{"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": "List all guests who have not provided their date of birth, along with their email if available."}, {"role": "assistant", "content": "SELECT guest_id, first_name, last_name, email FROM hospitality_technology.guests WHERE date_of_birth IS NULL;"}, {"role": "user", "content": "Now, filter these results to only include guests from the USA."}, {"role": "assistant", "content": "SELECT guest_id, first_name, last_name, email FROM hospitality_technology.guests WHERE date_of_birth IS NULL AND country_code = 'USA';"}, {"role": "user", "content": "The query is missing their city information. Can you include that as well?"}, {"role": "assistant", "content": "SELECT guest_id, first_name, last_name, email, city FROM hospitality_technology.guests WHERE date_of_birth IS NULL AND country_code = 'USA';"}, {"role": "user", "content": "Actually, I need to see the results ordered by created_at in descending order."}, {"role": "assistant", "content": "SELECT guest_id, first_name, last_name, email, city, created_at FROM hospitality_technology.guests WHERE date_of_birth IS NULL AND country_code = 'USA' ORDER BY created_at DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.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 nodes that were last seen after January 1, 2023, along with their IP addresses and ports."}, {"role": "assistant", "content": "SELECT node_id, ip_address, port FROM blockchain.nodes WHERE last_seen > '2023-01-01 00:00:00';"}, {"role": "user", "content": "Now, filter these results to only show nodes with a port number greater than 5000."}, {"role": "assistant", "content": "SELECT node_id, ip_address, port FROM blockchain.nodes WHERE last_seen > '2023-01-01 00:00:00' AND port > 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 blockchain.nodes ( node_id text PRIMARY KEY, ip_address text, port int, last_seen timestamp )\n"}
{"conversations": [{"role": "user", "content": "Get the total ERC20 balance per contract_address across all wallets from erc20_balances."}, {"role": "assistant", "content": "SELECT contract_address,\n       SUM(CAST(amount AS NUMERIC)) AS total_balance\nFROM erc20_balances\nGROUP BY contract_address\nORDER BY total_balance DESC;"}, {"role": "user", "content": "Include the token symbol, decimals, and its latest USD price from token_prices."}, {"role": "assistant", "content": "WITH latest_price AS (\n  SELECT tp.address AS contract_address,\n         tp.symbol,\n         tp.decimals,\n         tp.price AS usd_price\n  FROM token_prices tp\n  JOIN (\n    SELECT address, MAX(timestamp) AS max_ts\n    FROM token_prices\n    GROUP BY address\n  ) l ON tp.address = l.address AND tp.timestamp = l.max_ts\n)\nSELECT b.contract_address,\n       lp.symbol,\n       lp.decimals,\n       SUM(CAST(b.amount AS NUMERIC)) AS total_balance,\n       lp.usd_price\nFROM erc20_balances b\nLEFT JOIN latest_price lp\n  ON b.contract_address = lp.contract_address\nGROUP BY b.contract_address, lp.symbol, lp.decimals, lp.usd_price\nORDER BY total_balance DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE erc20_balances ( block_number bigint, contract_address varchar, wallet_address varchar, amount varchar, pk varchar )\nCREATE TABLE erc20_balances_historical ( block_number bigint, contract_address text, wallet_address text, amount text, pk integer )\nCREATE TABLE nft_holders ( block_number.bigint, contract_address.text, wallet_address.text, token_id.text, contract_type.text, amount.text, pk.text )\nCREATE TABLE nft_holder_historical (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    contract_address varchar NOT NULL, -- Event contract address\n    wallet_address varchar NOT NULL, -- The wallet address for the contract(with bloom filter)\n    token_id varchar NOT NULL, -- NFT token id\n    contract_type varchar NOT NULL, -- NFT contract type\n    amount varchar NOT NULL, -- The quantity held in the wallet\n    pk integer NOT NULL  -- Partition key for the table(floor(block_number / 7200))\n)\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_coins_metadata (\n    object_id varchar NOT NULL, -- object id of the coin metadata object\n    coin_type varchar NOT NULL, -- coin type, eg. 0x...66::reap_token::REAP_TOKEN\n    status varchar NOT NULL, -- coin status, eg. exists, deleted\n    decimals bigint NOT NULL, -- decimals of the coin\n    description varchar NOT NULL, -- description of the coin\n    icon_url varchar NOT NULL, -- icon url of the coin\n    symbol varchar NOT NULL, -- symbol of the coin\n    name varchar NOT NULL  -- name of the coin\n)\nCREATE TABLE nft_metadata ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, token_id varchar NOT NULL, contract_name varchar NOT NULL, erc_type varchar NOT NULL, amount bigint NOT NULL, minter varchar NOT NULL, owner varchar NOT NULL, mint_block_number bigint NOT NULL, mint_time bigint NOT NULL, mint_transaction_hash varchar NOT NULL, mint_price varchar NOT NULL, token_uri varchar NOT NULL, metadata varchar NOT NULL, name varchar NOT NULL, image_uri varchar NOT NULL, traits varchar NOT NULL, updated_at bigint NOT NULL, status varchar NOT NULL, rarity_score real NOT NULL, rarity_rank integer NOT NULL, unique_attribute_count integer NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_collections ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, name varchar NOT NULL, symbol varchar NOT NULL, deploy_block_number bigint NOT NULL, deploy_block_time bigint NOT NULL, erc_type varchar NOT NULL, owner varchar NOT NULL, traits varchar NOT NULL, description varchar NOT NULL, slug varchar NOT NULL, media_info varchar NOT NULL, image_url varchar NOT NULL, banner_image_url varchar NOT NULL, updated_at bigint NOT NULL, banner varchar NOT NULL, token_count bigint NOT NULL, floor_price varchar NOT NULL, floor_price_symbol varchar NOT NULL, floor_price_contract varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_prices ( uuid.text, blockchain.text, address.text, decimals.bigint, symbol.text, price.real, timestamp.timestamp )\nCREATE TABLE token_balances (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n    tick varchar NOT NULL, -- Token tick\n    wallet_address varchar(42) NOT NULL, -- Address of owner\n    total_supply decimal(38,0) NOT NULL, -- Max supply\n    amount decimal(38,0) NOT NULL  -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_activities ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\nCREATE TABLE mud_holesky_redstone ( address text, table_id text, key_bytes text, key0 text, key1 text, static_data text, encoded_lengths text, dynamic_data text, is_deleted boolean, block_number bigint, log_index bigint )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\nCREATE TABLE token_balances_avalanche (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n    tick varchar(20) NOT NULL, -- Ticker: Identifier of the inscription\n    wallet_address varchar(42) NOT NULL, -- Address of owner\n    total_supply decimal(38,0) NOT NULL, -- Max supply: Set max supply of the inscription\n    amount decimal(38,0) NOT NULL  -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id varchar )\n"}
{"conversations": [{"role": "user", "content": "Show 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 service locations are not accessible and belong to agencies with a jurisdiction level of 'Local'? Show the location name and city."}, {"role": "assistant", "content": "SELECT sl.location_name, sl.city\nFROM government_services.service_locations sl\nINNER JOIN government_services.agencies a ON sl.agency_id = a.agency_id\nWHERE sl.is_accessible = FALSE\n  AND a.jurisdiction_level = 'Local';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.agencies ( agency_id text, agency_name text, jurisdiction_level text, primary_contact_email text, main_phone_number text, website_url text, established_date date, parent_agency_id text )\nCREATE TABLE government_services.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.service_locations (\n    location_id character varying(64) NOT NULL, -- unique identifier for the physical location\n    agency_id character varying(64) NOT NULL, -- FK to agencies table\n    location_name character varying(200), -- e.g., Downtown DMV Office\n    address text NOT NULL,\n    city character varying(100),\n    state character varying(50),\n    postal_code character varying(20),\n    latitude numeric(9, 6),\n    longitude numeric(9, 6),\n    operating_hours text, -- description of opening times\n    contact_phone character varying(32),\n    is_accessible boolean, -- accessibility information (e.g., wheelchair access)\n    PRIMARY KEY (location_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Show the 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": "For each player, show how many achievements they have unlocked in games with items of type 'Consumable'."}, {"role": "assistant", "content": "SELECT pa.player_id, COUNT(DISTINCT pa.achievement_id) AS achievements_unlocked\nFROM gaming_technology.player_achievements pa\nJOIN gaming_technology.in_game_items i ON pa.achievement_id IS NOT NULL AND i.item_type = 'Consumable'\nGROUP BY pa.player_id;"}, {"role": "user", "content": "This query didn't run because achievements and items aren't directly related. Can you instead count, for each player, the number of unique achievements unlocked in any game that contains at least one consumable item?"}, {"role": "assistant", "content": "SELECT pa.player_id, COUNT(DISTINCT pa.achievement_id) AS achievements_unlocked\nFROM gaming_technology.player_achievements pa\nJOIN gaming_technology.in_game_items igi ON igi.item_type = 'Consumable'\nJOIN gaming_technology.achievements a ON pa.achievement_id = a.achievement_id AND a.game_id = igi.game_id\nGROUP BY pa.player_id;"}, {"role": "user", "content": "Sorry, my schema doesn't have an achievements table. Can you instead show, for each player, the total number of distinct achievements they've unlocked in games that have any items of type 'Consumable' in in_game_items?"}, {"role": "assistant", "content": "SELECT pa.player_id, COUNT(DISTINCT pa.achievement_id) AS achievements_unlocked\nFROM gaming_technology.player_achievements pa\nWHERE pa.achievement_id IN (\n    SELECT DISTINCT pa2.achievement_id\n    FROM gaming_technology.player_achievements pa2\n    JOIN gaming_technology.in_game_items igi ON pa2.achievement_id IS NOT NULL AND igi.item_type = 'Consumable'\n)\nGROUP BY pa.player_id;"}, {"role": "user", "content": "Now, only show players who have unlocked more than 3 such achievements."}, {"role": "assistant", "content": "SELECT pa.player_id, COUNT(DISTINCT pa.achievement_id) AS achievements_unlocked\nFROM gaming_technology.player_achievements pa\nWHERE pa.achievement_id IN (\n    SELECT DISTINCT pa2.achievement_id\n    FROM gaming_technology.player_achievements pa2\n    JOIN gaming_technology.in_game_items igi ON pa2.achievement_id IS NOT NULL AND igi.item_type = 'Consumable'\n)\nGROUP BY pa.player_id\nHAVING COUNT(DISTINCT pa.achievement_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 gaming_technology.developers ( developer_id uuid PRIMARY KEY, name text, country text, founded_year int, website text, created_at timestamptz )\nCREATE TABLE gaming_technology.game_sessions ( session_id uuid PRIMARY KEY, player_id uuid, game_id uuid, server_id uuid, start_time timestamptz, end_time timestamptz, duration_seconds int, score int, session_data jsonb )\nCREATE TABLE gaming_technology.servers ( server_id.uuid, game_id.uuid, server_name.text, region.text, ip_address.text, port.integer, current_players.integer, max_players.integer, status.text, last_heartbeat.timestamptz )\nCREATE TABLE gaming_technology.player_achievements ( player_achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), player_id uuid NOT NULL, achievement_id uuid NOT NULL, unlocked_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (player_achievement_id), UNIQUE (player_id, achievement_id) )\nCREATE TABLE gaming_technology.in_game_items ( item_id uuid, game_id uuid, item_name text, item_type text, description text, rarity text, cost_currency text, cost_amount numeric, attributes jsonb )\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 nodes that share the same IP address but have different node_ids."}, {"role": "assistant", "content": "SELECT n1.ip_address, n1.node_id as node_id1, n2.node_id as node_id2 FROM blockchain.nodes n1 JOIN blockchain.nodes n2 ON n1.ip_address = n2.ip_address AND n1.node_id != n2.node_id;"}, {"role": "user", "content": "Now, modify this to only show IP addresses that have more than 2 nodes associated with them."}, {"role": "assistant", "content": "SELECT ip_address, COUNT(node_id) as node_count FROM blockchain.nodes GROUP BY ip_address HAVING COUNT(node_id) > 2;"}, {"role": "user", "content": "Can you also include the earliest and latest last_seen timestamps for each of these IP addresses?"}, {"role": "assistant", "content": "SELECT ip_address, COUNT(node_id) as node_count, MIN(last_seen) as earliest_seen, MAX(last_seen) as latest_seen FROM blockchain.nodes GROUP BY ip_address HAVING COUNT(node_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 blockchain.nodes ( node_id text PRIMARY KEY, ip_address text, port int, last_seen timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show me the list of hashtags that have been used, along with the time they were first used."}, {"role": "assistant", "content": "SELECT tag_name, created_at \nFROM social_media.hashtags;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users (\n    user_id character varying(64) NOT NULL,  -- unique identifier for the user\n    username character varying(50) NOT NULL UNIQUE, -- user's unique handle\n    email character varying(128) NOT NULL UNIQUE, -- user's email address\n    password_hash text NOT NULL, -- hashed password\n    full_name character varying(100), -- user's full name\n    profile_picture_url text, -- URL to the profile picture\n    bio text, -- short user biography\n    location character varying(100), -- user's location\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of account creation\n    updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last profile update\n    is_verified boolean NOT NULL DEFAULT false, -- verification status\n    PRIMARY KEY (user_id)\n)\nCREATE TABLE social_media.comments (\n    comment_id character varying(64) NOT NULL, -- unique identifier for the comment\n    post_id character varying(64) NOT NULL, -- identifier of the post being commented on (FK to posts.post_id)\n    user_id character varying(64) NOT NULL, -- identifier of the user who made the comment (FK to users.user_id)\n    parent_comment_id character varying(64), -- identifier of the parent comment if it's a reply (FK to comments.comment_id)\n    content text NOT NULL, -- textual content of the comment\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of comment creation\n    updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last comment edit\n    PRIMARY KEY (comment_id)\n)\nCREATE TABLE social_media.likes (\n    like_id character varying(64) NOT NULL, -- unique identifier for the like\n    user_id character varying(64) NOT NULL, -- identifier of the user who liked (FK to users.user_id)\n    post_id character varying(64), -- identifier of the post being liked (FK to posts.post_id, nullable)\n    comment_id character varying(64), -- identifier of the comment being liked (FK to comments.comment_id, nullable)\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of when the like occurred\n    PRIMARY KEY (like_id),\n    CONSTRAINT unique_user_like UNIQUE (user_id, post_id, comment_id), -- prevent duplicate likes\n    CONSTRAINT check_like_target CHECK (post_id IS NOT NULL OR comment_id IS NOT NULL) -- ensure it likes something\n)\nCREATE TABLE social_media.follows (\n    follow_id character varying(64) NOT NULL, -- unique identifier for the follow relationship\n    follower_user_id character varying(64) NOT NULL, -- identifier of the user who is following (FK to users.user_id)\n    following_user_id character varying(64) NOT NULL, -- identifier of the user being followed (FK to users.user_id)\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of when the follow started\n    PRIMARY KEY (follow_id),\n    CONSTRAINT unique_follow UNIQUE (follower_user_id, following_user_id) -- prevent duplicate follows\n)\nCREATE TABLE social_media.hashtags (\n    hashtag_id character varying(64) NOT NULL, -- unique identifier for the hashtag\n    tag_name character varying(100) NOT NULL UNIQUE, -- the actual hashtag text (without '#')\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when the hashtag was first used\n    PRIMARY KEY (hashtag_id)\n)\nCREATE TABLE social_media.post_hashtags (\n    post_hashtag_id character varying(64) NOT NULL, -- unique identifier for the post-hashtag link\n    post_id character varying(64) NOT NULL, -- identifier of the post (FK to posts.post_id)\n    hashtag_id character varying(64) NOT NULL, -- identifier of the hashtag (FK to hashtags.hashtag_id)\n    PRIMARY KEY (post_hashtag_id),\n    CONSTRAINT unique_post_hashtag UNIQUE (post_id, hashtag_id) -- prevent duplicate tags on a post\n)\nCREATE TABLE social_media.messages (\n    message_id character varying(64) NOT NULL, -- unique identifier for the message\n    conversation_id character varying(64) NOT NULL, -- identifier for the conversation thread (FK to conversations.conversation_id)\n    sender_user_id character varying(64) NOT NULL, -- identifier of the sender (FK to users.user_id)\n    content text, -- textual content of the message\n    media_url text, -- URL to attached media (image/video)\n    media_type character varying(20), -- type of media ('image', 'video', null)\n    sent_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when message was sent\n    read_at timestamp, -- timestamp when message was read by recipient(s)\n    PRIMARY KEY (message_id)\n)\nCREATE TABLE social_media.conversations (\n    conversation_id character varying(64) NOT NULL, -- unique identifier for the conversation\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when conversation was initiated\n    last_message_at timestamp, -- timestamp of the last message in the conversation\n    is_group_chat boolean NOT NULL DEFAULT false, -- indicates if it's a group chat or direct message\n    group_name character varying(100), -- name of the group chat (if applicable)\n    PRIMARY KEY (conversation_id)\n)\nCREATE TABLE social_media.conversation_participants (\n    participant_id character varying(64) NOT NULL, -- unique identifier for the participant entry\n    conversation_id character varying(64) NOT NULL, -- identifier of the conversation (FK to conversations.conversation_id)\n    user_id character varying(64) NOT NULL, -- identifier of the user in the conversation (FK to users.user_id)\n    joined_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when user joined the conversation\n    last_read_at timestamp, -- timestamp indicating up to when the user has read messages\n    PRIMARY KEY (participant_id),\n    CONSTRAINT unique_user_conversation UNIQUE (conversation_id, user_id) -- prevent user being added multiple times\n)\nCREATE TABLE social_media.notifications (\n    notification_id character varying(64) NOT NULL, -- unique identifier for the notification\n    recipient_user_id character varying(64) NOT NULL, -- user receiving the notification (FK to users.user_id)\n    sender_user_id character varying(64), -- user triggering the notification (FK to users.user_id, can be null for system notifications)\n    notification_type character varying(30) NOT NULL, -- type of notification ('like', 'comment', 'follow', 'mention', 'message')\n    target_entity_id character varying(64), -- ID of the related entity (post_id, comment_id, user_id, conversation_id)\n    target_entity_type character varying(20), -- type of the related entity ('post', 'comment', 'user', 'conversation')\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp notification was created\n    read_at timestamp, -- timestamp notification was marked as read\n    PRIMARY KEY (notification_id)\n)\nCREATE TABLE social_media.user_settings (\n    setting_id character varying(64) NOT NULL, -- unique identifier for the setting entry\n    user_id character varying(64) NOT NULL UNIQUE, -- user the settings belong to (FK to users.user_id)\n    theme character varying(20) DEFAULT 'light', -- UI theme ('light', 'dark')\n    email_notifications_enabled boolean DEFAULT true, -- enable/disable email notifications\n    push_notifications_enabled boolean DEFAULT true, -- enable/disable push notifications\n    private_profile boolean DEFAULT false, -- is the user profile private\n    updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last setting change\n    PRIMARY KEY (setting_id)\n)\n"}
{"conversations": [{"role": "user", "content": "For each Avalanche token tick, calculate the total transfer volume and transaction count over the past 7 days using token_activities_avalanche. Include the token tick, total_volume, and tx_count."}, {"role": "assistant", "content": "SELECT\n  tick,\n  SUM(amt) AS total_volume,\n  COUNT(*) AS tx_count\nFROM token_activities_avalanche\nWHERE block_timestamp >= CURRENT_DATE - INTERVAL '7 days'\nGROUP BY tick;"}, {"role": "user", "content": "Also include the creator address from token_info for each tick, and filter where total_volume > 1000 and creator starts with '0x1'."}, {"role": "assistant", "content": "SELECT\n  a.tick,\n  SUM(a.amt) AS total_volume,\n  COUNT(*) AS tx_count,\n  i.creator\nFROM token_activities_avalanche a\nJOIN token_info i\n  ON a.tick = i.tick\nWHERE a.block_timestamp >= CURRENT_DATE - INTERVAL '7 days'\nGROUP BY a.tick, i.creator\nHAVING SUM(a.amt) > 1000\n  AND i.creator LIKE '0x1%';"}, {"role": "user", "content": "Sort the results by total_volume descending and limit to the top 5 tokens."}, {"role": "assistant", "content": "SELECT\n  a.tick,\n  SUM(a.amt) AS total_volume,\n  COUNT(*) AS tx_count,\n  i.creator\nFROM token_activities_avalanche a\nJOIN token_info i\n  ON a.tick = i.tick\nWHERE a.block_timestamp >= CURRENT_DATE - INTERVAL '7 days'\nGROUP BY a.tick, i.creator\nHAVING SUM(a.amt) > 1000\n  AND i.creator LIKE '0x1%'\nORDER BY total_volume DESC\nLIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp.timestamp, block_number.bigint, transaction_hash.text, transaction_index.bigint, from_address.text, contract_address.text, symbol.text, total_supply.text, name.text, decimals.bigint, is_erc20.integer, is_erc721.integer, is_erc1155.integer, is_proxy.integer, extra_info.text, pk.integer )\nCREATE TABLE erc1155_approval_for_all (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the transaction\n    transaction_index integer NOT NULL, -- Index of the transaction within the block\n    transaction_hash varchar(66) NOT NULL, -- Transaction hash\n    log_index integer NOT NULL, -- Log index\n    contract_address varchar(42) NOT NULL  -- Event contract address\n)\nCREATE TABLE erc20_balances_historical ( block_number bigint, 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_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 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 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_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 )\n"}
{"conversations": [{"role": "user", "content": "Show the guest's full name, reservation ID, check-in date, and status for all reservations made via 'Phone'."}, {"role": "assistant", "content": "SELECT g.first_name, g.last_name, r.reservation_id, r.check_in_date, r.status FROM hospitality_technology.reservations r JOIN hospitality_technology.guests g ON r.guest_id = g.guest_id WHERE r.booking_source = 'Phone';"}, {"role": "user", "content": "Now, only show reservations with a status of 'Confirmed' or 'Pending'."}, {"role": "assistant", "content": "SELECT g.first_name, g.last_name, r.reservation_id, r.check_in_date, r.status FROM hospitality_technology.reservations r JOIN hospitality_technology.guests g ON r.guest_id = g.guest_id WHERE r.booking_source = 'Phone' AND r.status IN ('Confirmed', 'Pending');"}, {"role": "user", "content": "Sort the results by check-in date descending and limit to the first 20."}, {"role": "assistant", "content": "SELECT g.first_name, g.last_name, r.reservation_id, r.check_in_date, r.status FROM hospitality_technology.reservations r JOIN hospitality_technology.guests g ON r.guest_id = g.guest_id WHERE r.booking_source = 'Phone' AND r.status IN ('Confirmed', 'Pending') ORDER BY r.check_in_date DESC LIMIT 20;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.guests ( guest_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, email character varying(255) UNIQUE, phone_number character varying(30), date_of_birth date, address_line1 character varying(255), city character varying(100), state_province character varying(100), postal_code character varying(20), country_code character varying(3), preferences text, loyalty_member_id character varying(64) UNIQUE, communication_consent boolean DEFAULT true, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (guest_id) )\nCREATE TABLE hospitality_technology.reservations (\n    reservation_id character varying(64) NOT NULL,  -- unique identifier for the booking\n    property_id character varying(64) NOT NULL, -- FK to properties table\n    guest_id character varying(64) NOT NULL, -- FK to guests table (primary guest)\n    room_id character varying(64), -- FK to rooms table (assigned room, might be null initially)\n    room_type_id character varying(64) NOT NULL, -- FK to room_types table (booked room type)\n    check_in_date date NOT NULL, -- scheduled check-in date\n    check_out_date date NOT NULL, -- scheduled check-out date\n    actual_check_in_ts timestamp with time zone, -- actual check-in time\n    actual_check_out_ts timestamp with time zone, -- actual check-out time\n    num_adults integer NOT NULL, -- number of adults\n    num_children integer DEFAULT 0, -- number of children\n    status character varying(50) NOT NULL, -- e.g., Pending, Confirmed, CheckedIn, CheckedOut, Cancelled, NoShow\n    booking_source character varying(100), -- e.g., Website, OTA (Expedia, Booking.com), Phone, WalkIn\n    rate_plan_id character varying(64), -- FK to rate_plans table (optional)\n    total_amount numeric(12, 2), -- estimated or final total cost\n    amount_paid numeric(12, 2) DEFAULT 0.00, -- amount already paid\n    special_requests text, -- specific guest requests for this booking\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (reservation_id),\n    FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n    FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id),\n    FOREIGN KEY (room_id) REFERENCES hospitality_technology.rooms(room_id),\n    FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id)\n)\nCREATE TABLE hospitality_technology.staff (\n    staff_id character varying(64) NOT NULL,  -- unique identifier for the staff member\n    property_id character varying(64) NOT NULL, -- FK to properties table (primary property)\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    position character varying(100) NOT NULL, -- e.g., Front Desk Agent, Housekeeper, Manager, Concierge\n    work_email character varying(255) UNIQUE, -- staff member's work email\n    work_phone character varying(30),\n    hire_date date NOT NULL,\n    termination_date date, -- date employment ended (if applicable)\n    is_active boolean NOT NULL DEFAULT true, -- currently employed flag\n    access_level integer NOT NULL, -- permission level within systems (e.g., 1=basic, 5=admin)\n    manager_id character varying(64), -- FK to staff table (self-referencing for supervisor)\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (staff_id),\n    FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n    FOREIGN KEY (manager_id) REFERENCES hospitality_technology.staff(staff_id)\n)\nCREATE TABLE hospitality_technology.services ( service_id.text, property_id.text, service_name.text, description.text, category.text, price.numeric, unit.text, is_available.boolean, department.text )\n"}
