRIMARY KEY (lawyer_id) )\nCREATE TABLE legal_services.law_firms ( firm_id character varying(64) NOT NULL, firm_name character varying(200) NOT NULL, address text NOT NULL, phone character varying(32), website character varying(255), founded_date date, managing_partner_id character varying(64), PRIMARY KEY (firm_id) )\nCREATE TABLE legal_services.cases ( case_id character varying(64) NOT NULL, case_number character varying(100) UNIQUE, case_name text NOT NULL, client_id character varying(64) NOT NULL, lead_lawyer_id character varying(64) NOT NULL, case_type character varying(100) NOT NULL, status character varying(50) NOT NULL, date_opened timestamp NOT NULL, date_closed timestamp, description text, court_jurisdiction character varying(128), PRIMARY KEY (case_id) )\nCREATE TABLE legal_services.documents ( document_id character varying(64) NOT NULL, case_id character varying(64) NOT NULL, document_name character varying(255) NOT NULL, document_type character varying(100), storage_path text NOT NULL, uploaded_by_lawyer_id character varying(64), upload_timestamp timestamp NOT NULL, version integer DEFAULT 1, description text, PRIMARY KEY (document_id) )\nCREATE TABLE legal_services.time_entries ( entry_id character varying(64) NOT NULL, case_id character varying(64) NOT NULL, lawyer_id character varying(64) NOT NULL, date_worked date NOT NULL, hours_spent numeric(5, 2) NOT NULL CHECK (hours_spent > 0), billing_rate numeric(10, 2) NOT NULL, description text NOT NULL, is_billable boolean DEFAULT true, is_billed boolean DEFAULT false, invoice_id character varying(64), created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (entry_id) )\nCREATE TABLE legal_services.appointments ( appointment_id character varying(64) NOT NULL, client_id character varying(64) NOT NULL, lawyer_id character varying(64) NOT NULL, case_id character varying(64), start_time timestamp NOT NULL, end_time timestamp NOT NULL, location text, subject character varying(255), notes text, status character varying(50) NOT NULL, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (appointment_id) )\n"}
{"conversations": [{"role": "user", "content": "Show me the top 5 narratives by market cap, along with their top 3 coins and 24-hour trading volume."}, {"role": "assistant", "content": "SELECT narrative, top_3_coins, volume_24h FROM narrative_info ORDER BY market_cap DESC LIMIT 5;"}, {"role": "user", "content": "Can you also include the 7-day price change percentage and filter for narratives with a positive 7-day price change?"}, {"role": "assistant", "content": "SELECT narrative, top_3_coins, volume_24h, price_change_percentage_7d FROM narrative_info WHERE price_change_percentage_7d > 0 ORDER BY market_cap DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE narrative_info ( narrative character varying(512) NOT NULL, -- the id of narrative top_3_coins text, -- the top 3 tokens in the narrative price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour in the narrative price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours in the narrative price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days in the narrative market_cap double precision, -- the market cap of the narrative volume_24h double precision, -- the trade volume of the narrative trend_rank bigint, -- the trending rank of the narrative, value 1 expresses the most popular narrative token_num bigint, -- total token number in the narrative ,PRIMARY KEY (narrative) )\n  \"CREATE TABLE smart_money_token_inflow (\",\n    \"token_address character varying(100) NOT NULL, -- the token's address\",\n    \"token_symbol character varying(100), -- the tokens's symbol\",\n    \"token_amount numeric(38,2), -- the absolute value of the amount if user bought minus  the amount user sold of this token\",\n    \"usd_value numeric(38,2), -- the absolute usd value of the bought token minus sold token\",\n    \"avg_price numeric(38,6), -- the average cost price of user spent on this token\",\n    \"type int, -- the direction of the trade on this token. 1 means buying, 2 means selling\",\n    \"address_amount integer, -- the amount of the user bought this token\",\n    \"narrative character varying(100), -- the category or narrative of the token\",\n    \"chain character varying(100), -- the chain that the token resides\",\n    \",PRIMARY KEY (token_address, chain)\",\n\n"}
{"conversations": [{"role": "user", "content": "Retrieve the product_id, product_name, base_premium, and created_at for all active insurance products with a base_premium greater than 1000, ordered by base_premium descending."}, {"role": "assistant", "content": "SELECT\n  product_id,\n  product_name,\n  base_premium,\n  created_at\nFROM insurance.insurance_products\nWHERE is_active = true\n  AND base_premium > 1000\nORDER BY base_premium DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.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)\n"}
{"conversations": [{"role": "user", "content": "What is the average number of days by which paid invoices were paid late? Calculate the average of (payment_date - due_date) for invoices with status 'Paid'."}, {"role": "assistant", "content": "SELECT AVG((payment_date::date - due_date)) AS average_late_days\nFROM legal_services.invoices\nWHERE status = 'Paid';"}], "system": "You are an SQL statement expert. Given the table structure 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 character varying(64) NOT NULL, invoice_number character varying(100) UNIQUE NOT NULL, client_id character varying(64) NOT NULL, case_id character varying(64), issue_date date NOT NULL, due_date date NOT NULL, total_amount numeric(12, 2) NOT NULL, amount_paid numeric(12, 2) DEFAULT 0.00, status character varying(50) NOT NULL, payment_date timestamp, notes text, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (invoice_id) )\n"}
{"conversations": [{"role": "user", "content": "What proportion of posts have received at least one like? Return the ratio as a decimal between 0 and 1."}, {"role": "assistant", "content": "SELECT COUNT(DISTINCT CASE WHEN l.post_id IS NOT NULL THEN p.post_id END)::float / COUNT(DISTINCT p.post_id) AS like_ratio\nFROM social_media.posts p\nLEFT JOIN social_media.likes l ON p.post_id = l.post_id;"}, {"role": "user", "content": "Please break down this ratio by media_type, excluding posts without a media_type."}, {"role": "assistant", "content": "SELECT p.media_type,\n       COUNT(DISTINCT CASE WHEN l.post_id IS NOT NULL THEN p.post_id END)::float / COUNT(*) AS like_ratio\nFROM social_media.posts p\nLEFT JOIN social_media.likes l ON p.post_id = l.post_id\nWHERE p.media_type IS NOT NULL\nGROUP BY p.media_type;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.posts ( post_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, content text, media_url text, media_type character varying(20), created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, visibility character varying(20) NOT NULL DEFAULT 'public', location_lat numeric(9,6), location_lon numeric(9,6), PRIMARY KEY (post_id) )\nCREATE TABLE social_media.likes ( like_id text PRIMARY KEY, user_id text, post_id text, comment_id text, created_at timestamp )\nCREATE TABLE social_media.hashtags ( hashtag_id character varying(64) NOT NULL, tag_name character varying(100) NOT NULL UNIQUE, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (hashtag_id) )\nCREATE TABLE social_media.messages (\n    message_id character varying(64) NOT NULL, -- unique identifier for the message\n    conversation_id character varying(64) NOT NULL, -- identifier for the conversation thread (FK to conversations.conversation_id)\n    sender_user_id character varying(64) NOT NULL, -- identifier of the sender (FK to users.user_id)\n    content text, -- textual content of the message\n    media_url text, -- URL to attached media (image/video)\n    media_type character varying(20), -- type of media ('image', 'video', null)\n    sent_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when message was sent\n    read_at timestamp, -- timestamp when message was read by recipient(s)\n    PRIMARY KEY (message_id)\n)\nCREATE TABLE social_media.conversation_participants ( participant_id.text, conversation_id.text, user_id.text, joined_at.timestamp, last_read_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show me all policies along with the date and amount of their most recent premium payment."}, {"role": "assistant", "content": "SELECT p.policy_id, p.policy_number, pp.payment_date AS most_recent_payment_date, pp.amount_paid AS most_recent_payment_amount\nFROM insurance.policies p\nJOIN LATERAL (\n  SELECT payment_date, amount_paid\n  FROM insurance.premium_payments\n  WHERE policy_id = p.policy_id\n  ORDER BY payment_date DESC\n  LIMIT 1\n) pp ON TRUE;"}, {"role": "user", "content": "Actually, only show policies where the most recent payment was made in 2024."}, {"role": "assistant", "content": "SELECT p.policy_id, p.policy_number, pp.payment_date AS most_recent_payment_date, pp.amount_paid AS most_recent_payment_amount\nFROM insurance.policies p\nJOIN LATERAL (\n  SELECT payment_date, amount_paid\n  FROM insurance.premium_payments\n  WHERE policy_id = p.policy_id\n  ORDER BY payment_date DESC\n  LIMIT 1\n) pp ON TRUE\nWHERE EXTRACT(YEAR FROM pp.payment_date) = 2024;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.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.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 the name and symbol for all assets that do not have a corresponding entry with the key 'website' in the metadata table."}, {"role": "assistant", "content": "SELECT T1.name , T1.symbol FROM trading_platform.assets AS T1 LEFT JOIN trading_platform.metadata AS T2 ON T1.asset_id  =  T2.asset_id AND T2.key  =  'website' WHERE T2.metadata_id IS NULL"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.users ( user_id character varying(64) NOT NULL, username character varying(128) NOT NULL, email character varying(128) NOT NULL, password_hash text NOT NULL, created_at timestamp NOT NULL, PRIMARY KEY (user_id) )\nCREATE TABLE trading_platform.wallets ( wallet_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, address character varying(128) NOT NULL, private_key text NOT NULL, created_at timestamp NOT NULL, PRIMARY KEY (wallet_id) )\nCREATE TABLE trading_platform.orders ( order_id text PRIMARY KEY, user_id text, wallet_id text, asset_id text, order_type text, quantity numeric, price numeric, status text, created_at timestamp )\nCREATE TABLE trading_platform.trades (\n    trade_id character varying(64) NOT NULL,  -- unique identifier for the trade\n    order_id character varying(64) NOT NULL, -- identifier of the order that led to the trade\n    buyer_id character varying(64) NOT NULL, -- identifier of the buyer\n    seller_id character varying(64) NOT NULL, -- identifier of the seller\n    asset_id character varying(64) NOT NULL, -- identifier of the asset being traded\n    quantity numeric(38,14) NOT NULL, -- quantity of the asset in the trade\n    price numeric(38,14) NOT NULL, -- price per unit of the asset\n    traded_at timestamp NOT NULL, -- time when the trade was executed\n    PRIMARY KEY (trade_id)\n)\nCREATE TABLE trading_platform.assets ( asset_id text PRIMARY KEY, name text, symbol text, type text )\nCREATE TABLE trading_platform.utxos ( utxo_id.text, transaction_id.text, output_index.integer, address.text, amount.numeric, spent.boolean )\nCREATE TABLE trading_platform.dapps ( dapp_id.text, name.text, description.text, url.text )\nCREATE TABLE trading_platform.metadata (\n    metadata_id character varying(64) NOT NULL,  -- unique identifier for the metadata\n    asset_id character varying(64) NOT NULL, -- identifier of the asset the metadata is associated with\n    key character varying(128) NOT NULL, -- key of the metadata\n    value text NOT NULL, -- value of the metadata\n    PRIMARY KEY (metadata_id)\n)\nCREATE TABLE trading_platform.kyc_audit (\n    kyc_audit_id character varying(64) NOT NULL,  -- unique identifier for the KYC audit\n    user_id character varying(64) NOT NULL, -- identifier of the user being audited\n    status character varying(32) NOT NULL, -- status of the KYC audit (e.g., pending, approved, rejected)\n    reviewed_at timestamp NOT NULL, -- time when the KYC audit was reviewed\n    PRIMARY KEY (kyc_audit_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List pairs of citizens who share the same email domain."}, {"role": "assistant", "content": "SELECT c1.first_name AS first1,\n       c1.last_name AS last1,\n       c2.first_name AS first2,\n       c2.last_name AS last2,\n       SPLIT_PART(c1.contact_email, '@', 2) AS domain\nFROM government_services.citizens c1\nJOIN government_services.citizens c2\n  ON SPLIT_PART(c1.contact_email, '@', 2) = SPLIT_PART(c2.contact_email, '@', 2)\n AND c1.citizen_id < c2.citizen_id\nWHERE c1.contact_email IS NOT NULL\n  AND c2.contact_email IS NOT NULL;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens (\n    citizen_id character varying(64) NOT NULL,  -- unique identifier for the citizen\n    national_id_number character varying(128) NOT NULL UNIQUE, -- official national identification number\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    date_of_birth date NOT NULL,\n    gender character varying(20),\n    primary_address text NOT NULL, -- full primary residential address\n    contact_email character varying(128) UNIQUE,\n    contact_phone character varying(32),\n    registration_date timestamp NOT NULL, -- when the citizen profile was created\n    is_verified boolean DEFAULT false, -- whether identity has been officially verified\n    PRIMARY KEY (citizen_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Show me all insurance plans that have more than 5 patients enrolled as their primary insurance, along with the provider name and count of patients."}, {"role": "assistant", "content": "SELECT ip.plan_id, ip.plan_name, ip.insurance_provider, COUNT(pi.patient_id) AS patient_count FROM healthcare.insurance_plans ip JOIN healthcare.patient_insurance pi ON ip.plan_id = pi.plan_id WHERE pi.is_primary = true GROUP BY ip.plan_id, ip.plan_name, ip.insurance_provider HAVING COUNT(pi.patient_id) > 5 ORDER BY patient_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.doctors ( doctor_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, specialty character varying(100) NOT NULL, license_number character varying(50) UNIQUE NOT NULL, phone_number character varying(20), email character varying(128) UNIQUE, hospital_affiliation_id character varying(64), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (doctor_id) )\nCREATE TABLE healthcare.appointments ( appointment_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, doctor_id character varying(64) NOT NULL, appointment_time timestamp with time zone NOT NULL, duration_minutes integer NOT NULL, reason text, status character varying(32) NOT NULL, location_id character varying(64), notes text, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (appointment_id) )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id character varying(64) NOT NULL, record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, doctor_id character varying(64) NOT NULL, diagnosis_code character varying(20) NOT NULL, code_type character varying(10) NOT NULL DEFAULT 'ICD-10', description text, diagnosis_date date NOT NULL, status character varying(32) NOT NULL, is_chronic boolean DEFAULT false, PRIMARY KEY (diagnosis_id) )\nCREATE TABLE healthcare.medications ( medication_id character varying(64) NOT NULL, medication_name character varying(255) NOT NULL, generic_name character varying(255), manufacturer character varying(100), ndc_code character varying(20) UNIQUE, description text, PRIMARY KEY (medication_id) )\nCREATE TABLE healthcare.prescriptions ( prescription_id character varying(64) NOT NULL, record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, doctor_id character varying(64) NOT NULL, medication_id character varying(64) NOT NULL, dosage character varying(100) NOT NULL, frequency character varying(100) NOT NULL, route character varying(50), start_date date NOT NULL, end_date date, quantity_dispensed numeric(10,2), refills_allowed integer NOT NULL DEFAULT 0, prescription_date timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (prescription_id) )\nCREATE TABLE healthcare.insurance_plans ( plan_id character varying(64) NOT NULL, plan_name character varying(200) NOT NULL, insurance_provider character varying(100) NOT NULL, plan_type character varying(50), contact_phone character varying(20), website character varying(255), PRIMARY KEY (plan_id) )\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, plan_id character varying(64) NOT NULL, policy_number character varying(100) NOT NULL, group_number character varying(100), subscriber_name character varying(200), effective_date date NOT NULL, expiration_date date, is_primary boolean NOT NULL DEFAULT true, PRIMARY KEY (patient_insurance_id), UNIQUE (patient_id, plan_id, policy_number) )\n"}
{"conversations": [{"role": "user", "content": "Find all pairs of users where the registration times are within 30 minutes of each other, and show both user IDs, usernames, and the time difference in minutes."}, {"role": "assistant", "content": "SELECT u1.user_id AS user1_id, u1.username AS user1_name, u2.user_id AS user2_id, u2.username AS user2_name, ROUND(ABS(EXTRACT(EPOCH FROM u1.created_at - u2.created_at))/60,2) AS diff_minutes FROM web3.users u1 JOIN web3.users u2 ON u1.user_id < u2.user_id WHERE ABS(EXTRACT(EPOCH FROM u1.created_at - u2.created_at))/60 <= 30;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.users ( user_id.text, username.text, email.text, password_hash.text, created_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "Find all wallet addresses that don't have an associated user_id."}, {"role": "assistant", "content": "SELECT address_id FROM blockchain.wallets WHERE user_id IS NULL;"}, {"role": "user", "content": "Now show me these addresses along with their private_key, and join with another table to see if they have any transactions."}, {"role": "assistant", "content": "SELECT w.address_id, w.private_key FROM blockchain.wallets w WHERE w.user_id IS NULL;"}, {"role": "user", "content": "Actually, I want to see the count of such wallet addresses grouped by the first 3 characters of their address_id."}, {"role": "assistant", "content": "SELECT SUBSTRING(address_id, 1, 3) as address_prefix, COUNT(*) as address_count FROM blockchain.wallets WHERE user_id IS NULL GROUP BY SUBSTRING(address_id, 1, 3);"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE blockchain.wallets ( wallet_id.text, user_id.text, address_id.text, private_key.text )\n"}
{"conversations": [{"role": "user", "content": "Show the total trade amount for each account. Include the account_id and account_number."}, {"role": "assistant", "content": "SELECT\n  T1.account_id,\n  T1.account_number,\n  SUM(T2.total_amount) AS total_traded_amount\nFROM financial_services.accounts AS T1\nINNER JOIN financial_services.trades AS T2\n  ON T1.account_id = T2.account_id\nGROUP BY\n  T1.account_id,\n  T1.account_number;"}, {"role": "user", "content": "Only include trades with a status of 'SETTLED'."}, {"role": "assistant", "content": "SELECT\n  T1.account_id,\n  T1.account_number,\n  SUM(T2.total_amount) AS total_traded_amount\nFROM financial_services.accounts AS T1\nINNER JOIN financial_services.trades AS T2\n  ON T1.account_id = T2.account_id\nWHERE\n  T2.status = 'SETTLED'\nGROUP BY\n  T1.account_id,\n  T1.account_number;"}, {"role": "user", "content": "Filter out accounts where the total traded amount for settled trades is less than 5000."}, {"role": "assistant", "content": "SELECT\n  T1.account_id,\n  T1.account_number,\n  SUM(T2.total_amount) AS total_traded_amount\nFROM financial_services.accounts AS T1\nINNER JOIN financial_services.trades AS T2\n  ON T1.account_id = T2.account_id\nWHERE\n  T2.status = 'SETTLED'\nGROUP BY\n  T1.account_id,\n  T1.account_number\nHAVING\n  SUM(T2.total_amount) >= 5000;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.customers ( customer_id text, first_name text, last_name text, date_of_birth date, ssn_hash text, address text, city text, state text, zip_code text, country text, email text, phone_number text, created_at timestamp, status text, risk_profile text )\nCREATE TABLE financial_services.accounts ( account_id text, customer_id text, account_number text, account_type text, balance numeric, currency text, opened_date date, status text, interest_rate numeric, last_updated_at timestamp )\nCREATE TABLE financial_services.transactions (\n    transaction_id character varying(64) NOT NULL, -- unique identifier for the transaction\n    account_id character varying(64) NOT NULL, -- account involved in the transaction\n    related_account_id character varying(64), -- counterpart account for transfers\n    transaction_type character varying(50) NOT NULL, -- e.g., Deposit, Withdrawal, Transfer, Payment, Fee, Interest\n    amount numeric(19, 4) NOT NULL, -- transaction amount\n    currency character varying(3) NOT NULL, -- transaction currency\n    transaction_date timestamp NOT NULL, -- exact time of the transaction\n    effective_date date NOT NULL, -- date the transaction affects the balance\n    description text, -- description or memo of the transaction\n    status character varying(32) NOT NULL, -- e.g., Pending, Completed, Failed, Reversed\n    reference_number character varying(128), -- external reference if applicable (e.g., check number)\n    PRIMARY KEY (transaction_id),\n    FOREIGN KEY (account_id) REFERENCES financial_services.accounts(account_id),\n    FOREIGN KEY (related_account_id) REFERENCES financial_services.accounts(account_id)\n)\nCREATE TABLE financial_services.securities ( security_id.text, ticker_symbol.text, isin_code.text, cusip_code.text, security_name.text, security_type.text, exchange.text, currency.text, issuer_name.text, sector.text, last_updated.timestamp )\nCREATE TABLE financial_services.trades ( trade_id text PRIMARY KEY, account_id text, security_id text, order_id text, trade_type text, quantity numeric, price_per_unit numeric, total_amount numeric, commission numeric, trade_timestamp timestamp, settlement_date date, status text, execution_venue text )\nCREATE TABLE financial_services.market_data ( data_point_id.bigint, security_id.text, data_timestamp.timestamp, open_price.numeric, high_price.numeric, low_price.numeric, close_price.numeric, adjusted_close_price.numeric, volume.bigint, source.text )\nCREATE TABLE financial_services.employees (\n    employee_id character varying(64) NOT NULL,  -- unique identifier for the employee\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    job_title character varying(100) NOT NULL, -- e.g., Teller, Branch Manager, Financial Advisor, Analyst\n    department character varying(100), -- e.g., Retail Banking, Wealth Management, IT\n    branch_id character varying(64), -- Identifier for the branch they work at (if applicable)\n    email character varying(128) NOT NULL UNIQUE,\n    phone_extension character varying(20),\n    hire_date date NOT NULL,\n    termination_date date, -- Date of termination, null if currently employed\n    manager_id character varying(64), -- Self-referencing key for manager relationship\n    status character varying(32) NOT NULL, -- e.g., Active, Terminated, On Leave\n    PRIMARY KEY (employee_id),\n    FOREIGN KEY (branch_id) REFERENCES financial_services.branches(branch_id), -- Assuming a branches table exists\n    FOREIGN KEY (manager_id) REFERENCES financial_services.employees(employee_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List all claims, including the claim ID, incident date, estimated loss, and the name of the insurance product associated with the policy under which the claim was made."}, {"role": "assistant", "content": "SELECT\n  c.claim_id,\n  c.incident_date,\n  c.estimated_loss,\n  ip.product_name\nFROM insurance.claims AS c\nJOIN insurance.policies AS p\n  ON c.policy_id = p.policy_id\nJOIN insurance.insurance_products AS ip\n  ON p.product_id = ip.product_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.customers ( customer_id text, first_name text, last_name text, date_of_birth date, ssn_hash text, address_line1 text, address_line2 text, city text, state text, zip_code text, country text, phone_number text, email text, created_at timestamp, updated_at timestamp, status text )\nCREATE TABLE insurance.claims (\n    claim_id character varying(64) NOT NULL, -- unique identifier for the claim\n    policy_id character varying(64) NOT NULL, -- identifier of the policy under which the claim is made (FK to policies)\n    customer_id character varying(64) NOT NULL, -- identifier of the customer making the claim (FK to customers)\n    incident_date timestamp NOT NULL, -- date and time of the incident leading to the claim\n    reported_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- date the claim was reported\n    description text NOT NULL, -- detailed description of the incident and claim\n    estimated_loss numeric(15, 2), -- initial estimated cost of the loss\n    status character varying(30) NOT NULL, -- e.g., Filed, Processing, Under Review, Approved, Denied, Settled\n    settlement_amount numeric(15, 2), -- final amount paid out\n    settlement_date date,\n    claim_handler_id character varying(64), -- identifier for the employee handling the claim (FK to employees/adjusters)\n    police_report_number character varying(100),\n    PRIMARY KEY (claim_id)\n)\nCREATE TABLE insurance.insurance_products (\n    product_id character varying(64) NOT NULL, -- unique identifier for the insurance product\n    product_name character varying(150) NOT NULL, -- name of the insurance product (e.g., 'Comprehensive Auto Insurance')\n    product_type character varying(50) NOT NULL, -- category like 'Auto', 'Home', 'Life', 'Health', 'Travel'\n    description text, -- detailed description of the product\n    base_premium numeric(10, 2) NOT NULL, -- starting premium before adjustments\n    coverage_details text, -- details about what is covered (could be JSON or structured text)\n    underwriting_rules text, -- rules used for assessing risk and eligibility\n    is_active boolean NOT NULL DEFAULT true, -- whether the product is currently offered\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n    updated_at timestamp,\n    PRIMARY KEY (product_id)\n)\nCREATE TABLE insurance.claim_documents ( document_id character varying(64) NOT NULL, claim_id character varying(64) NOT NULL, document_type character varying(50) NOT NULL, file_name character varying(255) NOT NULL, file_path character varying(512) NOT NULL, file_size_bytes integer, mime_type character varying(100), uploaded_by character varying(64), uploaded_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, description text, PRIMARY KEY (document_id) )\n"}
{"conversations": [{"role": "user", "content": "Could you list each game_id along with the count of hidden achievements and the count of visible achievements?"}, {"role": "assistant", "content": "SELECT game_id,\n       SUM(CASE WHEN hidden THEN 1 ELSE 0 END) AS hidden_count,\n       SUM(CASE WHEN NOT hidden THEN 1 ELSE 0 END) AS visible_count\nFROM gaming_technology.achievements\nGROUP BY game_id;"}, {"role": "user", "content": "Actually, please provide pairs of one hidden and one visible achievement name for each game where both types exist."}, {"role": "assistant", "content": "SELECT h.game_id,\n       h.name AS hidden_name,\n       v.name AS visible_name\nFROM gaming_technology.achievements h\nJOIN gaming_technology.achievements v\n  ON h.game_id = v.game_id\n AND h.hidden = TRUE\n AND v.hidden = FALSE\nWHERE EXISTS (\n  SELECT 1 FROM gaming_technology.achievements x\n   WHERE x.game_id = h.game_id\n     AND x.hidden = FALSE\n)\nAND EXISTS (\n  SELECT 1 FROM gaming_technology.achievements y\n   WHERE y.game_id = h.game_id\n     AND y.hidden = TRUE\n);"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.achievements ( achievement_id.uuid, game_id.uuid, name.text, description.text, icon_url.text, points.integer, hidden.boolean )\n"}
{"conversations": [{"role": "user", "content": "List all employees who were hired in the last two years along with their department and status."}, {"role": "assistant", "content": "SELECT employee_id, first_name, last_name, department, status FROM financial_services.employees WHERE hire_date >= (CURRENT_DATE - INTERVAL '2 years');"}, {"role": "user", "content": "Now also include their manager's full name in the output."}, {"role": "assistant", "content": "SELECT e.employee_id, e.first_name, e.last_name, e.department, e.status, m.first_name || ' ' || m.last_name AS manager_full_name FROM financial_services.employees e LEFT JOIN financial_services.employees m ON e.manager_id = m.employee_id WHERE e.hire_date >= (CURRENT_DATE - INTERVAL '2 years');"}, {"role": "user", "content": "Only include employees whose status is 'Active' and whose manager is also currently 'Active'."}, {"role": "assistant", "content": "SELECT e.employee_id, e.first_name, e.last_name, e.department, e.status, m.first_name || ' ' || m.last_name AS manager_full_name FROM financial_services.employees e LEFT JOIN financial_services.employees m ON e.manager_id = m.employee_id WHERE e.hire_date >= (CURRENT_DATE - INTERVAL '2 years') AND e.status = 'Active' AND m.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 financial_services.customers ( customer_id.text, first_name.text, last_name.text, date_of_birth.date, ssn_hash.text, address.text, city.text, state.text, zip_code.text, country.text, email.text, phone_number.text, created_at.timestamp, status.text, risk_profile.text )\nCREATE TABLE financial_services.accounts ( account_id.text, customer_id.text, account_number.text, account_type.text, balance.numeric, currency.text, opened_date.date, status.text, interest_rate.numeric, last_updated_at.timestamp )\nCREATE TABLE financial_services.transactions ( transaction_id.text, account_id.text, related_account_id.text, transaction_type.text, amount.numeric, currency.text, transaction_date.timestamp, effective_date.date, description.text, status.text, reference_number.text )\nCREATE TABLE financial_services.trades ( trade_id.text, account_id.text, security_id.text, order_id.text, trade_type.text, quantity.numeric, price_per_unit.numeric, total_amount.numeric, commission.numeric, trade_timestamp.timestamp, settlement_date.date, status.text, execution_venue.text )\nCREATE TABLE financial_services.employees ( employee_id.text, first_name.text, last_name.text, job_title.text, department.text, branch_id.text, email.text, phone_extension.text, hire_date.date, termination_date.date, manager_id.text, status.text )\n"}
{"conversations": [{"role": "user", "content": "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 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": "Find all users who registered with a Yahoo email address, along with their registration dates."}, {"role": "assistant", "content": "SELECT user_id, username, email, password_hash FROM blockchain.users WHERE email LIKE '%@yahoo.com';"}, {"role": "user", "content": "This query doesn't show registration dates. Can you modify it to include the registration date?"}, {"role": "assistant", "content": "I notice the users table doesn't have a registration date column. Would you like me to show other available information from the users table?"}, {"role": "user", "content": "Then just show me the count of Yahoo email users instead."}, {"role": "assistant", "content": "SELECT COUNT(*) as yahoo_user_count FROM blockchain.users WHERE email LIKE '%@yahoo.com';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE blockchain.blocks ( block_id text, previous_block_id text, timestamp timestamp, nonce integer, merkle_root text, difficulty integer )\nCREATE TABLE blockchain.transactions (\n    transaction_id character varying(64) NOT NULL,  -- unique identifier for the transaction\n    block_id character varying(64) NOT NULL, -- identifier of the block containing the transaction\n    sender_address character varying(128) NOT NULL, -- address of the sender\n    receiver_address character varying(128) NOT NULL, -- address of the receiver\n    amount numeric(38,14) NOT NULL, -- amount transferred\n    timestamp timestamp NOT NULL, -- time when the transaction was created\n    signature text NOT NULL, -- digital signature of the transaction\n    PRIMARY KEY (transaction_id)\n)\nCREATE TABLE blockchain.addresses ( address_id text PRIMARY KEY, public_key text, balance numeric )\nCREATE TABLE blockchain.users ( user_id character varying(64) NOT NULL, username character varying(128) NOT NULL, email character varying(128) NOT NULL, password_hash text NOT NULL, PRIMARY KEY (user_id) )\n"}