{"conversations": [{"role": "user", "content": "Calculate the average total amount and average amount paid for reservations grouped by booking source."}, {"role": "assistant", "content": "SELECT booking_source, AVG(total_amount) AS avg_total_amount, AVG(amount_paid) AS avg_amount_paid FROM hospitality_technology.reservations GROUP BY booking_source;"}, {"role": "user", "content": "Now, only include booking sources where the average total amount is greater than 500 and sort the results by average total amount descending."}, {"role": "assistant", "content": "SELECT booking_source, AVG(total_amount) AS avg_total_amount, AVG(amount_paid) AS avg_amount_paid FROM hospitality_technology.reservations GROUP BY booking_source HAVING AVG(total_amount) > 500 ORDER BY avg_total_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 hospitality_technology.reservations ( reservation_id text, property_id text, guest_id text, room_id text, room_type_id text, check_in_date date, check_out_date date, actual_check_in_ts timestamp, actual_check_out_ts timestamp, num_adults integer, num_children integer, status text, booking_source text, rate_plan_id text, total_amount numeric, amount_paid numeric, special_requests text, created_at timestamp, updated_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show me all vehicles that had maintenance in the past month, including their make, model, maintenance service_date, and depot name."}, {"role": "assistant", "content": "SELECT v.vehicle_id,\n       v.make,\n       v.model,\n       m.service_date,\n       l.name AS depot_name\nFROM transportation.maintenance_logs AS m\nJOIN transportation.vehicles AS v\n  ON m.vehicle_id = v.vehicle_id\nLEFT JOIN transportation.locations AS l\n  ON v.depot_id = l.location_id\nWHERE m.service_date >= CURRENT_DATE - INTERVAL '1 month';"}, {"role": "user", "content": "Now, include only those records where the maintenance cost is greater than 500, and order the results by cost descending."}, {"role": "assistant", "content": "SELECT v.vehicle_id,\n       v.make,\n       v.model,\n       m.service_date,\n       m.cost,\n       l.name AS depot_name\nFROM transportation.maintenance_logs AS m\nJOIN transportation.vehicles AS v\n  ON m.vehicle_id = v.vehicle_id\nLEFT JOIN transportation.locations AS l\n  ON v.depot_id = l.location_id\nWHERE m.service_date >= CURRENT_DATE - INTERVAL '1 month'\n  AND m.cost > 500\nORDER BY m.cost DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles ( vehicle_id.text, license_plate.text, vin.text, make.text, model.text, year.integer, type.text, capacity.integer, fuel_type.text, status.text, depot_id.text, acquisition_date.date )\nCREATE TABLE transportation.drivers ( driver_id.text, employee_id.text, first_name.text, last_name.text, license_number.text, license_expiry_date.date, contact_number.text, email.text, hire_date.date, status.text )\nCREATE TABLE transportation.locations ( location_id.text, name.text, type.text, address_line1.text, city.text, state_province.text, postal_code.text, country.text, latitude.numeric, longitude.numeric, timezone.text )\nCREATE TABLE transportation.maintenance_logs ( log_id.text, vehicle_id.text, service_date.date, odometer_reading.integer, service_type.text, description.text, cost.numeric, mechanic_name.text, next_service_due_date.date )\nCREATE TABLE transportation.passengers ( passenger_id.text, first_name.text, last_name.text, email.text, phone_number.text, date_of_birth.date, loyalty_program_id.text, created_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "What is the reason behind the cost variation for maintenance of asset_id 'ASSET456' over the past year?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information on the reasons behind cost variations for maintenance. The data in the maintenance_records table includes only the cost amount and other basic details of each maintenance record, but it does not contain explanations or factors influencing cost changes."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.maintenance_records ( record_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, asset_type character varying(32) NOT NULL, maintenance_type character varying(128) NOT NULL, staff_id character varying(64), start_datetime timestamp NOT NULL, end_datetime timestamp, description text NOT NULL, cost numeric(12, 2), status character varying(32) NOT NULL DEFAULT 'Completed', PRIMARY KEY (record_id), FOREIGN KEY (staff_id) REFERENCES train_station_management.staff(staff_id) )\n"}
{"conversations": [{"role": "user", "content": "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 the content and sent time for messages sent by user 'U101'."}, {"role": "assistant", "content": "SELECT content, sent_at FROM social_media.messages WHERE sender_user_id = 'U101';"}, {"role": "user", "content": "Could you also include the group name for those messages and only show messages sent in group chats?"}, {"role": "assistant", "content": "SELECT m.content, m.sent_at, c.name AS group_name FROM social_media.messages m JOIN social_media.conversations c ON m.conversation_id = c.conversation_id WHERE m.sender_user_id = 'U101' AND c.type = 'group';"}, {"role": "user", "content": "Now filter to include only messages sent in June 2024 and order them by sent time descending."}, {"role": "assistant", "content": "SELECT m.content, m.sent_at, c.name AS group_name FROM social_media.messages m JOIN social_media.conversations c ON m.conversation_id = c.conversation_id WHERE m.sender_user_id = 'U101' AND c.type = 'group' AND m.sent_at >= '2024-06-01' AND m.sent_at < '2024-07-01' ORDER BY m.sent_at DESC;"}, {"role": "user", "content": "Also limit the results to the top 15."}, {"role": "assistant", "content": "SELECT m.content, m.sent_at, c.name AS group_name FROM social_media.messages m JOIN social_media.conversations c ON m.conversation_id = c.conversation_id WHERE m.sender_user_id = 'U101' AND c.type = 'group' AND m.sent_at >= '2024-06-01' AND m.sent_at < '2024-07-01' ORDER BY m.sent_at DESC LIMIT 15;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.messages (\n    message_id character varying(64) NOT NULL, -- unique identifier for the message\n    conversation_id character varying(64) NOT NULL, -- identifier for the conversation thread (FK to conversations.conversation_id)\n    sender_user_id character varying(64) NOT NULL, -- identifier of the sender (FK to users.user_id)\n    content text, -- textual content of the message\n    media_url text, -- URL to attached media (image/video)\n    media_type character varying(20), -- type of media ('image', 'video', null)\n    sent_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when message was sent\n    read_at timestamp, -- timestamp when message was read by recipient(s)\n    PRIMARY KEY (message_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List all staff members who processed payments for guest ID 'G123', including their first name, last name, and the payment ID."}, {"role": "assistant", "content": "SELECT T1.first_name, T1.last_name, T2.payment_id FROM staff AS T1 JOIN payments AS T2 ON T1.staff_id = T2.staff_id_processed WHERE T2.guest_id = 'G123';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.staff ( staff_id text PRIMARY KEY, property_id text, first_name text, last_name text, position text, work_email text, work_phone text, hire_date date, termination_date date, is_active boolean, access_level int, manager_id text, created_at timestamp )\nCREATE TABLE hospitality_technology.services ( service_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, service_name character varying(150) NOT NULL, description text, category character varying(100), price numeric(10, 2) NOT NULL, unit character varying(30), is_available boolean NOT NULL DEFAULT true, department character varying(100), PRIMARY KEY (service_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id) )\nCREATE TABLE hospitality_technology.payments ( 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 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": "Show the total number of bookings grouped by payment_transaction_id."}, {"role": "assistant", "content": "SELECT payment_transaction_id, COUNT(*) AS booking_count FROM transportation.bookings GROUP BY payment_transaction_id;"}, {"role": "user", "content": "Exclude entries with null payment_transaction_id and order the results by the booking count descending."}, {"role": "assistant", "content": "SELECT payment_transaction_id, COUNT(*) AS booking_count FROM transportation.bookings WHERE payment_transaction_id IS NOT NULL GROUP BY payment_transaction_id ORDER BY booking_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles ( vehicle_id text PRIMARY KEY, license_plate text, vin text, make text, model text, year int, type text, capacity int, fuel_type text, status text, depot_id text, acquisition_date date )\nCREATE TABLE transportation.drivers ( driver_id text PRIMARY KEY, employee_id text, first_name text, last_name text, license_number text, license_expiry_date date, contact_number text, email text, hire_date date, status text )\nCREATE TABLE transportation.routes ( route_id text PRIMARY KEY, route_number text, description text, origin_location_id text, destination_location_id text, distance_km numeric, estimated_duration_minutes int, type text )\nCREATE TABLE transportation.trips ( trip_id text PRIMARY KEY, route_id text, vehicle_id text, driver_id text, scheduled_departure timestamp, actual_departure timestamp, scheduled_arrival timestamp, actual_arrival timestamp, origin_location_id text, destination_location_id text, status text, passenger_count int, cargo_manifest_id text )\nCREATE TABLE transportation.locations ( location_id text PRIMARY KEY, name text, type text, address_line1 text, city text, state_province text, postal_code text, country text, latitude numeric, longitude numeric, timezone text )\nCREATE TABLE transportation.maintenance_logs ( log_id text PRIMARY KEY, vehicle_id text, service_date date, odometer_reading int, service_type text, description text, cost numeric, mechanic_name text, next_service_due_date date )\nCREATE TABLE transportation.fuel_logs ( fuel_log_id text PRIMARY KEY, vehicle_id text, trip_id text, log_timestamp timestamp, fuel_type text, quantity numeric, unit text, cost_per_unit numeric, total_cost numeric, odometer_reading int, location_id text )\nCREATE TABLE transportation.bookings ( booking_id text PRIMARY KEY, passenger_id text, trip_id text, seat_number text, booking_time timestamp, status text, fare numeric, payment_transaction_id text, special_requests text )\n"}
{"conversations": [{"role": "user", "content": "What 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 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": "Count the number of logs for each action type."}, {"role": "assistant", "content": "SELECT action,\n       COUNT(*) AS count\nFROM trading_platform.logs\nGROUP BY action;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.logs ( log_id text PRIMARY KEY, user_id text, action text, details text, logged_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "List usernames and the length of their 'bio' field for users whose 'is_verified' status is true."}, {"role": "assistant", "content": "SELECT username, LENGTH(bio) AS bio_length FROM social_media.users WHERE is_verified IS TRUE;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id text PRIMARY KEY, username text, email text, password_hash text, full_name text, profile_picture_url text, bio text, location text, created_at timestamp, updated_at timestamp, is_verified bool )\n"}
{"conversations": [{"role": "user", "content": "Show me the top 5 projects by valuation that completed fundraising rounds in the last 12 months, along with their token symbol and price from the token_basic_info table."}, {"role": "assistant", "content": "SELECT pfr.project_name, pfr.valuation, tbi.token_symbol, tbi.price FROM project_fundraising_record pfr LEFT JOIN token_basic_info tbi ON pfr.project_name = tbi.token_name WHERE pfr.investment_date >= DATE_SUB(CURRENT_DATE, INTERVAL 12 MONTH) ORDER BY pfr.valuation DESC LIMIT 5;"}, {"role": "user", "content": "Can you also include the 24-hour trading volume for these projects' tokens and filter to only include projects with valuation over $100 million?"}, {"role": "assistant", "content": "SELECT pfr.project_name, pfr.valuation, tbi.token_symbol, tbi.price, tbi.total_volume FROM project_fundraising_record pfr LEFT JOIN token_basic_info tbi ON pfr.project_name = tbi.token_name WHERE pfr.investment_date >= DATE_SUB(CURRENT_DATE, INTERVAL 12 MONTH) AND pfr.valuation > 100000000 ORDER BY pfr.valuation DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\n \"CREATE TABLE project_fundraising_record (\",\n    \"id character varying(32) NOT NULL,  -- fundraising record id\",\n    \"project_id character varying(32) NOT NULL, -- the invested project's id\",\n    \"project_name character varying(128) NOT NULL, -- name of the invested project\",\n    \"rounds_name character varying(32), -- name of the fundraising round\",\n    \"investment_value numeric(38,14), -- amount of the fundraising in USD\",\n    \"investment_date character varying(128), -- the date of the investment happened\",\n    \"introduction character varying(128), -- the introduction of the invested project\",\n    \"valuation numeric(38,14), -- the valuation of the project in USD when invested\",\n\nCREATE TABLE token_basic_info ( coin_id character varying(100) NOT NULL, -- the id of the token token_name character varying(100) NOT NULL, -- the token's name token_symbol character varying(100) NOT NULL, -- the token's symbol token_address character varying(100) NOT NULL, -- the token's address chain text, -- the chain that the token resides price double precision, -- the current price of the token price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days highest_price_24h double precision, -- the highest price of the token in 24 hours lowest_price_24h double precision,  -- the lowest price of the token in 24 hours market_cap double precision, -- the market cap of the token market_cap_rank bigint, -- the rank of the token market cap in desc market_cap_change_percentage_24h text, -- the percentage of market cap changes in 24 hours total_volume text, -- the trade volum of the token both in decentralized exchange(DEX) and centralized exchange(CEX) narrative text, -- the category or narrative of the token trend_rank biging, -- the trending rank of the token, value 1 expresses the most popular token. ,PRIMARY KEY (coin_id, chain) )\nCREATE TABLE narrative_info ( narrative character varying(512) NOT NULL, -- the id of narrative top_3_coins text, -- the top 3 tokens in the narrative price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour in the narrative price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours in the narrative price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days in the narrative market_cap double precision, -- the market cap of the narrative volume_24h double precision, -- the trade volume of the narrative trend_rank bigint, -- the trending rank of the narrative, value 1 expresses the most popular narrative token_num bigint, -- total token number in the narrative ,PRIMARY KEY (narrative) )\nCREATE TABLE token_dexpool_info ( pair_address character varying(512) NOT NULL, token_name character varying(100) NOT NULL, token_symbol character varying(100) NOT NULL, chain text, price double precision, price_change_percentage_1h double precision, price_change_percentage_6h double precision, price_change_percentage_24h double precision, makers_24h double precision, volume_24h double precision, liquidity double precision, market_cap double precision, trend_rank bigint )\nCREATE TABLE smart_money_profit ( address character varying(100) NOT NULL, rank INT, profit numeric(38,6), roi numeric(38,2), realized_ratio numeric(38,2), most_profit_token character varying(100), last_trade_time character varying(100), chain character varying(100) )\n  \"CREATE TABLE smart_money_token_performance (\",\n    \"token_address character varying(100) NOT NULL, -- the token's address\",\n    \"token_symbol character varying(100), -- the tokens's symbol\",\n    \"pnl numeric(38,2), -- the profit users made on this token\",\n    \"net_flow numeric(38,2), -- the netflow of the token, means the money user spent minus the the money user sold of this token\",\n    \"avg_cost numeric(38,16), -- the average cost price of user spent on this token\",\n    \"price double precision, -- the current price of the token\",\n    \"realized_ratio numeric(10,2), -- the ratio user sold of the token\",\n    \"roi numeric(10,2), -- the roi users made of this token\",\n    \"chain character varying(100), -- the chain that the token resides\",\n    \"PRIMARY KEY (token_address, chain));\",\n\n  \"CREATE TABLE smart_money_token_inflow (\",\n    \"token_address character varying(100) NOT NULL, -- the token's address\",\n    \"token_symbol character varying(100), -- the tokens's symbol\",\n    \"token_amount numeric(38,2), -- the absolute value of the amount if user bought minus  the amount user sold of this token\",\n    \"usd_value numeric(38,2), -- the absolute usd value of the bought token minus sold token\",\n    \"avg_price numeric(38,6), -- the average cost price of user spent on this token\",\n    \"type int, -- the direction of the trade on this token. 1 means buying, 2 means selling\",\n    \"address_amount integer, -- the amount of the user bought this token\",\n    \"narrative character varying(100), -- the category or narrative of the token\",\n    \"chain character varying(100), -- the chain that the token resides\",\n    \",PRIMARY KEY (token_address, chain)\",\n\n"}
{"conversations": [{"role": "user", "content": "What is the average number of wallets each user owns?"}, {"role": "assistant", "content": "SELECT\n  AVG(wallet_count) AS avg_wallets_per_user\nFROM (\n  SELECT user_id, COUNT(*) AS wallet_count\n  FROM web3.wallets\n  GROUP BY user_id\n) AS sub;"}, {"role": "user", "content": "Actually, calculate the average only for users who own more than one wallet."}, {"role": "assistant", "content": "SELECT\n  AVG(wallet_count) AS avg_wallets_per_user\nFROM (\n  SELECT user_id, COUNT(*) AS wallet_count\n  FROM web3.wallets\n  GROUP BY user_id\n  HAVING COUNT(*) > 1\n) AS sub;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.wallets ( wallet_id text PRIMARY KEY, user_id text, address text, private_key text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "How many documents are there for each document_type? Show document_type and count ordered by the count in descending order."}, {"role": "assistant", "content": "SELECT document_type,\n       COUNT(*) AS count\nFROM legal_services.documents\nGROUP BY document_type\nORDER BY count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.documents ( document_id.text, case_id.text, document_name.text, document_type.text, storage_path.text, uploaded_by_lawyer_id.text, upload_timestamp.timestamp, version.integer, description.text )\n"}
{"conversations": [{"role": "user", "content": "For each player, count the total number of achievements they've unlocked."}, {"role": "assistant", "content": "SELECT player_id,\n       COUNT(*) AS total_achievements\nFROM gaming_technology.player_achievements\nGROUP BY player_id;"}, {"role": "user", "content": "Exclude players with fewer than 10 achievements."}, {"role": "assistant", "content": "SELECT player_id,\n       COUNT(*) AS total_achievements\nFROM gaming_technology.player_achievements\nGROUP BY player_id\nHAVING COUNT(*) >= 10;"}, {"role": "user", "content": "Additionally, provide the month when they achieved their 10th achievement. Show player_id, total_achievements, and the month of the 10th unlock."}, {"role": "assistant", "content": "WITH ranked AS (\n  SELECT player_id,\n         unlocked_at,\n         ROW_NUMBER() OVER (PARTITION BY player_id ORDER BY unlocked_at) AS rn\n  FROM gaming_technology.player_achievements\n),\ncounts AS (\n  SELECT player_id,\n         COUNT(*) AS total_achievements\n  FROM gaming_technology.player_achievements\n  GROUP BY player_id\n  HAVING COUNT(*) >= 10\n)\nSELECT c.player_id,\n       c.total_achievements,\n       EXTRACT(MONTH FROM r.unlocked_at) AS tenth_achievement_month\nFROM counts c\nJOIN ranked r\n  ON c.player_id = r.player_id\n AND r.rn = 10;"}, {"role": "user", "content": "Finally, order by total_achievements descending."}, {"role": "assistant", "content": "WITH ranked AS (\n  SELECT player_id,\n         unlocked_at,\n         ROW_NUMBER() OVER (PARTITION BY player_id ORDER BY unlocked_at) AS rn\n  FROM gaming_technology.player_achievements\n),\ncounts AS (\n  SELECT player_id,\n         COUNT(*) AS total_achievements\n  FROM gaming_technology.player_achievements\n  GROUP BY player_id\n  HAVING COUNT(*) >= 10\n)\nSELECT c.player_id,\n       c.total_achievements,\n       EXTRACT(MONTH FROM r.unlocked_at) AS tenth_achievement_month\nFROM counts c\nJOIN ranked r\n  ON c.player_id = r.player_id\n AND r.rn = 10\nORDER BY c.total_achievements DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.player_achievements (\n    player_achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for this unlock instance\n    player_id uuid NOT NULL, -- FK linking to the player who unlocked it\n    achievement_id uuid NOT NULL, -- FK linking to the achievement definition\n    unlocked_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the achievement was unlocked\n    PRIMARY KEY (player_achievement_id),\n    UNIQUE (player_id, achievement_id) -- Ensure a player can only unlock an achievement once\n    -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n    -- FOREIGN KEY (achievement_id) REFERENCES gaming_technology.achievements(achievement_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Find all users who registered with a Yahoo email address, along with their registration dates."}, {"role": "assistant", "content": "SELECT user_id, username, email, password_hash FROM blockchain.users WHERE email LIKE '%@yahoo.com';"}, {"role": "user", "content": "This query doesn't show registration dates. Can you modify it to include the registration date?"}, {"role": "assistant", "content": "I notice the users table doesn't have a registration date column. Would you like me to show other available information from the users table?"}, {"role": "user", "content": "Then just show me the count of Yahoo email users instead."}, {"role": "assistant", "content": "SELECT COUNT(*) as yahoo_user_count FROM blockchain.users WHERE email LIKE '%@yahoo.com';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE blockchain.blocks ( block_id text, previous_block_id text, timestamp timestamp, nonce integer, merkle_root text, difficulty integer )\nCREATE TABLE blockchain.transactions (\n    transaction_id character varying(64) NOT NULL,  -- unique identifier for the transaction\n    block_id character varying(64) NOT NULL, -- identifier of the block containing the transaction\n    sender_address character varying(128) NOT NULL, -- address of the sender\n    receiver_address character varying(128) NOT NULL, -- address of the receiver\n    amount numeric(38,14) NOT NULL, -- amount transferred\n    timestamp timestamp NOT NULL, -- time when the transaction was created\n    signature text NOT NULL, -- digital signature of the transaction\n    PRIMARY KEY (transaction_id)\n)\nCREATE TABLE blockchain.addresses ( address_id text PRIMARY KEY, public_key text, balance numeric )\nCREATE TABLE blockchain.users ( user_id character varying(64) NOT NULL, username character varying(128) NOT NULL, email character varying(128) NOT NULL, password_hash text NOT NULL, PRIMARY KEY (user_id) )\n"}
{"conversations": [{"role": "user", "content": "Find all pairs of transactions where both transactions have the same nonce and from_address, but different transaction_id. Show both transaction IDs, the shared from_address, shared nonce, and their block numbers."}, {"role": "assistant", "content": "SELECT t1.transaction_id AS transaction_id_1, t2.transaction_id AS transaction_id_2, t1.from_address, t1.nonce, t1.block_number AS block_number_1, t2.block_number AS block_number_2\nFROM web3.transactions t1\nJOIN web3.transactions t2\n  ON t1.from_address = t2.from_address\n AND t1.nonce = t2.nonce\n AND t1.transaction_id < t2.transaction_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.transactions (\n    transaction_id character varying(64) NOT NULL,  -- unique identifier for the transaction\n    from_address character varying(128) NOT NULL, -- address of the sender\n    to_address character varying(128), -- address of the receiver (can be null for contract deployment)\n    value numeric(38,14) NOT NULL, -- value transferred\n    gas_used integer NOT NULL, -- amount of gas used by the transaction\n    gas_price numeric(38,14) NOT NULL, -- price of gas at the time of the transaction\n    block_number integer NOT NULL, -- block number containing the transaction\n    timestamp timestamp NOT NULL, -- time when the transaction was mined\n    input_data text, -- input data of the transaction (can be null)\n    status character varying(32) NOT NULL, -- status of the transaction (e.g., success, failed)\n    nonce integer NOT NULL, -- nonce of the sender at the time of the transaction\n    PRIMARY KEY (transaction_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Can you list each game alongside another game in the same genre but by a different developer?"}, {"role": "assistant", "content": "SELECT g1.genre, g1.title AS game1, g2.title AS game2\nFROM gaming_technology.games g1\nJOIN gaming_technology.games g2\n  ON g1.genre = g2.genre\n  AND g1.developer_id <> g2.developer_id;"}, {"role": "user", "content": "Exclude any pairs where either game was released before 2019."}, {"role": "assistant", "content": "SELECT g1.genre, g1.title AS game1, g2.title AS game2\nFROM gaming_technology.games g1\nJOIN gaming_technology.games g2\n  ON g1.genre = g2.genre\n  AND g1.developer_id <> g2.developer_id\nWHERE g1.release_date >= '2019-01-01'\n  AND g2.release_date >= '2019-01-01';"}, {"role": "user", "content": "Limit the output to the first 10 pairs ordered by genre and developer_id."}, {"role": "assistant", "content": "SELECT g1.genre, g1.title AS game1, g2.title AS game2\nFROM gaming_technology.games g1\nJOIN gaming_technology.games g2\n  ON g1.genre = g2.genre\n  AND g1.developer_id <> g2.developer_id\nWHERE g1.release_date >= '2019-01-01'\n  AND g2.release_date >= '2019-01-01'\nORDER BY g1.genre, g1.developer_id\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 gaming_technology.games ( game_id.uuid, title.text, developer_id.uuid, publisher_id.uuid, genre.text, release_date.date, description.text, platform.text, engine.text, website.text )\n"}
{"conversations": [{"role": "user", "content": "For each property, list the name of the room type and the number of rooms of that type at the property."}, {"role": "assistant", "content": "SELECT T1.property_name, T2.type_name, count(T3.room_id) AS room_count FROM hospitality_technology.properties AS T1 JOIN hospitality_technology.room_types AS T2 ON T1.property_id = T2.property_id JOIN hospitality_technology.rooms AS T3 ON T2.room_type_id = T3.room_type_id GROUP BY T1.property_name, T2.type_name ORDER BY T1.property_name, T2.type_name;"}, {"role": "user", "content": "Only include room types that have a base rate above 150, and sort the results by property name and then by room type count descending."}, {"role": "assistant", "content": "SELECT T1.property_name, T2.type_name, count(T3.room_id) AS room_count FROM hospitality_technology.properties AS T1 JOIN hospitality_technology.room_types AS T2 ON T1.property_id = T2.property_id JOIN hospitality_technology.rooms AS T3 ON T2.room_type_id = T3.room_type_id WHERE T2.base_rate > 150 GROUP BY T1.property_name, T2.type_name ORDER BY T1.property_name, room_count DESC;"}, {"role": "user", "content": "The SQL failed. I meant available rooms, not just any room. Please rewrite the query to only count rooms with status 'Available'."}, {"role": "assistant", "content": "SELECT T1.property_name, T2.type_name, count(T3.room_id) AS room_count FROM hospitality_technology.properties AS T1 JOIN hospitality_technology.room_types AS T2 ON T1.property_id = T2.property_id JOIN hospitality_technology.rooms AS T3 ON T2.room_type_id = T3.room_type_id WHERE T2.base_rate > 150 AND T3.status = 'Available' GROUP BY T1.property_name, T2.type_name ORDER BY T1.property_name, room_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.properties ( property_id character varying(64) NOT NULL, property_name character varying(255) NOT NULL, address_line1 character varying(255) NOT NULL, address_line2 character varying(255), city character varying(100) NOT NULL, state_province character varying(100), postal_code character varying(20) NOT NULL, country_code character varying(3) NOT NULL, phone_number character varying(30), email_address character varying(255), property_type character varying(50) NOT NULL, star_rating numeric(2,1), timezone character varying(64) NOT NULL, manager_staff_id character varying(64), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (property_id) )\nCREATE TABLE hospitality_technology.rooms ( room_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, room_number character varying(10) NOT NULL, room_type_id character varying(64) NOT NULL, floor integer, status character varying(50) NOT NULL, is_smoking boolean NOT NULL DEFAULT false, features text, current_condition text, last_cleaned_at timestamp with time zone, PRIMARY KEY (room_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id) )\nCREATE TABLE hospitality_technology.room_types ( room_type_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, type_name character varying(100) NOT NULL, description text, base_rate numeric(10, 2) NOT NULL, max_occupancy integer NOT NULL, bed_type character varying(50), area_sqft numeric(8,2), amenities text, PRIMARY KEY (room_type_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id) )\nCREATE TABLE hospitality_technology.guests ( guest_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, email character varying(255) UNIQUE, phone_number character varying(30), date_of_birth date, address_line1 character varying(255), city character varying(100), state_province character varying(100), postal_code character varying(20), country_code character varying(3), preferences text, loyalty_member_id character varying(64) UNIQUE, communication_consent boolean DEFAULT true, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (guest_id) )\nCREATE TABLE hospitality_technology.reservations ( reservation_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, guest_id character varying(64) NOT NULL, room_id character varying(64), room_type_id character varying(64) NOT NULL, check_in_date date NOT NULL, check_out_date date NOT NULL, actual_check_in_ts timestamp with time zone, actual_check_out_ts timestamp with time zone, num_adults integer NOT NULL, num_children integer DEFAULT 0, status character varying(50) NOT NULL, booking_source character varying(100), rate_plan_id character varying(64), total_amount numeric(12, 2), amount_paid numeric(12, 2) DEFAULT 0.00, special_requests text, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (reservation_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (room_id) REFERENCES hospitality_technology.rooms(room_id), FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id) )\nCREATE TABLE hospitality_technology.services ( service_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, service_name character varying(150) NOT NULL, description text, category character varying(100), price numeric(10, 2) NOT NULL, unit character varying(30), is_available boolean NOT NULL DEFAULT true, department character varying(100), PRIMARY KEY (service_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id) )\nCREATE TABLE hospitality_technology.service_orders ( order_id character varying(64) NOT NULL, reservation_id character varying(64), guest_id character varying(64) NOT NULL, service_id character varying(64) NOT NULL, staff_id_ordered character varying(64), staff_id_delivered character varying(64), order_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, delivery_timestamp timestamp with time zone, quantity integer NOT NULL DEFAULT 1, unit_price numeric(10, 2) NOT NULL, total_price numeric(12, 2) NOT NULL, status character varying(50) NOT NULL, notes text, bill_id character varying(64), PRIMARY KEY (order_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (service_id) REFERENCES hospitality_technology.services(service_id), FOREIGN KEY (staff_id_ordered) REFERENCES hospitality_technology.staff(staff_id), FOREIGN KEY (staff_id_delivered) REFERENCES hospitality_technology.staff(staff_id) )\nCREATE TABLE hospitality_technology.payments ( payment_id character varying(64) NOT NULL, reservation_id character varying(64), guest_id character varying(64) NOT NULL, bill_id character varying(64), amount numeric(12,2) NOT NULL, currency_code character varying(3) NOT NULL, payment_method character varying(50) NOT NULL, card_type character varying(50), card_last_four character varying(4), transaction_ref character varying(128), payment_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, status character varying(50) NOT NULL, staff_id_processed character varying(64), notes text, PRIMARY KEY (payment_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (staff_id_processed) REFERENCES hospitality_technology.staff(staff_id) )\nCREATE TABLE hospitality_technology.reviews ( review_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, reservation_id character varying(64) UNIQUE, guest_id character varying(64) NOT NULL, rating_overall integer, rating_cleanliness integer, rating_service integer, rating_location integer, rating_value integer, comment text, review_source character varying(100), review_date timestamp with time zone NOT NULL DEFAULT current_timestamp, is_public boolean DEFAULT true, staff_response text, response_staff_id character varying(64), response_date timestamp with time zone, PRIMARY KEY (review_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (response_staff_id) REFERENCES hospitality_technology.staff(staff_id) )\n"}
{"conversations": [{"role": "user", "content": "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": "Can you show me each user's address and the date their wallet was created?"}, {"role": "assistant", "content": "SELECT user_id, address, created_at FROM trading_platform.wallets;"}, {"role": "user", "content": "Now, can you show only wallets created after '2024-01-01' and include the user_id and address?"}, {"role": "assistant", "content": "SELECT user_id, address, created_at FROM trading_platform.wallets WHERE created_at > '2024-01-01';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.wallets ( wallet_id text, user_id text, address text, private_key text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show all messages that include a media attachment, along with the sender's user ID and the conversation ID."}, {"role": "assistant", "content": "SELECT message_id, sender_user_id, conversation_id, media_url, media_type, sent_at FROM social_media.messages WHERE media_url IS NOT NULL AND media_url <> '';"}, {"role": "user", "content": "Only include messages sent after May 1st, 2024 and show the media_type as well."}, {"role": "assistant", "content": "SELECT message_id, sender_user_id, conversation_id, media_url, media_type, sent_at FROM social_media.messages WHERE media_url IS NOT NULL AND media_url <> '' AND sent_at > '2024-05-01';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.messages ( message_id text PRIMARY KEY, conversation_id text, sender_user_id text, content text, media_url text, media_type text, sent_at timestamp, read_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "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 each agent along with their manager's contact_email. Include agent_id, first_name, last_name, manager_id, and manager's contact_email."}, {"role": "assistant", "content": "SELECT a.agent_id,\n       a.first_name,\n       a.last_name,\n       a.manager_id,\n       m.contact_email AS manager_contact_email\nFROM insurance.agents a\nLEFT JOIN insurance.agents m\n  ON a.manager_id = m.agent_id;"}, {"role": "user", "content": "Actually, only include records where the manager is currently active."}, {"role": "assistant", "content": "SELECT a.agent_id,\n       a.first_name,\n       a.last_name,\n       a.manager_id,\n       m.contact_email AS manager_contact_email\nFROM insurance.agents a\nLEFT JOIN insurance.agents m\n  ON a.manager_id = m.agent_id\nWHERE 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 insurance.agents ( agent_id.text, first_name.text, last_name.text, agency_name.text, license_number.text, license_state.text, contact_email.text, contact_phone.text, hire_date.date, termination_date.date, status.text, commission_rate.numeric, manager_id.text )\n"}
{"conversations": [{"role": "user", "content": "List all premium payments made after April 1, 2024, including the payment_id, policy_id, customer_id, and amount_paid."}, {"role": "assistant", "content": "SELECT payment_id, policy_id, customer_id, amount_paid\nFROM insurance.premium_payments\nWHERE payment_date > '2024-04-01';"}], "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 ( 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) )\n"}
{"conversations": [{"role": "user", "content": "List all appointments scheduled for '2024-07-25' with a status of 'Scheduled'."}, {"role": "assistant", "content": "SELECT * FROM legal_services.appointments WHERE DATE(start_time) = '2024-07-25' AND status = 'Scheduled'"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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": "Retrieve the contract_id, creator_address, and deployment timestamp for all contracts where the contract code contains the word 'token'."}, {"role": "assistant", "content": "SELECT contract_id, creator_address, timestamp\nFROM blockchain.smart_contracts\nWHERE code ILIKE '%token%';"}], "system": "You are an SQL statement expert. Given the table structure 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 (\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": "List the username and email of users whose first wallet creation date is the same day as their user registration date."}, {"role": "assistant", "content": "SELECT u.username, u.email FROM web3.users u JOIN (SELECT user_id, MIN(created_at) as first_wallet_created_at FROM web3.wallets GROUP BY user_id) w ON u.user_id = w.user_id WHERE DATE(u.created_at) = DATE(w.first_wallet_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.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.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.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": "Show me all insurance plans that have more than 5 patients enrolled, along with the provider name and count of patients, sorted by patient count in descending order."}, {"role": "assistant", "content": "SELECT i.plan_name, i.insurance_provider, COUNT(p.patient_id) AS patient_count FROM healthcare.insurance_plans i JOIN healthcare.patients p ON i.plan_id = p.primary_insurance_id GROUP BY i.plan_id HAVING COUNT(p.patient_id) > 5 ORDER BY patient_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id text, first_name text, last_name text, date_of_birth date, gender text, address text, phone_number text, email text, emergency_contact_name text, emergency_contact_phone text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.appointments ( appointment_id text, patient_id text, doctor_id text, appointment_time timestamp, duration_minutes integer, reason text, status text, location_id text, notes text, created_at timestamp )\nCREATE TABLE healthcare.insurance_plans (\n    plan_id character varying(64) NOT NULL, -- unique identifier for the insurance plan\n    plan_name character varying(200) NOT NULL, -- name of the insurance plan\n    insurance_provider character varying(100) NOT NULL, -- name of the insurance company\n    plan_type character varying(50), -- e.g., PPO, HMO, EPO\n    contact_phone character varying(20), -- provider contact number\n    website character varying(255), -- provider website\n    PRIMARY KEY (plan_id)\n)\n"}
{"conversations": [{"role": "user", "content": "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": "What is the average token price held by Binance exchange across all chains?"}, {"role": "assistant", "content": "SELECT AVG(price) as average_token_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\nCREATE TABLE cex_token_balance ( snapshot_time.text, chain.text, address.text, exchange.text, token_address.text, token_symbol.text, balance.numeric, usd_value.numeric, price.numeric )\n  \"CREATE TABLE smart_money_token_inflow (\",\n    \"token_address character varying(100) NOT NULL, -- the token's address\",\n    \"token_symbol character varying(100), -- the tokens's symbol\",\n    \"token_amount numeric(38,2), -- the absolute value of the amount if user bought minus  the amount user sold of this token\",\n    \"usd_value numeric(38,2), -- the absolute usd value of the bought token minus sold token\",\n    \"avg_price numeric(38,6), -- the average cost price of user spent on this token\",\n    \"type int, -- the direction of the trade on this token. 1 means buying, 2 means selling\",\n    \"address_amount integer, -- the amount of the user bought this token\",\n    \"narrative character varying(100), -- the category or narrative of the token\",\n    \"chain character varying(100), -- the chain that the token resides\",\n    \",PRIMARY KEY (token_address, chain)\",\n\n"}
{"conversations": [{"role": "user", "content": "What are the training programs or certifications completed by a staff member with the role of Platform Supervisor?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to information about the training programs or certifications completed by staff members. The data available to me only includes basic staff details such as name, role, and contact information. For details on training or certifications, please refer to the HR department or relevant training records."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.staff ( staff_id text PRIMARY KEY, first_name text, last_name text, role text, primary_station_id text, employee_number text UNIQUE, hire_date date, contact_email text UNIQUE, contact_phone text, is_active boolean )\n"}
{"conversations": [{"role": "user", "content": "Show the invoice number, issue date, total amount, and the client's full name for all invoices, including only those invoices that have not been paid fully."}, {"role": "assistant", "content": "SELECT i.invoice_number, i.issue_date, i.total_amount, c.first_name || ' ' || c.last_name AS client_full_name FROM legal_services.invoices i JOIN legal_services.clients c ON i.client_id = c.client_id WHERE i.amount_paid < i.total_amount;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.clients ( client_id.text, first_name.text, last_name.text, company_name.text, email.text, phone.text, address.text, date_registered.timestamp, status.text )\nCREATE TABLE legal_services.law_firms ( firm_id.text, firm_name.text, address.text, phone.text, website.text, founded_date.date, managing_partner_id.text )\nCREATE TABLE legal_services.documents ( document_id.text, case_id.text, document_name.text, document_type.text, storage_path.text, uploaded_by_lawyer_id.text, upload_timestamp.timestamp, version.integer, description.text )\nCREATE TABLE legal_services.time_entries ( entry_id.text, case_id.text, lawyer_id.text, date_worked.date, hours_spent.numeric, billing_rate.numeric, description.text, is_billable.boolean, is_billed.boolean, invoice_id.text, created_at.timestamp )\nCREATE TABLE legal_services.invoices ( invoice_id.text, invoice_number.text, client_id.text, case_id.text, issue_date.date, due_date.date, total_amount.numeric, amount_paid.numeric, status.text, payment_date.timestamp, notes.text, created_at.timestamp )\nCREATE TABLE legal_services.appointments ( appointment_id.text, client_id.text, lawyer_id.text, case_id.text, start_time.timestamp, end_time.timestamp, location.text, subject.text, notes.text, status.text, created_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "For each policy, find the latest payment date. Show the policy_id and the maximum payment_date."}, {"role": "assistant", "content": "SELECT policy_id, MAX(payment_date) AS latest_payment_date FROM insurance.premium_payments GROUP BY policy_id;"}, {"role": "user", "content": "Restrict the results to only show policies where the latest payment date was before '2024-01-01'."}, {"role": "assistant", "content": "SELECT policy_id, MAX(payment_date) AS latest_payment_date FROM insurance.premium_payments GROUP BY policy_id HAVING MAX(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 ( 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": "特定のラインIDに関連する組み立て手順と、使用されている材料の情報を取得したいです。ラインID、ステップ名、材料名、材料の説明を含めてください。"}, {"role": "assistant", "content": "SELECT s.line_id, s.step_name, m.material_name, m.description\nFROM manufacturing.assembly_steps s\nJOIN manufacturing.materials m ON s.step_id = m.material_id\nWHERE s.line_id = 'specific_line_id';"}, {"role": "user", "content": "さらに、特定の作業場所での手順だけを表示するようにできますか？例えば「Workstation_A」のみ。"}, {"role": "assistant", "content": "SELECT s.line_id, s.step_name, m.material_name, m.description\nFROM manufacturing.assembly_steps s\nJOIN manufacturing.materials m ON s.step_id = m.material_id\nWHERE s.line_id = 'specific_line_id'\nAND s.workstation = 'Workstation_A';"}, {"role": "user", "content": "もし標準作業時間が1時間未満の手順を除外したい場合はどうすればいいですか？"}, {"role": "assistant", "content": "SELECT s.line_id, s.step_name, m.material_name, m.description\nFROM manufacturing.assembly_steps s\nJOIN manufacturing.materials m ON s.step_id = m.material_id\nWHERE s.line_id = 'specific_line_id'\nAND s.workstation = 'Workstation_A'\nAND s.standard_duration_hours >= 1;"}, {"role": "user", "content": "最後に、ステップ番号を基準に昇順で並べ替えてください。"}, {"role": "assistant", "content": "SELECT s.line_id, s.step_name, m.material_name, m.description\nFROM manufacturing.assembly_steps s\nJOIN manufacturing.materials m ON s.step_id = m.material_id\nWHERE s.line_id = 'specific_line_id'\nAND s.workstation = 'Workstation_A'\nAND s.standard_duration_hours >= 1\nORDER BY s.step_number ASC;"}], "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 manufacturing.materials (\n    material_id character varying(64) NOT NULL,  -- unique identifier for the material\n    material_name character varying(128) NOT NULL, -- common name (e.g., Titanium Alloy Grade 5, Carbon Fiber Prepreg)\n    specification character varying(255), -- specification standard (e.g., AMS 4928)\n    description text, -- detailed description of properties\n    density_kg_m3 numeric(10, 4), -- density in kg per cubic meter\n    tensile_strength_mpa integer, -- tensile strength in Megapascals\n    PRIMARY KEY (material_id)\n)\nCREATE TABLE manufacturing.assembly_steps (\n    step_id character varying(64) NOT NULL, -- unique identifier for an assembly step/task\n    line_id character varying(64) NOT NULL, -- FK to the assembly line where this step occurs\n    step_number integer NOT NULL, -- sequence number of the step on the line\n    step_name character varying(255) NOT NULL, -- name of the task (e.g., Install Wing Root Fairing)\n    description text, -- detailed instructions or description\n    standard_duration_hours numeric(8,2), -- estimated time to complete the step\n    required_skill_level character varying(50), -- skill level needed (e.g., 'Mechanic II', 'Electrician I')\n    workstation character varying(100), -- specific workstation or area for the step\n    PRIMARY KEY (step_id)\n)\n"}
{"conversations": [{"role": "user", "content": "How many lawyers who are partners were hired in each year? Show the hire year and the count."}, {"role": "assistant", "content": "SELECT strftime('%Y', hire_date) AS hire_year ,  count(lawyer_id) FROM legal_services.lawyers WHERE is_partner  =  true GROUP BY hire_year"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.lawyers (\n    lawyer_id character varying(64) NOT NULL,  -- unique identifier for the lawyer\n    first_name character varying(100) NOT NULL, -- lawyer's first name\n    last_name character varying(100) NOT NULL, -- lawyer's last name\n    bar_number character varying(64) UNIQUE NOT NULL, -- lawyer's bar association number\n    firm_id character varying(64), -- FK to law_firms table\n    email character varying(128) UNIQUE NOT NULL, -- lawyer's professional email\n    phone character varying(32), -- lawyer's contact phone number\n    specialization text, -- areas of legal expertise\n    hire_date timestamp NOT NULL, -- date the lawyer was hired or joined\n    is_partner boolean DEFAULT false, -- flag indicating if the lawyer is a partner\n    PRIMARY KEY (lawyer_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Find all NFTs with a rarity rank less than 100 and show their name and the name of their collection."}, {"role": "assistant", "content": "SELECT nm.name AS nft_name, nc.name AS collection_name FROM nft_metadata nm JOIN nft_collections nc ON nm.contract_address = nc.contract_address WHERE nm.rarity_rank < 100;"}, {"role": "user", "content": "Filter that further to only include NFTs from collections named 'Bored Ape Yacht Club'."}, {"role": "assistant", "content": "SELECT nm.name AS nft_name, nc.name AS collection_name FROM nft_metadata nm JOIN nft_collections nc ON nm.contract_address = nc.contract_address WHERE nm.rarity_rank < 100 AND nc.name = 'Bored Ape Yacht Club';"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nCREATE TABLE token_metas ( block_timestamp timestamp, block_number bigint, transaction_hash varchar, transaction_index bigint, from_address varchar, contract_address varchar, symbol varchar, total_supply varchar, name varchar, decimals bigint, is_erc20 integer, is_erc721 integer, is_erc1155 integer, is_proxy integer, extra_info varchar, pk integer )\nCREATE TABLE erc1155_approval_for_all ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash varchar, log_index integer, contract_address varchar )\nCREATE TABLE erc20_balances ( block_number bigint, contract_address varchar, wallet_address varchar, amount varchar, pk varchar )\nCREATE TABLE nft_holders ( block_number bigint, contract_address varchar, wallet_address varchar, token_id varchar, contract_type varchar, amount varchar, pk varchar )\nCREATE TABLE nft_holder_historical ( block_number bigint, contract_address varchar, wallet_address varchar, token_id varchar, contract_type varchar, amount varchar, pk integer )\nCREATE TABLE sui_coins ( object_id varchar, status varchar, coin_type varchar, balance varchar, owner varchar )\nCREATE TABLE sui_nfts ( object_id varchar, status varchar, collection_type varchar, package_id varchar, previous_transaction varchar, display varchar, owner varchar, name varchar )\nCREATE TABLE nft_metadata ( blockchain varchar, contract_address varchar, token_id varchar, contract_name varchar, erc_type varchar, amount bigint, minter varchar, owner varchar, mint_block_number bigint, mint_time bigint, mint_transaction_hash varchar, mint_price varchar, token_uri varchar, metadata varchar, name varchar, image_uri varchar, traits varchar, updated_at bigint, status varchar, rarity_score real, rarity_rank integer, unique_attribute_count integer, pk integer )\nCREATE TABLE nft_collections ( blockchain varchar, contract_address varchar, name varchar, symbol varchar, deploy_block_number bigint, deploy_block_time bigint, erc_type varchar, owner varchar, traits varchar, description varchar, slug varchar, media_info varchar, image_url varchar, banner_image_url varchar, updated_at bigint, banner varchar, token_count bigint, floor_price varchar, floor_price_symbol varchar, floor_price_contract varchar, pk integer )\nCREATE TABLE token_prices ( uuid varchar, blockchain varchar, address varchar, decimals bigint, symbol varchar, price real, timestamp timestamp )\nCREATE TABLE token_prices_latest ( blockchain varchar, address varchar, decimals bigint, symbol varchar, price real, timestamp timestamp )\nCREATE TABLE erc20_approval ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash varchar, log_index integer, contract_address varchar, pk integer )\nCREATE TABLE token_balances ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply decimal, amount decimal )\nCREATE TABLE token_info ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar )\nCREATE TABLE token_activities ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\nCREATE TABLE mud_holesky_redstone ( address varchar, table_id varchar, key_bytes varchar, key0 varchar, key1 varchar, static_data varchar, encoded_lengths varchar, dynamic_data varchar, is_deleted boolean, block_number bigint, log_index bigint )\nCREATE TABLE token_balances_bitcoin ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply varchar, amount varchar )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\nCREATE TABLE token_balances_avalanche ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply decimal, amount decimal )\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id varchar )\n"}