{"conversations": [{"role": "user", "content": "List all patients who have insurance plans with group numbers, showing their patient IDs and the count of such plans per patient."}, {"role": "assistant", "content": "SELECT patient_id, COUNT(*) AS plan_count FROM healthcare.patient_insurance WHERE group_number IS NOT NULL GROUP BY patient_id;"}, {"role": "user", "content": "Actually, I only need patients who have more than 2 such plans."}, {"role": "assistant", "content": "SELECT patient_id, COUNT(*) AS plan_count FROM healthcare.patient_insurance WHERE group_number IS NOT NULL GROUP BY patient_id HAVING COUNT(*) > 2;"}, {"role": "user", "content": "Can you also include the earliest effective date among these plans for each patient?"}, {"role": "assistant", "content": "SELECT patient_id, COUNT(*) AS plan_count, MIN(effective_date) AS earliest_effective_date FROM healthcare.patient_insurance WHERE group_number IS NOT NULL GROUP BY patient_id HAVING COUNT(*) > 2;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patient_insurance (\n    patient_insurance_id character varying(64) NOT NULL, -- unique identifier for this patient-plan link\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    plan_id character varying(64) NOT NULL, -- FK to insurance_plans table\n    policy_number character varying(100) NOT NULL, -- patient's policy number\n    group_number character varying(100), -- group number, if applicable\n    subscriber_name character varying(200), -- name of the primary policy holder\n    effective_date date NOT NULL, -- date the coverage begins\n    expiration_date date, -- date the coverage ends (if known)\n    is_primary boolean NOT NULL DEFAULT true, -- indicates if this is the primary insurance\n    PRIMARY KEY (patient_insurance_id),\n    UNIQUE (patient_id, plan_id, policy_number) -- ensure a patient doesn't have the same policy twice\n)\n"}
{"conversations": [{"role": "user", "content": "List the first and last name of each citizen along with the city and state of the service location for their agency."}, {"role": "assistant", "content": "SELECT c.first_name, c.last_name, sl.city, sl.state\nFROM government_services.citizens c\nJOIN government_services.payments p ON c.citizen_id = p.citizen_id\nJOIN government_services.employees e ON p.application_id IS NOT NULL AND e.agency_id IS NOT NULL\nJOIN government_services.service_locations sl ON e.agency_id = sl.agency_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id text, national_id_number text, first_name text, last_name text, date_of_birth date, gender text, primary_address text, contact_email text, contact_phone text, registration_date timestamp, is_verified boolean )\nCREATE TABLE government_services.payments ( payment_id text, application_id text, citizen_id text, service_id text, amount numeric, currency text, payment_method text, payment_provider_reference text, payment_timestamp timestamp, status text, notes text )\nCREATE TABLE government_services.employees ( employee_id text, agency_id text, first_name text, last_name text, job_title text, department text, work_email text, work_phone text, hire_date date, termination_date date, access_level text, manager_employee_id text )\nCREATE TABLE government_services.service_locations ( location_id text, agency_id text, location_name text, address text, city text, state text, postal_code text, latitude numeric, longitude numeric, operating_hours text, contact_phone text, is_accessible boolean )\n"}
{"conversations": [{"role": "user", "content": "For each vehicle, find the vehicle in the same depot that was acquired immediately before it. Display the current vehicle_id, acquisition_date, previous vehicle_id, and its acquisition_date."}, {"role": "assistant", "content": "SELECT v.vehicle_id, v.acquisition_date, prev.vehicle_id AS previous_vehicle_id, prev.acquisition_date AS previous_acquisition_date FROM transportation.vehicles v JOIN transportation.vehicles prev ON v.depot_id = prev.depot_id AND prev.acquisition_date = (SELECT MAX(acquisition_date) FROM transportation.vehicles WHERE depot_id = v.depot_id AND acquisition_date < v.acquisition_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.vehicles ( vehicle_id text PRIMARY KEY, license_plate text, vin text, make text, model text, year int, type text, capacity int, fuel_type text, status text, depot_id text, acquisition_date date )\n"}
{"conversations": [{"role": "user", "content": "Please show me all locations that do not have a state or province recorded. Include the location name, city, and country."}, {"role": "assistant", "content": "SELECT name, city, country\nFROM transportation.locations\nWHERE state_province IS NULL OR state_province = '';"}, {"role": "user", "content": "For these locations, also include their location_id and type."}, {"role": "assistant", "content": "SELECT location_id, name, type, city, country\nFROM transportation.locations\nWHERE state_province IS NULL OR state_province = '';"}, {"role": "user", "content": "Could you additionally list any routes for which these locations are either the origin or the destination? Show the location name, route number, and specify if the location is origin or destination."}, {"role": "assistant", "content": "SELECT l.name, r.route_number,\n  CASE \n    WHEN r.origin_location_id = l.location_id THEN 'origin'\n    WHEN r.destination_location_id = l.location_id THEN 'destination'\n  END AS role\nFROM transportation.locations l\nJOIN transportation.routes r\n  ON r.origin_location_id = l.location_id OR r.destination_location_id = l.location_id\nWHERE l.state_province IS NULL OR l.state_province = '';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.routes ( route_id text PRIMARY KEY, route_number text, description text, origin_location_id text, destination_location_id text, distance_km numeric, estimated_duration_minutes int, type text )\nCREATE TABLE transportation.locations ( location_id character varying(64) NOT NULL, name character varying(255) NOT NULL, type character varying(64) NOT NULL, address_line1 character varying(255), city character varying(128), state_province character varying(128), postal_code character varying(32), country character varying(64) NOT NULL, latitude numeric(9, 6), longitude numeric(9, 6), timezone character varying(64), PRIMARY KEY (location_id) )\nCREATE TABLE transportation.bookings ( booking_id.text, passenger_id.text, trip_id.text, seat_number.text, booking_time.timestamp, status.text, fare.numeric, payment_transaction_id.text, special_requests.text )\n"}
{"conversations": [{"role": "user", "content": "I want a list of each department's top 3 longest-tenured active employees, showing their full names, hire_date, and their manager’s full names."}, {"role": "assistant", "content": "WITH ranked AS (\n  SELECT\n    e.department,\n    e.employee_id,\n    e.first_name || ' ' || e.last_name AS employee_full_name,\n    e.hire_date,\n    e.manager_id,\n    ROW_NUMBER() OVER (PARTITION BY e.department ORDER BY e.hire_date ASC) AS rn\n  FROM financial_services.employees e\n  WHERE e.status = 'Active'\n)\nSELECT\n  r.department,\n  r.employee_full_name,\n  r.hire_date,\n  m.first_name || ' ' || m.last_name AS manager_full_name\nFROM ranked r\nLEFT JOIN financial_services.employees m ON r.manager_id = m.employee_id\nWHERE r.rn <= 3;"}, {"role": "user", "content": "Actually, only include employees hired before '2018-01-01'."}, {"role": "assistant", "content": "WITH ranked AS (\n  SELECT\n    e.department,\n    e.employee_id,\n    e.first_name || ' ' || e.last_name AS employee_full_name,\n    e.hire_date,\n    e.manager_id,\n    ROW_NUMBER() OVER (PARTITION BY e.department ORDER BY e.hire_date ASC) AS rn\n  FROM financial_services.employees e\n  WHERE e.status = 'Active'\n    AND e.hire_date < '2018-01-01'\n)\nSELECT\n  r.department,\n  r.employee_full_name,\n  r.hire_date,\n  m.first_name || ' ' || m.last_name AS manager_full_name\nFROM ranked r\nLEFT JOIN financial_services.employees m ON r.manager_id = m.employee_id\nWHERE r.rn <= 3;"}, {"role": "user", "content": "Also, only consider departments that have at least 5 active employees in total before applying the top 3 filter."}, {"role": "assistant", "content": "WITH dept_counts AS (\n  SELECT department\n  FROM financial_services.employees\n  WHERE status = 'Active'\n  GROUP BY department\n  HAVING COUNT(*) >= 5\n),\nranked AS (\n  SELECT\n    e.department,\n    e.employee_id,\n    e.first_name || ' ' || e.last_name AS employee_full_name,\n    e.hire_date,\n    e.manager_id,\n    ROW_NUMBER() OVER (PARTITION BY e.department ORDER BY e.hire_date ASC) AS rn\n  FROM financial_services.employees e\n  JOIN dept_counts d ON e.department = d.department\n  WHERE e.status = 'Active'\n    AND e.hire_date < '2018-01-01'\n)\nSELECT\n  r.department,\n  r.employee_full_name,\n  r.hire_date,\n  m.first_name || ' ' || m.last_name AS manager_full_name\nFROM ranked r\nLEFT JOIN financial_services.employees m ON r.manager_id = m.employee_id\nWHERE r.rn <= 3;"}, {"role": "user", "content": "Finally, sort the result by department ascending and hire_date ascending."}, {"role": "assistant", "content": "WITH dept_counts AS (\n  SELECT department\n  FROM financial_services.employees\n  WHERE status = 'Active'\n  GROUP BY department\n  HAVING COUNT(*) >= 5\n),\nranked AS (\n  SELECT\n    e.department,\n    e.employee_id,\n    e.first_name || ' ' || e.last_name AS employee_full_name,\n    e.hire_date,\n    e.manager_id,\n    ROW_NUMBER() OVER (PARTITION BY e.department ORDER BY e.hire_date ASC) AS rn\n  FROM financial_services.employees e\n  JOIN dept_counts d ON e.department = d.department\n  WHERE e.status = 'Active'\n    AND e.hire_date < '2018-01-01'\n)\nSELECT\n  r.department,\n  r.employee_full_name,\n  r.hire_date,\n  m.first_name || ' ' || m.last_name AS manager_full_name\nFROM ranked r\nLEFT JOIN financial_services.employees m ON r.manager_id = m.employee_id\nWHERE r.rn <= 3\nORDER BY r.department ASC, r.hire_date ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.trades ( trade_id character varying(64) NOT NULL, account_id character varying(64) NOT NULL, security_id character varying(64) NOT NULL, order_id character varying(64), trade_type character varying(10) NOT NULL, quantity numeric(19, 8) NOT NULL, price_per_unit numeric(19, 8) NOT NULL, total_amount numeric(19, 4) NOT NULL, commission numeric(10, 4), trade_timestamp timestamp NOT NULL, settlement_date date, status character varying(32) NOT NULL, execution_venue character varying(100), PRIMARY KEY (trade_id), FOREIGN KEY (account_id) REFERENCES financial_services.accounts(account_id), FOREIGN KEY (security_id) REFERENCES financial_services.securities(security_id) )\nCREATE TABLE financial_services.employees ( employee_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, job_title character varying(100) NOT NULL, department character varying(100), branch_id character varying(64), email character varying(128) NOT NULL UNIQUE, phone_extension character varying(20), hire_date date NOT NULL, termination_date date, manager_id character varying(64), status character varying(32) NOT NULL, PRIMARY KEY (employee_id), FOREIGN KEY (branch_id) REFERENCES financial_services.branches(branch_id), FOREIGN KEY (manager_id) REFERENCES financial_services.employees(employee_id) )\n"}
{"conversations": [{"role": "user", "content": "List all premium payments for policy 'POL123'. Show payment ID, payment date, amount paid, and status."}, {"role": "assistant", "content": "SELECT payment_id, payment_date, amount_paid, status FROM insurance.premium_payments WHERE policy_id = 'POL123';"}, {"role": "user", "content": "Only show payments made on or after January 1, 2024."}, {"role": "assistant", "content": "SELECT payment_id, payment_date, amount_paid, status FROM insurance.premium_payments WHERE policy_id = 'POL123' AND payment_date >= '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.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": "For each service location, find the nearest accessible service location. Show the location_id, location_name, nearest_location_id, and the distance."}, {"role": "assistant", "content": "SELECT l.location_id,\n       l.location_name,\n       nearest.location_id AS nearest_location_id,\n       SQRT(POWER(l.latitude - nearest.latitude, 2) + POWER(l.longitude - nearest.longitude, 2)) AS distance\nFROM service_locations l\nJOIN LATERAL (\n  SELECT sl.location_id, sl.latitude, sl.longitude\n  FROM service_locations sl\n  WHERE sl.location_id <> l.location_id\n    AND sl.is_accessible = TRUE\n  ORDER BY POWER(l.latitude - sl.latitude, 2) + POWER(l.longitude - sl.longitude, 2)\n  LIMIT 1\n) AS nearest ON TRUE;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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 )\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": "List all security_ids that had at least one day where the high_price was more than twice the low_price, along with the maximum price difference (high_price - low_price) observed for each security."}, {"role": "assistant", "content": "SELECT security_id, MAX(high_price - low_price) AS max_price_difference FROM financial_services.market_data WHERE high_price > 2 * low_price GROUP BY security_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.market_data ( data_point_id bigint, security_id text, data_timestamp timestamp, open_price numeric, high_price numeric, low_price numeric, close_price numeric, adjusted_close_price numeric, volume bigint, source text )\n"}
{"conversations": [{"role": "user", "content": "Which cities are listed as primary_address for citizens who have a verified account? Can you show the city names and the number of verified citizens in each city?"}, {"role": "assistant", "content": "SELECT SPLIT_PART(primary_address, ',', 1) AS city, COUNT(*) AS verified_citizen_count FROM government_services.citizens WHERE is_verified = true GROUP BY city;"}, {"role": "user", "content": "Actually, could you only include cities with more than 10 verified citizens? And order them by the number of verified citizens in descending order."}, {"role": "assistant", "content": "SELECT SPLIT_PART(primary_address, ',', 1) AS city, COUNT(*) AS verified_citizen_count FROM government_services.citizens WHERE is_verified = true GROUP BY city HAVING COUNT(*) > 10 ORDER BY verified_citizen_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 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": "For each guest, list reservation_id, guest_id, check_in_date, and the next reservation_id and its check_in_date."}, {"role": "assistant", "content": "SELECT r1.reservation_id,\n       r1.guest_id,\n       r1.check_in_date,\n       r2.reservation_id AS next_reservation_id,\n       r2.check_in_date   AS next_check_in_date\nFROM reservations r1\nLEFT JOIN reservations r2\n  ON r1.guest_id = r2.guest_id\n AND r2.check_in_date = (\n       SELECT MIN(check_in_date)\n       FROM reservations\n       WHERE guest_id = r1.guest_id\n         AND check_in_date > r1.check_in_date\n     );"}, {"role": "user", "content": "Only include guests who have at least two reservations."}, {"role": "assistant", "content": "SELECT r1.reservation_id,\n       r1.guest_id,\n       r1.check_in_date,\n       r2.reservation_id AS next_reservation_id,\n       r2.check_in_date   AS next_check_in_date\nFROM reservations r1\nLEFT JOIN reservations r2\n  ON r1.guest_id = r2.guest_id\n AND r2.check_in_date = (\n       SELECT MIN(check_in_date)\n       FROM reservations\n       WHERE guest_id = r1.guest_id\n         AND check_in_date > r1.check_in_date\n     )\nWHERE r1.guest_id IN (\n  SELECT guest_id\n  FROM reservations\n  GROUP BY guest_id\n  HAVING COUNT(*) >= 2\n);"}, {"role": "user", "content": "Also, only show next reservations that occur within 30 days of the current reservation."}, {"role": "assistant", "content": "SELECT r1.reservation_id,\n       r1.guest_id,\n       r1.check_in_date,\n       r2.reservation_id AS next_reservation_id,\n       r2.check_in_date   AS next_check_in_date\nFROM reservations r1\nLEFT JOIN reservations r2\n  ON r1.guest_id = r2.guest_id\n AND r2.check_in_date = (\n       SELECT MIN(check_in_date)\n       FROM reservations\n       WHERE guest_id = r1.guest_id\n         AND check_in_date > r1.check_in_date\n     )\n   AND r2.check_in_date <= r1.check_in_date + INTERVAL '30 days'\nWHERE r1.guest_id IN (\n  SELECT guest_id\n  FROM reservations\n  GROUP BY guest_id\n  HAVING COUNT(*) >= 2\n);"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.reservations ( reservation_id text, property_id text, guest_id text, room_id text, room_type_id text, check_in_date date, check_out_date date, actual_check_in_ts timestamp, actual_check_out_ts timestamp, num_adults integer, num_children integer, status text, booking_source text, rate_plan_id text, total_amount numeric, amount_paid numeric, special_requests text, created_at timestamp, updated_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Can you narrow this down to only show cases where the case type is 'Criminal'?"}, {"role": "assistant", "content": "SELECT case_name, case_number, date_opened FROM legal_services.cases WHERE lead_lawyer_id = 'lawyer_abc' AND status = 'Open' AND case_type = 'Criminal';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.cases ( case_id.text, case_number.text, case_name.text, client_id.text, lead_lawyer_id.text, case_type.text, status.text, date_opened.timestamp, date_closed.timestamp, description.text, court_jurisdiction.text )\n"}
{"conversations": [{"role": "user", "content": "Show the full names and contact emails of all citizens who have applied for services with a standard fee greater than 100."}, {"role": "assistant", "content": "SELECT c.first_name || ' ' || c.last_name AS full_name, c.contact_email\nFROM government_services.citizens c\nJOIN government_services.services s ON c.citizen_id IS NOT NULL -- Replace with actual application linking table if exists\nWHERE s.standard_fee > 100;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id character varying(64) NOT NULL, national_id_number character varying(128) NOT NULL UNIQUE, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, gender character varying(20), primary_address text NOT NULL, contact_email character varying(128) UNIQUE, contact_phone character varying(32), registration_date timestamp NOT NULL, is_verified boolean DEFAULT false, PRIMARY KEY (citizen_id) )\nCREATE TABLE government_services.services ( service_id.text, agency_id.text, service_name.text, description.text, category.text, eligibility_criteria.text, standard_fee.numeric, average_processing_time_days.integer, is_active.boolean, online_application_url.text )\n"}
{"conversations": [{"role": "user", "content": "Which chain has the highest total USD inflow from buy transactions (type=1), and how many distinct tokens were involved in that inflow?"}, {"role": "assistant", "content": "SELECT chain, SUM(usd_value) AS total_inflow, COUNT(DISTINCT token_symbol) AS distinct_tokens\nFROM smart_money_token_inflow\nWHERE type = 1\nGROUP BY chain\nORDER BY total_inflow DESC\nLIMIT 1;"}, {"role": "user", "content": "I also want to see the average price at which those tokens were bought for that chain."}, {"role": "assistant", "content": "WITH inflow AS (\n  SELECT chain, SUM(usd_value) AS total_inflow\n  FROM smart_money_token_inflow\n  WHERE type = 1\n  GROUP BY chain\n), top_chain AS (\n  SELECT chain FROM inflow ORDER BY total_inflow DESC LIMIT 1\n)\nSELECT i.chain, AVG(i.avg_price) AS avg_buy_price\nFROM smart_money_token_inflow i\nJOIN top_chain t ON i.chain = t.chain\nWHERE i.type = 1;"}, {"role": "user", "content": "Actually, filter to narratives where the total USD inflow is above 50000."}, {"role": "assistant", "content": "SELECT narrative, SUM(usd_value) AS total_inflow, COUNT(DISTINCT token_symbol) AS distinct_tokens\nFROM smart_money_token_inflow\nWHERE type = 1\nGROUP BY narrative\nHAVING SUM(usd_value) > 50000;"}, {"role": "user", "content": "Please order the results by average price descending and show the top 2 chains."}, {"role": "assistant", "content": "SELECT chain, SUM(usd_value) AS total_inflow, COUNT(DISTINCT token_symbol) AS distinct_tokens, AVG(avg_price) AS avg_buy_price\nFROM smart_money_token_inflow\nWHERE type = 1\nGROUP BY chain\nORDER BY avg_buy_price DESC\nLIMIT 2;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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 all active managers along with their property IDs and the number of staff members they supervise, ordered by the number of supervised staff in descending order."}, {"role": "assistant", "content": "SELECT s.staff_id, s.property_id, s.first_name, s.last_name, COUNT(s2.staff_id) AS supervised_staff_count FROM hospitality_technology.staff s LEFT JOIN hospitality_technology.staff s2 ON s.staff_id = s2.manager_id WHERE s.position = 'Manager' AND s.is_active = true GROUP BY s.staff_id, s.property_id, s.first_name, s.last_name ORDER BY supervised_staff_count DESC;"}, {"role": "user", "content": "Now, include only managers who supervise at least 3 staff members and show their email addresses as well."}, {"role": "assistant", "content": "SELECT s.staff_id, s.property_id, s.first_name, s.last_name, s.work_email, COUNT(s2.staff_id) AS supervised_staff_count FROM hospitality_technology.staff s LEFT JOIN hospitality_technology.staff s2 ON s.staff_id = s2.manager_id WHERE s.position = 'Manager' AND s.is_active = true GROUP BY s.staff_id, s.property_id, s.first_name, s.last_name, s.work_email HAVING COUNT(s2.staff_id) >= 3 ORDER BY supervised_staff_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.staff (\n    staff_id character varying(64) NOT NULL,  -- unique identifier for the staff member\n    property_id character varying(64) NOT NULL, -- FK to properties table (primary property)\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    position character varying(100) NOT NULL, -- e.g., Front Desk Agent, Housekeeper, Manager, Concierge\n    work_email character varying(255) UNIQUE, -- staff member's work email\n    work_phone character varying(30),\n    hire_date date NOT NULL,\n    termination_date date, -- date employment ended (if applicable)\n    is_active boolean NOT NULL DEFAULT true, -- currently employed flag\n    access_level integer NOT NULL, -- permission level within systems (e.g., 1=basic, 5=admin)\n    manager_id character varying(64), -- FK to staff table (self-referencing for supervisor)\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (staff_id),\n    FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n    FOREIGN KEY (manager_id) REFERENCES hospitality_technology.staff(staff_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Provide a list of all employees and their corresponding managers. Please display the full name for both the employee and their manager."}, {"role": "assistant", "content": "SELECT e.first_name || ' ' || e.last_name AS employee_name, m.first_name || ' ' || m.last_name AS manager_name FROM financial_services.employees AS e LEFT JOIN financial_services.employees AS m ON e.manager_id = m.employee_id"}, {"role": "user", "content": "Restrict the list to only include employees who are currently in 'Active' status."}, {"role": "assistant", "content": "SELECT e.first_name || ' ' || e.last_name AS employee_name, m.first_name || ' ' || m.last_name AS manager_name FROM financial_services.employees AS e LEFT JOIN financial_services.employees AS m ON e.manager_id = m.employee_id WHERE e.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 financial_services.employees (\n    employee_id character varying(64) NOT NULL,  -- unique identifier for the employee\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    job_title character varying(100) NOT NULL, -- e.g., Teller, Branch Manager, Financial Advisor, Analyst\n    department character varying(100), -- e.g., Retail Banking, Wealth Management, IT\n    branch_id character varying(64), -- Identifier for the branch they work at (if applicable)\n    email character varying(128) NOT NULL UNIQUE,\n    phone_extension character varying(20),\n    hire_date date NOT NULL,\n    termination_date date, -- Date of termination, null if currently employed\n    manager_id character varying(64), -- Self-referencing key for manager relationship\n    status character varying(32) NOT NULL, -- e.g., Active, Terminated, On Leave\n    PRIMARY KEY (employee_id),\n    FOREIGN KEY (branch_id) REFERENCES financial_services.branches(branch_id), -- Assuming a branches table exists\n    FOREIGN KEY (manager_id) REFERENCES financial_services.employees(employee_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Find all non-smoking rooms that have not been cleaned in the last 7 days."}, {"role": "assistant", "content": "SELECT room_id, room_number, last_cleaned_at\nFROM hospitality_technology.rooms\nWHERE is_smoking = false\n  AND last_cleaned_at < NOW() - INTERVAL '7 days';"}, {"role": "user", "content": "Now also include only those rooms with 'Balcony' in the features."}, {"role": "assistant", "content": "SELECT room_id, room_number, last_cleaned_at, features\nFROM hospitality_technology.rooms\nWHERE is_smoking = false\n  AND last_cleaned_at < NOW() - INTERVAL '7 days'\n  AND features ILIKE '%Balcony%';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.rooms (\n    room_id character varying(64) NOT NULL,  -- unique identifier for the room\n    property_id character varying(64) NOT NULL, -- FK to properties table\n    room_number character varying(10) NOT NULL, -- room number identifier (e.g., '101', 'Suite 2B')\n    room_type_id character varying(64) NOT NULL, -- FK to room_types table\n    floor integer, -- floor number the room is on\n    status character varying(50) NOT NULL, -- e.g., Available, Occupied, Cleaning, OutOfOrder, Maintenance\n    is_smoking boolean NOT NULL DEFAULT false, -- smoking allowed flag\n    features text, -- description of features (e.g., Balcony, Sea View, Jacuzzi)\n    current_condition text, -- notes on room condition\n    last_cleaned_at timestamp with time zone, -- timestamp of last cleaning\n    PRIMARY KEY (room_id),\n    FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n    FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id)\n)\nCREATE TABLE hospitality_technology.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 )\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": "Show each asset's symbol and the number of unique addresses that have UTXOs associated with it."}, {"role": "assistant", "content": "SELECT a.symbol, COUNT(DISTINCT u.address) AS unique_addresses\nFROM trading_platform.assets a\nJOIN trading_platform.utxos u ON a.asset_id = u.transaction_id\nGROUP BY a.asset_id, a.symbol;"}, {"role": "user", "content": "Now show only assets with more than 5 unique addresses."}, {"role": "assistant", "content": "SELECT a.symbol, COUNT(DISTINCT u.address) AS unique_addresses\nFROM trading_platform.assets a\nJOIN trading_platform.utxos u ON a.asset_id = u.transaction_id\nGROUP BY a.asset_id, a.symbol\nHAVING COUNT(DISTINCT u.address) > 5;"}, {"role": "user", "content": "Please also include the total amount for each asset in the result."}, {"role": "assistant", "content": "SELECT a.symbol, COUNT(DISTINCT u.address) AS unique_addresses, COALESCE(SUM(u.amount), 0) AS total_amount\nFROM trading_platform.assets a\nJOIN trading_platform.utxos u ON a.asset_id = u.transaction_id\nGROUP BY a.asset_id, a.symbol\nHAVING COUNT(DISTINCT u.address) > 5;"}, {"role": "user", "content": "Order the results by total_amount ascending and limit to the top 3."}, {"role": "assistant", "content": "SELECT a.symbol, COUNT(DISTINCT u.address) AS unique_addresses, COALESCE(SUM(u.amount), 0) AS total_amount\nFROM trading_platform.assets a\nJOIN trading_platform.utxos u ON a.asset_id = u.transaction_id\nGROUP BY a.asset_id, a.symbol\nHAVING COUNT(DISTINCT u.address) > 5\nORDER BY total_amount ASC\nLIMIT 3;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.users (\n    user_id character varying(64) NOT NULL,  -- unique identifier for the user\n    username character varying(128) NOT NULL, -- username of the user\n    email character varying(128) NOT NULL, -- email address of the user\n    password_hash text NOT NULL, -- hashed password of the user\n    created_at timestamp NOT NULL, -- time when the user account was created\n    PRIMARY KEY (user_id)\n)\nCREATE TABLE trading_platform.assets ( asset_id text, name text, symbol text, type text )\nCREATE TABLE trading_platform.utxos ( utxo_id text PRIMARY KEY, transaction_id text, output_index int, address text, amount numeric, spent boolean )\nCREATE TABLE trading_platform.metadata ( metadata_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, key character varying(128) NOT NULL, value text NOT NULL, PRIMARY KEY (metadata_id) )\n"}
{"conversations": [{"role": "user", "content": "Find employees who are managers and list the number of employees they directly manage. Show the manager's full name and the count of their direct reports."}, {"role": "assistant", "content": "SELECT m.first_name || ' ' || m.last_name AS manager_full_name, COUNT(e.employee_id) AS number_of_direct_reports FROM government_services.employees AS e JOIN government_services.employees AS m ON e.manager_employee_id = m.employee_id GROUP BY m.employee_id, manager_full_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.employees (\n    employee_id character varying(64) NOT NULL, -- unique identifier for the government employee\n    agency_id character varying(64) NOT NULL, -- FK to agencies table\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    job_title character varying(150) NOT NULL,\n    department character varying(100),\n    work_email character varying(128) NOT NULL UNIQUE,\n    work_phone character varying(32),\n    hire_date date NOT NULL,\n    termination_date date, -- null if currently employed\n    access_level character varying(50), -- Role or permission level\n    manager_employee_id character varying(64), -- FK to self for reporting structure\n    PRIMARY KEY (employee_id)\n)\n"}