{"conversations": [{"role": "user", "content": "For 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": "我想查看所有检查记录中检查员的ID和检查结果，同时统计每个检查员的检查次数。"}, {"role": "assistant", "content": "db.inspections.aggregate([\n  {\n    $group: {\n      _id: '$inspector_employee_id',\n      total_inspections: { $count: {} },\n      results: { $push: '$result' }\n    }\n  },\n  {\n    $project: {\n      inspector_employee_id: '$_id',\n      total_inspections: 1,\n      results: 1,\n      _id: 0\n    }\n  }\n]);"}, {"role": "user", "content": "如果我想只统计检查结果为'Fail'的次数，应该怎么改？"}, {"role": "assistant", "content": "db.inspections.aggregate([\n  {\n    $match: {\n      result: 'Fail'\n    }\n  },\n  {\n    $group: {\n      _id: '$inspector_employee_id',\n      failed_inspections: { $count: {} }\n    }\n  },\n  {\n    $project: {\n      inspector_employee_id: '$_id',\n      failed_inspections: 1,\n      _id: 0\n    }\n  }\n]);"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nCollection 'inspections'. Document structure: { _id: <ObjectId (or inspection_id)>, inspection_id: String, build_id: String (reference), component_id: String (reference, optional), step_id: String (reference, optional), inspection_type: String, inspector_employee_id: String (reference), inspection_timestamp: ISODate, result: String, remarks: String }. Required: inspection_id, build_id, inspection_type, inspector_employee_id, inspection_timestamp, result. Indexes on build_id, component_id, step_id, inspector_employee_id, result.\n"}
{"conversations": [{"role": "user", "content": "List the full names of citizens who have uploaded documents with a verification status of 'Pending' and the type of document they uploaded."}, {"role": "assistant", "content": "SELECT T1.first_name, T1.last_name, T2.document_type FROM government_services.citizens AS T1 JOIN government_services.documents AS T2 ON T1.citizen_id = T2.citizen_id WHERE T2.verification_status = 'Pending';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.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": "Find all pairs of policies for the same customer where their coverage periods overlap. Return customer_id, the two policy numbers, and their start and end dates."}, {"role": "assistant", "content": "SELECT p1.customer_id,\n       p1.policy_number AS policy_number1,\n       p1.start_date AS start_date1,\n       p1.end_date   AS end_date1,\n       p2.policy_number AS policy_number2,\n       p2.start_date AS start_date2,\n       p2.end_date   AS end_date2\nFROM insurance.policies p1\nJOIN insurance.policies p2\n  ON p1.customer_id = p2.customer_id\n AND p1.policy_id < p2.policy_id\n AND p1.start_date <= p2.end_date\n AND p2.start_date <= p1.end_date;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.policies (\n    policy_id character varying(64) NOT NULL, -- unique identifier for the policy\n    customer_id character varying(64) NOT NULL, -- identifier for the policyholder (FK to customers)\n    product_id character varying(64) NOT NULL, -- identifier for the insurance product (FK to insurance_products)\n    agent_id character varying(64), -- identifier for the agent who sold the policy (FK to agents)\n    policy_number character varying(100) NOT NULL UNIQUE, -- customer-facing policy number\n    start_date date NOT NULL, -- date the policy coverage begins\n    end_date date NOT NULL, -- date the policy coverage ends\n    premium_amount numeric(12, 2) NOT NULL, -- total premium for the policy term\n    coverage_limit numeric(15, 2) NOT NULL, -- maximum amount covered\n    deductible numeric(10, 2) NOT NULL, -- amount customer pays before coverage kicks in\n    status character varying(30) NOT NULL, -- e.g., Active, Expired, Cancelled, Pending\n    issued_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the policy was issued\n    cancellation_date date,\n    cancellation_reason text,\n    PRIMARY KEY (policy_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Provide a count of agencies for each distinct jurisdiction level."}, {"role": "assistant", "content": "SELECT jurisdiction_level, COUNT(*) AS agency_count FROM government_services.agencies GROUP BY jurisdiction_level;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id text PRIMARY KEY, national_id_number text, first_name text, last_name text, date_of_birth date, gender text, primary_address text, contact_email text, contact_phone text, registration_date timestamp, is_verified boolean )\nCREATE TABLE government_services.agencies ( agency_id text PRIMARY KEY, agency_name text, jurisdiction_level text, primary_contact_email text, main_phone_number text, website_url text, established_date date, parent_agency_id text )\nCREATE TABLE government_services.documents ( document_id text PRIMARY KEY, application_id text, citizen_id text, document_type text, file_reference text, upload_timestamp timestamp, expiry_date date, verification_status text, verified_by_employee_id text, verification_timestamp timestamp )\nCREATE TABLE government_services.payments ( payment_id text PRIMARY KEY, application_id text, citizen_id text, service_id text, amount numeric, currency text, payment_method text, payment_provider_reference text, payment_timestamp timestamp, status text, notes text )\nCREATE TABLE government_services.service_locations ( location_id text PRIMARY KEY, agency_id text, location_name text, address text, city text, state text, postal_code text, latitude numeric, longitude numeric, operating_hours text, contact_phone text, is_accessible boolean )\nCREATE TABLE government_services.appointments ( appointment_id text PRIMARY KEY, citizen_id text, employee_id text, location_id text, service_id text, scheduled_start_time timestamp, scheduled_end_time timestamp, purpose text, status text, booking_method text, created_at timestamp, notes text )\n"}
{"conversations": [{"role": "user", "content": "Show me all transactions (transaction_id, amount, transaction_type) where the status is 'Completed' and the transaction_date is within the last 30 days, along with the security details (ticker_symbol, security_name) for securities traded on the same day as the transaction."}, {"role": "assistant", "content": "SELECT t.transaction_id, t.amount, t.transaction_type, s.ticker_symbol, s.security_name FROM financial_services.transactions t JOIN financial_services.market_data md ON DATE(t.transaction_date) = DATE(md.data_timestamp) JOIN financial_services.securities s ON md.security_id = s.security_id WHERE t.status = 'Completed' AND t.transaction_date >= CURRENT_DATE - INTERVAL '30 days'"}, {"role": "user", "content": "Now modify the query to only include transactions with amount greater than $1,000 and securities from the 'Technology' sector, sorted by transaction_date in descending order."}, {"role": "assistant", "content": "SELECT t.transaction_id, t.amount, t.transaction_type, s.ticker_symbol, s.security_name FROM financial_services.transactions t JOIN financial_services.market_data md ON DATE(t.transaction_date) = DATE(md.data_timestamp) JOIN financial_services.securities s ON md.security_id = s.security_id WHERE t.status = 'Completed' AND t.transaction_date >= CURRENT_DATE - INTERVAL '30 days' AND t.amount > 1000 AND s.sector = 'Technology' ORDER BY t.transaction_date DESC"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.transactions ( 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": "List for each fuel type the number of unique vehicle models available. Show the fuel_type and the model count."}, {"role": "assistant", "content": "SELECT fuel_type, COUNT(DISTINCT model) AS model_count FROM transportation.vehicles GROUP BY fuel_type ORDER BY fuel_type;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles ( vehicle_id text, license_plate text, vin text, make text, model text, year integer, type text, capacity integer, fuel_type text, status text, depot_id text, acquisition_date date )\n"}
{"conversations": [{"role": "user", "content": "Find all pairs of customers who live in the same state but have different risk profiles."}, {"role": "assistant", "content": "SELECT a.customer_id AS customer_id_a, a.first_name || ' ' || a.last_name AS full_name_a, a.risk_profile AS risk_profile_a, b.customer_id AS customer_id_b, b.first_name || ' ' || b.last_name AS full_name_b, b.risk_profile AS risk_profile_b, a.state\nFROM financial_services.customers a\nJOIN financial_services.customers b\n  ON a.state = b.state\n  AND a.risk_profile <> b.risk_profile;"}, {"role": "user", "content": "Now restrict to states that have more than 5 customers total."}, {"role": "assistant", "content": "SELECT a.customer_id AS customer_id_a, a.first_name || ' ' || a.last_name AS full_name_a, a.risk_profile AS risk_profile_a, b.customer_id AS customer_id_b, b.first_name || ' ' || b.last_name AS full_name_b, b.risk_profile AS risk_profile_b, a.state\nFROM financial_services.customers a\nJOIN financial_services.customers b\n  ON a.state = b.state\n  AND a.risk_profile <> b.risk_profile\nWHERE a.state IN (\n  SELECT state\n  FROM financial_services.customers\n  GROUP BY state\n  HAVING COUNT(*) > 5\n);"}, {"role": "user", "content": "Also include the state in the result."}, {"role": "assistant", "content": "SELECT a.customer_id AS customer_id_a, a.first_name || ' ' || a.last_name AS full_name_a, b.customer_id AS customer_id_b, b.first_name || ' ' || b.last_name AS full_name_b, a.state\nFROM financial_services.customers a\nJOIN financial_services.customers b\n  ON a.state = b.state\n  AND a.risk_profile <> b.risk_profile\nWHERE a.state IN (\n  SELECT state\n  FROM financial_services.customers\n  GROUP BY state\n  HAVING COUNT(*) > 5\n);"}, {"role": "user", "content": "Finally, order the output by state and then by a.customer_id."}, {"role": "assistant", "content": "SELECT a.customer_id AS customer_id_a, a.first_name || ' ' || a.last_name AS full_name_a, b.customer_id AS customer_id_b, b.first_name || ' ' || b.last_name AS full_name_b, a.state\nFROM financial_services.customers a\nJOIN financial_services.customers b\n  ON a.state = b.state\n  AND a.risk_profile <> b.risk_profile\nWHERE a.state IN (\n  SELECT state\n  FROM financial_services.customers\n  GROUP BY state\n  HAVING COUNT(*) > 5\n)\nORDER BY a.state, a.customer_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.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 )\n"}
{"conversations": [{"role": "user", "content": "我想了解某个组件的库存情况，包括库存数量、仓库位置和接收日期。"}, {"role": "assistant", "content": "SELECT ci.quantity, ci.location_warehouse, ci.received_date\nFROM manufacturing.component_inventory ci\nWHERE ci.component_id = 'specific_component_id';"}, {"role": "user", "content": "如果我想查询特定批次号的库存信息，应该怎么修改？"}, {"role": "assistant", "content": "SELECT ci.quantity, ci.location_warehouse, ci.received_date\nFROM manufacturing.component_inventory ci\nWHERE ci.component_id = 'specific_component_id' AND ci.batch_number = 'specific_batch_number';"}, {"role": "user", "content": "如果我想进一步筛选出接收日期在2023年之后的库存记录呢？"}, {"role": "assistant", "content": "SELECT ci.quantity, ci.location_warehouse, ci.received_date\nFROM manufacturing.component_inventory ci\nWHERE ci.component_id = 'specific_component_id' AND ci.batch_number = 'specific_batch_number' AND ci.received_date > '2023-01-01';"}, {"role": "user", "content": "请再加上按接收日期从新到旧排序。"}, {"role": "assistant", "content": "SELECT ci.quantity, ci.location_warehouse, ci.received_date\nFROM manufacturing.component_inventory ci\nWHERE ci.component_id = 'specific_component_id' AND ci.batch_number = 'specific_batch_number' AND ci.received_date > '2023-01-01'\nORDER BY ci.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\nCREATE TABLE manufacturing.components (\n    component_id character varying(64) NOT NULL, -- unique identifier for the component\n    part_number character varying(100) NOT NULL UNIQUE, -- manufacturer-specific part number\n    component_name character varying(255) NOT NULL, -- descriptive name (e.g., Landing Gear Strut, Wing Spar)\n    description text, -- detailed description\n    material_id character varying(64), -- FK linking to the material used\n    supplier_id character varying(64), -- FK linking to the supplier\n    weight_kg numeric(10,3), -- weight of the component in kg\n    cost_usd numeric(12,2), -- cost of the component in USD\n    criticality_level character varying(20), -- e.g., 'High', 'Medium', 'Low'\n    PRIMARY KEY (component_id)\n)\nCREATE TABLE manufacturing.suppliers (\n    supplier_id character varying(64) NOT NULL, -- unique identifier for the supplier\n    supplier_name character varying(255) NOT NULL, -- legal name of the supplier company\n    address text, -- primary address of the supplier\n    country character varying(100), -- country of the supplier\n    contact_person character varying(128), -- primary contact person\n    contact_email character varying(128), -- contact email\n    quality_rating numeric(3,1), -- supplier quality rating (e.g., 1.0 to 5.0)\n    certified_date date, -- date when supplier certification was last validated\n    PRIMARY KEY (supplier_id)\n)\nCREATE TABLE manufacturing.materials (\n    material_id character varying(64) NOT NULL,  -- unique identifier for the material\n    material_name character varying(128) NOT NULL, -- common name (e.g., Titanium Alloy Grade 5, Carbon Fiber Prepreg)\n    specification character varying(255), -- specification standard (e.g., AMS 4928)\n    description text, -- detailed description of properties\n    density_kg_m3 numeric(10, 4), -- density in kg per cubic meter\n    tensile_strength_mpa integer, -- tensile strength in Megapascals\n    PRIMARY KEY (material_id)\n)\nCREATE TABLE manufacturing.assembly_steps (\n    step_id character varying(64) NOT NULL, -- unique identifier for an assembly step/task\n    line_id character varying(64) NOT NULL, -- FK to the assembly line where this step occurs\n    step_number integer NOT NULL, -- sequence number of the step on the line\n    step_name character varying(255) NOT NULL, -- name of the task (e.g., Install Wing Root Fairing)\n    description text, -- detailed instructions or description\n    standard_duration_hours numeric(8,2), -- estimated time to complete the step\n    required_skill_level character varying(50), -- skill level needed (e.g., 'Mechanic II', 'Electrician I')\n    workstation character varying(100), -- specific workstation or area for the step\n    PRIMARY KEY (step_id)\n)\nCREATE TABLE manufacturing.inspections (\n    inspection_id character varying(64) NOT NULL, -- unique identifier for the inspection event\n    build_id character varying(64) NOT NULL, -- FK to the specific aircraft build being inspected\n    component_id character varying(64), -- FK to the specific component inspected (if applicable)\n    step_id character varying(64), -- FK to the assembly step after which inspection occurred (if applicable)\n    inspection_type character varying(100) NOT NULL, -- e.g., 'Visual', 'NDT', 'Functional Test'\n    inspector_employee_id character varying(64) NOT NULL, -- FK to the employee who performed the inspection\n    inspection_timestamp timestamp NOT NULL, -- time when the inspection was completed\n    result character varying(20) NOT NULL, -- 'Pass', 'Fail', 'Rework Needed'\n    remarks text, -- detailed notes or findings\n    PRIMARY KEY (inspection_id)\n)\nCREATE TABLE manufacturing.component_inventory (\n    inventory_record_id character varying(64) NOT NULL, -- unique ID for this inventory record/batch\n    component_id character varying(64) NOT NULL, -- FK to the component\n    quantity integer NOT NULL, -- number of units of this component in stock for this batch\n    location_warehouse character varying(100), -- warehouse identifier\n    location_bin character varying(100), -- specific bin or shelf location\n    received_date timestamp NOT NULL, -- when this batch was received\n    expiry_date date, -- expiry date if applicable (e.g., for sealants, adhesives)\n    batch_number character varying(100), -- supplier batch number\n    last_updated timestamp NOT NULL, -- timestamp of the last update to this record\n    PRIMARY KEY (inventory_record_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": "Show all routes where the estimated duration is at least 120 minutes including their route number, type, and origin and destination location IDs."}, {"role": "assistant", "content": "SELECT route_number, type, origin_location_id, destination_location_id\nFROM transportation.routes\nWHERE estimated_duration_minutes >= 120;"}, {"role": "user", "content": "Can you also include the distance in kilometers in the result?"}, {"role": "assistant", "content": "SELECT route_number, type, origin_location_id, destination_location_id, distance_km\nFROM transportation.routes\nWHERE estimated_duration_minutes >= 120;"}, {"role": "user", "content": "I would like to see the results ordered by distance in descending order."}, {"role": "assistant", "content": "SELECT route_number, type, origin_location_id, destination_location_id, distance_km\nFROM transportation.routes\nWHERE estimated_duration_minutes >= 120\nORDER BY distance_km DESC;"}, {"role": "user", "content": "Actually, please only show routes where the type is 'Intercity'."}, {"role": "assistant", "content": "SELECT route_number, type, origin_location_id, destination_location_id, distance_km\nFROM transportation.routes\nWHERE estimated_duration_minutes >= 120 AND type = 'Intercity'\nORDER BY 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.routes ( route_id text PRIMARY KEY, route_number text, description text, origin_location_id text, destination_location_id text, distance_km numeric, estimated_duration_minutes int, type text )\n"}
{"conversations": [{"role": "user", "content": "Show me all active electric vehicles along with their depot location details, including the depot's city and timezone."}, {"role": "assistant", "content": "SELECT v.vehicle_id, v.license_plate, v.make, v.model, v.year, l.name AS depot_name, l.city, l.timezone FROM transportation.vehicles v JOIN transportation.locations l ON v.depot_id = l.location_id WHERE v.fuel_type = 'electric' AND v.status = 'active';"}, {"role": "user", "content": "Now filter these results to only show vehicles acquired in the last 2 years and order them by acquisition date with the newest first."}, {"role": "assistant", "content": "SELECT v.vehicle_id, v.license_plate, v.make, v.model, v.year, v.acquisition_date, l.name AS depot_name, l.city, l.timezone FROM transportation.vehicles v JOIN transportation.locations l ON v.depot_id = l.location_id WHERE v.fuel_type = 'electric' AND v.status = 'active' AND v.acquisition_date >= DATE_SUB(CURRENT_DATE, INTERVAL 2 YEAR) ORDER BY v.acquisition_date DESC;"}, {"role": "user", "content": "Can you also include the count of completed trips for each vehicle in the results?"}, {"role": "assistant", "content": "SELECT v.vehicle_id, v.license_plate, v.make, v.model, v.year, v.acquisition_date, l.name AS depot_name, l.city, l.timezone, COUNT(t.trip_id) AS completed_trips FROM transportation.vehicles v JOIN transportation.locations l ON v.depot_id = l.location_id LEFT JOIN transportation.trips t ON v.vehicle_id = t.vehicle_id AND t.status = 'completed' WHERE v.fuel_type = 'electric' AND v.status = 'active' AND v.acquisition_date >= DATE_SUB(CURRENT_DATE, INTERVAL 2 YEAR) GROUP BY v.vehicle_id, v.license_plate, v.make, v.model, v.year, v.acquisition_date, l.name, l.city, l.timezone ORDER BY v.acquisition_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 transportation.vehicles ( vehicle_id.text, license_plate.text, vin.text, make.text, model.text, year.integer, type.text, capacity.integer, fuel_type.text, status.text, depot_id.text, acquisition_date.date )\nCREATE TABLE transportation.trips ( trip_id.text, route_id.text, vehicle_id.text, driver_id.text, scheduled_departure.timestamp, actual_departure.timestamp, scheduled_arrival.timestamp, actual_arrival.timestamp, origin_location_id.text, destination_location_id.text, status.text, passenger_count.integer, cargo_manifest_id.text )\nCREATE TABLE transportation.locations ( location_id.text, name.text, type.text, address_line1.text, city.text, state_province.text, postal_code.text, country.text, latitude.numeric, longitude.numeric, timezone.text )\nCREATE TABLE transportation.maintenance_logs ( log_id.text, vehicle_id.text, service_date.date, odometer_reading.integer, service_type.text, description.text, cost.numeric, mechanic_name.text, next_service_due_date.date )\nCREATE TABLE transportation.fuel_logs ( fuel_log_id.text, vehicle_id.text, trip_id.text, log_timestamp.timestamp, fuel_type.text, quantity.numeric, unit.text, cost_per_unit.numeric, total_cost.numeric, odometer_reading.integer, location_id.text )\nCREATE TABLE transportation.passengers ( passenger_id.text, first_name.text, last_name.text, email.text, phone_number.text, date_of_birth.date, loyalty_program_id.text, created_at.timestamp )\nCREATE TABLE transportation.bookings ( booking_id.text, passenger_id.text, trip_id.text, seat_number.text, booking_time.timestamp, status.text, fare.numeric, payment_transaction_id.text, special_requests.text )\n"}
{"conversations": [{"role": "user", "content": "Generate a report showing the total number of achievement unlocks broken down by the calendar day they occurred. Show the date and the total number of unlocks for that day."}, {"role": "assistant", "content": "SELECT DATE(unlocked_at) AS unlock_date, COUNT(player_achievement_id) AS unlock_count FROM gaming_technology.player_achievements GROUP BY DATE(unlocked_at);"}, {"role": "user", "content": "Only show days with more than 50 unlocks."}, {"role": "assistant", "content": "SELECT DATE(unlocked_at) AS unlock_date, COUNT(player_achievement_id) AS unlock_count FROM gaming_technology.player_achievements GROUP BY DATE(unlocked_at) HAVING COUNT(player_achievement_id) > 50;"}, {"role": "user", "content": "Also include the number of unique players who unlocked achievements on those days."}, {"role": "assistant", "content": "SELECT DATE(unlocked_at) AS unlock_date, COUNT(player_achievement_id) AS unlock_count, COUNT(DISTINCT player_id) AS unique_player_count FROM gaming_technology.player_achievements GROUP BY DATE(unlocked_at) HAVING COUNT(player_achievement_id) > 50;"}, {"role": "user", "content": "Order the results by unlock_count descending and limit to the top 10 days."}, {"role": "assistant", "content": "SELECT DATE(unlocked_at) AS unlock_date, COUNT(player_achievement_id) AS unlock_count, COUNT(DISTINCT player_id) AS unique_player_count FROM gaming_technology.player_achievements GROUP BY DATE(unlocked_at) HAVING COUNT(player_achievement_id) > 50 ORDER BY unlock_count 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 gaming_technology.player_achievements ( player_achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), player_id uuid NOT NULL, achievement_id uuid NOT NULL, unlocked_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (player_achievement_id), UNIQUE (player_id, achievement_id) )\n"}
{"conversations": [{"role": "user", "content": "List 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": "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": "How many agents were hired in the current year and what is their average commission rate?"}, {"role": "assistant", "content": "SELECT COUNT(*) AS hired_this_year, AVG(commission_rate) AS average_commission_rate FROM insurance.agents WHERE EXTRACT(YEAR FROM hire_date) = EXTRACT(YEAR FROM CURRENT_DATE);"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.agents ( agent_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, agency_name character varying(150), license_number character varying(100) NOT NULL UNIQUE, license_state character varying(50) NOT NULL, contact_email character varying(128) UNIQUE, contact_phone character varying(30), hire_date date, termination_date date, status character varying(20) NOT NULL DEFAULT 'Active', commission_rate numeric(5, 4) NOT NULL DEFAULT 0.05, manager_id character varying(64), PRIMARY KEY (agent_id) )\n"}
{"conversations": [{"role": "user", "content": "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": "Show me the average difficulty for blocks that have a previous block versus those that don't have a previous block."}, {"role": "assistant", "content": "SELECT CASE WHEN previous_block_id IS NULL THEN 'No Previous Block' ELSE 'Has Previous Block' END AS block_type, AVG(difficulty) AS avg_difficulty FROM blockchain.blocks GROUP BY block_type;"}, {"role": "user", "content": "Now break this down further by year, showing the yearly averages for each block type."}, {"role": "assistant", "content": "SELECT EXTRACT(YEAR FROM timestamp) AS year, CASE WHEN previous_block_id IS NULL THEN 'No Previous Block' ELSE 'Has Previous Block' END AS block_type, AVG(difficulty) AS avg_difficulty FROM blockchain.blocks GROUP BY EXTRACT(YEAR FROM timestamp), block_type ORDER BY year;"}, {"role": "user", "content": "Can you also include the count of blocks for each year and type combination?"}, {"role": "assistant", "content": "SELECT EXTRACT(YEAR FROM timestamp) AS year, CASE WHEN previous_block_id IS NULL THEN 'No Previous Block' ELSE 'Has Previous Block' END AS block_type, COUNT(*) AS block_count, AVG(difficulty) AS avg_difficulty FROM blockchain.blocks GROUP BY EXTRACT(YEAR FROM timestamp), block_type ORDER BY 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 blockchain.blocks ( block_id character varying(64) NOT NULL, previous_block_id character varying(64), timestamp timestamp NOT NULL, nonce integer NOT NULL, merkle_root character varying(128) NOT NULL, difficulty integer NOT NULL, PRIMARY KEY (block_id) )\n"}
{"conversations": [{"role": "user", "content": "For each contract, can you list the token symbols and total supply of all tokens created by that contract, along with the contract's current status?"}, {"role": "assistant", "content": "SELECT c.contract_id, c.address AS contract_address, c.status, t.token_symbol, t.total_supply\nFROM web3.contracts c\nJOIN web3.tokens t ON c.address = t.contract_address\nORDER BY c.contract_id, t.token_symbol;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.contracts ( contract_id text, address text, abi text, bytecode text, deployer_address text, deployed_at timestamp, network_id text, status text )\nCREATE TABLE web3.events ( event_id text, contract_id text, event_name text, data text, emitted_at timestamp, transaction_id text, log_index integer )\nCREATE TABLE web3.transactions ( transaction_id text, from_address text, to_address text, value numeric, gas_used integer, gas_price numeric, block_number integer, timestamp timestamp, input_data text, status text, nonce integer )\nCREATE TABLE web3.tokens ( token_id text, contract_address text, token_name text, token_symbol text, decimals integer, total_supply numeric )\nCREATE TABLE web3.token_transfers ( transfer_id text, token_id text, from_address text, to_address text, value numeric, transaction_id text, log_index integer )\nCREATE TABLE web3.users ( user_id text, username text, email text, password_hash text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show the count of applications submitted per day for the last 7 days. Include the date and application_count, ordered by date ascending."}, {"role": "assistant", "content": "SELECT CAST(submitted_at AS date) AS date,\n       COUNT(*) AS application_count\nFROM government_services.applications\nWHERE submitted_at >= CURRENT_DATE - INTERVAL '7 days'\nGROUP BY CAST(submitted_at AS date)\nORDER BY 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 government_services.applications ( application_id text, citizen_id text, service_id text, submitted_at timestamp, status text, last_updated_at timestamp, assigned_employee_id text, decision_date date, notes text, reference_number text )\nCREATE TABLE government_services.documents (\n    document_id character varying(64) NOT NULL, -- unique identifier for the document instance\n    application_id character varying(64), -- FK to applications table (optional, could be linked to citizen directly)\n    citizen_id character varying(64) NOT NULL, -- FK to citizens table\n    document_type character varying(100) NOT NULL, -- e.g., Passport Scan, Proof of Address, Birth Certificate\n    file_reference text NOT NULL, -- reference to the stored file (e.g., S3 URL, internal path)\n    upload_timestamp timestamp NOT NULL,\n    expiry_date date,\n    verification_status character varying(30) DEFAULT 'Pending', -- e.g., Pending, Verified, Rejected\n    verified_by_employee_id character varying(64), -- FK to employees table\n    verification_timestamp timestamp,\n    PRIMARY KEY (document_id)\n)\nCREATE TABLE government_services.payments ( payment_id text PRIMARY KEY, application_id text, citizen_id text, service_id text, amount numeric, currency text, payment_method text, payment_provider_reference text, payment_timestamp timestamp, status text, notes text )\nCREATE TABLE government_services.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": "What is the average ROI and total profit for smart money addresses on the Arbitrum chain?"}, {"role": "assistant", "content": "SELECT AVG(roi) AS avg_roi, SUM(profit) AS total_profit\nFROM smart_money_profit\nWHERE chain = 'Arbitrum';"}, {"role": "user", "content": "Can you break this down by most profitable token as well?"}, {"role": "assistant", "content": "SELECT most_profit_token, AVG(roi) AS avg_roi, SUM(profit) AS total_profit\nFROM smart_money_profit\nWHERE chain = 'Arbitrum'\nGROUP BY most_profit_token\nORDER BY total_profit DESC;"}, {"role": "user", "content": "Please only include tokens where the average ROI is greater than 1, and order by average ROI descending."}, {"role": "assistant", "content": "SELECT most_profit_token, AVG(roi) AS avg_roi, SUM(profit) AS total_profit\nFROM smart_money_profit\nWHERE chain = 'Arbitrum'\nGROUP BY most_profit_token\nHAVING AVG(roi) > 1\nORDER BY avg_roi DESC;"}, {"role": "user", "content": "Also include the number of addresses contributing to each token's statistics."}, {"role": "assistant", "content": "SELECT most_profit_token, AVG(roi) AS avg_roi, SUM(profit) AS total_profit, COUNT(DISTINCT address) AS address_count\nFROM smart_money_profit\nWHERE chain = 'Arbitrum'\nGROUP BY most_profit_token\nHAVING AVG(roi) > 1\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 smart_money_profit ( address.text, rank.numeric, profit.numeric, roi.numeric, realized_ratio.numeric, most_profit_token.text, last_trade_time.text, chain.text )\n"}
{"conversations": [{"role": "user", "content": "Show me the name and founding date of every law firm."}, {"role": "assistant", "content": "SELECT firm_name, founded_date\nFROM law_firms;"}, {"role": "user", "content": "Also include the firm's phone number."}, {"role": "assistant", "content": "SELECT firm_name, phone, founded_date\nFROM law_firms;"}, {"role": "user", "content": "Exclude any firms that don't have a website specified."}, {"role": "assistant", "content": "SELECT firm_name, phone, founded_date\nFROM law_firms\nWHERE website IS NOT NULL;"}, {"role": "user", "content": "Finally, order the list by firm_name in descending order."}, {"role": "assistant", "content": "SELECT firm_name, phone, founded_date\nFROM law_firms\nWHERE website IS NOT NULL\nORDER BY firm_name DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.law_firms (\n    firm_id character varying(64) NOT NULL,  -- unique identifier for the law firm\n    firm_name character varying(200) NOT NULL, -- official name of the law firm\n    address text NOT NULL, -- primary address of the firm\n    phone character varying(32), -- firm's main phone number\n    website character varying(255), -- firm's website URL\n    founded_date date, -- date the firm was established\n    managing_partner_id character varying(64), -- FK to lawyers table (optional)\n    PRIMARY KEY (firm_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Show me all reservations with more than 2 adults, along with their property names and room types."}, {"role": "assistant", "content": "SELECT r.reservation_id, p.property_name, rt.room_type_name, r.check_in_date, r.check_out_date, r.num_adults FROM hospitality_technology.reservations r JOIN hospitality_technology.properties p ON r.property_id = p.property_id JOIN hospitality_technology.room_types rt ON r.room_type_id = rt.room_type_id WHERE r.num_adults > 2;"}, {"role": "user", "content": "Now, include only reservations with a total amount over $500 and order them by check-in date."}, {"role": "assistant", "content": "SELECT r.reservation_id, p.property_name, rt.room_type_name, r.check_in_date, r.check_out_date, r.num_adults, r.total_amount FROM hospitality_technology.reservations r JOIN hospitality_technology.properties p ON r.property_id = p.property_id JOIN hospitality_technology.room_types rt ON r.room_type_id = rt.room_type_id WHERE r.num_adults > 2 AND r.total_amount > 500 ORDER BY r.check_in_date;"}, {"role": "user", "content": "The query is missing the guest ID. Can you include that as well?"}, {"role": "assistant", "content": "SELECT r.reservation_id, r.guest_id, p.property_name, rt.room_type_name, r.check_in_date, r.check_out_date, r.num_adults, r.total_amount FROM hospitality_technology.reservations r JOIN hospitality_technology.properties p ON r.property_id = p.property_id JOIN hospitality_technology.room_types rt ON r.room_type_id = rt.room_type_id WHERE r.num_adults > 2 AND r.total_amount > 500 ORDER BY r.check_in_date;"}, {"role": "user", "content": "Actually, I need to see only reservations from properties with a star rating of 4.0 or higher."}, {"role": "assistant", "content": "SELECT r.reservation_id, r.guest_id, p.property_name, rt.room_type_name, r.check_in_date, r.check_out_date, r.num_adults, r.total_amount, p.star_rating FROM hospitality_technology.reservations r JOIN hospitality_technology.properties p ON r.property_id = p.property_id JOIN hospitality_technology.room_types rt ON r.room_type_id = rt.room_type_id WHERE r.num_adults > 2 AND r.total_amount > 500 AND p.star_rating >= 4.0 ORDER BY r.check_in_date;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.properties ( property_id character varying(64) NOT NULL, property_name character varying(255) NOT NULL, address_line1 character varying(255) NOT NULL, address_line2 character varying(255), city character varying(100) NOT NULL, state_province character varying(100), postal_code character varying(20) NOT NULL, country_code character varying(3) NOT NULL, phone_number character varying(30), email_address character varying(255), property_type character varying(50) NOT NULL, star_rating numeric(2,1), timezone character varying(64) NOT NULL, manager_staff_id character varying(64), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (property_id) )\nCREATE TABLE hospitality_technology.rooms ( room_id text PRIMARY KEY, property_id text, room_number text, room_type_id text, floor int, status text, is_smoking boolean, features text, current_condition text, last_cleaned_at timestamp )\nCREATE TABLE hospitality_technology.guests ( guest_id text, first_name text, last_name text, email text, phone_number text, date_of_birth date, address_line1 text, city text, state_province text, postal_code text, country_code text, preferences text, loyalty_member_id text, communication_consent boolean, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.reservations ( reservation_id.text, property_id.text, guest_id.text, room_id.text, room_type_id.text, check_in_date.date, check_out_date.date, actual_check_in_ts.timestamp, actual_check_out_ts.timestamp, num_adults.integer, num_children.integer, status.text, booking_source.text, rate_plan_id.text, total_amount.numeric, amount_paid.numeric, special_requests.text, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE hospitality_technology.staff ( staff_id text, property_id text, first_name text, last_name text, position text, work_email text, work_phone text, hire_date date, termination_date date, is_active boolean, access_level integer, manager_id text, created_at timestamp )\nCREATE TABLE hospitality_technology.services ( service_id text PRIMARY KEY, property_id text, service_name text, description text, category text, price numeric, unit text, is_available boolean, department text )\nCREATE TABLE hospitality_technology.service_orders ( order_id character varying(64) NOT NULL, reservation_id character varying(64), guest_id character varying(64) NOT NULL, service_id character varying(64) NOT NULL, staff_id_ordered character varying(64), staff_id_delivered character varying(64), order_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, delivery_timestamp timestamp with time zone, quantity integer NOT NULL DEFAULT 1, unit_price numeric(10, 2) NOT NULL, total_price numeric(12, 2) NOT NULL, status character varying(50) NOT NULL, notes text, bill_id character varying(64), PRIMARY KEY (order_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (service_id) REFERENCES hospitality_technology.services(service_id), FOREIGN KEY (staff_id_ordered) REFERENCES hospitality_technology.staff(staff_id), FOREIGN KEY (staff_id_delivered) REFERENCES hospitality_technology.staff(staff_id) )\nCREATE TABLE hospitality_technology.payments ( payment_id.text, reservation_id.text, guest_id.text, bill_id.text, amount.numeric, currency_code.text, payment_method.text, card_type.text, card_last_four.text, transaction_ref.text, payment_timestamp.timestamp, status.text, staff_id_processed.text, notes.text )\nCREATE TABLE hospitality_technology.reviews ( review_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, reservation_id character varying(64) UNIQUE, guest_id character varying(64) NOT NULL, rating_overall integer, rating_cleanliness integer, rating_service integer, rating_location integer, rating_value integer, comment text, review_source character varying(100), review_date timestamp with time zone NOT NULL DEFAULT current_timestamp, is_public boolean DEFAULT true, staff_response text, response_staff_id character varying(64), response_date timestamp with time zone, PRIMARY KEY (review_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (response_staff_id) REFERENCES hospitality_technology.staff(staff_id) )\n"}
{"conversations": [{"role": "user", "content": "List all service orders for spa services with their guest names and total prices, ordered by total price in descending order."}, {"role": "assistant", "content": "SELECT g.first_name, g.last_name, so.order_id, so.total_price FROM hospitality_technology.service_orders so JOIN hospitality_technology.guests g ON so.guest_id = g.guest_id WHERE so.service_id LIKE 'SPA%' ORDER BY so.total_price DESC;"}, {"role": "user", "content": "Now, include only orders with a total price over $100 and show the property ID where the service was ordered."}, {"role": "assistant", "content": "SELECT g.first_name, g.last_name, so.order_id, so.total_price, r.property_id FROM hospitality_technology.service_orders so JOIN hospitality_technology.guests g ON so.guest_id = g.guest_id JOIN hospitality_technology.reservations r ON so.reservation_id = r.reservation_id WHERE so.service_id LIKE 'SPA%' AND so.total_price > 100 ORDER BY so.total_price DESC;"}, {"role": "user", "content": "The query is missing the service name. Can you include that as well?"}, {"role": "assistant", "content": "SELECT g.first_name, g.last_name, so.order_id, so.total_price, r.property_id, s.service_name FROM hospitality_technology.service_orders so JOIN hospitality_technology.guests g ON so.guest_id = g.guest_id JOIN hospitality_technology.reservations r ON so.reservation_id = r.reservation_id JOIN hospitality_technology.services s ON so.service_id = s.service_id WHERE so.service_id LIKE 'SPA%' AND so.total_price > 100 ORDER BY so.total_price DESC;"}, {"role": "user", "content": "Actually, I only need orders from properties in California, and order by property ID first, then by total price."}, {"role": "assistant", "content": "SELECT g.first_name, g.last_name, so.order_id, so.total_price, r.property_id, s.service_name FROM hospitality_technology.service_orders so JOIN hospitality_technology.guests g ON so.guest_id = g.guest_id JOIN hospitality_technology.reservations r ON so.reservation_id = r.reservation_id JOIN hospitality_technology.services s ON so.service_id = s.service_id JOIN hospitality_technology.properties p ON r.property_id = p.property_id WHERE so.service_id LIKE 'SPA%' AND so.total_price > 100 AND p.state_province = 'California' ORDER BY r.property_id, so.total_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 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 (\n    guest_id character varying(64) NOT NULL,  -- unique identifier for the guest profile\n    first_name character varying(100) NOT NULL, -- guest's first name\n    last_name character varying(100) NOT NULL, -- guest's last name\n    email character varying(255) UNIQUE, -- guest's email address (unique identifier?)\n    phone_number character varying(30), -- guest's phone number\n    date_of_birth date, -- guest's date of birth\n    address_line1 character varying(255), -- guest's home address\n    city character varying(100),\n    state_province character varying(100),\n    postal_code character varying(20),\n    country_code character varying(3),\n    preferences text, -- notes on guest preferences (e.g., allergies, room location)\n    loyalty_member_id character varying(64) UNIQUE, -- FK to loyalty_members table\n    communication_consent boolean DEFAULT true, -- consent for marketing communications\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (guest_id)\n)\nCREATE TABLE hospitality_technology.reservations (\n    reservation_id character varying(64) NOT NULL,  -- unique identifier for the booking\n    property_id character varying(64) NOT NULL, -- FK to properties table\n    guest_id character varying(64) NOT NULL, -- FK to guests table (primary guest)\n    room_id character varying(64), -- FK to rooms table (assigned room, might be null initially)\n    room_type_id character varying(64) NOT NULL, -- FK to room_types table (booked room type)\n    check_in_date date NOT NULL, -- scheduled check-in date\n    check_out_date date NOT NULL, -- scheduled check-out date\n    actual_check_in_ts timestamp with time zone, -- actual check-in time\n    actual_check_out_ts timestamp with time zone, -- actual check-out time\n    num_adults integer NOT NULL, -- number of adults\n    num_children integer DEFAULT 0, -- number of children\n    status character varying(50) NOT NULL, -- e.g., Pending, Confirmed, CheckedIn, CheckedOut, Cancelled, NoShow\n    booking_source character varying(100), -- e.g., Website, OTA (Expedia, Booking.com), Phone, WalkIn\n    rate_plan_id character varying(64), -- FK to rate_plans table (optional)\n    total_amount numeric(12, 2), -- estimated or final total cost\n    amount_paid numeric(12, 2) DEFAULT 0.00, -- amount already paid\n    special_requests text, -- specific guest requests for this booking\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (reservation_id),\n    FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n    FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id),\n    FOREIGN KEY (room_id) REFERENCES hospitality_technology.rooms(room_id),\n    FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id)\n)\nCREATE TABLE hospitality_technology.service_orders ( order_id character varying(64) NOT NULL, reservation_id character varying(64), guest_id character varying(64) NOT NULL, service_id character varying(64) NOT NULL, staff_id_ordered character varying(64), staff_id_delivered character varying(64), order_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, delivery_timestamp timestamp with time zone, quantity integer NOT NULL DEFAULT 1, unit_price numeric(10, 2) NOT NULL, total_price numeric(12, 2) NOT NULL, status character varying(50) NOT NULL, notes text, bill_id character varying(64), PRIMARY KEY (order_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (service_id) REFERENCES hospitality_technology.services(service_id), FOREIGN KEY (staff_id_ordered) REFERENCES hospitality_technology.staff(staff_id), FOREIGN KEY (staff_id_delivered) REFERENCES hospitality_technology.staff(staff_id) )\nCREATE TABLE hospitality_technology.payments ( payment_id text, reservation_id text, guest_id text, bill_id text, amount numeric, currency_code text, payment_method text, card_type text, card_last_four text, transaction_ref text, payment_timestamp timestamp, status text, staff_id_processed text, notes text )\nCREATE TABLE hospitality_technology.reviews ( review_id 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": "How many posts have a media file attached?"}, {"role": "assistant", "content": "SELECT count(*) FROM social_media.posts WHERE media_url IS NOT NULL;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id text PRIMARY KEY, username text, email text, password_hash text, full_name text, profile_picture_url text, bio text, location text, created_at timestamp, updated_at timestamp, is_verified bool )\nCREATE TABLE social_media.posts ( post_id text PRIMARY KEY, user_id text, content text, media_url text, media_type text, created_at timestamp, updated_at timestamp, visibility text, location_lat numeric, location_lon numeric )\nCREATE TABLE social_media.comments ( comment_id text PRIMARY KEY, post_id text, user_id text, parent_comment_id text, content text, created_at timestamp, updated_at timestamp )\nCREATE TABLE social_media.likes ( like_id text PRIMARY KEY, user_id text, post_id text, comment_id text, created_at timestamp )\nCREATE TABLE social_media.hashtags ( hashtag_id text PRIMARY KEY, tag_name text, created_at timestamp )\nCREATE TABLE social_media.post_hashtags ( post_hashtag_id text PRIMARY KEY, post_id text, hashtag_id text )\nCREATE TABLE social_media.messages ( message_id text PRIMARY KEY, conversation_id text, sender_user_id text, content text, media_url text, media_type text, sent_at timestamp, read_at timestamp )\nCREATE TABLE social_media.conversations ( conversation_id text PRIMARY KEY, created_at timestamp, last_message_at timestamp, is_group_chat bool, group_name text )\nCREATE TABLE social_media.conversation_participants ( participant_id text PRIMARY KEY, conversation_id text, user_id text, joined_at timestamp, last_read_at timestamp )\nCREATE TABLE social_media.notifications ( notification_id text PRIMARY KEY, recipient_user_id text, sender_user_id text, notification_type text, target_entity_id text, target_entity_type text, created_at timestamp, read_at timestamp )\nCREATE TABLE social_media.user_settings ( setting_id text PRIMARY KEY, user_id text, theme text, email_notifications_enabled bool, push_notifications_enabled bool, private_profile bool, updated_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "List the application ID and citizen ID for all documents of type 'Proof of Address'."}, {"role": "assistant", "content": "SELECT application_id, citizen_id FROM government_services.documents WHERE document_type = 'Proof of 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 government_services.documents ( document_id text, application_id text, citizen_id text, document_type text, file_reference text, upload_timestamp timestamp, expiry_date date, verification_status text, verified_by_employee_id text, verification_timestamp timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show the application ID, payment amount, and payment method for all payments that have a status of 'Completed' and are related to services in the 'Licensing' category."}, {"role": "assistant", "content": "SELECT p.application_id, p.amount, p.payment_method\nFROM government_services.payments p\nJOIN government_services.services s ON p.service_id = s.service_id\nWHERE p.status = 'Completed' AND s.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.citizens ( citizen_id text, national_id_number text, first_name text, last_name text, date_of_birth date, gender text, primary_address text, contact_email text, contact_phone text, registration_date timestamp, is_verified boolean )\nCREATE TABLE government_services.services ( service_id text 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, 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 (\n    document_id character varying(64) NOT NULL, -- unique identifier for the document instance\n    application_id character varying(64), -- FK to applications table (optional, could be linked to citizen directly)\n    citizen_id character varying(64) NOT NULL, -- FK to citizens table\n    document_type character varying(100) NOT NULL, -- e.g., Passport Scan, Proof of Address, Birth Certificate\n    file_reference text NOT NULL, -- reference to the stored file (e.g., S3 URL, internal path)\n    upload_timestamp timestamp NOT NULL,\n    expiry_date date,\n    verification_status character varying(30) DEFAULT 'Pending', -- e.g., Pending, Verified, Rejected\n    verified_by_employee_id character varying(64), -- FK to employees table\n    verification_timestamp timestamp,\n    PRIMARY KEY (document_id)\n)\nCREATE TABLE government_services.payments ( payment_id text PRIMARY KEY, application_id text, citizen_id text, service_id text, amount numeric, currency text, payment_method text, payment_provider_reference text, payment_timestamp timestamp, status text, notes text )\nCREATE TABLE government_services.employees (\n    employee_id character varying(64) NOT NULL, -- unique identifier for the government employee\n    agency_id character varying(64) NOT NULL, -- FK to agencies table\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    job_title character varying(150) NOT NULL,\n    department character varying(100),\n    work_email character varying(128) NOT NULL UNIQUE,\n    work_phone character varying(32),\n    hire_date date NOT NULL,\n    termination_date date, -- null if currently employed\n    access_level character varying(50), -- Role or permission level\n    manager_employee_id character varying(64), -- FK to self for reporting structure\n    PRIMARY KEY (employee_id)\n)\nCREATE TABLE government_services.service_locations ( location_id text PRIMARY KEY, agency_id text, location_name text, address text, city text, state text, postal_code text, latitude numeric, longitude numeric, operating_hours text, contact_phone text, is_accessible boolean )\nCREATE TABLE government_services.appointments ( appointment_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, employee_id character varying(64), location_id character varying(64), service_id character varying(64), scheduled_start_time timestamp NOT NULL, scheduled_end_time timestamp, purpose text NOT NULL, status character varying(30) NOT NULL, booking_method character varying(50), created_at timestamp NOT NULL, notes text, PRIMARY KEY (appointment_id) )\nCREATE TABLE government_services.notifications ( notification_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, application_id character varying(64), message_subject character varying(255), message_body text NOT NULL, channel character varying(30) NOT NULL, sent_at timestamp NOT NULL, status character varying(30) NOT NULL, related_entity_type character varying(50), related_entity_id character varying(64), PRIMARY KEY (notification_id) )\n"}
{"conversations": [{"role": "user", "content": "Show me pairs of a block and its previous block where the previous block's difficulty was greater than 100000. Include details for both blocks."}, {"role": "assistant", "content": "SELECT t1.block_id AS current_block_id, t2.block_id AS previous_block_id, t1.timestamp AS current_timestamp, t2.timestamp AS previous_timestamp, t1.difficulty AS current_difficulty, t2.difficulty AS previous_difficulty FROM blockchain.blocks AS t1 JOIN blockchain.blocks AS t2 ON t1.previous_block_id = t2.block_id WHERE t2.difficulty > 100000;"}, {"role": "user", "content": "Okay, now filter those results to only include pairs where the time difference between the current block and its predecessor is less than 600 seconds."}, {"role": "assistant", "content": "SELECT t1.block_id AS current_block_id, t2.block_id AS previous_block_id, t1.timestamp AS current_timestamp, t2.timestamp AS previous_timestamp, t1.difficulty AS current_difficulty, t2.difficulty AS previous_difficulty FROM blockchain.blocks AS t1 JOIN blockchain.blocks AS t2 ON t1.previous_block_id = t2.block_id WHERE t2.difficulty > 100000 AND EXTRACT(EPOCH FROM (t1.timestamp - t2.timestamp)) < 600;"}, {"role": "user", "content": "Further refine the list to only include blocks mined in October 2023."}, {"role": "assistant", "content": "SELECT t1.block_id AS current_block_id, t2.block_id AS previous_block_id, t1.timestamp AS current_timestamp, t2.timestamp AS previous_timestamp, t1.difficulty AS current_difficulty, t2.difficulty AS previous_difficulty FROM blockchain.blocks AS t1 JOIN blockchain.blocks AS t2 ON t1.previous_block_id = t2.block_id WHERE t2.difficulty > 100000 AND EXTRACT(EPOCH FROM (t1.timestamp - t2.timestamp)) < 600 AND t1.timestamp >= '2023-10-01' AND t1.timestamp < '2023-11-01';"}, {"role": "user", "content": "Finally, from this filtered list, only show pairs where the current block's difficulty is less than the previous block's difficulty."}, {"role": "assistant", "content": "SELECT t1.block_id AS current_block_id, t2.block_id AS previous_block_id, t1.timestamp AS current_timestamp, t2.timestamp AS previous_timestamp, t1.difficulty AS current_difficulty, t2.difficulty AS previous_difficulty FROM blockchain.blocks AS t1 JOIN blockchain.blocks AS t2 ON t1.previous_block_id = t2.block_id WHERE t2.difficulty > 100000 AND EXTRACT(EPOCH FROM (t1.timestamp - t2.timestamp)) < 600 AND t1.timestamp >= '2023-10-01' AND t1.timestamp < '2023-11-01' AND t1.difficulty < t2.difficulty;"}], "system": "You are an SQL statement expert. Given the table structure 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 character varying(64) NOT NULL, previous_block_id character varying(64), timestamp timestamp NOT NULL, nonce integer NOT NULL, merkle_root character varying(128) NOT NULL, difficulty integer NOT NULL, PRIMARY KEY (block_id) )\n"}