{"conversations": [{"role": "user", "content": "What is the total payment amount for each currency recorded in the payments table?"}, {"role": "assistant", "content": "SELECT currency ,  sum(amount) FROM government_services.payments GROUP BY currency"}, {"role": "user", "content": "Now, only show currencies where the total amount paid is greater than 10000."}, {"role": "assistant", "content": "SELECT currency ,  sum(amount) FROM government_services.payments GROUP BY currency HAVING sum(amount)  >  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 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": "Show me the usernames and the group names of group chats where each user has posted at least one post containing a hashtag."}, {"role": "assistant", "content": "SELECT u.username, c.group_name\nFROM social_media.users u\nJOIN social_media.posts p ON u.user_id = p.user_id\nJOIN social_media.post_hashtags ph ON p.post_id = ph.post_id\nJOIN social_media.conversations c ON p.user_id = u.user_id AND c.is_group_chat = TRUE\nGROUP BY u.username, c.group_name;"}, {"role": "user", "content": "Can you also show when each group chat was created?"}, {"role": "assistant", "content": "SELECT u.username, c.group_name, c.created_at\nFROM social_media.users u\nJOIN social_media.posts p ON u.user_id = p.user_id\nJOIN social_media.post_hashtags ph ON p.post_id = ph.post_id\nJOIN social_media.conversations c ON p.user_id = u.user_id AND c.is_group_chat = TRUE\nGROUP BY u.username, c.group_name, c.created_at;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.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.hashtags ( hashtag_id.text, tag_name.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.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": "Show me all invoices where the amount paid is exactly equal to the total amount."}, {"role": "assistant", "content": "SELECT * FROM legal_services.invoices WHERE amount_paid = total_amount;"}, {"role": "user", "content": "Instead, show only the invoice_number, client_id, and payment_date for these invoices, and sort by payment_date descending."}, {"role": "assistant", "content": "SELECT invoice_number, client_id, payment_date FROM legal_services.invoices WHERE amount_paid = total_amount ORDER BY payment_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 legal_services.invoices (\n    invoice_id character varying(64) NOT NULL,  -- unique identifier for the invoice\n    invoice_number character varying(100) UNIQUE NOT NULL, -- user-facing invoice number\n    client_id character varying(64) NOT NULL, -- FK to clients table\n    case_id character varying(64), -- FK to cases table (optional, could be general retainer)\n    issue_date date NOT NULL, -- date the invoice was generated\n    due_date date NOT NULL, -- date the payment is due\n    total_amount numeric(12, 2) NOT NULL, -- total amount due on the invoice\n    amount_paid numeric(12, 2) DEFAULT 0.00, -- amount already paid\n    status character varying(50) NOT NULL, -- e.g., Draft, Sent, Paid, Partially Paid, Overdue, Void\n    payment_date timestamp, -- date the invoice was fully paid (nullable)\n    notes text, -- additional notes or terms on the invoice\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n    PRIMARY KEY (invoice_id)\n)\n"}
{"conversations": [{"role": "user", "content": "How many documents were uploaded in the year 2023?"}, {"role": "assistant", "content": "SELECT count(*) FROM government_services.documents WHERE date_part('year', upload_timestamp) = 2023;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.documents ( document_id character varying(64) NOT NULL, application_id character varying(64), citizen_id character varying(64) NOT NULL, document_type character varying(100) NOT NULL, file_reference text NOT NULL, upload_timestamp timestamp NOT NULL, expiry_date date, verification_status character varying(30) DEFAULT 'Pending', verified_by_employee_id character varying(64), verification_timestamp timestamp, PRIMARY KEY (document_id) )\n"}
{"conversations": [{"role": "user", "content": "List all insurance products that have 'auto' in their product type and are currently active, showing their product name and base premium."}, {"role": "assistant", "content": "SELECT product_name, base_premium FROM insurance.insurance_products WHERE product_type LIKE '%auto%' AND is_active = true;"}, {"role": "user", "content": "Now order these results by base premium in descending order and include the coverage details."}, {"role": "assistant", "content": "SELECT product_name, base_premium, coverage_details FROM insurance.insurance_products WHERE product_type LIKE '%auto%' AND is_active = true ORDER BY base_premium DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.claims ( claim_id character varying(64) NOT NULL, policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, incident_date timestamp NOT NULL, reported_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, description text NOT NULL, estimated_loss numeric(15, 2), status character varying(30) NOT NULL, settlement_amount numeric(15, 2), settlement_date date, claim_handler_id character varying(64), police_report_number character varying(100), PRIMARY KEY (claim_id) )\nCREATE TABLE insurance.insurance_products ( product_id character varying(64) NOT NULL, product_name character varying(150) NOT NULL, product_type character varying(50) NOT NULL, description text, base_premium numeric(10, 2) NOT NULL, coverage_details text, underwriting_rules text, is_active boolean NOT NULL DEFAULT true, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, updated_at timestamp, PRIMARY KEY (product_id) )\nCREATE TABLE insurance.policy_beneficiaries ( beneficiary_id character varying(64) NOT NULL, policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, relationship character varying(50) NOT NULL, percentage_share numeric(5, 2) NOT NULL CHECK (percentage_share > 0 AND percentage_share <= 100), contact_info text, added_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (beneficiary_id), UNIQUE (policy_id, customer_id) )\n"}
{"conversations": [{"role": "user", "content": "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": "What is the schedule of trains arriving at platform 1A at station XYZ on December 25th, 2023?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information about train schedules or specific arrival times as this data is not included in the platform management table. For train schedules, please refer to the train timetable or contact the station's customer service."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.platforms (\n    platform_id character varying(64) NOT NULL, -- Unique identifier for the platform\n    station_id character varying(64) NOT NULL, -- Foreign key referencing stations\n    platform_number character varying(10) NOT NULL, -- Platform identifier (e.g., '1A', '5')\n    track_number character varying(10), -- Associated track number, if different\n    status character varying(32) NOT NULL DEFAULT 'Operational', -- e.g., Operational, Maintenance, Closed\n    length_meters numeric(8,2), -- Length of the platform in meters\n    accessible boolean NOT NULL DEFAULT false, -- Is the platform accessible (e.g., wheelchair)?\n    PRIMARY KEY (platform_id),\n    FOREIGN KEY (station_id) REFERENCES train_station_management.stations(station_id)\n)\n"}
{"conversations": [{"role": "user", "content": "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 user IDs of users who have private profiles and have liked any post or comment."}, {"role": "assistant", "content": "SELECT DISTINCT T1.user_id FROM social_media.user_settings AS T1 JOIN social_media.likes AS T2 ON T1.user_id = T2.user_id WHERE T1.private_profile = true;"}, {"role": "user", "content": "Now, only show those who have push notifications enabled as well."}, {"role": "assistant", "content": "SELECT DISTINCT T1.user_id FROM social_media.user_settings AS T1 JOIN social_media.likes AS T2 ON T1.user_id = T2.user_id WHERE T1.private_profile = true AND T1.push_notifications_enabled = true;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.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 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.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": "Retrieve the count of active insurance products for each product_type and order the results by the count descending."}, {"role": "assistant", "content": "SELECT product_type,\n       COUNT(*) AS active_count\nFROM insurance.insurance_products\nWHERE is_active = TRUE\nGROUP BY product_type\nORDER BY active_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 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 )\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 me the number of players registered in each country, along with the number of different games available for each country."}, {"role": "assistant", "content": "SELECT p.country_code, COUNT(DISTINCT p.player_id) AS player_count, COUNT(DISTINCT g.game_id) AS game_count\nFROM gaming_technology.players p\nCROSS JOIN gaming_technology.games g\nGROUP BY p.country_code;"}, {"role": "user", "content": "This doesn't make sense; the game count should be the number of games, not all possible combinations. Can you fix it to just show the count of players per country?"}, {"role": "assistant", "content": "SELECT p.country_code, COUNT(*) AS player_count\nFROM gaming_technology.players p\nGROUP BY p.country_code;"}, {"role": "user", "content": "Now add in the total number of servers located in each country, based on the players' country code matching the server's region."}, {"role": "assistant", "content": "SELECT p.country_code, COUNT(*) AS player_count,\n       (SELECT COUNT(*) FROM gaming_technology.servers s WHERE s.region = p.country_code) AS server_count\nFROM gaming_technology.players p\nGROUP BY p.country_code;"}, {"role": "user", "content": "Show only countries where there are at least 5 servers."}, {"role": "assistant", "content": "SELECT p.country_code, COUNT(*) AS player_count,\n       (SELECT COUNT(*) FROM gaming_technology.servers s WHERE s.region = p.country_code) AS server_count\nFROM gaming_technology.players p\nGROUP BY p.country_code\nHAVING (SELECT COUNT(*) FROM gaming_technology.servers s WHERE s.region = p.country_code) >= 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, 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 (\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.servers ( server_id uuid NOT NULL DEFAULT gen_random_uuid(), game_id uuid NOT NULL, server_name character varying(150), region character varying(50) NOT NULL, ip_address character varying(45), port integer, current_players integer NOT NULL DEFAULT 0, max_players integer NOT NULL, status character varying(30) NOT NULL DEFAULT 'offline', last_heartbeat timestamp with time zone, PRIMARY KEY (server_id) )\nCREATE TABLE gaming_technology.achievements ( achievement_id uuid, game_id uuid, name text, description text, icon_url text, points integer, hidden boolean )\nCREATE TABLE gaming_technology.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) )\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": "能否帮我统计特定车站(station_id 为 'station_xyz')的所有工作人员数量？"}, {"role": "assistant", "content": "MATCH (s:Station {station_id: 'station_xyz'})<-[:BASED_AT]-(staff:Staff)\nRETURN COUNT(staff) AS total_staff"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\n// Node Label: :Station\n// Properties:\n//   station_id: String (Constraint: UNIQUE)\n//   station_name: String\n//   city: String (Index recommended)\n//   state_province: String\n//   country_code: String\n//   address: String\n//   timezone: String\n//   number_of_platforms: Integer\n//   created_at: DateTime\n//   last_updated_at: DateTime\n// Example Cypher CREATE:\n// CREATE (:Station {station_id: 'station_xyz', station_name: 'Grand Central Terminal', city: 'New York', ...})\n// Node Label: :Platform\n// Properties:\n//   platform_id: String (Constraint: UNIQUE)\n//   platform_number: String\n//   track_number: String\n//   status: String\n//   length_meters: Float\n//   accessible: Boolean\n// Relationship: (:Platform)-[:LOCATED_AT]->(:Station)\n// Example Cypher CREATE:\n// MATCH (s:Station {station_id: 'station_xyz'})\n// CREATE (p:Platform {platform_id: 'plat_123', ...})-[:LOCATED_AT]->(s)\n// Node Label: :Train\n// Properties:\n//   train_id: String (Constraint: UNIQUE)\n//   train_number: String (Constraint: UNIQUE)\n//   model: String\n//   manufacturer: String\n//   year_manufactured: Integer\n//   capacity: Integer\n//   status: String\n//   last_maintenance_date: Date\n//   next_maintenance_date: Date\n// Example Cypher CREATE:\n// CREATE (:Train {train_id: 'train_789', train_number: 'Acela 2151', ...})\n// Node Label: :TrainCar\n// Properties:\n//   car_id: String (Constraint: UNIQUE)\n//   car_number: String\n//   car_type: String\n//   class: String\n//   capacity: Integer\n//   features: String (Or List<String> if driver supports)\n// Relationship: (:TrainCar)-[:PART_OF_TRAIN]->(:Train)\n// Example Cypher CREATE:\n// MATCH (t:Train {train_id: 'train_789'})\n// CREATE (c:TrainCar {car_id: 'car_abc', ...})-[:PART_OF_TRAIN]->(t)\n// Node Label: :Route\n// Properties:\n//   route_id: String (Constraint: UNIQUE)\n//   route_name: String\n//   description: String\n//   is_active: Boolean\n// Relationships:\n//   (:Route)-[:STARTS_AT]->(:Station)\n//   (:Route)-[:ENDS_AT]->(:Station)\n// Example Cypher CREATE:\n// MATCH (origin:Station {station_id: 'station_bos'}), (dest:Station {station_id: 'station_was'})\n// CREATE (r:Route {route_id: 'route_ne_corr', ...})-[:STARTS_AT]->(origin), (r)-[:ENDS_AT]->(dest)\n// Relationship: (:Route)-[rel:HAS_STOP]->(:Station)\n// Relationship Properties on :HAS_STOP:\n//   sequence_order: Integer\n//   distance_from_previous_km: Float\n//   typical_stop_duration_minutes: Integer\n// Example Cypher CREATE:\n// MATCH (r:Route {route_id: 'route_ne_corr'}), (s:Station {station_id: 'station_pvd'})\n// CREATE (r)-[:HAS_STOP {sequence_order: 2, distance_from_previous_km: 70.5, ...}]->(s)\n// Node Label: :ScheduledTrip (or just :Trip)\n// Properties:\n//   schedule_id: String (Constraint: UNIQUE)\n//   departure_datetime: DateTime\n//   arrival_datetime: DateTime\n//   status: String\n//   notes: String\n// Relationships:\n//   (:ScheduledTrip)-[:USES_TRAIN]->(:Train)\n//   (:ScheduledTrip)-[:FOLLOWS_ROUTE]->(:Route)\n// Example Cypher CREATE:\n// MATCH (t:Train {train_id: 'train_789'}), (r:Route {route_id: 'route_ne_corr'})\n// CREATE (sched:ScheduledTrip {schedule_id: 'sched_1122', ...})-[:USES_TRAIN]->(t), (sched)-[:FOLLOWS_ROUTE]->(r)\n// Relationship: (:ScheduledTrip)-[rel:SCHEDULED_STOP]->(:Station)\n// Relationship Properties on :SCHEDULED_STOP:\n//   sequence_order: Integer\n//   platform_id: String (references Platform node if modeled, or just store ID)\n//   scheduled_arrival_time: DateTime\n//   scheduled_departure_time: DateTime\n//   actual_arrival_time: DateTime\n//   actual_departure_time: DateTime\n//   status: String\n// Example Cypher CREATE:\n// MATCH (sched:ScheduledTrip {schedule_id: 'sched_1122'}), (s:Station {station_id: 'station_pvd'})\n// CREATE (sched)-[:SCHEDULED_STOP {sequence_order: 2, platform_id: 'plat_pvd_1', ...}]->(s)\n// Node Label: :Passenger\n// Properties:\n//   passenger_id: String (Constraint: UNIQUE)\n//   first_name: String\n//   last_name: String\n//   email: String (Constraint: UNIQUE, if not null)\n//   phone_number: String (Constraint: UNIQUE, if not null)\n//   date_of_birth: Date\n//   loyalty_program_id: String\n//   created_at: DateTime\n// Example Cypher CREATE:\n// CREATE (:Passenger {passenger_id: 'pass_pqr', first_name: 'Alice', ...})\n// Node Label: :Booking\n// Properties:\n//   booking_id: String (Constraint: UNIQUE)\n//   booking_datetime: DateTime\n//   status: String\n//   total_price: Float\n//   currency_code: String\n//   special_requests: String\n// Relationships:\n//   (:Passenger)-[:MADE_BOOKING]->(:Booking)\n//   (:Booking)-[:FOR_TRIP]->(:ScheduledTrip)\n// Example Cypher CREATE:\n// MATCH (p:Passenger {passenger_id: 'pass_pqr'}), (sched:ScheduledTrip {schedule_id: 'sched_1122'})\n// CREATE (p)-[:MADE_BOOKING]->(b:Booking {booking_id: 'book_zyx', ...})-[:FOR_TRIP]->(sched)\n// Node Label: :Ticket\n// Properties:\n//   ticket_id: String (Constraint: UNIQUE)\n//   seat_number: String\n//   ticket_type: String\n//   price: Float\n//   is_checked_in: Boolean\n//   qr_code_data: String\n// Relationships:\n//   (:Ticket)-[:PART_OF_BOOKING]->(:Booking)\n//   (:Ticket)-[:ASSIGNED_TO_CAR]->(:TrainCar)\n// Example Cypher CREATE:\n// MATCH (b:Booking {booking_id: 'book_zyx'}), (c:TrainCar {car_id: 'car_abc'})\n// CREATE (t:Ticket {ticket_id: 'tkt_1a2b', ...})-[:PART_OF_BOOKING]->(b), (t)-[:ASSIGNED_TO_CAR]->(c)\n// Node Label: :Staff\n// Properties:\n//   staff_id: String (Constraint: UNIQUE)\n//   first_name: String\n//   last_name: String\n//   role: String\n//   employee_number: String (Constraint: UNIQUE)\n//   hire_date: Date\n//   contact_email: String (Constraint: UNIQUE, if not null)\n//   contact_phone: String\n//   is_active: Boolean\n// Relationship (Optional):\n//   (:Staff)-[:BASED_AT]->(:Station)\n// Example Cypher CREATE:\n// CREATE (:Staff {staff_id: 'staff_mno', first_name: 'Bob', ...})\n// OPTIONAL MATCH (s:Station {station_id: 'station_xyz'}) // If primary_station_id exists\n// WITH s, staff_mno // Need to get the created staff node reference\n// WHERE s IS NOT NULL\n// CREATE (staff_mno)-[:BASED_AT]->(s)\n"}
{"conversations": [{"role": "user", "content": "List 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": "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": "For each group chat, list its ID, name, creation time, and the creation time of the next group chat created after it, ordered by creation time."}, {"role": "assistant", "content": "SELECT conversation_id, group_name, created_at, LEAD(created_at) OVER (ORDER BY created_at) AS next_group_chat_created_at FROM social_media.conversations WHERE is_group_chat = true ORDER BY created_at;"}, {"role": "user", "content": "Only show pairs where the next group chat was created within 48 hours of the current one, and also include the time difference in hours."}, {"role": "assistant", "content": "WITH RankedGroupChats AS ( SELECT conversation_id, group_name, created_at, LEAD(created_at) OVER (ORDER BY created_at) AS next_group_chat_created_at FROM social_media.conversations WHERE is_group_chat = true ) SELECT conversation_id, group_name, created_at, next_group_chat_created_at, EXTRACT(EPOCH FROM (next_group_chat_created_at - created_at)) / 3600 AS time_difference_hours FROM RankedGroupChats WHERE next_group_chat_created_at IS NOT NULL AND EXTRACT(EPOCH FROM (next_group_chat_created_at - created_at)) <= 48 * 3600 ORDER BY created_at;"}, {"role": "user", "content": "Further refine: Only include group chats whose names contain 'Discuss'."}, {"role": "assistant", "content": "WITH RankedGroupChats AS ( SELECT conversation_id, group_name, created_at, LEAD(created_at) OVER (ORDER BY created_at) AS next_group_chat_created_at FROM social_media.conversations WHERE is_group_chat = true ) SELECT conversation_id, group_name, created_at, next_group_chat_created_at, EXTRACT(EPOCH FROM (next_group_chat_created_at - created_at)) / 3600 AS time_difference_hours FROM RankedGroupChats WHERE next_group_chat_created_at IS NOT NULL AND EXTRACT(EPOCH FROM (next_group_chat_created_at - created_at)) <= 48 * 3600 AND group_name LIKE '%Discuss%' ORDER BY created_at;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.conversations ( conversation_id character varying(64) NOT NULL, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, last_message_at timestamp, is_group_chat boolean NOT NULL DEFAULT false, group_name character varying(100), PRIMARY KEY (conversation_id) )\n"}
{"conversations": [{"role": "user", "content": "What are the safety ratings or crash statistics for the Boeing 787 Dreamliner?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to safety ratings or crash statistics for specific aircraft models like the Boeing 787 Dreamliner. My data is limited to the information in the aircraft_models table, which includes details such as model name, manufacturer, passenger capacity, and technical specifications. For safety-related information, I recommend consulting official aviation authorities or safety reports."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE manufacturing.aircraft_models ( model_id text, model_name text, manufacturer text, passenger_capacity integer, max_range_km integer, engine_type text, wingspan_m numeric, status text, first_flight_date date )\n"}
{"conversations": [{"role": "user", "content": "Show me the top 5 narratives by market cap, along with their 24-hour trading volume and 7-day price change percentage."}, {"role": "assistant", "content": "SELECT narrative.text, volume_24h.numeric, price_change_percentage_7d.numeric FROM narrative_info ORDER BY market_cap.numeric DESC LIMIT 5;"}, {"role": "user", "content": "Can you also include the top 3 coins for each of these narratives?"}, {"role": "assistant", "content": "SELECT narrative.text, volume_24h.numeric, price_change_percentage_7d.numeric, top_3_coins.text FROM narrative_info ORDER BY market_cap.numeric DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE narrative_info ( narrative.text, top_3_coins.text, price_change_percentage_1h.numeric, price_change_percentage_24h.numeric, price_change_percentage_7d.numeric, market_cap.numeric, volume_24h.numeric, trend_rank.numeric, token_num.numeric )\n"}
{"conversations": [{"role": "user", "content": "Show all likes made by user 'U555' on comments, including the comment_id and like creation time."}, {"role": "assistant", "content": "SELECT like_id, comment_id, created_at\nFROM social_media.likes\nWHERE user_id = 'U555' AND comment_id IS NOT NULL;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.posts ( post_id.text, user_id.text, content.text, media_url.text, media_type.text, created_at.timestamp, updated_at.timestamp, visibility.text, location_lat.numeric, location_lon.numeric )\nCREATE TABLE social_media.likes ( like_id.text, user_id.text, post_id.text, comment_id.text, created_at.timestamp )\nCREATE TABLE social_media.hashtags ( hashtag_id text, tag_name text, created_at timestamp )\nCREATE TABLE social_media.post_hashtags ( post_hashtag_id text, post_id text, hashtag_id text )\nCREATE TABLE social_media.conversation_participants ( participant_id character varying(64) NOT NULL, conversation_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, joined_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, last_read_at timestamp, PRIMARY KEY (participant_id), CONSTRAINT unique_user_conversation UNIQUE (conversation_id, user_id) )\nCREATE TABLE social_media.notifications (\n    notification_id character varying(64) NOT NULL, -- unique identifier for the notification\n    recipient_user_id character varying(64) NOT NULL, -- user receiving the notification (FK to users.user_id)\n    sender_user_id character varying(64), -- user triggering the notification (FK to users.user_id, can be null for system notifications)\n    notification_type character varying(30) NOT NULL, -- type of notification ('like', 'comment', 'follow', 'mention', 'message')\n    target_entity_id character varying(64), -- ID of the related entity (post_id, comment_id, user_id, conversation_id)\n    target_entity_type character varying(20), -- type of the related entity ('post', 'comment', 'user', 'conversation')\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp notification was created\n    read_at timestamp, -- timestamp notification was marked as read\n    PRIMARY KEY (notification_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List all unique wallet addresses present in the system."}, {"role": "assistant", "content": "SELECT DISTINCT address FROM trading_platform.wallets;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.wallets ( wallet_id text, user_id text, address text, private_key text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Get the number of documents for each case, showing case_id and document count, ordered by count descending."}, {"role": "assistant", "content": "SELECT case_id,\n       COUNT(*) AS document_count\nFROM legal_services.documents\nGROUP BY case_id\nORDER BY document_count DESC;"}, {"role": "user", "content": "Actually, only count documents of type 'Evidence'."}, {"role": "assistant", "content": "SELECT case_id,\n       COUNT(*) AS evidence_count\nFROM legal_services.documents\nWHERE document_type = 'Evidence'\nGROUP BY case_id\nORDER BY evidence_count DESC;"}, {"role": "user", "content": "Also, include the case_name from the cases table."}, {"role": "assistant", "content": "SELECT d.case_id,\n       c.case_name,\n       COUNT(*) AS evidence_count\nFROM legal_services.documents d\nJOIN legal_services.cases c ON d.case_id = c.case_id\nWHERE d.document_type = 'Evidence'\nGROUP BY d.case_id, c.case_name\nORDER BY evidence_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.clients ( client_id text PRIMARY KEY, first_name text, last_name text, company_name text, email text UNIQUE, phone text, address text, date_registered timestamp, status text )\nCREATE TABLE legal_services.cases ( case_id text, case_number text, case_name text, client_id text, lead_lawyer_id text, case_type text, status text, date_opened timestamp, date_closed timestamp, description text, court_jurisdiction text )\nCREATE TABLE legal_services.documents ( document_id.text, case_id.text, document_name.text, document_type.text, storage_path.text, uploaded_by_lawyer_id.text, upload_timestamp.timestamp, version.integer, description.text )\nCREATE TABLE legal_services.time_entries ( entry_id text PRIMARY KEY, case_id text, lawyer_id text, date_worked date, hours_spent numeric, billing_rate numeric, description text, is_billable bool, is_billed bool, invoice_id text, created_at timestamp )\nCREATE TABLE legal_services.invoices ( invoice_id text PRIMARY KEY, invoice_number text UNIQUE, client_id text, case_id text, issue_date date, due_date date, total_amount numeric, amount_paid numeric, status text, payment_date timestamp, notes text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "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": "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": "List all invoices where amount_paid is less than total_amount."}, {"role": "assistant", "content": "SELECT *\nFROM legal_services.invoices\nWHERE amount_paid < total_amount;"}, {"role": "user", "content": "Only include those with due_date before today."}, {"role": "assistant", "content": "SELECT *\nFROM legal_services.invoices\nWHERE amount_paid < total_amount\n  AND due_date < CURRENT_DATE;"}, {"role": "user", "content": "Now also compute how many days each invoice is overdue as difference between CURRENT_DATE and due_date, and only show those overdue by more than 30 days."}, {"role": "assistant", "content": "SELECT invoice_id,\n       invoice_number,\n       client_id,\n       total_amount,\n       amount_paid,\n       due_date,\n       CURRENT_DATE - due_date AS days_overdue\nFROM legal_services.invoices\nWHERE amount_paid < total_amount\n  AND due_date < CURRENT_DATE\n  AND CURRENT_DATE - due_date > 30;"}, {"role": "user", "content": "Finally, order the result by days_overdue descending."}, {"role": "assistant", "content": "SELECT invoice_id,\n       invoice_number,\n       client_id,\n       total_amount,\n       amount_paid,\n       due_date,\n       CURRENT_DATE - due_date AS days_overdue\nFROM legal_services.invoices\nWHERE amount_paid < total_amount\n  AND due_date < CURRENT_DATE\n  AND CURRENT_DATE - due_date > 30\nORDER BY days_overdue DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.invoices ( invoice_id.text, invoice_number.text, client_id.text, case_id.text, issue_date.date, due_date.date, total_amount.numeric, amount_paid.numeric, status.text, payment_date.timestamp, notes.text, created_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "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": "What are the training programs or certifications completed by a staff member with the role of Platform Supervisor?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to information about the training programs or certifications completed by staff members. The data available to me only includes basic staff details such as name, role, and contact information. For details on training or certifications, please refer to the HR department or relevant training records."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.staff ( staff_id text PRIMARY KEY, first_name text, last_name text, role text, primary_station_id text, employee_number text UNIQUE, hire_date date, contact_email text UNIQUE, contact_phone text, is_active boolean )\n"}
{"conversations": [{"role": "user", "content": "List 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": "List all food and beverage services (category = 'Food & Beverage') with their names, prices, and units, where the price is less than $20."}, {"role": "assistant", "content": "SELECT service_name, price, unit FROM hospitality_technology.services WHERE category = 'Food & Beverage' AND price < 20;"}, {"role": "user", "content": "Now, filter these results to only include services that are priced per item (unit = 'Per Item')."}, {"role": "assistant", "content": "SELECT service_name, price, unit FROM hospitality_technology.services WHERE category = 'Food & Beverage' AND price < 20 AND unit = 'Per Item';"}, {"role": "user", "content": "The query is missing the department information. Can you include that as well?"}, {"role": "assistant", "content": "SELECT service_name, price, unit, department FROM hospitality_technology.services WHERE category = 'Food & Beverage' AND price < 20 AND unit = 'Per Item';"}, {"role": "user", "content": "Actually, I only need services from the 'F&B' department, and order them by price in ascending order."}, {"role": "assistant", "content": "SELECT service_name, price, unit, department FROM hospitality_technology.services WHERE category = 'Food & Beverage' AND price < 20 AND unit = 'Per Item' AND department = 'F&B' ORDER BY price 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": "Show me the total transaction amount by transaction_type for all transactions processed by employees in the 'Trading' department, along with their department name."}, {"role": "assistant", "content": "SELECT t.transaction_type, SUM(t.amount) AS total_amount, e.department\nFROM financial_services.transactions t\nJOIN financial_services.employees e ON t.account_id IN (\n    SELECT account_id \n    FROM financial_services.accounts \n    WHERE branch_id = e.branch_id\n)\nWHERE e.department = 'Trading'\nGROUP BY t.transaction_type, e.department;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.transactions (\n    transaction_id character varying(64) NOT NULL, -- unique identifier for the transaction\n    account_id character varying(64) NOT NULL, -- account involved in the transaction\n    related_account_id character varying(64), -- counterpart account for transfers\n    transaction_type character varying(50) NOT NULL, -- e.g., Deposit, Withdrawal, Transfer, Payment, Fee, Interest\n    amount numeric(19, 4) NOT NULL, -- transaction amount\n    currency character varying(3) NOT NULL, -- transaction currency\n    transaction_date timestamp NOT NULL, -- exact time of the transaction\n    effective_date date NOT NULL, -- date the transaction affects the balance\n    description text, -- description or memo of the transaction\n    status character varying(32) NOT NULL, -- e.g., Pending, Completed, Failed, Reversed\n    reference_number character varying(128), -- external reference if applicable (e.g., check number)\n    PRIMARY KEY (transaction_id),\n    FOREIGN KEY (account_id) REFERENCES financial_services.accounts(account_id),\n    FOREIGN KEY (related_account_id) REFERENCES financial_services.accounts(account_id)\n)\nCREATE TABLE financial_services.employees ( employee_id text, first_name text, last_name text, job_title text, department text, branch_id text, email text, phone_extension text, hire_date date, termination_date date, manager_id text, status text )\n"}
{"conversations": [{"role": "user", "content": "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_trunc('month', CURRENT_DATE - INTERVAL '12 months') 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_trunc('month', CURRENT_DATE - INTERVAL '12 months') 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) )\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"}
{"conversations": [{"role": "user", "content": "Show me the top 5 NFT collections with the highest floor price on Ethereum, along with their names and contract addresses, but only include collections with more than 5000 tokens."}, {"role": "assistant", "content": "SELECT nc.name, nc.contract_address, nc.floor_price FROM nft_collections nc WHERE nc.blockchain = 'Ethereum' AND nc.token_count > 5000 ORDER BY CAST(nc.floor_price AS decimal) DESC LIMIT 5;"}, {"role": "user", "content": "Can you join this with the nft_metadata table to include the average rarity score for these collections?"}, {"role": "assistant", "content": "SELECT nc.name, nc.contract_address, nc.floor_price, AVG(nm.rarity_score) as avg_rarity_score FROM nft_collections nc JOIN nft_metadata nm ON nc.contract_address = nm.contract_address WHERE nc.blockchain = 'Ethereum' AND nc.token_count > 5000 GROUP BY nc.name, nc.contract_address, nc.floor_price ORDER BY CAST(nc.floor_price AS decimal) DESC LIMIT 5;"}, {"role": "user", "content": "Now filter these results to only show collections with an average rarity score above 75."}, {"role": "assistant", "content": "SELECT nc.name, nc.contract_address, nc.floor_price, AVG(nm.rarity_score) as avg_rarity_score FROM nft_collections nc JOIN nft_metadata nm ON nc.contract_address = nm.contract_address WHERE nc.blockchain = 'Ethereum' AND nc.token_count > 5000 GROUP BY nc.name, nc.contract_address, nc.floor_price HAVING AVG(nm.rarity_score) > 75 ORDER BY CAST(nc.floor_price AS decimal) DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp timestamp(6) NOT NULL, block_number bigint NOT NULL, transaction_hash varchar NOT NULL, transaction_index bigint NOT NULL, from_address varchar NOT NULL, contract_address varchar NOT NULL, symbol varchar NOT NULL, total_supply varchar NOT NULL, name varchar NOT NULL, decimals bigint NOT NULL, is_erc20 integer NOT NULL, is_erc721 integer NOT NULL, is_erc1155 integer NOT NULL, is_proxy integer NOT NULL, extra_info varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE erc1155_approval_for_all ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar(66) NOT NULL, log_index integer NOT NULL, contract_address varchar(42) NOT NULL )\nCREATE TABLE erc20_balances ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE erc20_balances_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_holders ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, token_id varchar NOT NULL, contract_type varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE nft_holder_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, token_id varchar NOT NULL, contract_type varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_coins_metadata ( object_id varchar NOT NULL, coin_type varchar NOT NULL, status varchar NOT NULL, decimals bigint NOT NULL, description varchar NOT NULL, icon_url varchar NOT NULL, symbol varchar NOT NULL, name varchar NOT NULL )\nCREATE TABLE sui_nfts ( object_id varchar NOT NULL, status varchar NOT NULL, collection_type varchar NOT NULL, package_id varchar NOT NULL, previous_transaction varchar NOT NULL, display varchar NOT NULL, owner varchar NOT NULL, name varchar NOT NULL )\nCREATE TABLE nft_metadata ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, token_id varchar NOT NULL, contract_name varchar NOT NULL, erc_type varchar NOT NULL, amount bigint NOT NULL, minter varchar NOT NULL, owner varchar NOT NULL, mint_block_number bigint NOT NULL, mint_time bigint NOT NULL, mint_transaction_hash varchar NOT NULL, mint_price varchar NOT NULL, token_uri varchar NOT NULL, metadata varchar NOT NULL, name varchar NOT NULL, image_uri varchar NOT NULL, traits varchar NOT NULL, updated_at bigint NOT NULL, status varchar NOT NULL, rarity_score real NOT NULL, rarity_rank integer NOT NULL, unique_attribute_count integer NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_collections ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, name varchar NOT NULL, symbol varchar NOT NULL, deploy_block_number bigint NOT NULL, deploy_block_time bigint NOT NULL, erc_type varchar NOT NULL, owner varchar NOT NULL, traits varchar NOT NULL, description varchar NOT NULL, slug varchar NOT NULL, media_info varchar NOT NULL, image_url varchar NOT NULL, banner_image_url varchar NOT NULL, updated_at bigint NOT NULL, banner varchar NOT NULL, token_count bigint NOT NULL, floor_price varchar NOT NULL, floor_price_symbol varchar NOT NULL, floor_price_contract varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_prices ( uuid varchar(36) NOT NULL, blockchain varchar(36) NOT NULL, address varchar(42) NOT NULL, decimals bigint NOT NULL, symbol varchar(36) NOT NULL, price real NOT NULL, timestamp timestamp(6) NOT NULL )\nCREATE TABLE token_prices_latest ( blockchain varchar(36) NOT NULL, address varchar(42) NOT NULL, decimals bigint NOT NULL, symbol varchar(36) NOT NULL, price real NOT NULL, timestamp timestamp(6) NOT NULL )\nCREATE TABLE erc20_approval ( block_number bigint NOT NULL, block_timestamp timestamp(6) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar NOT NULL, log_index integer NOT NULL, contract_address varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_balances ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar NOT NULL, wallet_address varchar(42) NOT NULL, total_supply decimal(38,0) NOT NULL, amount decimal(38,0) NOT NULL )\nCREATE TABLE token_info ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar(255) NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar(20) NOT NULL, tick varchar(255) NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(62) NOT NULL, to_address varchar(62) NOT NULL )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar(20) NOT NULL, tick varchar(255) NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(42) NOT NULL, to_address varchar(42) NOT NULL )\nCREATE TABLE token_balances_avalanche ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar(20) NOT NULL, wallet_address varchar(42) NOT NULL, total_supply decimal(38,0) NOT NULL, amount decimal(38,0) NOT NULL )\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar(20) NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL, minted decimal(38,0) NOT NULL, holders decimal(38,0) NOT NULL, txs decimal(38,0) NOT NULL, updated_timestamp timestamp(3) NOT NULL, completed_timestamp timestamp(3) NOT NULL, id varchar(255) NOT NULL )\n"}
{"conversations": [{"role": "user", "content": "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 the total number of customers in each state."}, {"role": "assistant", "content": "SELECT\n  state,\n  COUNT(customer_id)\nFROM insurance.customers\nGROUP BY\n  state;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.customers ( customer_id text, first_name text, last_name text, date_of_birth date, ssn_hash text, address_line1 text, address_line2 text, city text, state text, zip_code text, country text, phone_number text, email text, created_at timestamp, updated_at timestamp, status text )\nCREATE TABLE insurance.claims (\n    claim_id character varying(64) NOT NULL, -- unique identifier for the claim\n    policy_id character varying(64) NOT NULL, -- identifier of the policy under which the claim is made (FK to policies)\n    customer_id character varying(64) NOT NULL, -- identifier of the customer making the claim (FK to customers)\n    incident_date timestamp NOT NULL, -- date and time of the incident leading to the claim\n    reported_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- date the claim was reported\n    description text NOT NULL, -- detailed description of the incident and claim\n    estimated_loss numeric(15, 2), -- initial estimated cost of the loss\n    status character varying(30) NOT NULL, -- e.g., Filed, Processing, Under Review, Approved, Denied, Settled\n    settlement_amount numeric(15, 2), -- final amount paid out\n    settlement_date date,\n    claim_handler_id character varying(64), -- identifier for the employee handling the claim (FK to employees/adjusters)\n    police_report_number character varying(100),\n    PRIMARY KEY (claim_id)\n)\nCREATE TABLE insurance.insurance_products (\n    product_id character varying(64) NOT NULL, -- unique identifier for the insurance product\n    product_name character varying(150) NOT NULL, -- name of the insurance product (e.g., 'Comprehensive Auto Insurance')\n    product_type character varying(50) NOT NULL, -- category like 'Auto', 'Home', 'Life', 'Health', 'Travel'\n    description text, -- detailed description of the product\n    base_premium numeric(10, 2) NOT NULL, -- starting premium before adjustments\n    coverage_details text, -- details about what is covered (could be JSON or structured text)\n    underwriting_rules text, -- rules used for assessing risk and eligibility\n    is_active boolean NOT NULL DEFAULT true, -- whether the product is currently offered\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n    updated_at timestamp,\n    PRIMARY KEY (product_id)\n)\nCREATE TABLE insurance.claim_documents ( document_id character varying(64) NOT NULL, claim_id character varying(64) NOT NULL, document_type character varying(50) NOT NULL, file_name character varying(255) NOT NULL, file_path character varying(512) NOT NULL, file_size_bytes integer, mime_type character varying(100), uploaded_by character varying(64), uploaded_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, description text, PRIMARY KEY (document_id) )\n"}
{"conversations": [{"role": "user", "content": "Show all users whose full name starts with 'A' and who have updated their profile in June 2024. Please include their usernames and updated_at timestamps."}, {"role": "assistant", "content": "SELECT username, updated_at FROM social_media.users WHERE full_name ILIKE 'A%' AND EXTRACT(YEAR FROM updated_at) = 2024 AND EXTRACT(MONTH FROM updated_at) = 6;"}, {"role": "user", "content": "I also want to know which of them have a verified profile. Can you add the verification status to the results?"}, {"role": "assistant", "content": "SELECT username, updated_at, is_verified FROM social_media.users WHERE full_name ILIKE 'A%' AND EXTRACT(YEAR FROM updated_at) = 2024 AND EXTRACT(MONTH FROM updated_at) = 6;"}, {"role": "user", "content": "Now, please only show the users who are verified."}, {"role": "assistant", "content": "SELECT username, updated_at FROM social_media.users WHERE full_name ILIKE 'A%' AND EXTRACT(YEAR FROM updated_at) = 2024 AND EXTRACT(MONTH FROM updated_at) = 6 AND 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 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 )\n"}
{"conversations": [{"role": "user", "content": "For each patient, find the next appointment after each one. Return patient_id, appointment_id, next_appointment_id, and the waiting time in minutes between them."}, {"role": "assistant", "content": "SELECT A.patient_id,\n       A.appointment_id AS current_id,\n       B.appointment_id AS next_id,\n       EXTRACT(EPOCH FROM (B.appointment_time - A.appointment_time)) / 60 AS wait_minutes\nFROM healthcare.appointments A\nJOIN healthcare.appointments B\n  ON A.patient_id = B.patient_id\n AND B.appointment_time = (\n       SELECT MIN(appointment_time)\n       FROM healthcare.appointments\n       WHERE patient_id = A.patient_id\n         AND appointment_time > A.appointment_time\n   );"}, {"role": "user", "content": "Now include only the pairs where the waiting time is less than 30 minutes."}, {"role": "assistant", "content": "SELECT A.patient_id,\n       A.appointment_id AS current_id,\n       B.appointment_id AS next_id,\n       EXTRACT(EPOCH FROM (B.appointment_time - A.appointment_time)) / 60 AS wait_minutes\nFROM healthcare.appointments A\nJOIN healthcare.appointments B\n  ON A.patient_id = B.patient_id\n AND B.appointment_time = (\n       SELECT MIN(appointment_time)\n       FROM healthcare.appointments\n       WHERE patient_id = A.patient_id\n         AND appointment_time > A.appointment_time\n   )\nWHERE EXTRACT(EPOCH FROM (B.appointment_time - A.appointment_time)) / 60 < 30;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.appointments ( appointment_id text PRIMARY KEY, patient_id text, doctor_id text, appointment_time timestamp, duration_minutes int, reason text, status text, location_id text, notes text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "List all routes that have a distance greater than 100 km, showing the route number, origin and destination location IDs."}, {"role": "assistant", "content": "SELECT route_number, origin_location_id, destination_location_id FROM transportation.routes WHERE distance_km > 100;"}, {"role": "user", "content": "Can you include the estimated duration in hours instead of minutes, and filter to only show intercity routes?"}, {"role": "assistant", "content": "SELECT route_number, origin_location_id, destination_location_id, (estimated_duration_minutes/60) AS estimated_duration_hours FROM transportation.routes WHERE distance_km > 100 AND type = 'intercity';"}, {"role": "user", "content": "Now order the results by distance in descending order and include the count of bookings for each route."}, {"role": "assistant", "content": "SELECT r.route_number, r.origin_location_id, r.destination_location_id, (r.estimated_duration_minutes/60) AS estimated_duration_hours, r.distance_km, COUNT(b.booking_id) AS booking_count FROM transportation.routes r LEFT JOIN transportation.bookings b ON r.route_id = b.trip_id WHERE r.distance_km > 100 AND r.type = 'intercity' GROUP BY r.route_number, r.origin_location_id, r.destination_location_id, r.estimated_duration_minutes, r.distance_km ORDER BY r.distance_km DESC;"}, {"role": "user", "content": "I only want to see routes with more than 10 bookings and distance between 100 and 500 km."}, {"role": "assistant", "content": "SELECT r.route_number, r.origin_location_id, r.destination_location_id, (r.estimated_duration_minutes/60) AS estimated_duration_hours, r.distance_km, COUNT(b.booking_id) AS booking_count FROM transportation.routes r LEFT JOIN transportation.bookings b ON r.route_id = b.trip_id WHERE r.distance_km BETWEEN 100 AND 500 AND r.type = 'intercity' GROUP BY r.route_number, r.origin_location_id, r.destination_location_id, r.estimated_duration_minutes, r.distance_km HAVING COUNT(b.booking_id) > 10 ORDER BY r.distance_km DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.drivers ( driver_id 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 character varying(64) NOT NULL, route_number character varying(32) NOT NULL UNIQUE, description text, origin_location_id character varying(64) NOT NULL, destination_location_id character varying(64) NOT NULL, distance_km numeric(10, 2), estimated_duration_minutes integer, type character varying(32) NOT NULL, PRIMARY KEY (route_id) )\nCREATE TABLE transportation.passengers ( passenger_id character varying(64) NOT NULL, first_name character varying(128) NOT NULL, last_name character varying(128) NOT NULL, email character varying(128) UNIQUE, phone_number character varying(32) UNIQUE, date_of_birth date, loyalty_program_id character varying(64), created_at timestamp with time zone NOT NULL, PRIMARY KEY (passenger_id) )\nCREATE TABLE transportation.bookings ( booking_id character varying(64) NOT NULL, passenger_id character varying(64) NOT NULL, trip_id character varying(64) NOT NULL, seat_number character varying(16), booking_time timestamp with time zone NOT NULL, status character varying(32) NOT NULL, fare numeric(10, 2) NOT NULL, payment_transaction_id character varying(128), special_requests text, PRIMARY KEY (booking_id) )\n"}
{"conversations": [{"role": "user", "content": "What is the 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 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": "Show all SUI coins with 'exists' status and more than 8 decimal places. Display coin_type, symbol, name, and decimals."}, {"role": "assistant", "content": "SELECT coin_type, symbol, name, decimals\nFROM sui_coins_metadata\nWHERE status = 'exists' AND decimals > 8;"}, {"role": "user", "content": "Add the total balance for each coin_type by joining with sui_coins."}, {"role": "assistant", "content": "SELECT scm.coin_type, scm.symbol, scm.name, scm.decimals, SUM(sc.balance::numeric) AS total_balance\nFROM sui_coins_metadata scm\nJOIN sui_coins sc ON scm.coin_type = sc.coin_type\nWHERE scm.status = 'exists' AND scm.decimals > 8\nGROUP BY scm.coin_type, scm.symbol, scm.name, scm.decimals;"}, {"role": "user", "content": "Can you also include only coins where the total_balance is greater than 1,000,000 and show the description?"}, {"role": "assistant", "content": "SELECT scm.coin_type, scm.symbol, scm.name, scm.decimals, scm.description, SUM(sc.balance::numeric) AS total_balance\nFROM sui_coins_metadata scm\nJOIN sui_coins sc ON scm.coin_type = sc.coin_type\nWHERE scm.status = 'exists' AND scm.decimals > 8\nGROUP BY scm.coin_type, scm.symbol, scm.name, scm.decimals, scm.description\nHAVING SUM(sc.balance::numeric) > 1000000;"}, {"role": "user", "content": "Actually, only show the top 5 coins with the highest total_balance."}, {"role": "assistant", "content": "SELECT scm.coin_type, scm.symbol, scm.name, scm.decimals, scm.description, SUM(sc.balance::numeric) AS total_balance\nFROM sui_coins_metadata scm\nJOIN sui_coins sc ON scm.coin_type = sc.coin_type\nWHERE scm.status = 'exists' AND scm.decimals > 8\nGROUP BY scm.coin_type, scm.symbol, scm.name, scm.decimals, scm.description\nHAVING SUM(sc.balance::numeric) > 1000000\nORDER BY total_balance 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 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": "Show me each service order along with the next order placed by the same guest, including both order IDs and the time difference in minutes between the two orders."}, {"role": "assistant", "content": "SELECT a.order_id,\n       b.order_id AS next_order_id,\n       EXTRACT(EPOCH FROM (b.order_timestamp - a.order_timestamp)) / 60 AS diff_minutes\nFROM hospitality_technology.service_orders a\nJOIN hospitality_technology.service_orders b\n  ON a.guest_id = b.guest_id\n AND b.order_timestamp > a.order_timestamp;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.service_orders ( order_id.text, reservation_id.text, guest_id.text, service_id.text, staff_id_ordered.text, staff_id_delivered.text, order_timestamp.timestamp, delivery_timestamp.timestamp, quantity.integer, unit_price.numeric, total_price.numeric, status.text, notes.text, bill_id.text )\n"}
{"conversations": [{"role": "user", "content": "Give a list of all policies where the deductible is less than 1000. Show policy_id, policy_number, start_date, and deductible."}, {"role": "assistant", "content": "SELECT policy_id, policy_number, start_date, deductible\nFROM insurance.policies\nWHERE deductible < 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 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": "For each player, show their player_id and the number of different games they have played sessions on."}, {"role": "assistant", "content": "SELECT player_id, COUNT(DISTINCT game_id) AS games_played\nFROM gaming_technology.game_sessions\nGROUP BY player_id;"}, {"role": "user", "content": "Only include players who have played at least 3 different games."}, {"role": "assistant", "content": "SELECT player_id, COUNT(DISTINCT game_id) AS games_played\nFROM gaming_technology.game_sessions\nGROUP BY player_id\nHAVING COUNT(DISTINCT game_id) >= 3;"}, {"role": "user", "content": "For these players, also show the total number of sessions they've played."}, {"role": "assistant", "content": "SELECT player_id, COUNT(DISTINCT game_id) AS games_played, COUNT(session_id) AS total_sessions\nFROM gaming_technology.game_sessions\nGROUP BY player_id\nHAVING COUNT(DISTINCT game_id) >= 3;"}, {"role": "user", "content": "Sort the result by total_sessions in descending order."}, {"role": "assistant", "content": "SELECT player_id, COUNT(DISTINCT game_id) AS games_played, COUNT(session_id) AS total_sessions\nFROM gaming_technology.game_sessions\nGROUP BY player_id\nHAVING COUNT(DISTINCT game_id) >= 3\nORDER BY total_sessions DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.games (\n    game_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game\n    title character varying(200) NOT NULL, -- official title of the game\n    developer_id uuid NOT NULL, -- FK linking to the developers table\n    publisher_id uuid, -- FK linking to a potential publishers table (optional)\n    genre character varying(100), -- primary genre (e.g., RPG, FPS, Strategy)\n    release_date date, -- official release date\n    description text, -- short description or synopsis of the game\n    platform character varying(50) NOT NULL, -- primary platform (e.g., PC, PlayStation 5, Xbox Series X, Mobile)\n    engine character varying(100), -- game engine used (e.g., Unreal Engine 5, Unity)\n    website character varying(255), -- official website URL\n    PRIMARY KEY (game_id)\n    -- FOREIGN KEY (developer_id) REFERENCES gaming_technology.developers(developer_id) -- Example FK constraint\n)\nCREATE TABLE gaming_technology.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.player_achievements (\n    player_achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for this unlock instance\n    player_id uuid NOT NULL, -- FK linking to the player who unlocked it\n    achievement_id uuid NOT NULL, -- FK linking to the achievement definition\n    unlocked_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the achievement was unlocked\n    PRIMARY KEY (player_achievement_id),\n    UNIQUE (player_id, achievement_id) -- Ensure a player can only unlock an achievement once\n    -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n    -- FOREIGN KEY (achievement_id) REFERENCES gaming_technology.achievements(achievement_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Show me all room types with 'King' in the bed_type field, along with their property IDs and base rates."}, {"role": "assistant", "content": "SELECT room_type_id, property_id, type_name, bed_type, base_rate FROM hospitality_technology.room_types WHERE bed_type LIKE '%King%';"}, {"role": "user", "content": "Now, join this with the guests table to show only room types from properties where the guest's country code is 'USA' and the guest is a loyalty member."}, {"role": "assistant", "content": "SELECT rt.room_type_id, rt.property_id, rt.type_name, rt.bed_type, rt.base_rate FROM hospitality_technology.room_types rt JOIN hospitality_technology.guests g ON rt.property_id = g.property_id WHERE rt.bed_type LIKE '%King%' AND g.country_code = 'USA' AND g.loyalty_member_id IS NOT NULL;"}, {"role": "user", "content": "The query is missing the max occupancy. Can you include that as well?"}, {"role": "assistant", "content": "SELECT rt.room_type_id, rt.property_id, rt.type_name, rt.bed_type, rt.base_rate, rt.max_occupancy FROM hospitality_technology.room_types rt JOIN hospitality_technology.guests g ON rt.property_id = g.property_id WHERE rt.bed_type LIKE '%King%' AND g.country_code = 'USA' AND g.loyalty_member_id IS NOT NULL;"}, {"role": "user", "content": "Actually, I need to see only room types with a base rate below $300, and order them by max occupancy in descending order."}, {"role": "assistant", "content": "SELECT rt.room_type_id, rt.property_id, rt.type_name, rt.bed_type, rt.base_rate, rt.max_occupancy FROM hospitality_technology.room_types rt JOIN hospitality_technology.guests g ON rt.property_id = g.property_id WHERE rt.bed_type LIKE '%King%' AND g.country_code = 'USA' AND g.loyalty_member_id IS NOT NULL AND rt.base_rate < 300 ORDER BY rt.max_occupancy DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.room_types ( room_type_id text PRIMARY KEY, property_id text, type_name text, description text, base_rate numeric, max_occupancy int, bed_type text, area_sqft numeric, amenities text )\nCREATE TABLE hospitality_technology.guests ( guest_id text, first_name text, last_name text, email text, phone_number text, date_of_birth date, address_line1 text, city text, state_province text, postal_code text, country_code text, preferences text, loyalty_member_id text, communication_consent boolean, created_at timestamp, updated_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "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": "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": "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": "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": "Can you show me each doctor and the number of prescriptions they wrote for each patient they treated? Include the doctor's full name, the patient's full name, and the total count of prescriptions."}, {"role": "assistant", "content": "SELECT d.first_name, d.last_name, p.first_name, p.last_name, COUNT(pr.prescription_id) AS prescription_count FROM healthcare.prescriptions pr JOIN healthcare.doctors d ON pr.doctor_id = d.doctor_id JOIN healthcare.patients p ON pr.patient_id = p.patient_id GROUP BY d.doctor_id, d.first_name, d.last_name, p.patient_id, p.first_name, p.last_name;"}, {"role": "user", "content": "Actually, only show combinations where the doctor has written more than 2 prescriptions for that patient."}, {"role": "assistant", "content": "SELECT d.first_name, d.last_name, p.first_name, p.last_name, COUNT(pr.prescription_id) AS prescription_count FROM healthcare.prescriptions pr JOIN healthcare.doctors d ON pr.doctor_id = d.doctor_id JOIN healthcare.patients p ON pr.patient_id = p.patient_id GROUP BY d.doctor_id, d.first_name, d.last_name, p.patient_id, p.first_name, p.last_name HAVING COUNT(pr.prescription_id) > 2;"}, {"role": "user", "content": "Also, include the date of the most recent prescription for each combination, and sort the results by the prescription count in descending order."}, {"role": "assistant", "content": "SELECT d.first_name, d.last_name, p.first_name, p.last_name, COUNT(pr.prescription_id) AS prescription_count, MAX(pr.prescription_date) AS most_recent_prescription_date FROM healthcare.prescriptions pr JOIN healthcare.doctors d ON pr.doctor_id = d.doctor_id JOIN healthcare.patients p ON pr.patient_id = p.patient_id GROUP BY d.doctor_id, d.first_name, d.last_name, p.patient_id, p.first_name, p.last_name HAVING COUNT(pr.prescription_id) > 2 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.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.medications ( medication_id character varying(64) NOT NULL, medication_name character varying(255) NOT NULL, generic_name character varying(255), manufacturer character varying(100), ndc_code character varying(20) UNIQUE, description text, PRIMARY KEY (medication_id) )\nCREATE TABLE healthcare.prescriptions ( prescription_id character varying(64) NOT NULL, record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, doctor_id character varying(64) NOT NULL, medication_id character varying(64) NOT NULL, dosage character varying(100) NOT NULL, frequency character varying(100) NOT NULL, route character varying(50), start_date date NOT NULL, end_date date, quantity_dispensed numeric(10,2), refills_allowed integer NOT NULL DEFAULT 0, prescription_date timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (prescription_id) )\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": "What are the fuel consumption rates per hour for the Boeing 747-8 model?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information on the fuel consumption rates for the Boeing 747-8 model as this data is not included in the aircraft_models table. The table contains details such as model name, manufacturer, passenger capacity, and other specifications, but fuel consumption data is not available. If you have another question or need assistance with something else related to the table, I'm happy to help."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE manufacturing.aircraft_models ( model_id.text, model_name.text, manufacturer.text, passenger_capacity.integer, max_range_km.integer, engine_type.text, wingspan_m.numeric, status.text, first_flight_date.date )\n"}
{"conversations": [{"role": "user", "content": "Provide a breakdown of the total number of conversations, showing how many are group chats and how many are not. Also, show the count of conversations that have a recorded last message time."}, {"role": "assistant", "content": "SELECT COUNT(*) AS total_conversations, COUNT(CASE WHEN is_group_chat = true THEN 1 END) AS group_chat_count, COUNT(CASE WHEN is_group_chat = false THEN 1 END) AS private_chat_count, COUNT(last_message_at) AS conversations_with_messages_count FROM social_media.conversations;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.conversations ( conversation_id character varying(64) NOT NULL, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, last_message_at timestamp, is_group_chat boolean NOT NULL DEFAULT false, group_name character varying(100), PRIMARY KEY (conversation_id) )\n"}
{"conversations": [{"role": "user", "content": "List the name and type for all insurance products with a base premium over 5000."}, {"role": "assistant", "content": "SELECT product_name, product_type FROM insurance.insurance_products WHERE base_premium > 5000;"}, {"role": "user", "content": "Can you refine that to only include products that are currently active?"}, {"role": "assistant", "content": "SELECT product_name, product_type FROM insurance.insurance_products WHERE base_premium > 5000 AND is_active = true;"}, {"role": "user", "content": "Please also include the base premium and sort the results by base premium descending."}, {"role": "assistant", "content": "SELECT product_name, product_type, base_premium FROM insurance.insurance_products WHERE base_premium > 5000 AND is_active = true ORDER BY base_premium DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.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": "I want to identify pairs of bookings that share the same payment_transaction_id, showing both booking IDs and the payment_transaction_id."}, {"role": "assistant", "content": "SELECT b1.booking_id AS booking1, b2.booking_id AS booking2, b1.payment_transaction_id\nFROM transportation.bookings b1\nJOIN transportation.bookings b2\n  ON b1.payment_transaction_id = b2.payment_transaction_id\n  AND b1.booking_id < b2.booking_id;"}, {"role": "user", "content": "Now limit the results to only include pairs where both bookings have a status of 'Completed'."}, {"role": "assistant", "content": "SELECT b1.booking_id AS booking1, b2.booking_id AS booking2, b1.payment_transaction_id\nFROM transportation.bookings b1\nJOIN transportation.bookings b2\n  ON b1.payment_transaction_id = b2.payment_transaction_id\n  AND b1.booking_id < b2.booking_id\nWHERE b1.status = 'Completed'\n  AND b2.status = 'Completed';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.bookings ( booking_id.text, passenger_id.text, trip_id.text, seat_number.text, booking_time.timestamp, status.text, fare.numeric, payment_transaction_id.text, special_requests.text )\n"}
{"conversations": [{"role": "user", "content": "For each chain, find the narrative category that has the highest total market_cap and display the chain, narrative, and that total market_cap."}, {"role": "assistant", "content": "SELECT chain,\n       narrative,\n       total_cap\nFROM (\n  SELECT chain,\n         narrative,\n         SUM(market_cap) AS total_cap,\n         RANK() OVER (PARTITION BY chain ORDER BY SUM(market_cap) DESC) AS rnk\n  FROM token_basic_info\n  GROUP BY chain, narrative\n) t\nWHERE rnk = 1;"}, {"role": "user", "content": "I received an error about window functions. Can you rewrite the query without using window functions?"}, {"role": "assistant", "content": "WITH agg AS (\n  SELECT chain,\n         narrative,\n         SUM(market_cap) AS total_cap\n  FROM token_basic_info\n  GROUP BY chain, narrative\n),\nmax_cap AS (\n  SELECT chain,\n         MAX(total_cap) AS max_cap\n  FROM agg\n  GROUP BY chain\n)\nSELECT a.chain,\n       a.narrative,\n       a.total_cap\nFROM agg a\nJOIN max_cap m\n  ON a.chain = m.chain\n AND a.total_cap = m.max_cap;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_basic_info ( coin_id text, token_name text, token_symbol text, token_address text, chain text, price numeric, price_change_percentage_1h numeric, price_change_percentage_24h numeric, price_change_percentage_7d numeric, highest_price_24h numeric, lowest_price_24h numeric, market_cap numeric, market_cap_rank numeric, market_cap_change_percentage_24h text, total_volume text, narrative text, trend_rank numeric )\n"}