{"conversations": [{"role": "user", "content": "List all maintenance services performed on vehicle 'VHCL789', showing the service date and type."}, {"role": "assistant", "content": "SELECT service_date, service_type FROM transportation.maintenance_logs WHERE vehicle_id = 'VHCL789';"}, {"role": "user", "content": "Can you include the odometer reading at the time of service and sort by the most recent services first?"}, {"role": "assistant", "content": "SELECT service_date, service_type, odometer_reading FROM transportation.maintenance_logs WHERE vehicle_id = 'VHCL789' ORDER BY service_date DESC;"}, {"role": "user", "content": "Now show me only the oil change services for this vehicle."}, {"role": "assistant", "content": "SELECT service_date, service_type, odometer_reading FROM transportation.maintenance_logs WHERE vehicle_id = 'VHCL789' AND service_type = 'Oil Change' ORDER BY service_date DESC;"}, {"role": "user", "content": "Can you calculate the average mileage between oil changes for this vehicle?"}, {"role": "assistant", "content": "WITH oil_changes AS (SELECT odometer_reading, LAG(odometer_reading) OVER (ORDER BY service_date) AS prev_odometer FROM transportation.maintenance_logs WHERE vehicle_id = 'VHCL789' AND service_type = 'Oil Change') SELECT AVG(odometer_reading - prev_odometer) AS avg_miles_between_changes FROM oil_changes WHERE prev_odometer 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 transportation.maintenance_logs ( log_id text, vehicle_id text, service_date date, odometer_reading integer, service_type text, description text, cost numeric, mechanic_name text, next_service_due_date date )\n"}
{"conversations": [{"role": "user", "content": "How many unique wallets hold each NFT (by contract_address and token_id) currently?"}, {"role": "assistant", "content": "SELECT contract_address, token_id, COUNT(DISTINCT wallet_address) AS holder_count\nFROM nft_holders\nGROUP BY contract_address, token_id;"}, {"role": "user", "content": "Filter the results to only include NFTs with more than 10 holders."}, {"role": "assistant", "content": "SELECT contract_address, token_id, COUNT(DISTINCT wallet_address) AS holder_count\nFROM nft_holders\nGROUP BY contract_address, token_id\nHAVING COUNT(DISTINCT wallet_address) > 10;"}, {"role": "user", "content": "Order the results by holder_count descending and limit to the top 20."}, {"role": "assistant", "content": "SELECT contract_address, token_id, COUNT(DISTINCT wallet_address) AS holder_count\nFROM nft_holders\nGROUP BY contract_address, token_id\nHAVING COUNT(DISTINCT wallet_address) > 10\nORDER BY holder_count DESC\nLIMIT 20;"}, {"role": "user", "content": "Also show the total amount held across all wallets for each NFT."}, {"role": "assistant", "content": "SELECT contract_address,\n       token_id,\n       COUNT(DISTINCT wallet_address) AS holder_count,\n       SUM(CAST(amount AS numeric)) AS total_amount\nFROM nft_holders\nGROUP BY contract_address, token_id\nHAVING COUNT(DISTINCT wallet_address) > 10\nORDER BY holder_count DESC\nLIMIT 20;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp.timestamp, 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 text, wallet_address text, amount text, pk text )\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 (\n    object_id varchar NOT NULL, -- object id of the coin metadata object\n    coin_type varchar NOT NULL, -- coin type, eg. 0x...66::reap_token::REAP_TOKEN\n    status varchar NOT NULL, -- coin status, eg. exists, deleted\n    decimals bigint NOT NULL, -- decimals of the coin\n    description varchar NOT NULL, -- description of the coin\n    icon_url varchar NOT NULL, -- icon url of the coin\n    symbol varchar NOT NULL, -- symbol of the coin\n    name varchar NOT NULL  -- name of the coin\n)\nCREATE TABLE nft_metadata ( blockchain text, contract_address text, token_id text, contract_name text, erc_type text, amount bigint, minter text, owner text, mint_block_number bigint, mint_time bigint, mint_transaction_hash text, mint_price text, token_uri text, metadata text, name text, image_uri text, traits text, updated_at bigint, status text, rarity_score real, rarity_rank integer, unique_attribute_count integer, pk integer )\nCREATE TABLE nft_collections ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, name varchar NOT NULL, symbol varchar NOT NULL, deploy_block_number bigint NOT NULL, deploy_block_time bigint NOT NULL, erc_type varchar NOT NULL, owner varchar NOT NULL, traits varchar NOT NULL, description varchar NOT NULL, slug varchar NOT NULL, media_info varchar NOT NULL, image_url varchar NOT NULL, banner_image_url varchar NOT NULL, updated_at bigint NOT NULL, banner varchar NOT NULL, token_count bigint NOT NULL, floor_price varchar NOT NULL, floor_price_symbol varchar NOT NULL, floor_price_contract varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_prices ( uuid text, blockchain text, address text, decimals bigint, symbol text, price real, timestamp timestamp )\nCREATE TABLE token_balances ( 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 text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\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_balances_bitcoin ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply text, amount text )\nCREATE TABLE token_info_bitcoin ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, tick.text, max_supply.decimal, lim.decimal, wlim.decimal, dec.integer, creator.text )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_activities_avalanche (\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_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": "Could you provide the total number of game sessions and the number of distinct players for each game genre? Display the genre, session count, and player count."}, {"role": "assistant", "content": "SELECT g.genre, COUNT(gs.session_id) AS session_count, COUNT(DISTINCT gs.player_id) AS player_count FROM gaming_technology.game_sessions AS gs JOIN gaming_technology.games AS g ON gs.game_id = g.game_id WHERE g.genre IS NOT NULL GROUP BY g.genre ORDER BY g.genre;"}, {"role": "user", "content": "Thanks. Can you modify the query to only include games that were released after the year 2020?"}, {"role": "assistant", "content": "SELECT g.genre, COUNT(gs.session_id) AS session_count, COUNT(DISTINCT gs.player_id) AS player_count FROM gaming_technology.game_sessions AS gs JOIN gaming_technology.games AS g ON gs.game_id = g.game_id WHERE g.genre IS NOT NULL AND g.release_date >= '2021-01-01' GROUP BY g.genre ORDER BY g.genre;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.players (\n    player_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the player\n    username character varying(100) NOT NULL UNIQUE, -- player's chosen display name\n    email character varying(255) NOT NULL UNIQUE, -- player's email address for login/recovery\n    password_hash text NOT NULL, -- securely hashed password\n    registration_date timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the player account was created\n    last_login timestamp with time zone, -- timestamp of the last successful login\n    country_code character(2), -- player's country (ISO 3166-1 alpha-2)\n    status character varying(20) NOT NULL DEFAULT 'active', -- account status (e.g., active, banned, suspended)\n    profile_data jsonb, -- flexible field for avatar url, bio, preferences etc.\n    PRIMARY KEY (player_id)\n)\nCREATE TABLE gaming_technology.games (\n    game_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game\n    title character varying(200) NOT NULL, -- official title of the game\n    developer_id uuid NOT NULL, -- FK linking to the developers table\n    publisher_id uuid, -- FK linking to a potential publishers table (optional)\n    genre character varying(100), -- primary genre (e.g., RPG, FPS, Strategy)\n    release_date date, -- official release date\n    description text, -- short description or synopsis of the game\n    platform character varying(50) NOT NULL, -- primary platform (e.g., PC, PlayStation 5, Xbox Series X, Mobile)\n    engine character varying(100), -- game engine used (e.g., Unreal Engine 5, Unity)\n    website character varying(255), -- official website URL\n    PRIMARY KEY (game_id)\n    -- FOREIGN KEY (developer_id) REFERENCES gaming_technology.developers(developer_id) -- Example FK constraint\n)\nCREATE TABLE gaming_technology.game_sessions (\n    session_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game session\n    player_id uuid NOT NULL, -- FK linking to the players table\n    game_id uuid NOT NULL, -- FK linking to the games table\n    server_id uuid, -- FK linking to the servers table (nullable for single-player)\n    start_time timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the session began\n    end_time timestamp with time zone, -- when the session ended (null if ongoing)\n    duration_seconds integer, -- calculated duration of the session in seconds\n    score integer, -- player's score for the session, if applicable\n    session_data jsonb, -- flexible field for session-specific info (e.g., map played, character used)\n    PRIMARY KEY (session_id)\n    -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n    -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id),\n    -- FOREIGN KEY (server_id) REFERENCES gaming_technology.servers(server_id)\n)\nCREATE TABLE gaming_technology.servers (\n    server_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game server instance\n    game_id uuid NOT NULL, -- FK linking to the game this server hosts\n    server_name character varying(150), -- display name for the server\n    region character varying(50) NOT NULL, -- geographical region (e.g., us-east-1, eu-west-2)\n    ip_address character varying(45), -- IP address (IPv4 or IPv6)\n    port integer, -- network port number\n    current_players integer NOT NULL DEFAULT 0, -- number of players currently connected\n    max_players integer NOT NULL, -- maximum player capacity\n    status character varying(30) NOT NULL DEFAULT 'offline', -- server status (e.g., online, offline, maintenance)\n    last_heartbeat timestamp with time zone, -- last time the server reported its status\n    PRIMARY KEY (server_id)\n    -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id)\n)\nCREATE TABLE gaming_technology.achievements (\n    achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for an achievement definition\n    game_id uuid NOT NULL, -- FK linking to the game the achievement belongs to\n    name character varying(150) NOT NULL, -- name of the achievement\n    description text NOT NULL, -- how to unlock the achievement\n    icon_url character varying(255), -- URL for the achievement's icon\n    points integer DEFAULT 0, -- points awarded for unlocking (optional)\n    hidden boolean DEFAULT false, -- whether the achievement details are hidden until unlocked\n    PRIMARY KEY (achievement_id)\n    -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id)\n)\nCREATE TABLE gaming_technology.player_achievements (\n    player_achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for this unlock instance\n    player_id uuid NOT NULL, -- FK linking to the player who unlocked it\n    achievement_id uuid NOT NULL, -- FK linking to the achievement definition\n    unlocked_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the achievement was unlocked\n    PRIMARY KEY (player_achievement_id),\n    UNIQUE (player_id, achievement_id) -- Ensure a player can only unlock an achievement once\n    -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n    -- FOREIGN KEY (achievement_id) REFERENCES gaming_technology.achievements(achievement_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Show the total number of customers in each state."}, {"role": "assistant", "content": "SELECT\n  state,\n  COUNT(customer_id)\nFROM insurance.customers\nGROUP BY\n  state;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.customers ( customer_id text, first_name text, last_name text, date_of_birth date, ssn_hash text, address_line1 text, address_line2 text, city text, state text, zip_code text, country text, phone_number text, email text, created_at timestamp, updated_at timestamp, status text )\nCREATE TABLE insurance.claims (\n    claim_id character varying(64) NOT NULL, -- unique identifier for the claim\n    policy_id character varying(64) NOT NULL, -- identifier of the policy under which the claim is made (FK to policies)\n    customer_id character varying(64) NOT NULL, -- identifier of the customer making the claim (FK to customers)\n    incident_date timestamp NOT NULL, -- date and time of the incident leading to the claim\n    reported_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- date the claim was reported\n    description text NOT NULL, -- detailed description of the incident and claim\n    estimated_loss numeric(15, 2), -- initial estimated cost of the loss\n    status character varying(30) NOT NULL, -- e.g., Filed, Processing, Under Review, Approved, Denied, Settled\n    settlement_amount numeric(15, 2), -- final amount paid out\n    settlement_date date,\n    claim_handler_id character varying(64), -- identifier for the employee handling the claim (FK to employees/adjusters)\n    police_report_number character varying(100),\n    PRIMARY KEY (claim_id)\n)\nCREATE TABLE insurance.insurance_products (\n    product_id character varying(64) NOT NULL, -- unique identifier for the insurance product\n    product_name character varying(150) NOT NULL, -- name of the insurance product (e.g., 'Comprehensive Auto Insurance')\n    product_type character varying(50) NOT NULL, -- category like 'Auto', 'Home', 'Life', 'Health', 'Travel'\n    description text, -- detailed description of the product\n    base_premium numeric(10, 2) NOT NULL, -- starting premium before adjustments\n    coverage_details text, -- details about what is covered (could be JSON or structured text)\n    underwriting_rules text, -- rules used for assessing risk and eligibility\n    is_active boolean NOT NULL DEFAULT true, -- whether the product is currently offered\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n    updated_at timestamp,\n    PRIMARY KEY (product_id)\n)\nCREATE TABLE insurance.claim_documents ( document_id character varying(64) NOT NULL, claim_id character varying(64) NOT NULL, document_type character varying(50) NOT NULL, file_name character varying(255) NOT NULL, file_path character varying(512) NOT NULL, file_size_bytes integer, mime_type character varying(100), uploaded_by character varying(64), uploaded_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, description text, PRIMARY KEY (document_id) )\n"}
{"conversations": [{"role": "user", "content": "List 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 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 all payments processed in the last 90 days, showing payment ID, amount, currency, method, and status."}, {"role": "assistant", "content": "SELECT payment_id, amount, currency_code, payment_method, status FROM hospitality_technology.payments WHERE payment_timestamp >= CURRENT_DATE - INTERVAL '90 day';"}, {"role": "user", "content": "Now, only show payments with status 'Failed' or 'Canceled'."}, {"role": "assistant", "content": "SELECT payment_id, amount, currency_code, payment_method, status FROM hospitality_technology.payments WHERE payment_timestamp >= CURRENT_DATE - INTERVAL '90 day' AND (status = 'Failed' OR status = 'Canceled');"}], "system": "You are an SQL statement expert. Given the table structure 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": "For citizens who registered before January 1, 2023, show the total number of notifications sent to them for each channel. List the citizen's first name, last name, the channel, and the count of notifications."}, {"role": "assistant", "content": "SELECT\n  T1.first_name,\n  T1.last_name,\n  T2.channel,\n  COUNT(T2.notification_id) AS notification_count\nFROM government_services.citizens AS T1\nINNER JOIN government_services.notifications AS T2\n  ON T1.citizen_id = T2.citizen_id\nWHERE\n  T1.registration_date < '2023-01-01'\nGROUP BY\n  T1.citizen_id,\n  T1.first_name,\n  T1.last_name,\n  T2.channel;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens (\n    citizen_id character varying(64) NOT NULL,  -- unique identifier for the citizen\n    national_id_number character varying(128) NOT NULL UNIQUE, -- official national identification number\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    date_of_birth date NOT NULL,\n    gender character varying(20),\n    primary_address text NOT NULL, -- full primary residential address\n    contact_email character varying(128) UNIQUE,\n    contact_phone character varying(32),\n    registration_date timestamp NOT NULL, -- when the citizen profile was created\n    is_verified boolean DEFAULT false, -- whether identity has been officially verified\n    PRIMARY KEY (citizen_id)\n)\nCREATE TABLE government_services.agencies (\n    agency_id character varying(64) NOT NULL, -- unique identifier for the agency\n    agency_name character varying(255) NOT NULL, -- full name of the government agency\n    jurisdiction_level character varying(50) NOT NULL, -- e.g., Federal, State, County, City\n    primary_contact_email character varying(128),\n    main_phone_number character varying(32),\n    website_url character varying(255),\n    established_date date,\n    parent_agency_id character varying(64), -- FK to self for hierarchical structure\n    PRIMARY KEY (agency_id)\n)\nCREATE TABLE government_services.services (\n    service_id character varying(64) NOT NULL, -- unique identifier for the service\n    agency_id character varying(64) NOT NULL, -- FK to agencies table\n    service_name character varying(255) NOT NULL, -- name of the service (e.g., Driver's License Renewal)\n    description text,\n    category character varying(100), -- e.g., Licensing, Benefits, Taxation, Permits\n    eligibility_criteria text, -- description of who is eligible\n    standard_fee numeric(10, 2) DEFAULT 0.00, -- typical fee for the service\n    average_processing_time_days integer, -- estimated processing time\n    is_active boolean DEFAULT true, -- whether the service is currently offered\n    online_application_url character varying(255),\n    PRIMARY KEY (service_id)\n)\nCREATE TABLE government_services.documents (\n    document_id character varying(64) NOT NULL, -- unique identifier for the document instance\n    application_id character varying(64), -- FK to applications table (optional, could be linked to citizen directly)\n    citizen_id character varying(64) NOT NULL, -- FK to citizens table\n    document_type character varying(100) NOT NULL, -- e.g., Passport Scan, Proof of Address, Birth Certificate\n    file_reference text NOT NULL, -- reference to the stored file (e.g., S3 URL, internal path)\n    upload_timestamp timestamp NOT NULL,\n    expiry_date date,\n    verification_status character varying(30) DEFAULT 'Pending', -- e.g., Pending, Verified, Rejected\n    verified_by_employee_id character varying(64), -- FK to employees table\n    verification_timestamp timestamp,\n    PRIMARY KEY (document_id)\n)\nCREATE TABLE government_services.appointments (\n    appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment\n    citizen_id character varying(64) NOT NULL, -- FK to citizens table\n    employee_id character varying(64), -- FK to employees table (optional, if assigned)\n    location_id character varying(64), -- FK to service_locations table (if physical)\n    service_id character varying(64), -- FK to services table (optional, if related to specific service)\n    scheduled_start_time timestamp NOT NULL,\n    scheduled_end_time timestamp,\n    purpose text NOT NULL, -- reason for the appointment\n    status character varying(30) NOT NULL, -- e.g., Scheduled, Completed, Cancelled, No-Show\n    booking_method character varying(50), -- e.g., Online, Phone, In-Person\n    created_at timestamp NOT NULL, -- when the appointment was booked\n    notes text,\n    PRIMARY KEY (appointment_id)\n)\nCREATE TABLE government_services.notifications (\n    notification_id character varying(64) NOT NULL, -- unique identifier for the notification\n    citizen_id character varying(64) NOT NULL, -- FK to citizens table\n    application_id character varying(64), -- FK to applications table (optional)\n    message_subject character varying(255),\n    message_body text NOT NULL,\n    channel character varying(30) NOT NULL, -- e.g., Email, SMS, Portal Message, Mail\n    sent_at timestamp NOT NULL,\n    status character varying(30) NOT NULL, -- e.g., Queued, Sent, Delivered, Failed, Read\n    related_entity_type character varying(50), -- e.g., Application, Appointment, Document Request\n    related_entity_id character varying(64), -- ID of the related entity\n    PRIMARY KEY (notification_id)\n)\n"}
{"conversations": [{"role": "user", "content": "What is the total number of drivers hired each year? Provide the hire_year and driver_count."}, {"role": "assistant", "content": "SELECT EXTRACT(YEAR FROM hire_date) AS hire_year,\n       COUNT(*)                  AS driver_count\nFROM transportation.drivers\nGROUP BY EXTRACT(YEAR FROM hire_date);"}, {"role": "user", "content": "Now only include years where driver_count > 3 and order the results by driver_count DESC."}, {"role": "assistant", "content": "SELECT hire_year, driver_count\nFROM (\n  SELECT EXTRACT(YEAR FROM hire_date) AS hire_year,\n         COUNT(*)                  AS driver_count\n  FROM transportation.drivers\n  GROUP BY EXTRACT(YEAR FROM hire_date)\n) sub\nWHERE driver_count > 3\nORDER BY driver_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.drivers ( driver_id text, employee_id text, first_name text, last_name text, license_number text, license_expiry_date date, contact_number text, email text, hire_date date, status text )\n"}
{"conversations": [{"role": "user", "content": "For the 'DeFi' narrative, what is the average ROI and the total net inflow (usd_value where type=1) from smart money token inflow?"}, {"role": "assistant", "content": "SELECT AVG(sm.roi) AS avg_roi, SUM(smt.usd_value) AS total_net_inflow\nFROM smart_money_token_inflow smt\nJOIN smart_money_profit sm ON smt.chain = sm.chain\nWHERE smt.narrative = 'DeFi' AND smt.type = 1;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_basic_info ( coin_id text, token_name text, token_symbol text, token_address text, chain text, price numeric, price_change_percentage_1h numeric, price_change_percentage_24h numeric, price_change_percentage_7d numeric, highest_price_24h numeric, lowest_price_24h numeric, market_cap numeric, market_cap_rank numeric, market_cap_change_percentage_24h text, total_volume text, narrative text, trend_rank numeric )\nCREATE TABLE narrative_info ( narrative text, top_3_coins text, price_change_percentage_1h numeric, price_change_percentage_24h numeric, price_change_percentage_7d numeric, market_cap numeric, volume_24h numeric, trend_rank numeric, token_num numeric )\nCREATE TABLE cex_token_balance ( snapshot_time text, chain text, address text, exchange text, token_address text, token_symbol text, balance numeric, usd_value numeric, price numeric )\nCREATE TABLE smart_money_profit ( address text, rank numeric, profit numeric, roi numeric, realized_ratio numeric, most_profit_token text, last_trade_time text, chain text )\nCREATE TABLE smart_money_token_inflow ( token_address text, token_symbol text, token_amount numeric, usd_value numeric, avg_price numeric, type numeric, address_amount numeric, narrative text, chain text )\n"}
{"conversations": [{"role": "user", "content": "Which bed types are offered in each property and how many different room types are associated with each bed type?"}, {"role": "assistant", "content": "SELECT property_id, bed_type, COUNT(DISTINCT room_type_id) AS room_type_count FROM hospitality_technology.room_types GROUP BY property_id, bed_type;"}, {"role": "user", "content": "Now, show only bed types that are available for at least 3 different room types within the same property."}, {"role": "assistant", "content": "SELECT property_id, bed_type, COUNT(DISTINCT room_type_id) AS room_type_count FROM hospitality_technology.room_types GROUP BY property_id, bed_type HAVING COUNT(DISTINCT room_type_id) >= 3;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.room_types ( room_type_id text PRIMARY KEY, property_id text, type_name text, description text, base_rate numeric, max_occupancy int, bed_type text, area_sqft numeric, amenities text )\n"}