{"conversations": [{"role": "user", "content": "List 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": "For all NFT collections on the Ethereum blockchain, show me the collection name and the current floor price. Sort by floor price descending."}, {"role": "assistant", "content": "SELECT name, floor_price FROM nft_collections WHERE blockchain = 'Ethereum' ORDER BY CAST(floor_price AS FLOAT) DESC;"}, {"role": "user", "content": "Include also the collection symbol and the number of tokens in each collection."}, {"role": "assistant", "content": "SELECT name, symbol, floor_price, token_count FROM nft_collections WHERE blockchain = 'Ethereum' ORDER BY CAST(floor_price AS FLOAT) DESC;"}, {"role": "user", "content": "Can you also show the owner of each collection in the result?"}, {"role": "assistant", "content": "SELECT name, symbol, floor_price, token_count, owner FROM nft_collections WHERE blockchain = 'Ethereum' ORDER BY CAST(floor_price AS FLOAT) DESC;"}, {"role": "user", "content": "Now only include collections whose floor price is greater than 1 ETH."}, {"role": "assistant", "content": "SELECT name, symbol, floor_price, token_count, owner FROM nft_collections WHERE blockchain = 'Ethereum' AND CAST(floor_price AS FLOAT) > 1 AND floor_price_symbol = 'ETH' ORDER BY CAST(floor_price AS FLOAT) DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp timestamp(6) NOT NULL, block_number bigint NOT NULL, transaction_hash varchar NOT NULL, transaction_index bigint NOT NULL, from_address varchar NOT NULL, contract_address varchar NOT NULL, symbol varchar NOT NULL, total_supply varchar NOT NULL, name varchar NOT NULL, decimals bigint NOT NULL, is_erc20 integer NOT NULL, is_erc721 integer NOT NULL, is_erc1155 integer NOT NULL, is_proxy integer NOT NULL, extra_info varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE erc20_balances ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE erc20_balances_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_holders ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, token_id varchar NOT NULL, contract_type varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE nft_holder_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, token_id varchar NOT NULL, contract_type varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_metadata ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, token_id varchar NOT NULL, contract_name varchar NOT NULL, erc_type varchar NOT NULL, amount bigint NOT NULL, minter varchar NOT NULL, owner varchar NOT NULL, mint_block_number bigint NOT NULL, mint_time bigint NOT NULL, mint_transaction_hash varchar NOT NULL, mint_price varchar NOT NULL, token_uri varchar NOT NULL, metadata varchar NOT NULL, name varchar NOT NULL, image_uri varchar NOT NULL, traits varchar NOT NULL, updated_at bigint NOT NULL, status varchar NOT NULL, rarity_score real NOT NULL, rarity_rank integer NOT NULL, unique_attribute_count integer NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_collections ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, name varchar NOT NULL, symbol varchar NOT NULL, deploy_block_number bigint NOT NULL, deploy_block_time bigint NOT NULL, erc_type varchar NOT NULL, owner varchar NOT NULL, traits varchar NOT NULL, description varchar NOT NULL, slug varchar NOT NULL, media_info varchar NOT NULL, image_url varchar NOT NULL, banner_image_url varchar NOT NULL, updated_at bigint NOT NULL, banner varchar NOT NULL, token_count bigint NOT NULL, floor_price varchar NOT NULL, floor_price_symbol varchar NOT NULL, floor_price_contract varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_prices ( uuid varchar(36) NOT NULL, blockchain varchar(36) NOT NULL, address varchar(42) NOT NULL, decimals bigint NOT NULL, symbol varchar(36) NOT NULL, price real NOT NULL, timestamp timestamp(6) NOT NULL )\nCREATE TABLE token_prices_latest ( blockchain varchar(36) NOT NULL, address varchar(42) NOT NULL, decimals bigint NOT NULL, symbol varchar(36) NOT NULL, price real NOT NULL, timestamp timestamp(6) NOT NULL )\nCREATE TABLE erc20_approval ( block_number bigint NOT NULL, block_timestamp timestamp(6) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar NOT NULL, log_index integer NOT NULL, contract_address varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_activities ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar NOT NULL, tick varchar NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(42) NOT NULL, to_address varchar(42) NOT NULL )\nCREATE TABLE mud_holesky_redstone ( address varchar NOT NULL, table_id varchar NOT NULL, key_bytes varchar NOT NULL, key0 varchar NOT NULL, key1 varchar NOT NULL, static_data varchar NOT NULL, encoded_lengths varchar NOT NULL, dynamic_data varchar NOT NULL, is_deleted boolean NOT NULL, block_number bigint NOT NULL, log_index bigint NOT NULL )\nCREATE TABLE token_balances_bitcoin ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar(255) NOT NULL, wallet_address varchar(42) NOT NULL, total_supply varchar NOT NULL, amount varchar NOT NULL )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar(20) NOT NULL, tick varchar(255) NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(62) NOT NULL, to_address varchar(62) NOT NULL )\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar(20) NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL, minted decimal(38,0) NOT NULL, holders decimal(38,0) NOT NULL, txs decimal(38,0) NOT NULL, updated_timestamp timestamp(3) NOT NULL, completed_timestamp timestamp(3) NOT NULL, id varchar(255) NOT NULL )\n"}
{"conversations": [{"role": "user", "content": "Find all smart contract IDs and the block IDs that were mined within 5 minutes before or after the contract deployment timestamp."}, {"role": "assistant", "content": "SELECT T1.contract_id, T2.block_id FROM blockchain.smart_contracts AS T1 JOIN blockchain.blocks AS T2 ON T2.timestamp BETWEEN T1.timestamp - INTERVAL '5 minute' AND T1.timestamp + INTERVAL '5 minute';"}, {"role": "user", "content": "Also include the timestamp for both the contract deployment and the block mining."}, {"role": "assistant", "content": "SELECT T1.contract_id, T1.timestamp AS contract_timestamp, T2.block_id, T2.timestamp AS block_timestamp FROM blockchain.smart_contracts AS T1 JOIN blockchain.blocks AS T2 ON T2.timestamp BETWEEN T1.timestamp - INTERVAL '5 minute' AND T1.timestamp + INTERVAL '5 minute';"}, {"role": "user", "content": "Filter the results to only include contracts deployed in the year 2023."}, {"role": "assistant", "content": "SELECT T1.contract_id, T1.timestamp AS contract_timestamp, T2.block_id, T2.timestamp AS block_timestamp FROM blockchain.smart_contracts AS T1 JOIN blockchain.blocks AS T2 ON T2.timestamp BETWEEN T1.timestamp - INTERVAL '5 minute' AND T1.timestamp + INTERVAL '5 minute' WHERE EXTRACT(YEAR FROM T1.timestamp) = 2023;"}, {"role": "user", "content": "Order the results by contract ID and then by block ID."}, {"role": "assistant", "content": "SELECT T1.contract_id, T1.timestamp AS contract_timestamp, T2.block_id, T2.timestamp AS block_timestamp FROM blockchain.smart_contracts AS T1 JOIN blockchain.blocks AS T2 ON T2.timestamp BETWEEN T1.timestamp - INTERVAL '5 minute' AND T1.timestamp + INTERVAL '5 minute' WHERE EXTRACT(YEAR FROM T1.timestamp) = 2023 ORDER BY T1.contract_id, T2.block_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 (\n    block_id character varying(64) NOT NULL,  -- unique identifier for the block\n    previous_block_id character varying(64), -- identifier of the previous block\n    timestamp timestamp NOT NULL, -- time when the block was mined\n    nonce integer NOT NULL, -- nonce value used in the proof of work\n    merkle_root character varying(128) NOT NULL, -- root of the Merkle tree for transactions\n    difficulty integer NOT NULL, -- difficulty level of the block\n    PRIMARY KEY (block_id)\n)\nCREATE TABLE blockchain.addresses (\n    address_id character varying(128) NOT NULL,  -- unique identifier for the address\n    public_key text NOT NULL, -- public key associated with the address\n    balance numeric(38,14) NOT NULL, -- current balance of the address\n    PRIMARY KEY (address_id)\n)\nCREATE TABLE blockchain.nodes (\n    node_id character varying(64) NOT NULL,  -- unique identifier for the node\n    ip_address character varying(15) NOT NULL, -- IP address of the node\n    port integer NOT NULL, -- port number of the node\n    last_seen timestamp NOT NULL, -- last time the node was active\n    PRIMARY KEY (node_id)\n)\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)\nCREATE TABLE blockchain.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    PRIMARY KEY (user_id)\n)\nCREATE TABLE blockchain.smart_contracts (\n    contract_id character varying(64) NOT NULL,  -- unique identifier for the smart contract\n    creator_address character varying(128) NOT NULL, -- address of the creator of the contract\n    code text NOT NULL, -- code of the smart contract\n    timestamp timestamp NOT NULL, -- time when the contract was deployed\n    PRIMARY KEY (contract_id)\n)\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": "Show me all properties in California with a star rating above 3.5, along with their room types and base rates."}, {"role": "assistant", "content": "SELECT p.property_name, p.city, p.star_rating, rt.type_name, rt.base_rate FROM hospitality_technology.properties p JOIN hospitality_technology.room_types rt ON p.property_id = rt.property_id WHERE p.state_province = 'California' AND p.star_rating > 3.5;"}, {"role": "user", "content": "Now, filter the results to only include room types with a max occupancy of at least 4 people."}, {"role": "assistant", "content": "SELECT p.property_name, p.city, p.star_rating, rt.type_name, rt.base_rate FROM hospitality_technology.properties p JOIN hospitality_technology.room_types rt ON p.property_id = rt.property_id WHERE p.state_province = 'California' AND p.star_rating > 3.5 AND rt.max_occupancy >= 4;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.properties ( property_id text, property_name text, address_line1 text, address_line2 text, city text, state_province text, postal_code text, country_code text, phone_number text, email_address text, property_type text, star_rating numeric, timezone text, manager_staff_id text, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.rooms ( room_id text, property_id text, room_number text, room_type_id text, floor integer, status text, is_smoking boolean, features text, current_condition text, last_cleaned_at timestamp )\nCREATE TABLE hospitality_technology.room_types ( room_type_id text, property_id text, type_name text, description text, base_rate numeric, max_occupancy integer, bed_type text, area_sqft numeric, amenities text )\nCREATE TABLE hospitality_technology.guests ( guest_id text, first_name text, last_name text, email text, phone_number text, date_of_birth date, address_line1 text, city text, state_province text, postal_code text, country_code text, preferences text, loyalty_member_id text, communication_consent boolean, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.reservations ( reservation_id text, property_id text, guest_id text, room_id text, room_type_id text, check_in_date date, check_out_date date, actual_check_in_ts timestamp, actual_check_out_ts timestamp, num_adults integer, num_children integer, status text, booking_source text, rate_plan_id text, total_amount numeric, amount_paid numeric, special_requests text, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.staff ( staff_id text, property_id text, first_name text, last_name text, position text, work_email text, work_phone text, hire_date date, termination_date date, is_active boolean, access_level integer, manager_id text, created_at timestamp )\nCREATE TABLE hospitality_technology.services ( service_id text, property_id text, service_name text, description text, category text, price numeric, unit text, is_available boolean, department text )\nCREATE TABLE hospitality_technology.service_orders ( order_id text, reservation_id text, guest_id text, service_id text, staff_id_ordered text, staff_id_delivered text, order_timestamp timestamp, delivery_timestamp timestamp, quantity integer, unit_price numeric, total_price numeric, status text, notes text, bill_id text )\nCREATE TABLE hospitality_technology.reviews ( review_id text, property_id text, reservation_id text, guest_id text, rating_overall integer, rating_cleanliness integer, rating_service integer, rating_location integer, rating_value integer, comment text, review_source text, review_date timestamp, is_public boolean, staff_response text, response_staff_id text, response_date timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show all routes including their number, type, and description."}, {"role": "assistant", "content": "SELECT route_number ,  type ,  description FROM transportation.routes"}, {"role": "user", "content": "Only show routes of type 'City Bus'."}, {"role": "assistant", "content": "SELECT route_number ,  type ,  description FROM transportation.routes WHERE type  =  'City Bus'"}, {"role": "user", "content": "For these 'City Bus' routes, include the origin and destination city names."}, {"role": "assistant", "content": "SELECT T1.route_number ,  T1.type ,  T1.description ,  T2.city AS origin_city ,  T3.city AS destination_city FROM transportation.routes AS T1 JOIN transportation.locations AS T2 ON T1.origin_location_id  =  T2.location_id JOIN transportation.locations AS T3 ON T1.destination_location_id  =  T3.location_id WHERE T1.type  =  'City Bus'"}, {"role": "user", "content": "Order the results by route number in ascending order and limit to the first 10."}, {"role": "assistant", "content": "SELECT T1.route_number ,  T1.type ,  T1.description ,  T2.city AS origin_city ,  T3.city AS destination_city FROM transportation.routes AS T1 JOIN transportation.locations AS T2 ON T1.origin_location_id  =  T2.location_id JOIN transportation.locations AS T3 ON T1.destination_location_id  =  T3.location_id WHERE T1.type  =  'City Bus' ORDER BY T1.route_number ASC LIMIT 10"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles (\n    vehicle_id character varying(64) NOT NULL,  -- unique identifier for the vehicle\n    license_plate character varying(32) NOT NULL UNIQUE, -- vehicle license plate\n    vin character varying(17) UNIQUE, -- vehicle identification number\n    make character varying(64) NOT NULL, -- manufacturer of the vehicle\n    model character varying(64) NOT NULL, -- model of the vehicle\n    year integer NOT NULL, -- manufacturing year\n    type character varying(32) NOT NULL, -- type of vehicle (e.g., Bus, Train, Truck, Car, Van)\n    capacity integer, -- passenger or cargo capacity\n    fuel_type character varying(32) NOT NULL, -- e.g., Diesel, Gasoline, Electric, Hydrogen\n    status character varying(32) NOT NULL, -- e.g., Active, Maintenance, Decommissioned\n    depot_id character varying(64), -- identifier of the home depot/base\n    acquisition_date date, -- date the vehicle was acquired\n    PRIMARY KEY (vehicle_id)\n)\nCREATE TABLE transportation.drivers (\n    driver_id character varying(64) NOT NULL,  -- unique identifier for the driver\n    employee_id character varying(64) NOT NULL UNIQUE, -- employee reference number\n    first_name character varying(128) NOT NULL, -- driver's first name\n    last_name character varying(128) NOT NULL, -- driver's last name\n    license_number character varying(64) NOT NULL UNIQUE, -- driving license number\n    license_expiry_date date NOT NULL, -- expiry date of the license\n    contact_number character varying(32), -- phone number\n    email character varying(128) UNIQUE, -- email address\n    hire_date date NOT NULL, -- date the driver was hired\n    status character varying(32) NOT NULL, -- e.g., Active, On Leave, Terminated\n    PRIMARY KEY (driver_id)\n)\nCREATE TABLE transportation.routes (\n    route_id character varying(64) NOT NULL,  -- unique identifier for the route\n    route_number character varying(32) NOT NULL UNIQUE, -- public-facing route number/name\n    description text, -- description of the route\n    origin_location_id character varying(64) NOT NULL, -- identifier of the starting location\n    destination_location_id character varying(64) NOT NULL, -- identifier of the ending location\n    distance_km numeric(10, 2), -- estimated distance in kilometers\n    estimated_duration_minutes integer, -- estimated travel time in minutes\n    type character varying(32) NOT NULL, -- e.g., City Bus, Intercity Train, Cargo Delivery\n    PRIMARY KEY (route_id)\n)\nCREATE TABLE transportation.locations (\n    location_id character varying(64) NOT NULL,  -- unique identifier for the location\n    name character varying(255) NOT NULL, -- name of the location (e.g., Central Station, Depot Alpha, Pier 7)\n    type character varying(64) NOT NULL, -- e.g., Station, Stop, Depot, Port, Airport, Customer Address\n    address_line1 character varying(255), -- street address\n    city character varying(128), -- city name\n    state_province character varying(128), -- state or province\n    postal_code character varying(32), -- postal code\n    country character varying(64) NOT NULL, -- country name\n    latitude numeric(9, 6), -- geographic latitude\n    longitude numeric(9, 6), -- geographic longitude\n    timezone character varying(64), -- IANA timezone name (e.g., America/New_York)\n    PRIMARY KEY (location_id)\n)\nCREATE TABLE transportation.fuel_logs (\n    fuel_log_id character varying(64) NOT NULL,  -- unique identifier for the fuel log entry\n    vehicle_id character varying(64) NOT NULL, -- identifier of the vehicle fueled\n    trip_id character varying(64), -- optional: identifier of the trip during which fueling occurred\n    log_timestamp timestamp with time zone NOT NULL, -- time when fueling occurred\n    fuel_type character varying(32) NOT NULL, -- type of fuel added (matches vehicle's fuel type)\n    quantity numeric(10, 3) NOT NULL, -- amount of fuel added (e.g., Liters, Gallons, kWh)\n    unit character varying(16) NOT NULL, -- unit of quantity (e.g., L, gal, kWh)\n    cost_per_unit numeric(8, 4), -- price per unit of fuel\n    total_cost numeric(10, 2) NOT NULL, -- total cost of the fuel purchase\n    odometer_reading integer, -- vehicle mileage at time of fueling\n    location_id character varying(64), -- identifier of the fueling station/location\n    PRIMARY KEY (fuel_log_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Find all wallets that were created on the same day and list their wallet IDs, addresses, and the creation date."}, {"role": "assistant", "content": "SELECT w1.wallet_id, w1.address, w1.created_at::date AS creation_date FROM web3.wallets w1 JOIN (SELECT created_at::date AS creation_date FROM web3.wallets GROUP BY created_at::date HAVING COUNT(*) > 1) w2 ON w1.created_at::date = w2.creation_date ORDER BY creation_date, w1.wallet_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.wallets (\n    wallet_id character varying(64) NOT NULL,  -- unique identifier for the wallet\n    user_id character varying(64) NOT NULL, -- identifier of the user owning the wallet\n    address character varying(128) NOT NULL, -- address of the wallet\n    private_key text NOT NULL, -- private key of the wallet\n    created_at timestamp NOT NULL, -- time when the wallet was created\n    PRIMARY KEY (wallet_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List all ERC20 tokens where the price is between $1 and $10, including their names, symbols, and contract addresses."}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address FROM token_metas tm JOIN token_prices_latest tpl ON tm.contract_address = tpl.contract_address WHERE tm.is_erc20 = 1 AND tpl.price BETWEEN 1 AND 10;"}, {"role": "user", "content": "I think there's an error in your query - the token_prices_latest table isn't in the schema. Can you modify it to use the token_balances table instead?"}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address FROM token_metas tm JOIN token_balances tb ON tm.contract_address = tb.wallet_address WHERE tm.is_erc20 = 1 AND CAST(tb.amount AS decimal) BETWEEN 1 AND 10;"}, {"role": "user", "content": "That doesn't seem right either. Let's just get the basic ERC20 token information without price filtering for now."}, {"role": "assistant", "content": "SELECT name, symbol, contract_address FROM token_metas WHERE is_erc20 = 1 LIMIT 100;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp.timestamp, block_number.bigint, transaction_hash.text, transaction_index.bigint, from_address.text, contract_address.text, symbol.text, total_supply.text, name.text, decimals.bigint, is_erc20.integer, is_erc721.integer, is_erc1155.integer, is_proxy.integer, extra_info.text, pk.integer )\nCREATE TABLE erc1155_approval_for_all ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar(66) NOT NULL, log_index integer NOT NULL, contract_address varchar(42) NOT NULL )\nCREATE TABLE erc20_balances ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE erc20_balances_historical ( block_number bigint, contract_address text, wallet_address text, amount text, pk integer )\nCREATE TABLE nft_holders ( block_number bigint, contract_address text, wallet_address text, token_id text, contract_type text, amount text, pk text )\nCREATE TABLE nft_holder_historical ( block_number.bigint, contract_address.text, wallet_address.text, token_id.text, contract_type.text, amount.text, pk.integer )\nCREATE TABLE sui_nfts ( object_id text, status text, collection_type text, package_id text, previous_transaction text, display text, owner text, name text )\nCREATE TABLE nft_collections ( blockchain text, contract_address text, name text, symbol text, deploy_block_number bigint, deploy_block_time bigint, erc_type text, owner text, traits text, description text, slug text, media_info text, image_url text, banner_image_url text, updated_at bigint, banner text, token_count bigint, floor_price text, floor_price_symbol text, floor_price_contract text, pk integer )\nCREATE TABLE erc20_approval ( block_number bigint NOT NULL, block_timestamp timestamp(6) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar NOT NULL, log_index integer NOT NULL, contract_address varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_balances ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply decimal, amount decimal )\nCREATE TABLE token_info (\n    block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n    block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n    tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n    tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n    tick varchar NOT NULL, -- Token tick\n    max_supply decimal(38,0) NOT NULL, -- Max supply\n    lim decimal(38,0) NOT NULL, -- Limit of each mint\n    wlim decimal(38,0) NOT NULL, -- Limit of each address can maximum mint\n    dec integer NOT NULL, -- Decimal for minimum divie\n    creator varchar(42) NOT NULL  -- Address originating the inscription (matches from_address in transactions table)\n)\nCREATE TABLE token_activities ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\nCREATE TABLE mud_holesky_redstone ( address varchar NOT NULL, table_id varchar NOT NULL, key_bytes varchar NOT NULL, key0 varchar NOT NULL, key1 varchar NOT NULL, static_data varchar NOT NULL, encoded_lengths varchar NOT NULL, dynamic_data varchar NOT NULL, is_deleted boolean NOT NULL, block_number bigint NOT NULL, log_index bigint NOT NULL )\nCREATE TABLE token_balances_bitcoin ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply varchar, amount varchar )\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar )\nCREATE TABLE token_activities_avalanche ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\nCREATE TABLE token_balances_avalanche (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n    tick varchar(20) NOT NULL, -- Ticker: Identifier of the inscription\n    wallet_address varchar(42) NOT NULL, -- Address of owner\n    total_supply decimal(38,0) NOT NULL, -- Max supply: Set max supply of the inscription\n    amount decimal(38,0) NOT NULL  -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id varchar )\n"}
{"conversations": [{"role": "user", "content": "For each user, show their user ID and the count of unique wallet addresses they own."}, {"role": "assistant", "content": "SELECT user_id, COUNT(DISTINCT address) FROM wallets GROUP BY user_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.wallets ( wallet_id.text, user_id.text, address.text, private_key.text, created_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "List all properties that have at least one room with 'Ocean View' in its features, showing the property name and the total count of such rooms."}, {"role": "assistant", "content": "SELECT T1.property_name, COUNT(T2.room_id) FROM hospitality_technology.properties AS T1 JOIN hospitality_technology.rooms AS T2 ON T1.property_id = T2.property_id WHERE T2.features LIKE '%Ocean View%' GROUP BY T1.property_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 hospitality_technology.properties (\n    property_id character varying(64) NOT NULL,  -- unique identifier for the property (hotel, resort, etc.)\n    property_name character varying(255) NOT NULL, -- name of the property\n    address_line1 character varying(255) NOT NULL, -- primary address line\n    address_line2 character varying(255), -- secondary address line\n    city character varying(100) NOT NULL, -- city\n    state_province character varying(100), -- state or province\n    postal_code character varying(20) NOT NULL, -- zip or postal code\n    country_code character varying(3) NOT NULL, -- ISO country code (e.g., USA, CAN)\n    phone_number character varying(30), -- main contact phone\n    email_address character varying(255), -- main contact email\n    property_type character varying(50) NOT NULL, -- e.g., Hotel, Resort, B&B, Motel\n    star_rating numeric(2,1), -- star rating (e.g., 4.5)\n    timezone character varying(64) NOT NULL, -- IANA timezone ID (e.g., America/New_York)\n    manager_staff_id character varying(64), -- FK to staff table for the general manager\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, -- record creation time\n    updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, -- record last update time\n    PRIMARY KEY (property_id)\n)\nCREATE TABLE hospitality_technology.rooms ( 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 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 character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, email character varying(255) UNIQUE, phone_number character varying(30), date_of_birth date, address_line1 character varying(255), city character varying(100), state_province character varying(100), postal_code character varying(20), country_code character varying(3), preferences text, loyalty_member_id character varying(64) UNIQUE, communication_consent boolean DEFAULT true, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (guest_id) )\nCREATE TABLE hospitality_technology.reservations ( reservation_id text PRIMARY KEY, 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 int, num_children int, 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.services ( service_id.text, property_id.text, service_name.text, description.text, category.text, price.numeric, unit.text, is_available.boolean, department.text )\nCREATE TABLE hospitality_technology.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": "Find the average percentage share among all beneficiaries for each distinct relationship type."}, {"role": "assistant", "content": "SELECT relationship, AVG(percentage_share) FROM insurance.policy_beneficiaries GROUP BY relationship ORDER BY relationship;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.insurance_products ( product_id.text, product_name.text, product_type.text, description.text, base_premium.numeric, coverage_details.text, underwriting_rules.text, is_active.boolean, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE insurance.policy_beneficiaries ( beneficiary_id text PRIMARY KEY, policy_id text, customer_id text, first_name text, last_name text, relationship text, percentage_share numeric, contact_info text, added_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "For each event, display its event_id, the event_id of the previous event in the same transaction (if any), and the log_index of both events."}, {"role": "assistant", "content": "SELECT curr.event_id   AS current_event_id,\n       prev.event_id   AS previous_event_id,\n       curr.log_index  AS current_log_index,\n       prev.log_index  AS previous_log_index,\n       curr.transaction_id\nFROM web3.events curr\nLEFT JOIN web3.events prev\n  ON curr.transaction_id = prev.transaction_id\n AND curr.log_index = prev.log_index + 1;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.events ( event_id character varying(64) NOT NULL, contract_id character varying(64) NOT NULL, event_name character varying(128) NOT NULL, data text NOT NULL, emitted_at timestamp NOT NULL, transaction_id character varying(64) NOT NULL, log_index integer NOT NULL, PRIMARY KEY (event_id) )\n"}
{"conversations": [{"role": "user", "content": "List all pairs of cases that share the same court jurisdiction, including both case names and their common jurisdiction."}, {"role": "assistant", "content": "SELECT c1.case_name AS case_name_1, c2.case_name AS case_name_2, c1.court_jurisdiction\nFROM legal_services.cases c1\nJOIN legal_services.cases c2\n  ON c1.court_jurisdiction = c2.court_jurisdiction\n  AND c1.case_id < c2.case_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.cases ( case_id text, case_number text, case_name text, client_id text, lead_lawyer_id text, case_type text, status text, date_opened timestamp, date_closed timestamp, description text, court_jurisdiction text )\n"}
{"conversations": [{"role": "user", "content": "For each unique registration year, list the year and the number of users who registered in that year."}, {"role": "assistant", "content": "SELECT EXTRACT(YEAR FROM created_at) AS registration_year, COUNT(*) AS user_count\nFROM web3.users\nGROUP BY EXTRACT(YEAR FROM created_at)\nORDER BY registration_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.users ( user_id text PRIMARY KEY, username text, email text, password_hash text, created_at timestamp )\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": "I need to check the inventory status of components, including their batch details and warehouse location."}, {"role": "assistant", "content": "MATCH (i:InventoryBatch)-[:IS_INSTANCE_OF]->(c:Component)\nRETURN c.component_id, c.component_name, i.inventory_record_id, i.quantity, i.location_warehouse, i.location_bin, i.received_date, i.batch_number"}, {"role": "user", "content": "Can you filter this to show only batches with a quantity less than 50?"}, {"role": "assistant", "content": "MATCH (i:InventoryBatch)-[:IS_INSTANCE_OF]->(c:Component)\nWHERE i.quantity < 50\nRETURN c.component_id, c.component_name, i.inventory_record_id, i.quantity, i.location_warehouse, i.location_bin, i.received_date, i.batch_number"}, {"role": "user", "content": "What if I want to exclude batches with an expiry date before 2024?"}, {"role": "assistant", "content": "MATCH (i:InventoryBatch)-[:IS_INSTANCE_OF]->(c:Component)\nWHERE i.quantity < 50 AND i.expiry_date >= date('2024-01-01')\nRETURN c.component_id, c.component_name, i.inventory_record_id, i.quantity, i.location_warehouse, i.location_bin, i.received_date, i.batch_number"}, {"role": "user", "content": "Can you order the results by received date in descending order?"}, {"role": "assistant", "content": "MATCH (i:InventoryBatch)-[:IS_INSTANCE_OF]->(c:Component)\nWHERE i.quantity < 50 AND i.expiry_date >= date('2024-01-01')\nRETURN c.component_id, c.component_name, i.inventory_record_id, i.quantity, i.location_warehouse, i.location_bin, i.received_date, i.batch_number\nORDER BY i.received_date 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\nNode Label ':Component'. Properties: { component_id: String (Constraint: UNIQUE), part_number: String (Constraint: UNIQUE), component_name: String, description: String, weight_kg: Float, cost_usd: Float, criticality_level: String }. Relationships: (:Component)-[:MADE_OF]->(:Material {material_id}), (:Component)-[:SUPPLIED_BY]->(:Supplier {supplier_id}). Index on component_id, part_number.\nNode Label ':Supplier'. Properties: { supplier_id: String (Constraint: UNIQUE), supplier_name: String, address: String, country: String, contact_person: String, contact_email: String, quality_rating: Float, certified_date: Date }. Index on supplier_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 ':Inspection'. Properties: { inspection_id: String (Constraint: UNIQUE), inspection_type: String, inspection_timestamp: Datetime, result: String, remarks: String }. Relationships: (:AircraftBuild {build_id})-[:UNDERWENT]->(:Inspection), (:Inspection)-[:PERFORMED_BY]->(:Employee {employee_id}), (:Inspection)-[:INSPECTED_COMPONENT]->(:Component {component_id}) (optional), (:Inspection)-[:FOLLOWED_STEP]->(:AssemblyStep {step_id}) (optional). Index on inspection_id.\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": "List NFT collections deployed after block number 10000000 with more than 500 tokens, showing contract_address, name, and token_count."}, {"role": "assistant", "content": "SELECT contract_address, name, token_count\nFROM nft_collections\nWHERE deploy_block_number > 10000000\n  AND token_count > 500;"}, {"role": "user", "content": "Join with nft_metadata to calculate the average rarity_score per collection."}, {"role": "assistant", "content": "SELECT nc.contract_address,\n       nc.name,\n       nc.token_count,\n       AVG(nm.rarity_score) AS avg_rarity\nFROM nft_collections nc\nLEFT JOIN nft_metadata nm\n  ON nc.contract_address = nm.contract_address\nWHERE nc.deploy_block_number > 10000000\n  AND nc.token_count > 500\nGROUP BY nc.contract_address, nc.name, nc.token_count;"}, {"role": "user", "content": "Filter collections with average rarity_score above 80 and include floor_price."}, {"role": "assistant", "content": "SELECT nc.contract_address,\n       nc.name,\n       nc.token_count,\n       AVG(nm.rarity_score) AS avg_rarity,\n       nc.floor_price\nFROM nft_collections nc\nLEFT JOIN nft_metadata nm\n  ON nc.contract_address = nm.contract_address\nWHERE nc.deploy_block_number > 10000000\n  AND nc.token_count > 500\nGROUP BY nc.contract_address, nc.name, nc.token_count, nc.floor_price\nHAVING AVG(nm.rarity_score) > 80;"}, {"role": "user", "content": "Order the results by floor_price descending and limit to the top 5 collections."}, {"role": "assistant", "content": "SELECT nc.contract_address,\n       nc.name,\n       nc.token_count,\n       AVG(nm.rarity_score) AS avg_rarity,\n       nc.floor_price\nFROM nft_collections nc\nLEFT JOIN nft_metadata nm\n  ON nc.contract_address = nm.contract_address\nWHERE nc.deploy_block_number > 10000000\n  AND nc.token_count > 500\nGROUP BY nc.contract_address, nc.name, nc.token_count, nc.floor_price\nHAVING AVG(nm.rarity_score) > 80\nORDER BY CAST(nc.floor_price 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 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 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 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 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_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_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 ( address.text, table_id.text, key_bytes.text, key0.text, key1.text, static_data.text, encoded_lengths.text, dynamic_data.text, is_deleted.boolean, block_number.bigint, log_index.bigint )\nCREATE TABLE token_activities_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(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 )\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 smart money addresses that have a negative PNL but a positive Realized Ratio. Show the address, chain, PNL, and Realized Ratio."}, {"role": "assistant", "content": "SELECT token_address, chain, pnl, realized_ratio FROM smart_money_token_performance WHERE pnl < 0 AND realized_ratio > 0"}, {"role": "user", "content": "Can you refine the results to only include addresses where the absolute value of PNL is greater than 1000?"}, {"role": "assistant", "content": "SELECT token_address, chain, pnl, realized_ratio FROM smart_money_token_performance WHERE pnl < -1000 AND realized_ratio > 0"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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 documents of type 'Correspondence' uploaded in 2023. Show the document name, upload timestamp, and the name of the case it belongs to."}, {"role": "assistant", "content": "SELECT T1.document_name, T1.upload_timestamp, T2.case_name FROM legal_services.documents AS T1 JOIN legal_services.cases AS T2 ON T1.case_id = T2.case_id WHERE T1.document_type = 'Correspondence' AND EXTRACT(YEAR FROM T1.upload_timestamp) = 2023;"}, {"role": "user", "content": "Now, only show the documents for cases handled by lawyer with ID 'lawyer_001'."}, {"role": "assistant", "content": "SELECT T1.document_name, T1.upload_timestamp, T2.case_name FROM legal_services.documents AS T1 JOIN legal_services.cases AS T2 ON T1.case_id = T2.case_id WHERE T1.document_type = 'Correspondence' AND EXTRACT(YEAR FROM T1.upload_timestamp) = 2023 AND T2.lead_lawyer_id = 'lawyer_001';"}, {"role": "user", "content": "Additionally, include the first and last name of the lawyer who actually uploaded the document, and sort the results by upload timestamp descending."}, {"role": "assistant", "content": "SELECT T1.document_name, T1.upload_timestamp, T2.case_name, T3.first_name, T3.last_name FROM legal_services.documents AS T1 JOIN legal_services.cases AS T2 ON T1.case_id = T2.case_id JOIN legal_services.lawyers AS T3 ON T1.uploaded_by_lawyer_id = T3.lawyer_id WHERE T1.document_type = 'Correspondence' AND EXTRACT(YEAR FROM T1.upload_timestamp) = 2023 AND T2.lead_lawyer_id = 'lawyer_001' ORDER BY T1.upload_timestamp DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.clients ( client_id text PRIMARY KEY, first_name text, last_name text, company_name text, email text UNIQUE, phone text, address text, date_registered timestamp, status text )\nCREATE TABLE legal_services.law_firms ( firm_id text PRIMARY KEY, firm_name text, address text, phone text, website text, founded_date date, managing_partner_id text )\nCREATE TABLE legal_services.cases ( case_id.text, case_number.text, case_name.text, client_id.text, lead_lawyer_id.text, case_type.text, status.text, date_opened.timestamp, date_closed.timestamp, description.text, court_jurisdiction.text )\nCREATE TABLE legal_services.documents (\n    document_id character varying(64) NOT NULL,  -- unique identifier for the document\n    case_id character varying(64) NOT NULL, -- FK to cases table\n    document_name character varying(255) NOT NULL, -- name of the document file\n    document_type character varying(100), -- e.g., Pleading, Contract, Evidence, Correspondence\n    storage_path text NOT NULL, -- path or reference to the document storage location\n    uploaded_by_lawyer_id character varying(64), -- FK to lawyers table (who uploaded it)\n    upload_timestamp timestamp NOT NULL, -- time the document was uploaded\n    version integer DEFAULT 1, -- document version number\n    description text, -- brief description or notes about the document\n    PRIMARY KEY (document_id)\n)\nCREATE TABLE legal_services.appointments (\n    appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment\n    client_id character varying(64) NOT NULL, -- FK to clients table\n    lawyer_id character varying(64) NOT NULL, -- FK to lawyers table\n    case_id character varying(64), -- FK to cases table (optional, if related to a specific case)\n    start_time timestamp NOT NULL, -- scheduled start date and time\n    end_time timestamp NOT NULL, -- scheduled end date and time\n    location text, -- location of the meeting (address or virtual link)\n    subject character varying(255), -- subject or purpose of the appointment\n    notes text, -- additional notes for the appointment\n    status character varying(50) NOT NULL, -- e.g., Scheduled, Completed, Canceled, Rescheduled\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n    PRIMARY KEY (appointment_id)\n)\n"}
{"conversations": [{"role": "user", "content": "For each game_id, calculate the average points of achievements that have been unlocked at least once."}, {"role": "assistant", "content": "SELECT a.game_id, AVG(a.points) AS average_unlocked_points FROM gaming_technology.achievements a JOIN gaming_technology.player_achievements pa ON a.achievement_id = pa.achievement_id GROUP BY a.game_id;"}, {"role": "user", "content": "Only include games where the average unlocked achievement points is greater than 50."}, {"role": "assistant", "content": "SELECT a.game_id, AVG(a.points) AS average_unlocked_points FROM gaming_technology.achievements a JOIN gaming_technology.player_achievements pa ON a.achievement_id = pa.achievement_id GROUP BY a.game_id HAVING AVG(a.points) > 50;"}, {"role": "user", "content": "Also include the total number of unique players who unlocked achievements in each of these games."}, {"role": "assistant", "content": "SELECT a.game_id, AVG(a.points) AS average_unlocked_points, COUNT(DISTINCT pa.player_id) AS unique_players_unlocked FROM gaming_technology.achievements a JOIN gaming_technology.player_achievements pa ON a.achievement_id = pa.achievement_id GROUP BY a.game_id HAVING AVG(a.points) > 50;"}, {"role": "user", "content": "Order the results by the total number of unique players descending."}, {"role": "assistant", "content": "SELECT a.game_id, AVG(a.points) AS average_unlocked_points, COUNT(DISTINCT pa.player_id) AS unique_players_unlocked FROM gaming_technology.achievements a JOIN gaming_technology.player_achievements pa ON a.achievement_id = pa.achievement_id GROUP BY a.game_id HAVING AVG(a.points) > 50 ORDER BY unique_players_unlocked DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.achievements ( achievement_id.uuid, game_id.uuid, name.text, description.text, icon_url.text, points.integer, hidden.boolean )\nCREATE TABLE gaming_technology.player_achievements ( player_achievement_id.uuid, player_id.uuid, achievement_id.uuid, unlocked_at.timestamptz )\nCREATE TABLE gaming_technology.player_inventory ( inventory_id.uuid, player_id.uuid, item_id.uuid, quantity.integer, acquired_at.timestamptz, instance_data.jsonb )\n"}
{"conversations": [{"role": "user", "content": "Find 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": "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": "Find the contract address and name for all NFT collections listed on the 'Ethereum' blockchain."}, {"role": "assistant", "content": "SELECT contract_address, name FROM nft_collections WHERE blockchain = 'Ethereum'"}, {"role": "user", "content": "For these collections, can you show the count of unique wallet addresses holding NFTs in each collection by joining with nft_holders?"}, {"role": "assistant", "content": "SELECT T1.contract_address, T1.name, COUNT(DISTINCT T2.wallet_address) AS unique_holder_count FROM nft_collections AS T1 JOIN nft_holders AS T2 ON T1.contract_address = T2.contract_address WHERE T1.blockchain = 'Ethereum' GROUP BY T1.contract_address, T1.name"}, {"role": "user", "content": "Please filter the results to only include collections that have more than 100 unique holders."}, {"role": "assistant", "content": "SELECT T1.contract_address, T1.name, COUNT(DISTINCT T2.wallet_address) AS unique_holder_count FROM nft_collections AS T1 JOIN nft_holders AS T2 ON T1.contract_address = T2.contract_address WHERE T1.blockchain = 'Ethereum' GROUP BY T1.contract_address, T1.name HAVING COUNT(DISTINCT T2.wallet_address) > 100"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp timestamp(6) NOT NULL, block_number bigint NOT NULL, transaction_hash varchar NOT NULL, transaction_index bigint NOT NULL, from_address varchar NOT NULL, contract_address varchar NOT NULL, symbol varchar NOT NULL, total_supply varchar NOT NULL, name varchar NOT NULL, decimals bigint NOT NULL, is_erc20 integer NOT NULL, is_erc721 integer NOT NULL, is_erc1155 integer NOT NULL, is_proxy integer NOT NULL, extra_info varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE erc20_balances_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_holders ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, token_id varchar NOT NULL, contract_type varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE nft_holder_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, token_id varchar NOT NULL, contract_type varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE nft_collections ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, name varchar NOT NULL, symbol varchar NOT NULL, deploy_block_number bigint NOT NULL, deploy_block_time bigint NOT NULL, erc_type varchar NOT NULL, owner varchar NOT NULL, traits varchar NOT NULL, description varchar NOT NULL, slug varchar NOT NULL, media_info varchar NOT NULL, image_url varchar NOT NULL, banner_image_url varchar NOT NULL, updated_at bigint NOT NULL, banner varchar NOT NULL, token_count bigint NOT NULL, floor_price varchar NOT NULL, floor_price_symbol varchar NOT NULL, floor_price_contract varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_prices ( uuid varchar(36) NOT NULL, blockchain varchar(36) NOT NULL, address varchar(42) NOT NULL, decimals bigint NOT NULL, symbol varchar(36) NOT NULL, price real NOT NULL, timestamp timestamp(6) NOT NULL )\nCREATE TABLE token_prices_latest ( blockchain varchar(36) NOT NULL, address varchar(42) NOT NULL, decimals bigint NOT NULL, symbol varchar(36) NOT NULL, price real NOT NULL, timestamp timestamp(6) NOT NULL )\nCREATE TABLE token_info ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE token_activities ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar NOT NULL, tick varchar NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(42) NOT NULL, to_address varchar(42) NOT NULL )\nCREATE TABLE token_balances_bitcoin ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar(255) NOT NULL, wallet_address varchar(42) NOT NULL, total_supply varchar NOT NULL, amount varchar NOT NULL )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar(20) NOT NULL, tick varchar(255) NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(62) NOT NULL, to_address varchar(62) NOT NULL )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar(20) NOT NULL, tick varchar(255) NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(42) NOT NULL, to_address varchar(42) NOT NULL )\nCREATE TABLE token_balances_avalanche ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar(20) NOT NULL, wallet_address varchar(42) NOT NULL, total_supply decimal(38,0) NOT NULL, amount decimal(38,0) NOT NULL )\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar(20) NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL, minted decimal(38,0) NOT NULL, holders decimal(38,0) NOT NULL, txs decimal(38,0) NOT NULL, updated_timestamp timestamp(3) NOT NULL, completed_timestamp timestamp(3) NOT NULL, id varchar(255) NOT NULL )\n"}
{"conversations": [{"role": "user", "content": "Calculate the monthly total quantity of fuel consumed and the average cost_per_unit for each fuel_type in 2023."}, {"role": "assistant", "content": "SELECT date_trunc('month', log_timestamp) AS month,\n       fuel_type,\n       SUM(quantity)      AS total_quantity,\n       AVG(cost_per_unit) AS avg_cost_per_unit\nFROM transportation.fuel_logs\nWHERE log_timestamp >= '2023-01-01'\n  AND log_timestamp <  '2024-01-01'\nGROUP BY 1, fuel_type\nORDER BY 1, fuel_type;"}, {"role": "user", "content": "Now limit the results to fuel types where the total_quantity exceeds 1000 units in that month."}, {"role": "assistant", "content": "SELECT month,\n       fuel_type,\n       total_quantity,\n       avg_cost_per_unit\nFROM (\n  SELECT date_trunc('month', log_timestamp) AS month,\n         fuel_type,\n         SUM(quantity)      AS total_quantity,\n         AVG(cost_per_unit) AS avg_cost_per_unit\n  FROM transportation.fuel_logs\n  WHERE log_timestamp >= '2023-01-01'\n    AND log_timestamp <  '2024-01-01'\n  GROUP BY 1, fuel_type\n) sub\nWHERE total_quantity > 1000\nORDER BY month, 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": "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": "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": "Show me all trips that were delayed by more than 1 hour, including their vehicle and driver IDs, along with the origin and destination location IDs."}, {"role": "assistant", "content": "SELECT trip_id, vehicle_id, driver_id, origin_location_id, destination_location_id FROM transportation.trips WHERE EXTRACT(EPOCH FROM (actual_departure - scheduled_departure))/3600 > 1 AND status = 'Completed';"}, {"role": "user", "content": "Now include the passenger count for these trips, but only show trips that had more than 5 passengers."}, {"role": "assistant", "content": "SELECT trip_id, vehicle_id, driver_id, origin_location_id, destination_location_id, passenger_count FROM transportation.trips WHERE EXTRACT(EPOCH FROM (actual_departure - scheduled_departure))/3600 > 1 AND status = 'Completed' AND passenger_count > 5;"}, {"role": "user", "content": "Can you order these results by the delay time in descending order, showing the longest delays first?"}, {"role": "assistant", "content": "SELECT trip_id, vehicle_id, driver_id, origin_location_id, destination_location_id, passenger_count, (actual_departure - scheduled_departure) AS delay_time FROM transportation.trips WHERE EXTRACT(EPOCH FROM (actual_departure - scheduled_departure))/3600 > 1 AND status = 'Completed' AND passenger_count > 5 ORDER BY delay_time DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.trips (\n    trip_id character varying(64) NOT NULL,  -- unique identifier for a specific trip instance\n    route_id character varying(64), -- identifier of the route being followed (can be null for ad-hoc trips)\n    vehicle_id character varying(64) NOT NULL, -- identifier of the vehicle used\n    driver_id character varying(64) NOT NULL, -- identifier of the driver operating\n    scheduled_departure timestamp with time zone NOT NULL, -- planned departure time\n    actual_departure timestamp with time zone, -- actual departure time\n    scheduled_arrival timestamp with time zone NOT NULL, -- planned arrival time\n    actual_arrival timestamp with time zone, -- actual arrival time\n    origin_location_id character varying(64) NOT NULL, -- actual starting location (could differ from route origin)\n    destination_location_id character varying(64) NOT NULL, -- actual ending location (could differ from route destination)\n    status character varying(32) NOT NULL, -- e.g., Scheduled, In Progress, Completed, Delayed, Cancelled\n    passenger_count integer, -- number of passengers (if applicable)\n    cargo_manifest_id character varying(64), -- link to cargo details (if applicable)\n    PRIMARY KEY (trip_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Show the email address and the creation date for every user, ordered by their username alphabetically."}, {"role": "assistant", "content": "SELECT email, created_at FROM trading_platform.users ORDER BY username ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.users ( user_id.text, username.text, email.text, password_hash.text, created_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show me all properties in California with a star rating above 4.0, along with their room types and base rates."}, {"role": "assistant", "content": "SELECT p.property_id, p.property_name, p.star_rating, r.room_type_id, r.features FROM hospitality_technology.properties p JOIN hospitality_technology.rooms r ON p.property_id = r.property_id WHERE p.state_province = 'California' AND p.star_rating > 4.0;"}, {"role": "user", "content": "Now, filter the results to only include rooms that are currently available and have a non-smoking policy."}, {"role": "assistant", "content": "SELECT p.property_id, p.property_name, p.star_rating, r.room_type_id, r.features FROM hospitality_technology.properties p JOIN hospitality_technology.rooms r ON p.property_id = r.property_id WHERE p.state_province = 'California' AND p.star_rating > 4.0 AND r.status = 'available' AND r.is_smoking = false;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.properties ( property_id text, property_name text, address_line1 text, address_line2 text, city text, state_province text, postal_code text, country_code text, phone_number text, email_address text, property_type text, star_rating numeric, timezone text, manager_staff_id text, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.rooms ( room_id text, property_id text, room_number text, room_type_id text, floor integer, status text, is_smoking boolean, features text, current_condition text, last_cleaned_at timestamp )\nCREATE TABLE hospitality_technology.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": "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": "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": "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": "I need the total traded value (quantity * price) for each buyer and asset symbol for trades after '2024-06-01'. List buyer_id, asset symbol, and total_value."}, {"role": "assistant", "content": "SELECT t.buyer_id, m.value AS asset_symbol, SUM(t.quantity * t.price) AS total_value\nFROM trading_platform.trades t\nJOIN trading_platform.metadata m ON t.asset_id = m.asset_id AND m.key = 'symbol'\nWHERE t.traded_at > '2024-06-01'\nGROUP BY t.buyer_id, m.value;"}, {"role": "user", "content": "Only include results where total_value > 10000, and order by total_value descending."}, {"role": "assistant", "content": "SELECT t.buyer_id, m.value AS asset_symbol, SUM(t.quantity * t.price) AS total_value\nFROM trading_platform.trades t\nJOIN trading_platform.metadata m ON t.asset_id = m.asset_id AND m.key = 'symbol'\nWHERE t.traded_at > '2024-06-01'\nGROUP BY t.buyer_id, m.value\nHAVING SUM(t.quantity * t.price) > 10000\nORDER BY total_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 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.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.logs ( log_id character varying(64) NOT NULL, user_id character varying(64), action character varying(128) NOT NULL, details text NOT NULL, logged_at timestamp NOT NULL, PRIMARY KEY (log_id) )\nCREATE TABLE trading_platform.notifications ( notification_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, message text NOT NULL, sent_at timestamp NOT NULL, read_at timestamp, PRIMARY KEY (notification_id) )\n"}
{"conversations": [{"role": "user", "content": "List the document ID, document type, and the full name of the citizen who submitted the document, but only for documents submitted for applications with a status of 'Approved'."}, {"role": "assistant", "content": "SELECT T1.document_id, T1.document_type, T3.first_name, T3.last_name FROM government_services.documents AS T1 JOIN government_services.applications AS T2 ON T1.application_id = T2.application_id JOIN government_services.citizens AS T3 ON T1.citizen_id = T3.citizen_id WHERE T2.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 government_services.documents ( document_id.text, application_id.text, citizen_id.text, document_type.text, file_reference.text, upload_timestamp.timestamp, expiry_date.date, verification_status.text, verified_by_employee_id.text, verification_timestamp.timestamp )\n"}
{"conversations": [{"role": "user", "content": "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": "For each user, show their username and how many unique conversations they have sent at least one message in where the conversation is a group chat."}, {"role": "assistant", "content": "SELECT u.username, COUNT(DISTINCT m.conversation_id) AS group_chats_messaged_in\nFROM social_media.users u\nJOIN social_media.messages m ON u.user_id = m.sender_user_id\nJOIN social_media.conversations c ON m.conversation_id = c.conversation_id\nWHERE c.is_group_chat = TRUE\nGROUP BY u.username;"}, {"role": "user", "content": "Instead, show only users who have sent messages in more than one group chat, and include their email addresses."}, {"role": "assistant", "content": "SELECT u.username, u.email, COUNT(DISTINCT m.conversation_id) AS group_chats_messaged_in\nFROM social_media.users u\nJOIN social_media.messages m ON u.user_id = m.sender_user_id\nJOIN social_media.conversations c ON m.conversation_id = c.conversation_id\nWHERE c.is_group_chat = TRUE\nGROUP BY u.username, u.email\nHAVING COUNT(DISTINCT m.conversation_id) > 1;"}, {"role": "user", "content": "Also add the most recent message time sent by each user in these group chats."}, {"role": "assistant", "content": "SELECT u.username, u.email, COUNT(DISTINCT m.conversation_id) AS group_chats_messaged_in, MAX(m.sent_at) AS last_message_time\nFROM social_media.users u\nJOIN social_media.messages m ON u.user_id = m.sender_user_id\nJOIN social_media.conversations c ON m.conversation_id = c.conversation_id\nWHERE c.is_group_chat = TRUE\nGROUP BY u.username, u.email\nHAVING COUNT(DISTINCT m.conversation_id) > 1;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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 (\n    comment_id character varying(64) NOT NULL, -- unique identifier for the comment\n    post_id character varying(64) NOT NULL, -- identifier of the post being commented on (FK to posts.post_id)\n    user_id character varying(64) NOT NULL, -- identifier of the user who made the comment (FK to users.user_id)\n    parent_comment_id character varying(64), -- identifier of the parent comment if it's a reply (FK to comments.comment_id)\n    content text NOT NULL, -- textual content of the comment\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of comment creation\n    updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last comment edit\n    PRIMARY KEY (comment_id)\n)\nCREATE TABLE social_media.likes ( like_id text, user_id text, post_id text, comment_id text, created_at timestamp )\nCREATE TABLE social_media.follows ( follow_id character varying(64) NOT NULL, follower_user_id character varying(64) NOT NULL, following_user_id character varying(64) NOT NULL, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (follow_id), CONSTRAINT unique_follow UNIQUE (follower_user_id, following_user_id) )\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 character varying(64) NOT NULL, post_id character varying(64) NOT NULL, hashtag_id character varying(64) NOT NULL, PRIMARY KEY (post_hashtag_id), CONSTRAINT unique_post_hashtag UNIQUE (post_id, hashtag_id) )\nCREATE TABLE social_media.messages (\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 ( 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 (\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 ( 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": "Calculate the total quantity traded for each day in the dataset."}, {"role": "assistant", "content": "SELECT DATE_TRUNC('day', traded_at) AS trade_day, SUM(quantity) AS total_daily_quantity FROM trading_platform.trades GROUP BY DATE_TRUNC('day', traded_at) ORDER BY trade_day;"}, {"role": "user", "content": "Could you also include the total trade value (quantity * price) for each day in that report?"}, {"role": "assistant", "content": "SELECT DATE_TRUNC('day', traded_at) AS trade_day, SUM(quantity) AS total_daily_quantity, SUM(quantity * price) AS total_daily_value FROM trading_platform.trades GROUP BY DATE_TRUNC('day', traded_at) ORDER BY trade_day;"}, {"role": "user", "content": "Now, for each day, show how the total quantity compares to the overall average daily quantity across all days in the dataset."}, {"role": "assistant", "content": "WITH DailySummary AS (SELECT DATE_TRUNC('day', traded_at) AS trade_day, SUM(quantity) AS total_daily_quantity FROM trading_platform.trades GROUP BY DATE_TRUNC('day', traded_at)) SELECT trade_day, total_daily_quantity, total_daily_quantity - AVG(total_daily_quantity) OVER () AS quantity_difference_from_average FROM DailySummary ORDER BY trade_day;"}, {"role": "user", "content": "Finally, only show the days where the total quantity was higher than the overall average daily quantity."}, {"role": "assistant", "content": "WITH DailySummary AS (SELECT DATE_TRUNC('day', traded_at) AS trade_day, SUM(quantity) AS total_daily_quantity FROM trading_platform.trades GROUP BY DATE_TRUNC('day', traded_at)) SELECT trade_day, total_daily_quantity FROM DailySummary WHERE total_daily_quantity > (SELECT AVG(total_daily_quantity) FROM DailySummary) ORDER BY trade_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 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": "List all vehicles and their last maintenance service date along with the odometer reading, including only those that have not had a fuel refill in the past 30 days."}, {"role": "assistant", "content": "SELECT m.vehicle_id,\n       m.last_service_date,\n       m.last_odometer\nFROM (\n  SELECT l.vehicle_id,\n         MAX(l.service_date) AS last_service_date,\n         (SELECT odometer_reading\n          FROM transportation.maintenance_logs\n          WHERE vehicle_id = l.vehicle_id\n          ORDER BY service_date DESC\n          LIMIT 1) AS last_odometer\n  FROM transportation.maintenance_logs l\n  GROUP BY l.vehicle_id\n) AS m\nLEFT JOIN (\n  SELECT fl.vehicle_id,\n         MAX(fl.log_timestamp) AS last_fuel_date\n  FROM transportation.fuel_logs fl\n  GROUP BY fl.vehicle_id\n) AS f ON m.vehicle_id = f.vehicle_id\nWHERE COALESCE(f.last_fuel_date, '1900-01-01'::timestamp) < NOW() - INTERVAL '30 days';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.routes ( route_id character varying(64) NOT NULL, route_number character varying(32) NOT NULL UNIQUE, description text, origin_location_id character varying(64) NOT NULL, destination_location_id character varying(64) NOT NULL, distance_km numeric(10, 2), estimated_duration_minutes integer, type character varying(32) NOT NULL, PRIMARY KEY (route_id) )\nCREATE TABLE transportation.trips ( trip_id character varying(64) NOT NULL, route_id character varying(64), vehicle_id character varying(64) NOT NULL, driver_id character varying(64) NOT NULL, scheduled_departure timestamp with time zone NOT NULL, actual_departure timestamp with time zone, scheduled_arrival timestamp with time zone NOT NULL, actual_arrival timestamp with time zone, origin_location_id character varying(64) NOT NULL, destination_location_id character varying(64) NOT NULL, status character varying(32) NOT NULL, passenger_count integer, cargo_manifest_id character varying(64), PRIMARY KEY (trip_id) )\nCREATE TABLE transportation.locations ( location_id character varying(64) NOT NULL, name character varying(255) NOT NULL, type character varying(64) NOT NULL, address_line1 character varying(255), city character varying(128), state_province character varying(128), postal_code character varying(32), country character varying(64) NOT NULL, latitude numeric(9, 6), longitude numeric(9, 6), timezone character varying(64), PRIMARY KEY (location_id) )\nCREATE TABLE transportation.maintenance_logs ( log_id character varying(64) NOT NULL, vehicle_id character varying(64) NOT NULL, service_date date NOT NULL, odometer_reading integer, service_type character varying(128) NOT NULL, description text NOT NULL, cost numeric(10, 2), mechanic_name character varying(128), next_service_due_date date, PRIMARY KEY (log_id) )\nCREATE TABLE transportation.fuel_logs ( fuel_log_id character varying(64) NOT NULL, vehicle_id character varying(64) NOT NULL, trip_id character varying(64), log_timestamp timestamp with time zone NOT NULL, fuel_type character varying(32) NOT NULL, quantity numeric(10, 3) NOT NULL, unit character varying(16) NOT NULL, cost_per_unit numeric(8, 4), total_cost numeric(10, 2) NOT NULL, odometer_reading integer, location_id character varying(64), PRIMARY KEY (fuel_log_id) )\nCREATE TABLE transportation.passengers ( passenger_id character varying(64) NOT NULL, first_name character varying(128) NOT NULL, last_name character varying(128) NOT NULL, email character varying(128) UNIQUE, phone_number character varying(32) UNIQUE, date_of_birth date, loyalty_program_id character varying(64), created_at timestamp with time zone NOT NULL, PRIMARY KEY (passenger_id) )\nCREATE TABLE transportation.bookings ( booking_id character varying(64) NOT NULL, passenger_id character varying(64) NOT NULL, trip_id character varying(64) NOT NULL, seat_number character varying(16), booking_time timestamp with time zone NOT NULL, status character varying(32) NOT NULL, fare numeric(10, 2) NOT NULL, payment_transaction_id character varying(128), special_requests text, PRIMARY KEY (booking_id) )\n"}