{"conversations": [{"role": "user", "content": "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’d like to find all pairs of securities that belong to the same sector."}, {"role": "assistant", "content": "SELECT a.security_id, a.ticker_symbol, b.security_id AS pair_security_id, b.ticker_symbol AS pair_ticker_symbol, a.sector\nFROM financial_services.securities a\nJOIN financial_services.securities b ON a.sector = b.sector\nWHERE a.security_id < b.security_id;"}, {"role": "user", "content": "Actually, only include pairs where the two securities are listed on different exchanges."}, {"role": "assistant", "content": "SELECT a.security_id, a.ticker_symbol, a.exchange AS exchange_a, b.security_id AS pair_security_id, b.ticker_symbol AS pair_ticker_symbol, b.exchange AS exchange_b, a.sector\nFROM financial_services.securities a\nJOIN financial_services.securities b ON a.sector = b.sector AND a.security_id < b.security_id\nWHERE a.exchange <> b.exchange;"}, {"role": "user", "content": "Also, I want the results sorted by sector, then by exchange_a."}, {"role": "assistant", "content": "SELECT a.security_id, a.ticker_symbol, a.exchange AS exchange_a, b.security_id AS pair_security_id, b.ticker_symbol AS pair_ticker_symbol, b.exchange AS exchange_b, a.sector\nFROM financial_services.securities a\nJOIN financial_services.securities b ON a.sector = b.sector AND a.security_id < b.security_id\nWHERE a.exchange <> b.exchange\nORDER BY a.sector, a.exchange;"}, {"role": "user", "content": "One more thing: include both exchanges in the ORDER BY so that within each sector it’s sorted by exchange_a then exchange_b."}, {"role": "assistant", "content": "SELECT a.security_id, a.ticker_symbol, a.exchange AS exchange_a, b.security_id AS pair_security_id, b.ticker_symbol AS pair_ticker_symbol, b.exchange AS exchange_b, a.sector\nFROM financial_services.securities a\nJOIN financial_services.securities b ON a.sector = b.sector AND a.security_id < b.security_id\nWHERE a.exchange <> b.exchange\nORDER BY a.sector, a.exchange, b.exchange;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.securities ( security_id text PRIMARY KEY, ticker_symbol text, isin_code text, cusip_code text, security_name text, security_type text, exchange text, currency text, issuer_name text, sector text, last_updated timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show the name, symbol, and type of each asset, along with the total number of orders placed for each asset."}, {"role": "assistant", "content": "SELECT a.name, a.symbol, a.type, COUNT(o.order_id) AS order_count\nFROM trading_platform.assets a\nLEFT JOIN trading_platform.orders o ON a.asset_id = o.asset_id\nGROUP BY a.asset_id, a.name, a.symbol, a.type;"}, {"role": "user", "content": "Only include assets that have at least 10 orders, and order the result by order_count descending."}, {"role": "assistant", "content": "SELECT a.name, a.symbol, a.type, COUNT(o.order_id) AS order_count\nFROM trading_platform.assets a\nLEFT JOIN trading_platform.orders o ON a.asset_id = o.asset_id\nGROUP BY a.asset_id, a.name, a.symbol, a.type\nHAVING COUNT(o.order_id) >= 10\nORDER BY order_count DESC;"}, {"role": "user", "content": "Instead of all orders, only consider orders with status 'open'."}, {"role": "assistant", "content": "SELECT a.name, a.symbol, a.type, COUNT(o.order_id) AS open_order_count\nFROM trading_platform.assets a\nLEFT JOIN trading_platform.orders o ON a.asset_id = o.asset_id AND o.status = 'open'\nGROUP BY a.asset_id, a.name, a.symbol, a.type\nHAVING COUNT(o.order_id) >= 10\nORDER BY open_order_count DESC;"}, {"role": "user", "content": "The SQL doesn't work because some assets have no open orders, but I want to include those assets with a count of 0. Please update the query accordingly."}, {"role": "assistant", "content": "SELECT a.name, a.symbol, a.type, COUNT(o.order_id) AS open_order_count\nFROM trading_platform.assets a\nLEFT JOIN trading_platform.orders o ON a.asset_id = o.asset_id AND o.status = 'open'\nGROUP BY a.asset_id, a.name, a.symbol, a.type\nHAVING COUNT(o.order_id) >= 10 OR COUNT(o.order_id) = 0\nORDER BY open_order_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.wallets ( wallet_id.text, user_id.text, address.text, private_key.text, created_at.timestamp )\nCREATE TABLE trading_platform.orders ( order_id.text, user_id.text, wallet_id.text, asset_id.text, order_type.text, quantity.numeric, price.numeric, status.text, created_at.timestamp )\nCREATE TABLE trading_platform.trades (\n    trade_id character varying(64) NOT NULL,  -- unique identifier for the trade\n    order_id character varying(64) NOT NULL, -- identifier of the order that led to the trade\n    buyer_id character varying(64) NOT NULL, -- identifier of the buyer\n    seller_id character varying(64) NOT NULL, -- identifier of the seller\n    asset_id character varying(64) NOT NULL, -- identifier of the asset being traded\n    quantity numeric(38,14) NOT NULL, -- quantity of the asset in the trade\n    price numeric(38,14) NOT NULL, -- price per unit of the asset\n    traded_at timestamp NOT NULL, -- time when the trade was executed\n    PRIMARY KEY (trade_id)\n)\nCREATE TABLE trading_platform.assets ( asset_id text, name text, symbol text, type text )\nCREATE TABLE trading_platform.dapps ( dapp_id text PRIMARY KEY, name text, description text, url text )\nCREATE TABLE trading_platform.kyc_audit (\n    kyc_audit_id character varying(64) NOT NULL,  -- unique identifier for the KYC audit\n    user_id character varying(64) NOT NULL, -- identifier of the user being audited\n    status character varying(32) NOT NULL, -- status of the KYC audit (e.g., pending, approved, rejected)\n    reviewed_at timestamp NOT NULL, -- time when the KYC audit was reviewed\n    PRIMARY KEY (kyc_audit_id)\n)\nCREATE TABLE trading_platform.notifications ( notification_id.text, user_id.text, message.text, sent_at.timestamp, read_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "List all tokens from the token_dexpool_info table with a liquidity over $10 million and a positive 6-hour price change percentage on the Ethereum chain."}, {"role": "assistant", "content": "SELECT token_name, token_symbol, liquidity, price_change_percentage_6h FROM token_dexpool_info WHERE liquidity > 10000000 AND price_change_percentage_6h > 0 AND 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 narrative_info (\",\n    \"narrative character varying(512) NOT NULL, -- the id of narrative\",\n    \"top_3_coins text, -- the top 3 tokens in the narrative\",\n    \"price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour in the narrative\",\n    \"price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours in the narrative\",\n    \"price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days in the narrative\",\n    \"market_cap double precision, -- the market cap of the narrative\",\n    \"volume_24h double precision, -- the trade volume of the narrative\",\n    \"trend_rank bigint, -- the trending rank of the narrative, value 1 expresses the most popular narrative\",\n    \"token_num bigint, -- total token number in the narrative\",\n    \",PRIMARY KEY (narrative));\"\n\nCREATE TABLE token_dexpool_info ( pair_address character varying(512) NOT NULL, 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 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_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 smart contracts created by addresses that have created more than 3 contracts, along with the total number of contracts each creator has made."}, {"role": "assistant", "content": "SELECT sc.contract_id, sc.creator_address, COUNT(*) OVER (PARTITION BY sc.creator_address) AS total_contracts\nFROM blockchain.smart_contracts sc\nWHERE sc.creator_address IN (\n    SELECT creator_address\n    FROM blockchain.smart_contracts\n    GROUP BY creator_address\n    HAVING COUNT(*) > 3\n);"}, {"role": "user", "content": "Now filter these results to only show contracts created in the last 6 months."}, {"role": "assistant", "content": "SELECT sc.contract_id, sc.creator_address, COUNT(*) OVER (PARTITION BY sc.creator_address) AS total_contracts\nFROM blockchain.smart_contracts sc\nWHERE sc.creator_address IN (\n    SELECT creator_address\n    FROM blockchain.smart_contracts\n    GROUP BY creator_address\n    HAVING COUNT(*) > 3\n)\nAND sc.timestamp >= DATE_SUB(CURRENT_TIMESTAMP, INTERVAL 6 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 blockchain.smart_contracts ( contract_id.text, creator_address.text, code.text, timestamp.timestamp )\n"}
{"conversations": [{"role": "user", "content": "List the usernames and user IDs of all users whose bio contains the word 'developer'."}, {"role": "assistant", "content": "SELECT user_id, username\nFROM social_media.users\nWHERE bio ILIKE '%developer%';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users (\n    user_id character varying(64) NOT NULL,  -- unique identifier for the user\n    username character varying(50) NOT NULL UNIQUE, -- user's unique handle\n    email character varying(128) NOT NULL UNIQUE, -- user's email address\n    password_hash text NOT NULL, -- hashed password\n    full_name character varying(100), -- user's full name\n    profile_picture_url text, -- URL to the profile picture\n    bio text, -- short user biography\n    location character varying(100), -- user's location\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of account creation\n    updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last profile update\n    is_verified boolean NOT NULL DEFAULT false, -- verification status\n    PRIMARY KEY (user_id)\n)\nCREATE TABLE social_media.comments (\n    comment_id character varying(64) NOT NULL, -- unique identifier for the comment\n    post_id character varying(64) NOT NULL, -- identifier of the post being commented on (FK to posts.post_id)\n    user_id character varying(64) NOT NULL, -- identifier of the user who made the comment (FK to users.user_id)\n    parent_comment_id character varying(64), -- identifier of the parent comment if it's a reply (FK to comments.comment_id)\n    content text NOT NULL, -- textual content of the comment\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of comment creation\n    updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last comment edit\n    PRIMARY KEY (comment_id)\n)\nCREATE TABLE social_media.likes (\n    like_id character varying(64) NOT NULL, -- unique identifier for the like\n    user_id character varying(64) NOT NULL, -- identifier of the user who liked (FK to users.user_id)\n    post_id character varying(64), -- identifier of the post being liked (FK to posts.post_id, nullable)\n    comment_id character varying(64), -- identifier of the comment being liked (FK to comments.comment_id, nullable)\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of when the like occurred\n    PRIMARY KEY (like_id),\n    CONSTRAINT unique_user_like UNIQUE (user_id, post_id, comment_id), -- prevent duplicate likes\n    CONSTRAINT check_like_target CHECK (post_id IS NOT NULL OR comment_id IS NOT NULL) -- ensure it likes something\n)\nCREATE TABLE social_media.follows (\n    follow_id character varying(64) NOT NULL, -- unique identifier for the follow relationship\n    follower_user_id character varying(64) NOT NULL, -- identifier of the user who is following (FK to users.user_id)\n    following_user_id character varying(64) NOT NULL, -- identifier of the user being followed (FK to users.user_id)\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of when the follow started\n    PRIMARY KEY (follow_id),\n    CONSTRAINT unique_follow UNIQUE (follower_user_id, following_user_id) -- prevent duplicate follows\n)\nCREATE TABLE social_media.hashtags (\n    hashtag_id character varying(64) NOT NULL, -- unique identifier for the hashtag\n    tag_name character varying(100) NOT NULL UNIQUE, -- the actual hashtag text (without '#')\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when the hashtag was first used\n    PRIMARY KEY (hashtag_id)\n)\nCREATE TABLE social_media.conversations (\n    conversation_id character varying(64) NOT NULL, -- unique identifier for the conversation\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when conversation was initiated\n    last_message_at timestamp, -- timestamp of the last message in the conversation\n    is_group_chat boolean NOT NULL DEFAULT false, -- indicates if it's a group chat or direct message\n    group_name character varying(100), -- name of the group chat (if applicable)\n    PRIMARY KEY (conversation_id)\n)\nCREATE TABLE social_media.conversation_participants (\n    participant_id character varying(64) NOT NULL, -- unique identifier for the participant entry\n    conversation_id character varying(64) NOT NULL, -- identifier of the conversation (FK to conversations.conversation_id)\n    user_id character varying(64) NOT NULL, -- identifier of the user in the conversation (FK to users.user_id)\n    joined_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when user joined the conversation\n    last_read_at timestamp, -- timestamp indicating up to when the user has read messages\n    PRIMARY KEY (participant_id),\n    CONSTRAINT unique_user_conversation UNIQUE (conversation_id, user_id) -- prevent user being added multiple times\n)\nCREATE TABLE social_media.notifications (\n    notification_id character varying(64) NOT NULL, -- unique identifier for the notification\n    recipient_user_id character varying(64) NOT NULL, -- user receiving the notification (FK to users.user_id)\n    sender_user_id character varying(64), -- user triggering the notification (FK to users.user_id, can be null for system notifications)\n    notification_type character varying(30) NOT NULL, -- type of notification ('like', 'comment', 'follow', 'mention', 'message')\n    target_entity_id character varying(64), -- ID of the related entity (post_id, comment_id, user_id, conversation_id)\n    target_entity_type character varying(20), -- type of the related entity ('post', 'comment', 'user', 'conversation')\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp notification was created\n    read_at timestamp, -- timestamp notification was marked as read\n    PRIMARY KEY (notification_id)\n)\nCREATE TABLE social_media.user_settings (\n    setting_id character varying(64) NOT NULL, -- unique identifier for the setting entry\n    user_id character varying(64) NOT NULL UNIQUE, -- user the settings belong to (FK to users.user_id)\n    theme character varying(20) DEFAULT 'light', -- UI theme ('light', 'dark')\n    email_notifications_enabled boolean DEFAULT true, -- enable/disable email notifications\n    push_notifications_enabled boolean DEFAULT true, -- enable/disable push notifications\n    private_profile boolean DEFAULT false, -- is the user profile private\n    updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last setting change\n    PRIMARY KEY (setting_id)\n)\n"}
{"conversations": [{"role": "user", "content": "For each customer, could you list their full name, email, and the combined balance of all their accounts? Please also show the number of accounts they hold."}, {"role": "assistant", "content": "SELECT c.customer_id, c.first_name || ' ' || c.last_name AS full_name, c.email, SUM(a.balance) AS total_balance, COUNT(a.account_id) AS account_count\nFROM financial_services.customers c\nJOIN financial_services.accounts a ON c.customer_id = a.customer_id\nGROUP BY c.customer_id, c.first_name, c.last_name, c.email;"}, {"role": "user", "content": "Thanks! Now, can you show only customers with at least two accounts in different currencies, and display the number of distinct currencies as well?"}, {"role": "assistant", "content": "SELECT c.customer_id, c.first_name || ' ' || c.last_name AS full_name, c.email, SUM(a.balance) AS total_balance, COUNT(a.account_id) AS account_count, COUNT(DISTINCT a.currency) AS currency_count\nFROM financial_services.customers c\nJOIN financial_services.accounts a ON c.customer_id = a.customer_id\nGROUP BY c.customer_id, c.first_name, c.last_name, c.email\nHAVING COUNT(a.account_id) >= 2 AND COUNT(DISTINCT a.currency) >= 2;"}, {"role": "user", "content": "Could you also filter to only include customers whose total combined account balance is over 10,000 and show their risk_profile?"}, {"role": "assistant", "content": "SELECT c.customer_id, c.first_name || ' ' || c.last_name AS full_name, c.email, SUM(a.balance) AS total_balance, COUNT(a.account_id) AS account_count, COUNT(DISTINCT a.currency) AS currency_count, c.risk_profile\nFROM financial_services.customers c\nJOIN financial_services.accounts a ON c.customer_id = a.customer_id\nGROUP BY c.customer_id, c.first_name, c.last_name, c.email, c.risk_profile\nHAVING COUNT(a.account_id) >= 2 AND COUNT(DISTINCT a.currency) >= 2 AND SUM(a.balance) > 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 financial_services.customers ( customer_id text PRIMARY KEY, first_name text, last_name text, date_of_birth date, ssn_hash text, address text, city text, state text, zip_code text, country text, email text, phone_number text, created_at timestamp, status text, risk_profile text )\nCREATE TABLE financial_services.accounts ( account_id text PRIMARY KEY, customer_id text, account_number text, account_type text, balance numeric, currency text, opened_date date, status text, interest_rate numeric, last_updated_at timestamp )\nCREATE TABLE financial_services.transactions ( 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.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.employees ( employee_id text PRIMARY KEY, first_name text, last_name text, job_title text, department text, branch_id text, email text, phone_extension text, hire_date date, termination_date date, manager_id text, status text )\n"}
{"conversations": [{"role": "user", "content": "List all patients who have had appointments and were prescribed a medication manufactured by 'Merck'. Show the patient ID, full name, appointment ID, and medication name."}, {"role": "assistant", "content": "SELECT DISTINCT p.patient_id, p.first_name, p.last_name, a.appointment_id, m.medication_name\nFROM healthcare.patients p\nJOIN healthcare.appointments a ON p.patient_id = a.patient_id\nJOIN healthcare.medical_records mr ON a.appointment_id = mr.appointment_id\nJOIN healthcare.prescriptions pr ON mr.record_id = pr.record_id\nJOIN healthcare.medications m ON pr.medication_id = m.medication_id\nWHERE m.manufacturer = 'Merck';"}, {"role": "user", "content": "Only include patients who had more than one appointment where they were prescribed a Merck medication, and show the count of such appointments."}, {"role": "assistant", "content": "SELECT p.patient_id, p.first_name, p.last_name, COUNT(DISTINCT a.appointment_id) AS appointment_count\nFROM healthcare.patients p\nJOIN healthcare.appointments a ON p.patient_id = a.patient_id\nJOIN healthcare.medical_records mr ON a.appointment_id = mr.appointment_id\nJOIN healthcare.prescriptions pr ON mr.record_id = pr.record_id\nJOIN healthcare.medications m ON pr.medication_id = m.medication_id\nWHERE m.manufacturer = 'Merck'\nGROUP BY p.patient_id, p.first_name, p.last_name\nHAVING COUNT(DISTINCT a.appointment_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 healthcare.patients ( patient_id.text, first_name.text, last_name.text, date_of_birth.date, gender.text, address.text, phone_number.text, email.text, emergency_contact_name.text, emergency_contact_phone.text, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE healthcare.medical_records (\n    record_id character varying(64) NOT NULL,  -- unique identifier for the medical record entry\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    appointment_id character varying(64) UNIQUE, -- FK to appointments table (can be null if record not tied to specific appt)\n    doctor_id character varying(64) NOT NULL, -- FK to doctors table (doctor creating the record)\n    record_date timestamp with time zone NOT NULL, -- date the record/observation was made\n    chief_complaint text, -- patient's primary reason for visit\n    present_illness_history text, -- detailed history of the current issue\n    past_medical_history text, -- relevant past conditions/surgeries\n    physical_examination_notes text, -- findings from the physical exam\n    assessment text, -- doctor's assessment/diagnosis summary\n    treatment_plan text, -- planned course of action\n    vitals jsonb, -- store vitals like BP, HR, Temp as structured JSON\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (record_id)\n)\nCREATE TABLE healthcare.diagnoses (\n    diagnosis_id character varying(64) NOT NULL, -- unique identifier for the diagnosis entry\n    record_id character varying(64) NOT NULL, -- FK linking to the specific medical record entry\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    doctor_id character varying(64) NOT NULL, -- FK to doctors table (diagnosing doctor)\n    diagnosis_code character varying(20) NOT NULL, -- standard code (e.g., ICD-10)\n    code_type character varying(10) NOT NULL DEFAULT 'ICD-10', -- type of code used\n    description text, -- textual description of the diagnosis\n    diagnosis_date date NOT NULL, -- date the diagnosis was made\n    status character varying(32) NOT NULL, -- e.g., Active, Resolved, Ruled Out\n    is_chronic boolean DEFAULT false, -- flag for chronic conditions\n    PRIMARY KEY (diagnosis_id)\n)\nCREATE TABLE healthcare.medications ( medication_id text, medication_name text, generic_name text, manufacturer text, ndc_code text, description text )\nCREATE TABLE healthcare.prescriptions ( prescription_id text, record_id text, patient_id text, doctor_id text, medication_id text, dosage text, frequency text, route text, start_date date, end_date date, quantity_dispensed numeric, refills_allowed integer, prescription_date timestamp )\nCREATE TABLE healthcare.insurance_plans ( plan_id text, plan_name text, insurance_provider text, plan_type text, contact_phone text, website text )\nCREATE TABLE healthcare.patient_insurance (\n    patient_insurance_id character varying(64) NOT NULL, -- unique identifier for this patient-plan link\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    plan_id character varying(64) NOT NULL, -- FK to insurance_plans table\n    policy_number character varying(100) NOT NULL, -- patient's policy number\n    group_number character varying(100), -- group number, if applicable\n    subscriber_name character varying(200), -- name of the primary policy holder\n    effective_date date NOT NULL, -- date the coverage begins\n    expiration_date date, -- date the coverage ends (if known)\n    is_primary boolean NOT NULL DEFAULT true, -- indicates if this is the primary insurance\n    PRIMARY KEY (patient_insurance_id),\n    UNIQUE (patient_id, plan_id, policy_number) -- ensure a patient doesn't have the same policy twice\n)\n"}
{"conversations": [{"role": "user", "content": "List all cryptocurrency assets that have wallet addresses associated with them."}, {"role": "assistant", "content": "SELECT a.asset_id, a.name, a.symbol FROM trading_platform.assets a JOIN trading_platform.wallets w ON a.asset_id = w.asset_id WHERE a.type = 'cryptocurrency' GROUP BY a.asset_id, a.name, a.symbol;"}, {"role": "user", "content": "Now show me the count of wallets for each of these cryptocurrency assets."}, {"role": "assistant", "content": "SELECT a.asset_id, a.name, COUNT(w.wallet_id) AS wallet_count FROM trading_platform.assets a JOIN trading_platform.wallets w ON a.asset_id = w.asset_id WHERE a.type = 'cryptocurrency' GROUP BY a.asset_id, a.name ORDER BY wallet_count DESC;"}, {"role": "user", "content": "Actually, I want to see only cryptocurrency assets with more than 100 associated wallets."}, {"role": "assistant", "content": "SELECT a.asset_id, a.name, COUNT(w.wallet_id) AS wallet_count FROM trading_platform.assets a JOIN trading_platform.wallets w ON a.asset_id = w.asset_id WHERE a.type = 'cryptocurrency' GROUP BY a.asset_id, a.name HAVING COUNT(w.wallet_id) > 100 ORDER BY wallet_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.wallets ( wallet_id text, user_id text, address text, private_key text, created_at timestamp )\nCREATE TABLE trading_platform.assets ( asset_id text, name text, symbol text, type text )\nCREATE TABLE trading_platform.dapps ( dapp_id text PRIMARY KEY, name text, description text, url text )\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": "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": "Calculate for each player the timespan between their earliest and latest achievement unlocks."}, {"role": "assistant", "content": "SELECT pa_min.player_id,\n       pa_max.max_time - pa_min.min_time AS span\nFROM (\n  SELECT player_id,\n         MIN(unlocked_at) AS min_time\n  FROM gaming_technology.player_achievements\n  GROUP BY player_id\n) pa_min\nJOIN (\n  SELECT player_id,\n         MAX(unlocked_at) AS max_time\n  FROM gaming_technology.player_achievements\n  GROUP BY player_id\n) pa_max\n  ON pa_min.player_id = pa_max.player_id;"}, {"role": "user", "content": "Exclude players who only have one achievement."}, {"role": "assistant", "content": "WITH extremes AS (\n  SELECT player_id,\n         MIN(unlocked_at) AS min_time,\n         MAX(unlocked_at) AS max_time,\n         COUNT(*) AS cnt\n  FROM gaming_technology.player_achievements\n  GROUP BY player_id\n  HAVING COUNT(*) > 1\n)\nSELECT player_id,\n       max_time - min_time AS span\nFROM extremes;"}, {"role": "user", "content": "Also only keep players where the span is greater than 30 days."}, {"role": "assistant", "content": "WITH extremes AS (\n  SELECT player_id,\n         MIN(unlocked_at) AS min_time,\n         MAX(unlocked_at) AS max_time,\n         COUNT(*) AS cnt\n  FROM gaming_technology.player_achievements\n  GROUP BY player_id\n  HAVING COUNT(*) > 1\n)\nSELECT player_id,\n       max_time - min_time AS span\nFROM extremes\nWHERE max_time - min_time > INTERVAL '30 days';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.player_achievements (\n    player_achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for this unlock instance\n    player_id uuid NOT NULL, -- FK linking to the player who unlocked it\n    achievement_id uuid NOT NULL, -- FK linking to the achievement definition\n    unlocked_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the achievement was unlocked\n    PRIMARY KEY (player_achievement_id),\n    UNIQUE (player_id, achievement_id) -- Ensure a player can only unlock an achievement once\n    -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n    -- FOREIGN KEY (achievement_id) REFERENCES gaming_technology.achievements(achievement_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Which games have the highest number of different in-game items of type 'Weapon'? Show the game title and the count."}, {"role": "assistant", "content": "SELECT g.title AS game_title, COUNT(*) AS weapon_count\nFROM gaming_technology.in_game_items i\nJOIN gaming_technology.games g ON i.game_id = g.game_id\nWHERE i.item_type = 'Weapon'\nGROUP BY g.title\nORDER BY weapon_count DESC;"}, {"role": "user", "content": "Can you show only games where the weapon count is at least 5?"}, {"role": "assistant", "content": "SELECT g.title AS game_title, COUNT(*) AS weapon_count\nFROM gaming_technology.in_game_items i\nJOIN gaming_technology.games g ON i.game_id = g.game_id\nWHERE i.item_type = 'Weapon'\nGROUP BY g.title\nHAVING COUNT(*) >= 5\nORDER BY weapon_count DESC;"}, {"role": "user", "content": "Also, include each game's primary genre in the results."}, {"role": "assistant", "content": "SELECT g.title AS game_title, g.genre, COUNT(*) AS weapon_count\nFROM gaming_technology.in_game_items i\nJOIN gaming_technology.games g ON i.game_id = g.game_id\nWHERE i.item_type = 'Weapon'\nGROUP BY g.title, g.genre\nHAVING COUNT(*) >= 5\nORDER BY weapon_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.players (\n    player_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the player\n    username character varying(100) NOT NULL UNIQUE, -- player's chosen display name\n    email character varying(255) NOT NULL UNIQUE, -- player's email address for login/recovery\n    password_hash text NOT NULL, -- securely hashed password\n    registration_date timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the player account was created\n    last_login timestamp with time zone, -- timestamp of the last successful login\n    country_code character(2), -- player's country (ISO 3166-1 alpha-2)\n    status character varying(20) NOT NULL DEFAULT 'active', -- account status (e.g., active, banned, suspended)\n    profile_data jsonb, -- flexible field for avatar url, bio, preferences etc.\n    PRIMARY KEY (player_id)\n)\nCREATE TABLE gaming_technology.games (\n    game_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game\n    title character varying(200) NOT NULL, -- official title of the game\n    developer_id uuid NOT NULL, -- FK linking to the developers table\n    publisher_id uuid, -- FK linking to a potential publishers table (optional)\n    genre character varying(100), -- primary genre (e.g., RPG, FPS, Strategy)\n    release_date date, -- official release date\n    description text, -- short description or synopsis of the game\n    platform character varying(50) NOT NULL, -- primary platform (e.g., PC, PlayStation 5, Xbox Series X, Mobile)\n    engine character varying(100), -- game engine used (e.g., Unreal Engine 5, Unity)\n    website character varying(255), -- official website URL\n    PRIMARY KEY (game_id)\n    -- FOREIGN KEY (developer_id) REFERENCES gaming_technology.developers(developer_id) -- Example FK constraint\n)\nCREATE TABLE gaming_technology.achievements (\n    achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for an achievement definition\n    game_id uuid NOT NULL, -- FK linking to the game the achievement belongs to\n    name character varying(150) NOT NULL, -- name of the achievement\n    description text NOT NULL, -- how to unlock the achievement\n    icon_url character varying(255), -- URL for the achievement's icon\n    points integer DEFAULT 0, -- points awarded for unlocking (optional)\n    hidden boolean DEFAULT false, -- whether the achievement details are hidden until unlocked\n    PRIMARY KEY (achievement_id)\n    -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id)\n)\nCREATE TABLE gaming_technology.player_achievements (\n    player_achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for this unlock instance\n    player_id uuid NOT NULL, -- FK linking to the player who unlocked it\n    achievement_id uuid NOT NULL, -- FK linking to the achievement definition\n    unlocked_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the achievement was unlocked\n    PRIMARY KEY (player_achievement_id),\n    UNIQUE (player_id, achievement_id) -- Ensure a player can only unlock an achievement once\n    -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n    -- FOREIGN KEY (achievement_id) REFERENCES gaming_technology.achievements(achievement_id)\n)\nCREATE TABLE gaming_technology.in_game_items (\n    item_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the item definition\n    game_id uuid NOT NULL, -- FK linking to the game this item belongs to\n    item_name character varying(150) NOT NULL, -- name of the item\n    item_type character varying(50) NOT NULL, -- type (e.g., Cosmetic, Consumable, Weapon, Armor)\n    description text, -- description of the item\n    rarity character varying(30), -- item rarity (e.g., Common, Rare, Epic, Legendary)\n    cost_currency character varying(10), -- currency code if purchasable (e.g., USD, EUR, GOLD)\n    cost_amount numeric(12, 2), -- price if purchasable\n    attributes jsonb, -- flexible field for item stats or properties\n    PRIMARY KEY (item_id)\n    -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id)\n)\n"}