{"conversations": [{"role": "user", "content": "What is the current market price of a Boeing 737 MAX aircraft?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to the current market price of aircraft models. The data I have is limited to technical specifications and general information about aircraft models such as passenger capacity, range, and status. For pricing information, you may need to consult with manufacturers or industry reports."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE manufacturing.aircraft_models (\n    model_id character varying(64) NOT NULL,  -- unique identifier for the aircraft model\n    model_name character varying(128) NOT NULL, -- commercial name of the model (e.g., 737 MAX, A320neo)\n    manufacturer character varying(128) NOT NULL, -- manufacturer name (e.g., Boeing, Airbus)\n    passenger_capacity integer, -- typical passenger capacity\n    max_range_km integer, -- maximum flight range in kilometers\n    engine_type character varying(100), -- type of engines used\n    wingspan_m numeric(6,2), -- wingspan in meters\n    status character varying(50) NOT NULL, -- e.g., 'In Production', 'Development', 'Discontinued'\n    first_flight_date date, -- date of the model's first flight\n    PRIMARY KEY (model_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List all medical records, showing the record ID, record date, and the full name of the doctor who created the record. Include the patient ID as well."}, {"role": "assistant", "content": "SELECT mr.record_id, mr.record_date, mr.patient_id, d.first_name, d.last_name FROM healthcare.medical_records mr JOIN doctors d ON mr.doctor_id = d.doctor_id;"}, {"role": "user", "content": "Refine this to only include records where the chief_complaint is not null or empty and the doctor's specialty is 'Cardiology'."}, {"role": "assistant", "content": "SELECT mr.record_id, mr.record_date, mr.patient_id, d.first_name, d.last_name FROM healthcare.medical_records mr JOIN doctors d ON mr.doctor_id = d.doctor_id WHERE (mr.chief_complaint IS NOT NULL AND mr.chief_complaint != '') AND d.specialty = 'Cardiology';"}, {"role": "user", "content": "Also, sort the results by record_date in descending order and limit the output to the top 10 records."}, {"role": "assistant", "content": "SELECT mr.record_id, mr.record_date, mr.patient_id, d.first_name, d.last_name FROM healthcare.medical_records mr JOIN doctors d ON mr.doctor_id = d.doctor_id WHERE (mr.chief_complaint IS NOT NULL AND mr.chief_complaint != '') AND d.specialty = 'Cardiology' ORDER BY mr.record_date DESC LIMIT 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.medical_records (\n    record_id character varying(64) NOT NULL,  -- unique identifier for the medical record entry\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    appointment_id character varying(64) UNIQUE, -- FK to appointments table (can be null if record not tied to specific appt)\n    doctor_id character varying(64) NOT NULL, -- FK to doctors table (doctor creating the record)\n    record_date timestamp with time zone NOT NULL, -- date the record/observation was made\n    chief_complaint text, -- patient's primary reason for visit\n    present_illness_history text, -- detailed history of the current issue\n    past_medical_history text, -- relevant past conditions/surgeries\n    physical_examination_notes text, -- findings from the physical exam\n    assessment text, -- doctor's assessment/diagnosis summary\n    treatment_plan text, -- planned course of action\n    vitals jsonb, -- store vitals like BP, HR, Temp as structured JSON\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (record_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Provide a list of all vehicles and the total quantity of fuel refueled for each vehicle."}, {"role": "assistant", "content": "SELECT T1.license_plate, sum(T2.quantity) FROM transportation.vehicles AS T1 JOIN transportation.fuel_logs AS T2 ON T1.vehicle_id = T2.vehicle_id GROUP BY T1.license_plate"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles ( vehicle_id text PRIMARY KEY, license_plate text, vin text, make text, model text, year int, type text, capacity int, fuel_type text, status text, depot_id text, acquisition_date date )\nCREATE TABLE transportation.drivers ( driver_id text PRIMARY KEY, employee_id text, first_name text, last_name text, license_number text, license_expiry_date date, contact_number text, email text, hire_date date, status text )\nCREATE TABLE transportation.routes ( route_id text PRIMARY KEY, route_number text, description text, origin_location_id text, destination_location_id text, distance_km numeric, estimated_duration_minutes int, type text )\nCREATE TABLE transportation.trips ( trip_id text PRIMARY KEY, route_id text, vehicle_id text, driver_id text, scheduled_departure timestamp, actual_departure timestamp, scheduled_arrival timestamp, actual_arrival timestamp, origin_location_id text, destination_location_id text, status text, passenger_count int, cargo_manifest_id text )\nCREATE TABLE transportation.fuel_logs ( fuel_log_id text PRIMARY KEY, vehicle_id text, trip_id text, log_timestamp timestamp, fuel_type text, quantity numeric, unit text, cost_per_unit numeric, total_cost numeric, odometer_reading int, location_id text )\nCREATE TABLE transportation.passengers ( passenger_id text PRIMARY KEY, first_name text, last_name text, email text, phone_number text, date_of_birth date, loyalty_program_id text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "For each security issuer, show the count of market data points and the average close price for their securities."}, {"role": "assistant", "content": "SELECT T2.issuer_name, COUNT(T1.*) AS data_point_count, AVG(T1.close_price) AS avg_close_price FROM financial_services.market_data AS T1 JOIN financial_services.securities AS T2 ON T1.security_id = T2.security_id GROUP BY T2.issuer_name;"}, {"role": "user", "content": "Only include issuers who have more than 1000 market data points in total."}, {"role": "assistant", "content": "SELECT T2.issuer_name, COUNT(T1.*) AS data_point_count, AVG(T1.close_price) AS avg_close_price FROM financial_services.market_data AS T1 JOIN financial_services.securities AS T2 ON T1.security_id = T2.security_id GROUP BY T2.issuer_name HAVING COUNT(T1.*) > 1000;"}, {"role": "user", "content": "Also, include the average volume for each issuer and sort the results by average close price descending."}, {"role": "assistant", "content": "SELECT T2.issuer_name, COUNT(T1.*) AS data_point_count, AVG(T1.close_price) AS avg_close_price, AVG(T1.volume) AS avg_volume FROM financial_services.market_data AS T1 JOIN financial_services.securities AS T2 ON T1.security_id = T2.security_id GROUP BY T2.issuer_name HAVING COUNT(T1.*) > 1000 ORDER BY avg_close_price DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.market_data (\n    data_point_id bigserial NOT NULL, -- auto-incrementing primary key\n    security_id character varying(64) NOT NULL, -- identifier for the security\n    data_timestamp timestamp NOT NULL, -- timestamp for the data point (e.g., end of day, intraday)\n    open_price numeric(19, 8), -- opening price for the period\n    high_price numeric(19, 8), -- highest price during the period\n    low_price numeric(19, 8), -- lowest price during the period\n    close_price numeric(19, 8) NOT NULL, -- closing price for the period\n    adjusted_close_price numeric(19, 8), -- closing price adjusted for dividends and splits\n    volume bigint, -- trading volume during the period\n    source character varying(50), -- source of the market data (e.g., Bloomberg, Refinitiv)\n    PRIMARY KEY (data_point_id),\n    UNIQUE (security_id, data_timestamp), -- Ensure unique data point per security per time\n    FOREIGN KEY (security_id) REFERENCES financial_services.securities(security_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List patient_id, full name, policy_number, plan_type, and insurance_provider for all active primary insurance policies."}, {"role": "assistant", "content": "SELECT pi.patient_id,\n       p.first_name,\n       p.last_name,\n       pi.policy_number,\n       ip.plan_type,\n       ip.insurance_provider\nFROM healthcare.patient_insurance pi\nJOIN healthcare.patients p\n  ON p.patient_id = pi.patient_id\nJOIN healthcare.insurance_plans ip\n  ON ip.plan_id = pi.plan_id\nWHERE pi.is_primary = TRUE\n  AND pi.effective_date <= CURRENT_DATE\n  AND pi.expiration_date >= CURRENT_DATE;"}, {"role": "user", "content": "Now also restrict to policies expiring within the next 30 days."}, {"role": "assistant", "content": "SELECT pi.patient_id,\n       p.first_name,\n       p.last_name,\n       pi.policy_number,\n       ip.plan_type,\n       ip.insurance_provider\nFROM healthcare.patient_insurance pi\nJOIN healthcare.patients p\n  ON p.patient_id = pi.patient_id\nJOIN healthcare.insurance_plans ip\n  ON ip.plan_id = pi.plan_id\nWHERE pi.is_primary = TRUE\n  AND pi.effective_date <= CURRENT_DATE\n  AND pi.expiration_date BETWEEN CURRENT_DATE AND CURRENT_DATE + INTERVAL '30 days';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id text, first_name text, last_name text, date_of_birth date, gender text, address text, phone_number text, email text, emergency_contact_name text, emergency_contact_phone text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.appointments ( appointment_id text, patient_id text, doctor_id text, appointment_time timestamp, duration_minutes integer, reason text, status text, location_id text, notes text, created_at timestamp )\nCREATE TABLE healthcare.medical_records ( record_id text, patient_id text, appointment_id text, doctor_id text, record_date timestamp, chief_complaint text, present_illness_history text, past_medical_history text, physical_examination_notes text, assessment text, treatment_plan text, vitals text, created_at timestamp )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id text, record_id text, patient_id text, doctor_id text, diagnosis_code text, code_type text, description text, diagnosis_date date, status text, is_chronic boolean )\nCREATE TABLE healthcare.medications ( medication_id text, medication_name text, generic_name text, manufacturer text, ndc_code text, description text )\nCREATE TABLE healthcare.prescriptions ( prescription_id text, record_id text, patient_id text, doctor_id text, medication_id text, dosage text, frequency text, route text, start_date date, end_date date, quantity_dispensed numeric, refills_allowed integer, prescription_date timestamp )\nCREATE TABLE healthcare.insurance_plans ( plan_id text, plan_name text, insurance_provider text, plan_type text, contact_phone text, website text )\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id text, patient_id text, plan_id text, policy_number text, group_number text, subscriber_name text, effective_date date, expiration_date date, is_primary boolean )\n"}
{"conversations": [{"role": "user", "content": "List all events and any token transfers that occurred in the same transaction, showing event_id, event_name, transfer_id, and token_symbol."}, {"role": "assistant", "content": "SELECT\n  e.event_id,\n  e.event_name,\n  tt.transfer_id,\n  tk.token_symbol\nFROM web3.events e\nLEFT JOIN web3.token_transfers tt\n  ON e.transaction_id = tt.transaction_id\nLEFT JOIN web3.tokens tk\n  ON tt.token_id = tk.token_id\nORDER BY e.transaction_id, e.log_index;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.contracts ( contract_id character varying(64) NOT NULL, address character varying(128) NOT NULL, abi text NOT NULL, bytecode text NOT NULL, deployer_address character varying(128) NOT NULL, deployed_at timestamp NOT NULL, network_id character varying(64) NOT NULL, status character varying(32) NOT NULL, PRIMARY KEY (contract_id) )\nCREATE TABLE web3.events ( event_id.text, contract_id.text, event_name.text, data.text, emitted_at.timestamp, transaction_id.text, log_index.integer )\nCREATE TABLE web3.tokens (\n    token_id character varying(64) NOT NULL,  -- unique identifier for the token\n    contract_address character varying(128) NOT NULL, -- address of the token contract\n    token_name character varying(128) NOT NULL, -- name of the token\n    token_symbol character varying(32) NOT NULL, -- symbol of the token\n    decimals integer NOT NULL, -- number of decimals for the token\n    total_supply numeric(38,14) NOT NULL, -- total supply of the token\n    PRIMARY KEY (token_id)\n)\nCREATE TABLE web3.token_transfers ( transfer_id text PRIMARY KEY, token_id text, from_address text, to_address text, value numeric, transaction_id text, log_index int )\nCREATE TABLE web3.users ( user_id text, username text, email text, password_hash text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "List smart money addresses, their chain, and profit for those who have incurred a loss. Order the results by the magnitude of the loss (smallest profit value first)."}, {"role": "assistant", "content": "SELECT address, chain, profit FROM smart_money_profit WHERE profit < 0 ORDER BY profit ASC;"}, {"role": "user", "content": "From that list, show only the addresses that have a rank worse than 500 (rank number greater than 500)."}, {"role": "assistant", "content": "SELECT address, chain, profit FROM smart_money_profit WHERE profit < 0 AND rank > 500 ORDER BY profit ASC;"}, {"role": "user", "content": "Further refine the list to include only addresses on the 'Arbitrum' chain."}, {"role": "assistant", "content": "SELECT address, chain, profit FROM smart_money_profit WHERE profit < 0 AND rank > 500 AND chain = 'Arbitrum' ORDER BY profit ASC;"}, {"role": "user", "content": "Based on the filtered list (loss, rank worse than 500, Arbitrum chain), what is the average profit?"}, {"role": "assistant", "content": "SELECT AVG(profit) FROM smart_money_profit WHERE profit < 0 AND rank > 500 AND chain = 'Arbitrum';"}], "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_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"}
{"conversations": [{"role": "user", "content": "Get the number of direct reports for each manager, showing manager_id and report_count."}, {"role": "assistant", "content": "SELECT manager_id,\n       COUNT(*) AS report_count\nFROM hospitality_technology.staff\nWHERE manager_id IS NOT NULL\nGROUP BY manager_id;"}, {"role": "user", "content": "Exclude managers who have fewer than 2 direct reports."}, {"role": "assistant", "content": "SELECT manager_id,\n       COUNT(*) AS report_count\nFROM hospitality_technology.staff\nWHERE manager_id IS NOT NULL\nGROUP BY manager_id\nHAVING COUNT(*) >= 2;"}, {"role": "user", "content": "Also include the manager's full name alongside their ID."}, {"role": "assistant", "content": "SELECT m.staff_id AS manager_id,\n       m.first_name || ' ' || m.last_name AS manager_full_name,\n       COUNT(s.staff_id) AS report_count\nFROM hospitality_technology.staff s\nJOIN hospitality_technology.staff m\n  ON s.manager_id = m.staff_id\nGROUP BY m.staff_id, m.first_name, m.last_name\nHAVING COUNT(s.staff_id) >= 2;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.staff ( staff_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, position character varying(100) NOT NULL, work_email character varying(255) UNIQUE, work_phone character varying(30), hire_date date NOT NULL, termination_date date, is_active boolean NOT NULL DEFAULT true, access_level integer NOT NULL, manager_id character varying(64), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (staff_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (manager_id) REFERENCES hospitality_technology.staff(staff_id) )\n"}
{"conversations": [{"role": "user", "content": "Show each wallet address that has received token transfers of more than one type of token, along with the count of token types received."}, {"role": "assistant", "content": "SELECT tt.to_address, COUNT(DISTINCT tt.token_id) AS token_type_count\nFROM web3.token_transfers tt\nGROUP BY tt.to_address\nHAVING COUNT(DISTINCT tt.token_id) > 1;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.contracts ( contract_id text PRIMARY KEY, address text, abi text, bytecode text, deployer_address text, deployed_at timestamp, network_id text, status text )\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) )\nCREATE TABLE web3.tokens (\n    token_id character varying(64) NOT NULL,  -- unique identifier for the token\n    contract_address character varying(128) NOT NULL, -- address of the token contract\n    token_name character varying(128) NOT NULL, -- name of the token\n    token_symbol character varying(32) NOT NULL, -- symbol of the token\n    decimals integer NOT NULL, -- number of decimals for the token\n    total_supply numeric(38,14) NOT NULL, -- total supply of the token\n    PRIMARY KEY (token_id)\n)\nCREATE TABLE web3.token_transfers ( transfer_id character varying(64) NOT NULL, token_id character varying(64) NOT NULL, from_address character varying(128) NOT NULL, to_address character varying(128) NOT NULL, value numeric(38,14) NOT NULL, transaction_id character varying(64) NOT NULL, log_index integer NOT NULL, PRIMARY KEY (transfer_id) )\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)\nCREATE TABLE web3.users (\n    user_id character varying(64) NOT NULL,  -- unique identifier for the user\n    username character varying(128) NOT NULL, -- username of the user\n    email character varying(128) NOT NULL, -- email address of the user\n    password_hash text NOT NULL, -- hashed password of the user\n    created_at timestamp NOT NULL, -- time when the user account was created\n    PRIMARY KEY (user_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Can you help me get the total number of operational platforms across all stations?"}, {"role": "assistant", "content": "db.platforms.countDocuments({ status: 'Operational' });"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\n// db.createCollection('platforms')\n// Optional: db.platforms.createIndex({ platform_id: 1 }, { unique: true })\n// Optional: db.platforms.createIndex({ station_id: 1 })\n{\n  _id: ObjectId(),\n  platform_id: \"plat_123\", // String (unique)\n  station_id: \"station_xyz\", // String (references stations.station_id)\n  platform_number: \"1A\", // String\n  track_number: \"T1\", // String\n  status: \"Operational\", // String ('Operational', 'Maintenance', 'Closed')\n  length_meters: 250.50, // Decimal128 or Double\n  accessible: true // Boolean\n}\n// db.createCollection('routes')\n// Optional: db.routes.createIndex({ route_id: 1 }, { unique: true })\n{\n  _id: ObjectId(),\n  route_id: \"route_ne_corr\", // String (unique)\n  route_name: \"Northeast Corridor\", // String\n  description: \"High-speed rail linking Boston and Washington D.C.\", // String\n  origin_station_id: \"station_bos\", // String (references stations.station_id)\n  destination_station_id: \"station_was\", // String (references stations.station_id)\n  is_active: true // Boolean\n}\n// db.createCollection('route_stations')\n// Optional: db.route_stations.createIndex({ route_station_id: 1 }, { unique: true })\n// Optional: db.route_stations.createIndex({ route_id: 1, sequence_order: 1 }, { unique: true })\n{\n  _id: ObjectId(),\n  route_station_id: \"rs_ne_1\", // String (unique)\n  route_id: \"route_ne_corr\", // String (references routes.route_id)\n  station_id: \"station_bos\", // String (references stations.station_id)\n  sequence_order: 1, // Int32\n  distance_from_previous_km: null, // Decimal128 or Double (null for first stop)\n  typical_stop_duration_minutes: null // Int32 (null for origin/destination or if no stop)\n}\n// --- OR --- Embed within the Route document:\n// {\n//   _id: ObjectId(), route_id: \"route_ne_corr\", ...,\n//   stations: [\n//     { station_id: \"station_bos\", sequence_order: 1, distance_from_previous_km: null, typical_stop_duration_minutes: null },\n//     { station_id: \"station_pvd\", sequence_order: 2, distance_from_previous_km: 70.5, typical_stop_duration_minutes: 5 },\n//     ...\n//   ]\n// }\n// db.createCollection('schedules')\n// Optional: db.schedules.createIndex({ schedule_id: 1 }, { unique: true })\n// Optional: db.schedules.createIndex({ route_id: 1, departure_datetime: 1 })\n{\n  _id: ObjectId(),\n  schedule_id: \"sched_1122\", // String (unique)\n  train_id: \"train_789\", // String (references trains.train_id)\n  route_id: \"route_ne_corr\", // String (references routes.route_id)\n  departure_datetime: ISODate(\"2024-05-10T08:00:00-04:00\"), // Date (with timezone)\n  arrival_datetime: ISODate(\"2024-05-10T15:30:00-04:00\"), // Date (with timezone)\n  status: \"Scheduled\", // String ('Scheduled', 'On Time', 'Delayed', 'Cancelled', 'Arrived')\n  notes: \"Track work expected near Philadelphia\" // String\n}\n// db.createCollection('schedule_stops')\n// Optional: db.schedule_stops.createIndex({ stop_id: 1 }, { unique: true })\n// Optional: db.schedule_stops.createIndex({ schedule_id: 1, sequence_order: 1 }, { unique: true })\n{\n  _id: ObjectId(),\n  stop_id: \"stop_sched1122_1\", // String (unique)\n  schedule_id: \"sched_1122\", // String (references schedules.schedule_id)\n  station_id: \"station_bos\", // String (references stations.station_id)\n  platform_id: \"plat_bos_3\", // String (references platforms.platform_id, nullable)\n  sequence_order: 1, // Int32\n  scheduled_arrival_time: null, // Date\n  scheduled_departure_time: ISODate(\"2024-05-10T08:00:00-04:00\"), // Date\n  actual_arrival_time: null, // Date\n  actual_departure_time: ISODate(\"2024-05-10T08:01:00-04:00\"), // Date\n  status: \"On Time\" // String\n}\n// --- OR --- Embed within the Schedule document using an array 'stops'\n// db.createCollection('passengers')\n// Optional: db.passengers.createIndex({ passenger_id: 1 }, { unique: true })\n// Optional: db.passengers.createIndex({ email: 1 }, { unique: true, sparse: true })\n// Optional: db.passengers.createIndex({ phone_number: 1 }, { unique: true, sparse: true })\n{\n  _id: ObjectId(),\n  passenger_id: \"pass_pqr\", // String (unique)\n  first_name: \"Alice\", // String\n  last_name: \"Smith\", // String\n  email: \"alice.smith@example.com\", // String (unique, sparse)\n  phone_number: \"+15551234567\", // String (unique, sparse)\n  date_of_birth: ISODate(\"1990-03-20\"), // Date\n  loyalty_program_id: \"LOYALTY123\", // String\n  created_at: ISODate(\"2023-02-01T11:00:00Z\") // Date\n}\n// db.createCollection('staff')\n// Optional: db.staff.createIndex({ staff_id: 1 }, { unique: true })\n// Optional: db.staff.createIndex({ employee_number: 1 }, { unique: true })\n// Optional: db.staff.createIndex({ contact_email: 1 }, { unique: true, sparse: true })\n{\n  _id: ObjectId(),\n  staff_id: \"staff_mno\", // String (unique)\n  first_name: \"Bob\", // String\n  last_name: \"Jones\", // String\n  role: \"Conductor\", // String\n  primary_station_id: null, // String (references stations.station_id, nullable)\n  employee_number: \"E12345\", // String (unique)\n  hire_date: ISODate(\"2018-06-01\"), // Date\n  contact_email: \"bob.jones@example-rail.com\", // String (unique, sparse)\n  contact_phone: \"+15559876543\", // String\n  is_active: true // Boolean\n}\n"}
{"conversations": [{"role": "user", "content": "What is the total revenue generated by ticket sales at the station with ID 'ST101' for the past month?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information on the revenue generated by ticket sales as this data is not available in the current database table. The table only contains details about station information such as name, location, and platform count. If you have another question or need assistance with something else related to the station data, I'm happy to help."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.stations ( station_id.text, station_name.text, city.text, state_province.text, country_code.text, address.text, timezone.text, number_of_platforms.integer, created_at.timestamp, last_updated_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "List all beneficiaries who do not have any contact information provided. Show beneficiary_id, first_name, and last_name."}, {"role": "assistant", "content": "SELECT beneficiary_id, first_name, last_name FROM insurance.policy_beneficiaries WHERE contact_info IS NULL OR contact_info = ''"}], "system": "You are an SQL statement expert. Given the table structure 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, 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": "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": "List all claims that were reported more than 30 days after the incident date."}, {"role": "assistant", "content": "SELECT claim_id, policy_id, customer_id, incident_date, reported_date FROM insurance.claims WHERE DATEDIFF(reported_date, incident_date) > 30;"}, {"role": "user", "content": "Now show only claims that are still pending (status = 'pending')."}, {"role": "assistant", "content": "SELECT claim_id, policy_id, customer_id, incident_date, reported_date FROM insurance.claims WHERE DATEDIFF(reported_date, incident_date) > 30 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 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": "For each vehicle, list its vehicle_id, license_plate, and any older vehicle of the same type (showing older_vehicle_id and older year)."}, {"role": "assistant", "content": "SELECT cur.vehicle_id,\n       cur.license_plate,\n       old.vehicle_id AS older_vehicle_id,\n       old.year       AS older_vehicle_year\nFROM transportation.vehicles cur\nJOIN transportation.vehicles old\n  ON cur.type = old.type\n AND old.year < cur.year\nORDER BY cur.vehicle_id, old.year DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles (\n    vehicle_id character varying(64) NOT NULL,  -- unique identifier for the vehicle\n    license_plate character varying(32) NOT NULL UNIQUE, -- vehicle license plate\n    vin character varying(17) UNIQUE, -- vehicle identification number\n    make character varying(64) NOT NULL, -- manufacturer of the vehicle\n    model character varying(64) NOT NULL, -- model of the vehicle\n    year integer NOT NULL, -- manufacturing year\n    type character varying(32) NOT NULL, -- type of vehicle (e.g., Bus, Train, Truck, Car, Van)\n    capacity integer, -- passenger or cargo capacity\n    fuel_type character varying(32) NOT NULL, -- e.g., Diesel, Gasoline, Electric, Hydrogen\n    status character varying(32) NOT NULL, -- e.g., Active, Maintenance, Decommissioned\n    depot_id character varying(64), -- identifier of the home depot/base\n    acquisition_date date, -- date the vehicle was acquired\n    PRIMARY KEY (vehicle_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List all tokens with a price below $1 and a 24-hour trading volume over $5 million."}, {"role": "assistant", "content": "SELECT token_name, token_symbol, price, total_volume FROM token_basic_info WHERE price < 1 AND total_volume::numeric > 5000000;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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": "Find the top 5 employees who have verified the most documents. Display the employee full name and the count of verified documents, ordered by count descending."}, {"role": "assistant", "content": "SELECT e.first_name || ' ' || e.last_name AS full_name,\n       COUNT(*) AS verified_count\nFROM government_services.documents d\nJOIN government_services.employees e\n  ON d.verified_by_employee_id = e.employee_id\nWHERE d.verification_status = 'Verified'\nGROUP BY e.first_name, e.last_name\nORDER BY verified_count DESC\nLIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens (\n    citizen_id character varying(64) NOT NULL,  -- unique identifier for the citizen\n    national_id_number character varying(128) NOT NULL UNIQUE, -- official national identification number\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    date_of_birth date NOT NULL,\n    gender character varying(20),\n    primary_address text NOT NULL, -- full primary residential address\n    contact_email character varying(128) UNIQUE,\n    contact_phone character varying(32),\n    registration_date timestamp NOT NULL, -- when the citizen profile was created\n    is_verified boolean DEFAULT false, -- whether identity has been officially verified\n    PRIMARY KEY (citizen_id)\n)\nCREATE TABLE government_services.agencies ( agency_id text, agency_name text, jurisdiction_level text, primary_contact_email text, main_phone_number text, website_url text, established_date date, parent_agency_id text )\nCREATE TABLE government_services.applications ( application_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, service_id character varying(64) NOT NULL, submitted_at timestamp NOT NULL, status character varying(50) NOT NULL, last_updated_at timestamp NOT NULL, assigned_employee_id character varying(64), decision_date date, notes text, reference_number character varying(100) UNIQUE, PRIMARY KEY (application_id) )\nCREATE TABLE government_services.documents ( document_id text, application_id text, citizen_id text, document_type text, file_reference text, upload_timestamp timestamp, expiry_date date, verification_status text, verified_by_employee_id text, verification_timestamp timestamp )\nCREATE TABLE government_services.payments ( payment_id text, application_id text, citizen_id text, service_id text, amount numeric, currency text, payment_method text, payment_provider_reference text, payment_timestamp timestamp, status text, notes text )\nCREATE TABLE government_services.employees ( employee_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, job_title character varying(150) NOT NULL, department character varying(100), work_email character varying(128) NOT NULL UNIQUE, work_phone character varying(32), hire_date date NOT NULL, termination_date date, access_level character varying(50), manager_employee_id character varying(64), PRIMARY KEY (employee_id) )\nCREATE TABLE government_services.service_locations (\n    location_id character varying(64) NOT NULL, -- unique identifier for the physical location\n    agency_id character varying(64) NOT NULL, -- FK to agencies table\n    location_name character varying(200), -- e.g., Downtown DMV Office\n    address text NOT NULL,\n    city character varying(100),\n    state character varying(50),\n    postal_code character varying(20),\n    latitude numeric(9, 6),\n    longitude numeric(9, 6),\n    operating_hours text, -- description of opening times\n    contact_phone character varying(32),\n    is_accessible boolean, -- accessibility information (e.g., wheelchair access)\n    PRIMARY KEY (location_id)\n)\nCREATE TABLE government_services.notifications ( notification_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, application_id character varying(64), message_subject character varying(255), message_body text NOT NULL, channel character varying(30) NOT NULL, sent_at timestamp NOT NULL, status character varying(30) NOT NULL, related_entity_type character varying(50), related_entity_id character varying(64), PRIMARY KEY (notification_id) )\n"}
{"conversations": [{"role": "user", "content": "List the IDs of posts and their respective number of hashtags for posts that have two or more hashtags."}, {"role": "assistant", "content": "SELECT post_id, COUNT(hashtag_id) AS hashtag_count\nFROM social_media.post_hashtags\nGROUP BY post_id\nHAVING COUNT(hashtag_id) >= 2;"}, {"role": "user", "content": "Order the results by hashtag_count descending, and show only the top 10."}, {"role": "assistant", "content": "SELECT post_id, COUNT(hashtag_id) AS hashtag_count\nFROM social_media.post_hashtags\nGROUP BY post_id\nHAVING COUNT(hashtag_id) >= 2\nORDER BY hashtag_count DESC\nLIMIT 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.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 me the user_id and number of conversations they have joined. Only include users who joined more than one conversation."}, {"role": "assistant", "content": "SELECT user_id, COUNT(DISTINCT conversation_id) AS conversations_joined\nFROM social_media.conversation_participants\nGROUP BY user_id\nHAVING COUNT(DISTINCT conversation_id) > 1;"}, {"role": "user", "content": "Add the time they joined their most recent conversation as latest_joined_at."}, {"role": "assistant", "content": "SELECT user_id, COUNT(DISTINCT conversation_id) AS conversations_joined, MAX(joined_at) AS latest_joined_at\nFROM social_media.conversation_participants\nGROUP BY user_id\nHAVING COUNT(DISTINCT conversation_id) > 1;"}, {"role": "user", "content": "Also, show the IDs of the conversations for each user as a comma-separated list."}, {"role": "assistant", "content": "SELECT user_id,\n  COUNT(DISTINCT conversation_id) AS conversations_joined,\n  MAX(joined_at) AS latest_joined_at,\n  STRING_AGG(DISTINCT conversation_id, ',') AS conversation_ids\nFROM social_media.conversation_participants\nGROUP BY user_id\nHAVING COUNT(DISTINCT conversation_id) > 1;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.post_hashtags ( post_hashtag_id text, post_id text, hashtag_id text )\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": "Can you list each server along with its game title and how many players it can still accommodate (max_players - current_players)?"}, {"role": "assistant", "content": "SELECT s.server_id,\n       s.server_name,\n       g.title AS game_title,\n       (s.max_players - s.current_players) AS available_slots\nFROM gaming_technology.servers s\nJOIN gaming_technology.games g ON s.game_id = g.game_id;"}, {"role": "user", "content": "Only include servers that are currently 'online' or 'idle'."}, {"role": "assistant", "content": "SELECT s.server_id,\n       s.server_name,\n       g.title AS game_title,\n       (s.max_players - s.current_players) AS available_slots\nFROM gaming_technology.servers s\nJOIN gaming_technology.games g ON s.game_id = g.game_id\nWHERE s.status IN ('online', 'idle');"}, {"role": "user", "content": "Now show only those with available_slots greater than 10, sorted by available_slots descending."}, {"role": "assistant", "content": "SELECT s.server_id,\n       s.server_name,\n       g.title AS game_title,\n       (s.max_players - s.current_players) AS available_slots\nFROM gaming_technology.servers s\nJOIN gaming_technology.games g ON s.game_id = g.game_id\nWHERE s.status IN ('online', 'idle')\n  AND (s.max_players - s.current_players) > 10\nORDER BY available_slots DESC;"}, {"role": "user", "content": "Finally, include the game's release_date and only for games released after 2022-01-01."}, {"role": "assistant", "content": "SELECT s.server_id,\n       s.server_name,\n       g.title AS game_title,\n       g.release_date,\n       (s.max_players - s.current_players) AS available_slots\nFROM gaming_technology.servers s\nJOIN gaming_technology.games g ON s.game_id = g.game_id\nWHERE s.status IN ('online', 'idle')\n  AND (s.max_players - s.current_players) > 10\n  AND g.release_date > '2022-01-01'\nORDER BY available_slots DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.games ( game_id uuid 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, game_id.uuid, server_name.text, region.text, ip_address.text, port.integer, current_players.integer, max_players.integer, status.text, last_heartbeat.timestamptz )\nCREATE TABLE gaming_technology.player_achievements ( player_achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), player_id uuid NOT NULL, achievement_id uuid NOT NULL, unlocked_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (player_achievement_id), UNIQUE (player_id, achievement_id) )\nCREATE TABLE gaming_technology.player_inventory ( inventory_id uuid NOT NULL DEFAULT gen_random_uuid(), player_id uuid NOT NULL, item_id uuid NOT NULL, quantity integer NOT NULL DEFAULT 1, acquired_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, instance_data jsonb, PRIMARY KEY (inventory_id) )\n"}
{"conversations": [{"role": "user", "content": "Please list all law firms with their names and address, and also indicate the year they were founded."}, {"role": "assistant", "content": "SELECT firm_name, address, EXTRACT(YEAR FROM founded_date) AS founded_year FROM legal_services.law_firms;"}, {"role": "user", "content": "Just show those founded before 2015."}, {"role": "assistant", "content": "SELECT firm_name, address, EXTRACT(YEAR FROM founded_date) AS founded_year FROM legal_services.law_firms WHERE founded_date < '2015-01-01';"}, {"role": "user", "content": "Can you order them by founded_year descending?"}, {"role": "assistant", "content": "SELECT firm_name, address, EXTRACT(YEAR FROM founded_date) AS founded_year FROM legal_services.law_firms WHERE founded_date < '2015-01-01' ORDER BY founded_year DESC;"}, {"role": "user", "content": "Finally, only include firms with a non-null address."}, {"role": "assistant", "content": "SELECT firm_name, address, EXTRACT(YEAR FROM founded_date) AS founded_year FROM legal_services.law_firms WHERE founded_date < '2015-01-01' AND address IS NOT NULL ORDER BY founded_year DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.law_firms ( firm_id.text, firm_name.text, address.text, phone.text, website.text, founded_date.date, managing_partner_id.text )\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": "Find policies that have two different 'Spouse' beneficiaries. List policy_id, spouse1_id, and spouse2_id."}, {"role": "assistant", "content": "SELECT pb1.policy_id,\n       pb1.beneficiary_id AS spouse1_id,\n       pb2.beneficiary_id AS spouse2_id\nFROM insurance.policy_beneficiaries pb1\nJOIN insurance.policy_beneficiaries pb2\n  ON pb1.policy_id = pb2.policy_id\n     AND pb1.beneficiary_id < pb2.beneficiary_id\nWHERE pb1.relationship = 'Spouse'\n  AND pb2.relationship = 'Spouse';"}, {"role": "user", "content": "Also include first_name and last_name for both spouses."}, {"role": "assistant", "content": "SELECT pb1.policy_id,\n       pb1.beneficiary_id AS spouse1_id,\n       pb1.first_name AS spouse1_first_name,\n       pb1.last_name AS spouse1_last_name,\n       pb2.beneficiary_id AS spouse2_id,\n       pb2.first_name AS spouse2_first_name,\n       pb2.last_name AS spouse2_last_name\nFROM insurance.policy_beneficiaries pb1\nJOIN insurance.policy_beneficiaries pb2\n  ON pb1.policy_id = pb2.policy_id\n     AND pb1.beneficiary_id < pb2.beneficiary_id\nWHERE pb1.relationship = 'Spouse'\n  AND pb2.relationship = 'Spouse';"}], "system": "You are an SQL statement expert. Given the table structure 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 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": "Show the plan name and insurance provider for all insurance plans along with the total number of unique patients enrolled in each plan."}, {"role": "assistant", "content": "SELECT ip.plan_name, ip.insurance_provider, COUNT(DISTINCT pi.patient_id) AS enrolled_patient_count\nFROM healthcare.insurance_plans ip\nJOIN healthcare.patients_insurance pi ON ip.plan_id = pi.plan_id\nGROUP BY ip.plan_name, ip.insurance_provider;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id text, first_name text, last_name text, date_of_birth date, gender text, address text, phone_number text, email text, emergency_contact_name text, emergency_contact_phone text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.doctors ( doctor_id text, first_name text, last_name text, specialty text, license_number text, phone_number text, email text, hospital_affiliation_id text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.appointments (\n    appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    doctor_id character varying(64) NOT NULL, -- FK to doctors table\n    appointment_time timestamp with time zone NOT NULL, -- date and time of the appointment\n    duration_minutes integer NOT NULL, -- expected duration in minutes\n    reason text, -- reason for the visit\n    status character varying(32) NOT NULL, -- e.g., Scheduled, Completed, Cancelled, No-show\n    location_id character varying(64), -- FK to a potential locations/clinics table\n    notes text, -- notes related to scheduling\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (appointment_id)\n)\nCREATE TABLE healthcare.medical_records ( record_id text PRIMARY KEY, patient_id text, appointment_id text, doctor_id text, record_date timestamp, chief_complaint text, present_illness_history text, past_medical_history text, physical_examination_notes text, assessment text, treatment_plan text, vitals text, created_at timestamp )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id character varying(64) NOT NULL, record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, doctor_id character varying(64) NOT NULL, diagnosis_code character varying(20) NOT NULL, code_type character varying(10) NOT NULL DEFAULT 'ICD-10', description text, diagnosis_date date NOT NULL, status character varying(32) NOT NULL, is_chronic boolean DEFAULT false, PRIMARY KEY (diagnosis_id) )\nCREATE TABLE healthcare.medications (\n    medication_id character varying(64) NOT NULL, -- unique identifier for the medication type\n    medication_name character varying(255) NOT NULL, -- common or brand name\n    generic_name character varying(255), -- generic chemical name\n    manufacturer character varying(100), -- drug manufacturer\n    ndc_code character varying(20) UNIQUE, -- National Drug Code (optional but useful)\n    description text, -- description of the medication\n    PRIMARY KEY (medication_id)\n)\nCREATE TABLE healthcare.prescriptions ( prescription_id text, record_id text, patient_id text, doctor_id text, medication_id text, dosage text, frequency text, route text, start_date date, end_date date, quantity_dispensed numeric, refills_allowed integer, prescription_date timestamp )\nCREATE TABLE healthcare.insurance_plans ( plan_id.text, plan_name.text, insurance_provider.text, plan_type.text, contact_phone.text, website.text )\n"}
{"conversations": [{"role": "user", "content": "List the user IDs and the date they joined their most recent conversation."}, {"role": "assistant", "content": "SELECT user_id, MAX(joined_at) AS most_recent_joined_at\nFROM social_media.conversation_participants\nGROUP BY user_id;"}, {"role": "user", "content": "Can you also include the setting ID and last time they updated their user settings?"}, {"role": "assistant", "content": "SELECT cp.user_id, MAX(cp.joined_at) AS most_recent_joined_at, us.setting_id, us.updated_at AS last_settings_update\nFROM social_media.conversation_participants cp\nLEFT JOIN social_media.user_settings us ON cp.user_id = us.user_id\nGROUP BY cp.user_id, us.setting_id, us.updated_at;"}, {"role": "user", "content": "Only show users who joined their most recent conversation after June 1, 2024 and have push notifications enabled."}, {"role": "assistant", "content": "SELECT cp.user_id, MAX(cp.joined_at) AS most_recent_joined_at, us.setting_id, us.updated_at AS last_settings_update\nFROM social_media.conversation_participants cp\nLEFT JOIN social_media.user_settings us ON cp.user_id = us.user_id\nWHERE us.push_notifications_enabled = true\nGROUP BY cp.user_id, us.setting_id, us.updated_at\nHAVING MAX(cp.joined_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.conversation_participants ( participant_id text, conversation_id text, user_id text, joined_at timestamp, last_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": "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": "Show me the top 5 users who have interacted with DApps, along with the count of distinct DApps they interacted with and their wallet addresses."}, {"role": "assistant", "content": "SELECT w.user_id, COUNT(DISTINCT d.dapp_id) AS dapp_count, w.address FROM trading_platform.wallets w JOIN trading_platform.dapps d ON 1=1 GROUP BY w.user_id, w.address ORDER BY dapp_count DESC LIMIT 5;"}, {"role": "user", "content": "This query doesn't properly show DApp interactions. Please modify it to correctly join with a table that records user-DApp interactions."}, {"role": "assistant", "content": "I notice there's no interaction table in the provided schema. Without a table recording user-DApp interactions, I cannot generate this query accurately. Would you like to see users who have wallets and DApps separately instead?"}, {"role": "user", "content": "You're right. Instead, show me users who have wallets but have never interacted with any DApps, along with their wallet addresses."}, {"role": "assistant", "content": "SELECT w.user_id, w.address FROM trading_platform.wallets w WHERE NOT EXISTS (SELECT 1 FROM trading_platform.dapps d WHERE 1=1) GROUP BY w.user_id, w.address;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.wallets ( wallet_id.text, user_id.text, address.text, private_key.text, created_at.timestamp )\nCREATE TABLE trading_platform.trades ( trade_id character varying(64) NOT NULL, order_id character varying(64) NOT NULL, buyer_id character varying(64) NOT NULL, seller_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, quantity numeric(38,14) NOT NULL, price numeric(38,14) NOT NULL, traded_at timestamp NOT NULL, PRIMARY KEY (trade_id) )\nCREATE TABLE trading_platform.assets ( asset_id.text, name.text, symbol.text, type.text )\nCREATE TABLE trading_platform.dapps (\n    dapp_id character varying(64) NOT NULL,  -- unique identifier for the DApp\n    name character varying(128) NOT NULL, -- name of the DApp\n    description text NOT NULL, -- description of the DApp\n    url character varying(256) NOT NULL, -- URL of the DApp\n    PRIMARY KEY (dapp_id)\n)\nCREATE TABLE trading_platform.metadata ( metadata_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, key character varying(128) NOT NULL, value text NOT NULL, PRIMARY KEY (metadata_id) )\n"}
{"conversations": [{"role": "user", "content": "Find all smart contracts where the code length is greater than 1000 characters."}, {"role": "assistant", "content": "SELECT contract_id, creator_address, LENGTH(code) AS code_length 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 large_code_contract_count 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 large_code_contract_count FROM blockchain.smart_contracts WHERE LENGTH(code) > 1000 GROUP BY creator_address ORDER BY large_code_contract_count DESC;"}, {"role": "user", "content": "Now show only creators who have more than 3 such contracts."}, {"role": "assistant", "content": "SELECT creator_address, COUNT(*) AS large_code_contract_count FROM blockchain.smart_contracts WHERE LENGTH(code) > 1000 GROUP BY creator_address HAVING COUNT(*) > 3 ORDER BY large_code_contract_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE blockchain.smart_contracts ( contract_id.text, creator_address.text, code.text, timestamp.timestamp )\n"}
{"conversations": [{"role": "user", "content": "For each case type, calculate the average time to close cases in days, only including cases that have been closed."}, {"role": "assistant", "content": "SELECT case_type,\n       AVG(EXTRACT(EPOCH FROM (date_closed - date_opened)) / 86400) AS avg_close_days\nFROM legal_services.cases\nWHERE status = 'Closed'\n  AND date_closed IS NOT NULL\nGROUP BY case_type;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.cases ( case_id text, case_number text, case_name text, client_id text, lead_lawyer_id text, case_type text, status text, date_opened timestamp, date_closed timestamp, description text, court_jurisdiction text )\n"}
{"conversations": [{"role": "user", "content": "List all wallets holding the NFT with contract_address '0xabc123' and token_id '100' and the amount held."}, {"role": "assistant", "content": "SELECT wallet_address, amount\nFROM nft_holders\nWHERE contract_address = '0xabc123'\n  AND token_id = '100';"}, {"role": "user", "content": "Also include the NFT name from nft_metadata by joining on contract_address and token_id."}, {"role": "assistant", "content": "SELECT nh.wallet_address,\n       nh.amount,\n       nm.name\nFROM nft_holders nh\nJOIN nft_metadata nm ON nh.contract_address = nm.contract_address\n                   AND nh.token_id = nm.token_id\nWHERE nh.contract_address = '0xabc123'\n  AND nh.token_id = '100';"}, {"role": "user", "content": "Finally, add the collection name from nft_collections where blockchain is 'Ethereum'."}, {"role": "assistant", "content": "SELECT nh.wallet_address,\n       nh.amount,\n       nm.name,\n       nc.name AS collection_name\nFROM nft_holders nh\nJOIN nft_metadata nm ON nh.contract_address = nm.contract_address\n                   AND nh.token_id = nm.token_id\nJOIN nft_collections nc ON nh.contract_address = nc.contract_address\n                      AND nc.blockchain = 'Ethereum'\nWHERE nh.contract_address = '0xabc123'\n  AND nh.token_id = '100';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE erc1155_approval_for_all ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar(66) NOT NULL, log_index integer NOT NULL, contract_address varchar(42) NOT NULL )\nCREATE TABLE erc20_balances ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE erc20_balances_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_holders ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, token_id varchar NOT NULL, contract_type varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_coins_metadata ( object_id varchar NOT NULL, coin_type varchar NOT NULL, status varchar NOT NULL, decimals bigint NOT NULL, description varchar NOT NULL, icon_url varchar NOT NULL, symbol varchar NOT NULL, name varchar NOT NULL )\nCREATE TABLE sui_nfts ( object_id varchar NOT NULL, status varchar NOT NULL, collection_type varchar NOT NULL, package_id varchar NOT NULL, previous_transaction varchar NOT NULL, display varchar NOT NULL, owner varchar NOT NULL, name varchar NOT NULL )\nCREATE TABLE nft_metadata ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, token_id varchar NOT NULL, contract_name varchar NOT NULL, erc_type varchar NOT NULL, amount bigint NOT NULL, minter varchar NOT NULL, owner varchar NOT NULL, mint_block_number bigint NOT NULL, mint_time bigint NOT NULL, mint_transaction_hash varchar NOT NULL, mint_price varchar NOT NULL, token_uri varchar NOT NULL, metadata varchar NOT NULL, name varchar NOT NULL, image_uri varchar NOT NULL, traits varchar NOT NULL, updated_at bigint NOT NULL, status varchar NOT NULL, rarity_score real NOT NULL, rarity_rank integer NOT NULL, unique_attribute_count integer NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_collections ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, name varchar NOT NULL, symbol varchar NOT NULL, deploy_block_number bigint NOT NULL, deploy_block_time bigint NOT NULL, erc_type varchar NOT NULL, owner varchar NOT NULL, traits varchar NOT NULL, description varchar NOT NULL, slug varchar NOT NULL, media_info varchar NOT NULL, image_url varchar NOT NULL, banner_image_url varchar NOT NULL, updated_at bigint NOT NULL, banner varchar NOT NULL, token_count bigint NOT NULL, floor_price varchar NOT NULL, floor_price_symbol varchar NOT NULL, floor_price_contract varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_prices ( uuid varchar(36) NOT NULL, blockchain varchar(36) NOT NULL, address varchar(42) NOT NULL, decimals bigint NOT NULL, symbol varchar(36) NOT NULL, price real NOT NULL, timestamp timestamp(6) NOT NULL )\nCREATE TABLE token_prices_latest ( blockchain varchar(36) NOT NULL, address varchar(42) NOT NULL, decimals bigint NOT NULL, symbol varchar(36) NOT NULL, price real NOT NULL, timestamp timestamp(6) NOT NULL )\nCREATE TABLE erc20_approval ( block_number bigint NOT NULL, block_timestamp timestamp(6) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar NOT NULL, log_index integer NOT NULL, contract_address varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_balances ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar NOT NULL, wallet_address varchar(42) NOT NULL, total_supply decimal(38,0) NOT NULL, amount decimal(38,0) NOT NULL )\nCREATE TABLE token_info ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE token_activities ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar NOT NULL, tick varchar NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(42) NOT NULL, to_address varchar(42) NOT NULL )\nCREATE TABLE mud_holesky_redstone ( address varchar NOT NULL, table_id varchar NOT NULL, key_bytes varchar NOT NULL, key0 varchar NOT NULL, key1 varchar NOT NULL, static_data varchar NOT NULL, encoded_lengths varchar NOT NULL, dynamic_data varchar NOT NULL, is_deleted boolean NOT NULL, block_number bigint NOT NULL, log_index bigint NOT NULL )\nCREATE TABLE token_balances_bitcoin ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar(255) NOT NULL, wallet_address varchar(42) NOT NULL, total_supply varchar NOT NULL, amount varchar NOT NULL )\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar(255) NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar(20) NOT NULL, tick varchar(255) NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(62) NOT NULL, to_address varchar(62) NOT NULL )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar(20) NOT NULL, tick varchar(255) NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(42) NOT NULL, to_address varchar(42) NOT NULL )\nCREATE TABLE token_balances_avalanche ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar(20) NOT NULL, wallet_address varchar(42) NOT NULL, total_supply decimal(38,0) NOT NULL, amount decimal(38,0) NOT NULL )\n"}
{"conversations": [{"role": "user", "content": "List all unique actions that have been logged in the system."}, {"role": "assistant", "content": "SELECT DISTINCT action FROM trading_platform.logs;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.users ( user_id.text, username.text, email.text, password_hash.text, created_at.timestamp )\nCREATE TABLE trading_platform.wallets ( wallet_id text, user_id text, address text, private_key text, created_at timestamp )\nCREATE TABLE trading_platform.orders ( order_id text, user_id text, wallet_id text, asset_id text, order_type text, quantity numeric, price numeric, status text, created_at timestamp )\nCREATE TABLE trading_platform.trades ( trade_id character varying(64) NOT NULL, order_id character varying(64) NOT NULL, buyer_id character varying(64) NOT NULL, seller_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, quantity numeric(38,14) NOT NULL, price numeric(38,14) NOT NULL, traded_at timestamp NOT NULL, PRIMARY KEY (trade_id) )\nCREATE TABLE trading_platform.assets ( asset_id text, name text, symbol text, type text )\nCREATE TABLE trading_platform.dapps ( dapp_id text, name text, description text, url text )\nCREATE TABLE trading_platform.peers ( peer_id.text, ip_address.text, port.integer, last_seen.timestamp )\nCREATE TABLE trading_platform.metadata ( metadata_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, key character varying(128) NOT NULL, value text NOT NULL, PRIMARY KEY (metadata_id) )\nCREATE TABLE trading_platform.kyc_audit ( kyc_audit_id.text, user_id.text, status.text, reviewed_at.timestamp )\nCREATE TABLE trading_platform.logs ( log_id text PRIMARY KEY, user_id text, action text, details text, logged_at timestamp )\nCREATE TABLE trading_platform.notifications ( notification_id text, user_id text, message text, sent_at timestamp, read_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "How many documents are there for each document_type? Show document_type and count ordered by the count in descending order."}, {"role": "assistant", "content": "SELECT document_type,\n       COUNT(*) AS count\nFROM legal_services.documents\nGROUP BY document_type\nORDER BY count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.documents ( document_id.text, case_id.text, document_name.text, document_type.text, storage_path.text, uploaded_by_lawyer_id.text, upload_timestamp.timestamp, version.integer, description.text )\n"}
{"conversations": [{"role": "user", "content": "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": "Show me all claims with police reports that were filed in the last 3 months, along with the policy details and customer information."}, {"role": "assistant", "content": "SELECT c.claim_id, c.policy_id, c.customer_id, c.incident_date, c.reported_date, c.description, c.estimated_loss, c.status, c.settlement_amount, c.settlement_date, c.police_report_number, p.product_id, p.product_name, p.product_type, b.first_name, b.last_name, b.relationship FROM insurance.claims c JOIN insurance.insurance_products p ON c.policy_id = p.product_id JOIN insurance.policy_beneficiaries b ON c.customer_id = b.customer_id WHERE c.police_report_number IS NOT NULL AND c.reported_date >= CURRENT_DATE - INTERVAL '3 months';"}, {"role": "user", "content": "Now filter to only show claims where the estimated loss is above $10,000."}, {"role": "assistant", "content": "SELECT c.claim_id, c.policy_id, c.customer_id, c.incident_date, c.reported_date, c.description, c.estimated_loss, c.status, c.settlement_amount, c.settlement_date, c.police_report_number, p.product_id, p.product_name, p.product_type, b.first_name, b.last_name, b.relationship FROM insurance.claims c JOIN insurance.insurance_products p ON c.policy_id = p.product_id JOIN insurance.policy_beneficiaries b ON c.customer_id = b.customer_id WHERE c.police_report_number IS NOT NULL AND c.reported_date >= CURRENT_DATE - INTERVAL '3 months' AND c.estimated_loss > 10000;"}, {"role": "user", "content": "I also want to see the count of such claims per product type."}, {"role": "assistant", "content": "SELECT p.product_type, COUNT(c.claim_id) AS claim_count FROM insurance.claims c JOIN insurance.insurance_products p ON c.policy_id = p.product_id WHERE c.police_report_number IS NOT NULL AND c.reported_date >= CURRENT_DATE - INTERVAL '3 months' AND c.estimated_loss > 10000 GROUP BY p.product_type;"}, {"role": "user", "content": "Finally, show me the average estimated loss for these claims by product type."}, {"role": "assistant", "content": "SELECT p.product_type, AVG(c.estimated_loss) AS avg_estimated_loss FROM insurance.claims c JOIN insurance.insurance_products p ON c.policy_id = p.product_id WHERE c.police_report_number IS NOT NULL AND c.reported_date >= CURRENT_DATE - INTERVAL '3 months' AND c.estimated_loss > 10000 GROUP BY p.product_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 insurance.claims ( claim_id character varying(64) NOT NULL, policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, incident_date timestamp NOT NULL, reported_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, description text NOT NULL, estimated_loss numeric(15, 2), status character varying(30) NOT NULL, settlement_amount numeric(15, 2), settlement_date date, claim_handler_id character varying(64), police_report_number character varying(100), PRIMARY KEY (claim_id) )\nCREATE TABLE insurance.insurance_products ( product_id character varying(64) NOT NULL, product_name character varying(150) NOT NULL, product_type character varying(50) NOT NULL, description text, base_premium numeric(10, 2) NOT NULL, coverage_details text, underwriting_rules text, is_active boolean NOT NULL DEFAULT true, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, updated_at timestamp, PRIMARY KEY (product_id) )\nCREATE TABLE insurance.policy_beneficiaries ( beneficiary_id character varying(64) NOT NULL, policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, relationship character varying(50) NOT NULL, percentage_share numeric(5, 2) NOT NULL CHECK (percentage_share > 0 AND percentage_share <= 100), contact_info text, added_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (beneficiary_id), UNIQUE (policy_id, customer_id) )\n"}
{"conversations": [{"role": "user", "content": "Which states have the highest number of customers? Provide the top 5 states along with their customer counts, ordered by count descending."}, {"role": "assistant", "content": "SELECT\n  state,\n  COUNT(*) AS customer_count\nFROM insurance.customers\nGROUP BY state\nORDER BY customer_count DESC\nLIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.customers (\n    customer_id character varying(64) NOT NULL,  -- unique identifier for the customer\n    first_name character varying(100) NOT NULL, -- customer's first name\n    last_name character varying(100) NOT NULL, -- customer's last name\n    date_of_birth date NOT NULL, -- customer's date of birth\n    ssn_hash character varying(128), -- Hashed social security number (or national ID)\n    address_line1 character varying(255) NOT NULL,\n    address_line2 character varying(255),\n    city character varying(100) NOT NULL,\n    state character varying(50) NOT NULL,\n    zip_code character varying(20) NOT NULL,\n    country character varying(50) NOT NULL DEFAULT 'USA',\n    phone_number character varying(30),\n    email character varying(128) UNIQUE, -- unique email address\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the customer record was created\n    updated_at timestamp, -- when the customer record was last updated\n    status character varying(20) NOT NULL DEFAULT 'Active', -- e.g., Active, Inactive, Prospect\n    PRIMARY KEY (customer_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Show me the count of service orders for each distinct status."}, {"role": "assistant", "content": "SELECT status, COUNT(order_id) FROM hospitality_technology.service_orders GROUP BY status;"}, {"role": "user", "content": "Also, include the total quantity of items ordered for each status."}, {"role": "assistant", "content": "SELECT status, COUNT(order_id), SUM(quantity) FROM hospitality_technology.service_orders 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 hospitality_technology.reservations ( reservation_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, guest_id character varying(64) NOT NULL, room_id character varying(64), room_type_id character varying(64) NOT NULL, check_in_date date NOT NULL, check_out_date date NOT NULL, actual_check_in_ts timestamp with time zone, actual_check_out_ts timestamp with time zone, num_adults integer NOT NULL, num_children integer DEFAULT 0, status character varying(50) NOT NULL, booking_source character varying(100), rate_plan_id character varying(64), total_amount numeric(12, 2), amount_paid numeric(12, 2) DEFAULT 0.00, special_requests text, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (reservation_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (room_id) REFERENCES hospitality_technology.rooms(room_id), FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id) )\nCREATE TABLE hospitality_technology.service_orders ( order_id text PRIMARY KEY, reservation_id text, guest_id text, service_id text, staff_id_ordered text, staff_id_delivered text, order_timestamp timestamp, delivery_timestamp timestamp, quantity int, unit_price numeric, total_price numeric, status text, notes text, bill_id text )\n"}
{"conversations": [{"role": "user", "content": "Show all rooms that are on floor 3."}, {"role": "assistant", "content": "SELECT room_id, property_id, room_number FROM hospitality_technology.rooms WHERE floor = 3;"}, {"role": "user", "content": "For these rooms, include the property name and room number."}, {"role": "assistant", "content": "SELECT r.room_number, p.property_name FROM hospitality_technology.rooms AS r JOIN hospitality_technology.properties AS p ON r.property_id = p.property_id WHERE r.floor = 3;"}, {"role": "user", "content": "Also, include the type name and current status for each room."}, {"role": "assistant", "content": "SELECT r.room_number, p.property_name, rt.type_name, r.status FROM hospitality_technology.rooms AS r JOIN hospitality_technology.properties AS p ON r.property_id = p.property_id JOIN hospitality_technology.room_types AS rt ON r.room_type_id = rt.room_type_id AND r.property_id = rt.property_id WHERE r.floor = 3;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.properties ( property_id text, property_name text, address_line1 text, address_line2 text, city text, state_province text, postal_code text, country_code text, phone_number text, email_address text, property_type text, star_rating numeric, timezone text, manager_staff_id text, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.rooms ( room_id text, property_id text, room_number text, room_type_id text, floor integer, status text, is_smoking boolean, features text, current_condition text, last_cleaned_at timestamp )\nCREATE TABLE hospitality_technology.room_types ( room_type_id text, property_id text, type_name text, description text, base_rate numeric, max_occupancy integer, bed_type text, area_sqft numeric, amenities text )\n"}