{"conversations": [{"role": "user", "content": "I need to find every offline server alongside an online server in the same region."}, {"role": "assistant", "content": "SELECT s_off.server_id AS offline_id,\n       s_on.server_id AS online_id\nFROM gaming_technology.servers s_off\nJOIN gaming_technology.servers s_on\n  ON s_off.region = s_on.region\nWHERE s_off.status = 'offline'\n  AND s_on.status = 'online';"}, {"role": "user", "content": "Include the names of both servers, labeling them offline_server and online_server."}, {"role": "assistant", "content": "SELECT s_off.server_name AS offline_server,\n       s_on.server_name AS online_server\nFROM gaming_technology.servers s_off\nJOIN gaming_technology.servers s_on\n  ON s_off.region = s_on.region\nWHERE s_off.status = 'offline'\n  AND s_on.status = 'online';"}, {"role": "user", "content": "Also add the online server's current_players and status."}, {"role": "assistant", "content": "SELECT s_off.server_name AS offline_server,\n       s_on.server_name AS online_server,\n       s_on.current_players,\n       s_on.status AS online_status\nFROM gaming_technology.servers s_off\nJOIN gaming_technology.servers s_on\n  ON s_off.region = s_on.region\nWHERE s_off.status = 'offline'\n  AND s_on.status = 'online';"}, {"role": "user", "content": "Order the results by offline_server ascending."}, {"role": "assistant", "content": "SELECT s_off.server_name AS offline_server,\n       s_on.server_name AS online_server,\n       s_on.current_players,\n       s_on.status AS online_status\nFROM gaming_technology.servers s_off\nJOIN gaming_technology.servers s_on\n  ON s_off.region = s_on.region\nWHERE s_off.status = 'offline'\n  AND s_on.status = 'online'\nORDER BY offline_server ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.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 )\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": "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": "For each patient, find the next appointment after each one. Return patient_id, appointment_id, next_appointment_id, and the waiting time in minutes between them."}, {"role": "assistant", "content": "SELECT A.patient_id,\n       A.appointment_id AS current_id,\n       B.appointment_id AS next_id,\n       EXTRACT(EPOCH FROM (B.appointment_time - A.appointment_time)) / 60 AS wait_minutes\nFROM healthcare.appointments A\nJOIN healthcare.appointments B\n  ON A.patient_id = B.patient_id\n AND B.appointment_time = (\n       SELECT MIN(appointment_time)\n       FROM healthcare.appointments\n       WHERE patient_id = A.patient_id\n         AND appointment_time > A.appointment_time\n   );"}, {"role": "user", "content": "Now include only the pairs where the waiting time is less than 30 minutes."}, {"role": "assistant", "content": "SELECT A.patient_id,\n       A.appointment_id AS current_id,\n       B.appointment_id AS next_id,\n       EXTRACT(EPOCH FROM (B.appointment_time - A.appointment_time)) / 60 AS wait_minutes\nFROM healthcare.appointments A\nJOIN healthcare.appointments B\n  ON A.patient_id = B.patient_id\n AND B.appointment_time = (\n       SELECT MIN(appointment_time)\n       FROM healthcare.appointments\n       WHERE patient_id = A.patient_id\n         AND appointment_time > A.appointment_time\n   )\nWHERE EXTRACT(EPOCH FROM (B.appointment_time - A.appointment_time)) / 60 < 30;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.appointments ( appointment_id text PRIMARY KEY, patient_id text, doctor_id text, appointment_time timestamp, duration_minutes int, reason text, status text, location_id text, notes text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Find all pairs of products that share the same product_type but have differing active statuses, listing both their product_ids, product_types, and is_active flags."}, {"role": "assistant", "content": "SELECT p1.product_id AS product_id_1,\n       p1.product_type,\n       p1.is_active AS is_active_1,\n       p2.product_id AS product_id_2,\n       p2.is_active AS is_active_2\nFROM insurance.insurance_products p1\nJOIN insurance.insurance_products p2\n  ON p1.product_type = p2.product_type\n AND p1.is_active <> p2.is_active\n AND p1.product_id < p2.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.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": "List all trips including the name of the origin location and the name of the destination location."}, {"role": "assistant", "content": "SELECT t.trip_id, origin.name AS origin_location_name, destination.name AS destination_location_name FROM transportation.trips t JOIN transportation.locations origin ON t.origin_location_id = origin.location_id JOIN transportation.locations destination ON t.destination_location_id = destination.location_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles ( vehicle_id character varying(64) NOT NULL, license_plate character varying(32) NOT NULL UNIQUE, vin character varying(17) UNIQUE, make character varying(64) NOT NULL, model character varying(64) NOT NULL, year integer NOT NULL, type character varying(32) NOT NULL, capacity integer, fuel_type character varying(32) NOT NULL, status character varying(32) NOT NULL, depot_id character varying(64), acquisition_date date, PRIMARY KEY (vehicle_id) )\nCREATE TABLE transportation.drivers ( driver_id character varying(64) NOT NULL, employee_id character varying(64) NOT NULL UNIQUE, first_name character varying(128) NOT NULL, last_name character varying(128) NOT NULL, license_number character varying(64) NOT NULL UNIQUE, license_expiry_date date NOT NULL, contact_number character varying(32), email character varying(128) UNIQUE, hire_date date NOT NULL, status character varying(32) NOT NULL, PRIMARY KEY (driver_id) )\nCREATE TABLE transportation.trips ( trip_id character varying(64) NOT NULL, route_id character varying(64), vehicle_id character varying(64) NOT NULL, driver_id character varying(64) NOT NULL, scheduled_departure timestamp with time zone NOT NULL, actual_departure timestamp with time zone, scheduled_arrival timestamp with time zone NOT NULL, actual_arrival timestamp with time zone, origin_location_id character varying(64) NOT NULL, destination_location_id character varying(64) NOT NULL, status character varying(32) NOT NULL, passenger_count integer, cargo_manifest_id character varying(64), PRIMARY KEY (trip_id) )\nCREATE TABLE transportation.locations ( location_id character varying(64) NOT NULL, name character varying(255) NOT NULL, type character varying(64) NOT NULL, address_line1 character varying(255), city character varying(128), state_province character varying(128), postal_code character varying(32), country character varying(64) NOT NULL, latitude numeric(9, 6), longitude numeric(9, 6), timezone character varying(64), PRIMARY KEY (location_id) )\nCREATE TABLE transportation.maintenance_logs ( log_id character varying(64) NOT NULL, vehicle_id character varying(64) NOT NULL, service_date date NOT NULL, odometer_reading integer, service_type character varying(128) NOT NULL, description text NOT NULL, cost numeric(10, 2), mechanic_name character varying(128), next_service_due_date date, PRIMARY KEY (log_id) )\nCREATE TABLE transportation.passengers ( passenger_id character varying(64) NOT NULL, first_name character varying(128) NOT NULL, last_name character varying(128) NOT NULL, email character varying(128) UNIQUE, phone_number character varying(32) UNIQUE, date_of_birth date, loyalty_program_id character varying(64), created_at timestamp with time zone NOT NULL, PRIMARY KEY (passenger_id) )\n"}
{"conversations": [{"role": "user", "content": "Show me all managers (agents who have other agents reporting to them) along with their team size and average commission rate of their team members."}, {"role": "assistant", "content": "SELECT m.agent_id, m.first_name, m.last_name, COUNT(r.agent_id) as team_size, AVG(r.commission_rate) as avg_team_commission FROM insurance.agents m JOIN insurance.agents r ON m.agent_id = r.manager_id WHERE m.status = 'Active' GROUP BY m.agent_id, m.first_name, m.last_name;"}, {"role": "user", "content": "Now filter to only show managers with teams larger than 3 agents."}, {"role": "assistant", "content": "SELECT m.agent_id, m.first_name, m.last_name, COUNT(r.agent_id) as team_size, AVG(r.commission_rate) as avg_team_commission FROM insurance.agents m JOIN insurance.agents r ON m.agent_id = r.manager_id WHERE m.status = 'Active' GROUP BY m.agent_id, m.first_name, m.last_name HAVING COUNT(r.agent_id) > 3;"}, {"role": "user", "content": "I also want to see the highest commission rate in each manager's team."}, {"role": "assistant", "content": "SELECT m.agent_id, m.first_name, m.last_name, COUNT(r.agent_id) as team_size, AVG(r.commission_rate) as avg_team_commission, MAX(r.commission_rate) as max_team_commission FROM insurance.agents m JOIN insurance.agents r ON m.agent_id = r.manager_id WHERE m.status = 'Active' GROUP BY m.agent_id, m.first_name, m.last_name HAVING COUNT(r.agent_id) > 3;"}, {"role": "user", "content": "Finally, order the results by team size descending and then by average commission rate descending."}, {"role": "assistant", "content": "SELECT m.agent_id, m.first_name, m.last_name, COUNT(r.agent_id) as team_size, AVG(r.commission_rate) as avg_team_commission, MAX(r.commission_rate) as max_team_commission FROM insurance.agents m JOIN insurance.agents r ON m.agent_id = r.manager_id WHERE m.status = 'Active' GROUP BY m.agent_id, m.first_name, m.last_name HAVING COUNT(r.agent_id) > 3 ORDER BY team_size DESC, avg_team_commission DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.agents (\n    agent_id character varying(64) NOT NULL, -- unique identifier for the agent\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    agency_name character varying(150),\n    license_number character varying(100) NOT NULL UNIQUE, -- state insurance license number\n    license_state character varying(50) NOT NULL,\n    contact_email character varying(128) UNIQUE,\n    contact_phone character varying(30),\n    hire_date date,\n    termination_date date,\n    status character varying(20) NOT NULL DEFAULT 'Active', -- e.g., Active, Terminated, On Leave\n    commission_rate numeric(5, 4) NOT NULL DEFAULT 0.05, -- percentage commission\n    manager_id character varying(64), -- identifier for the agent's manager (FK to agents or employees)\n    PRIMARY KEY (agent_id)\n)\n"}
{"conversations": [{"role": "user", "content": "Show me all invoice numbers and due dates where the amount paid is exactly zero."}, {"role": "assistant", "content": "SELECT invoice_number, due_date FROM legal_services.invoices WHERE amount_paid = 0;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.invoices ( invoice_id text PRIMARY KEY, invoice_number text UNIQUE, client_id text, case_id text, issue_date date, due_date date, total_amount numeric, amount_paid numeric, status text, payment_date timestamp, notes text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show me all appointments along with any diagnoses recorded for the same patient on the same day. Include appointment_id, patient_id, appointment_time, and diagnosis_description."}, {"role": "assistant", "content": "SELECT T1.appointment_id, T1.patient_id, T1.appointment_time, T2.description FROM healthcare.appointments AS T1 JOIN healthcare.diagnoses AS T2 ON T1.patient_id = T2.patient_id AND DATE(T1.appointment_time) = T2.diagnosis_date;"}, {"role": "user", "content": "Refine this to only include diagnoses that are marked as 'chronic'."}, {"role": "assistant", "content": "SELECT T1.appointment_id, T1.patient_id, T1.appointment_time, T2.description FROM healthcare.appointments AS T1 JOIN healthcare.diagnoses AS T2 ON T1.patient_id = T2.patient_id AND DATE(T1.appointment_time) = T2.diagnosis_date WHERE T2.is_chronic = true;"}, {"role": "user", "content": "Additionally, filter to only include appointments where the status is 'Completed'."}, {"role": "assistant", "content": "SELECT T1.appointment_id, T1.patient_id, T1.appointment_time, T2.description FROM healthcare.appointments AS T1 JOIN healthcare.diagnoses AS T2 ON T1.patient_id = T2.patient_id AND DATE(T1.appointment_time) = T2.diagnosis_date WHERE T2.is_chronic = true AND T1.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 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) )\n"}
{"conversations": [{"role": "user", "content": "Can you help me find all bookings made by passengers from a specific city, say 'Boston', including the passenger details and the scheduled trip information?"}, {"role": "assistant", "content": "MATCH (p:Passenger)-[:MADE_BOOKING]->(b:Booking)-[:FOR_TRIP]->(st:ScheduledTrip)\nMATCH (p)-[:BASED_AT]->(s:Station)\nWHERE s.city = 'Boston'\nRETURN p.passenger_id, p.first_name, p.last_name, b.booking_id, b.booking_datetime, b.status, st.schedule_id"}, {"role": "user", "content": "Can you modify the query to include only bookings with a status of 'Confirmed'?"}, {"role": "assistant", "content": "MATCH (p:Passenger)-[:MADE_BOOKING]->(b:Booking)-[:FOR_TRIP]->(st:ScheduledTrip)\nMATCH (p)-[:BASED_AT]->(s:Station)\nWHERE s.city = 'Boston' AND b.status = 'Confirmed'\nRETURN p.passenger_id, p.first_name, p.last_name, b.booking_id, b.booking_datetime, b.status, st.schedule_id"}, {"role": "user", "content": "Can you also add the total price of each booking to the result?"}, {"role": "assistant", "content": "MATCH (p:Passenger)-[:MADE_BOOKING]->(b:Booking)-[:FOR_TRIP]->(st:ScheduledTrip)\nMATCH (p)-[:BASED_AT]->(s:Station)\nWHERE s.city = 'Boston' AND b.status = 'Confirmed'\nRETURN p.passenger_id, p.first_name, p.last_name, b.booking_id, b.booking_datetime, b.status, b.total_price, st.schedule_id"}, {"role": "user", "content": "Can you sort the results by booking datetime in ascending order?"}, {"role": "assistant", "content": "MATCH (p:Passenger)-[:MADE_BOOKING]->(b:Booking)-[:FOR_TRIP]->(st:ScheduledTrip)\nMATCH (p)-[:BASED_AT]->(s:Station)\nWHERE s.city = 'Boston' AND b.status = 'Confirmed'\nRETURN p.passenger_id, p.first_name, p.last_name, b.booking_id, b.booking_datetime, b.status, b.total_price, st.schedule_id\nORDER BY b.booking_datetime ASC"}], "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// 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: :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: :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": "Find projects from the project_fundraising_record table that have completed both a 'Seed' fundraising round and a 'Series A' fundraising round."}, {"role": "assistant", "content": "SELECT pf_seed.project_name FROM project_fundraising_record pf_seed JOIN project_fundraising_record pf_seriesa ON pf_seed.project_id = pf_seriesa.project_id WHERE pf_seed.rounds_name = 'Seed' AND pf_seriesa.rounds_name = 'Series A';"}, {"role": "user", "content": "For these projects that had both a 'Seed' and 'Series A' round, show the investment value for both rounds side by side."}, {"role": "assistant", "content": "SELECT pf_seed.project_name, pf_seed.investment_value AS seed_investment, pf_seriesa.investment_value AS seriesa_investment FROM project_fundraising_record pf_seed JOIN project_fundraising_record pf_seriesa ON pf_seed.project_id = pf_seriesa.project_id WHERE pf_seed.rounds_name = 'Seed' AND pf_seriesa.rounds_name = 'Series A';"}, {"role": "user", "content": "Filter the results to only include projects where the investment value in the 'Series A' round was greater than the investment value in the 'Seed' round."}, {"role": "assistant", "content": "SELECT pf_seed.project_name, pf_seed.investment_value AS seed_investment, pf_seriesa.investment_value AS seriesa_investment FROM project_fundraising_record pf_seed JOIN project_fundraising_record pf_seriesa ON pf_seed.project_id = pf_seriesa.project_id WHERE pf_seed.rounds_name = 'Seed' AND pf_seriesa.rounds_name = 'Series A' AND pf_seriesa.investment_value > pf_seed.investment_value;"}, {"role": "user", "content": "Order the results by the 'Series A' investment value in descending order and show the top 5 projects."}, {"role": "assistant", "content": "SELECT pf_seed.project_name, pf_seed.investment_value AS seed_investment, pf_seriesa.investment_value AS seriesa_investment FROM project_fundraising_record pf_seed JOIN project_fundraising_record pf_seriesa ON pf_seed.project_id = pf_seriesa.project_id WHERE pf_seed.rounds_name = 'Seed' AND pf_seriesa.rounds_name = 'Series A' AND pf_seriesa.investment_value > pf_seed.investment_value ORDER BY seriesa_investment DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE project_fundraising_record ( id character varying(32) NOT NULL,  -- fundraising record id project_id character varying(32) NOT NULL, -- the invested project's id project_name character varying(128) NOT NULL, -- name of the invested project rounds_name character varying(32), -- name of the fundraising round investment_value numeric(38,14), -- amount of the fundraising in USD investment_date character varying(128), -- the date of the investment happened introduction character varying(128), -- the introduction of the invested project valuation numeric(38,14), -- the valuation of the project in USD when invested )\nCREATE TABLE narrative_info ( narrative character varying(512) NOT NULL, -- the id of narrative top_3_coins text, -- the top 3 tokens in the narrative price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour in the narrative price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours in the narrative price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days in the narrative market_cap double precision, -- the market cap of the narrative volume_24h double precision, -- the trade volume of the narrative trend_rank bigint, -- the trending rank of the narrative, value 1 expresses the most popular narrative token_num bigint, -- total token number in the narrative ,PRIMARY KEY (narrative) )\nCREATE TABLE smart_money_profit ( address character varying(100) NOT NULL, -- the user's address rank INT, -- the rank of the address in trade performance, value 1 expresses the best address. profit numeric(38,6), -- the profit user made in a month roi numeric(38,2), -- the roi of the user in a month realized_ratio numeric(38,2), -- the percentage of the user's realized profit most_profit_token character varying(100), -- the token symbol of the user's most profitable trade last_trade_time character varying(100), -- the last trade time of the user chain character varying(100), -- the chain that the address resides PRIMARY KEY (address, chain) )\n"}
{"conversations": [{"role": "user", "content": "Find 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 the first name, last name, and hire date for all lawyers who were hired after the year 2020."}, {"role": "assistant", "content": "SELECT first_name, last_name, hire_date FROM legal_services.lawyers WHERE hire_date > '2020-12-31'"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.lawyers ( lawyer_id.text, first_name.text, last_name.text, bar_number.text, firm_id.text, email.text, phone.text, specialization.text, hire_date.timestamp, is_partner.boolean )\nCREATE TABLE legal_services.law_firms ( firm_id.text, firm_name.text, address.text, phone.text, website.text, founded_date.date, managing_partner_id.text )\nCREATE TABLE legal_services.cases ( case_id.text, case_number.text, case_name.text, client_id.text, lead_lawyer_id.text, case_type.text, status.text, date_opened.timestamp, date_closed.timestamp, description.text, court_jurisdiction.text )\nCREATE TABLE legal_services.time_entries ( entry_id.text, case_id.text, lawyer_id.text, date_worked.date, hours_spent.numeric, billing_rate.numeric, description.text, is_billable.boolean, is_billed.boolean, invoice_id.text, created_at.timestamp )\nCREATE TABLE legal_services.appointments ( appointment_id.text, client_id.text, lawyer_id.text, case_id.text, start_time.timestamp, end_time.timestamp, location.text, subject.text, notes.text, status.text, created_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "List all pairs of token transfers where the sender is the same but the recipients differ. Show both transfer IDs and the common sender address."}, {"role": "assistant", "content": "SELECT t1.transfer_id AS transfer_id_1, t2.transfer_id AS transfer_id_2, t1.from_address AS common_from_address\nFROM web3.token_transfers t1\nJOIN web3.token_transfers t2\n  ON t1.from_address = t2.from_address\n    AND t1.to_address <> t2.to_address\n    AND t1.transfer_id < t2.transfer_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.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": "Get all non-smoking rooms with status 'Available'."}, {"role": "assistant", "content": "SELECT room_id, property_id, room_number, floor\nFROM hospitality_technology.rooms\nWHERE is_smoking = FALSE\n  AND status = 'Available';"}, {"role": "user", "content": "Now include the property_name for each room."}, {"role": "assistant", "content": "SELECT r.room_id, r.room_number, p.property_name, r.floor\nFROM hospitality_technology.rooms r\nJOIN hospitality_technology.properties p\n  ON r.property_id = p.property_id\nWHERE r.is_smoking = FALSE\n  AND r.status = 'Available';"}], "system": "You are an SQL statement expert. Given the table structure 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 )\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 medical record entries where the treatment_plan mentions a medication name. Return patient_id, record_id, and the matching medication_name."}, {"role": "assistant", "content": "SELECT mr.patient_id,\n       mr.record_id,\n       m.medication_name\nFROM healthcare.medical_records AS mr\nJOIN healthcare.medications AS m\n  ON mr.treatment_plan ILIKE '%' || m.medication_name || '%';"}, {"role": "user", "content": "Actually, only include medications manufactured by 'Pfizer'."}, {"role": "assistant", "content": "SELECT mr.patient_id,\n       mr.record_id,\n       m.medication_name\nFROM healthcare.medical_records AS mr\nJOIN healthcare.medications AS m\n  ON mr.treatment_plan ILIKE '%' || m.medication_name || '%'\nWHERE m.manufacturer = 'Pfizer';"}, {"role": "user", "content": "Also sort the results by record_date descending."}, {"role": "assistant", "content": "SELECT mr.patient_id,\n       mr.record_id,\n       m.medication_name\nFROM healthcare.medical_records AS mr\nJOIN healthcare.medications AS m\n  ON mr.treatment_plan ILIKE '%' || m.medication_name || '%'\nWHERE m.manufacturer = 'Pfizer'\nORDER BY mr.record_date DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients (\n    patient_id character varying(64) NOT NULL,  -- unique identifier for the patient\n    first_name character varying(100) NOT NULL, -- patient's first name\n    last_name character varying(100) NOT NULL, -- patient's last name\n    date_of_birth date NOT NULL, -- patient's date of birth\n    gender character varying(10), -- patient's gender (e.g., Male, Female, Other)\n    address text, -- patient's home address\n    phone_number character varying(20), -- patient's phone number\n    email character varying(128) UNIQUE, -- patient's email address\n    emergency_contact_name character varying(200), -- name of emergency contact\n    emergency_contact_phone character varying(20), -- phone number of emergency contact\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, -- record creation time\n    updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, -- record last update time\n    PRIMARY KEY (patient_id)\n)\nCREATE TABLE healthcare.doctors (\n    doctor_id character varying(64) NOT NULL,  -- unique identifier for the doctor\n    first_name character varying(100) NOT NULL, -- doctor's first name\n    last_name character varying(100) NOT NULL, -- doctor's last name\n    specialty character varying(100) NOT NULL, -- doctor's medical specialty\n    license_number character varying(50) UNIQUE NOT NULL, -- doctor's medical license number\n    phone_number character varying(20), -- doctor's contact phone\n    email character varying(128) UNIQUE, -- doctor's contact email\n    hospital_affiliation_id character varying(64), -- FK to hospitals table (optional)\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (doctor_id)\n)\nCREATE TABLE healthcare.appointments (\n    appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    doctor_id character varying(64) NOT NULL, -- FK to doctors table\n    appointment_time timestamp with time zone NOT NULL, -- date and time of the appointment\n    duration_minutes integer NOT NULL, -- expected duration in minutes\n    reason text, -- reason for the visit\n    status character varying(32) NOT NULL, -- e.g., Scheduled, Completed, Cancelled, No-show\n    location_id character varying(64), -- FK to a potential locations/clinics table\n    notes text, -- notes related to scheduling\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (appointment_id)\n)\nCREATE TABLE healthcare.medical_records (\n    record_id character varying(64) NOT NULL,  -- unique identifier for the medical record entry\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    appointment_id character varying(64) UNIQUE, -- FK to appointments table (can be null if record not tied to specific appt)\n    doctor_id character varying(64) NOT NULL, -- FK to doctors table (doctor creating the record)\n    record_date timestamp with time zone NOT NULL, -- date the record/observation was made\n    chief_complaint text, -- patient's primary reason for visit\n    present_illness_history text, -- detailed history of the current issue\n    past_medical_history text, -- relevant past conditions/surgeries\n    physical_examination_notes text, -- findings from the physical exam\n    assessment text, -- doctor's assessment/diagnosis summary\n    treatment_plan text, -- planned course of action\n    vitals jsonb, -- store vitals like BP, HR, Temp as structured JSON\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (record_id)\n)\nCREATE TABLE healthcare.medications (\n    medication_id character varying(64) NOT NULL, -- unique identifier for the medication type\n    medication_name character varying(255) NOT NULL, -- common or brand name\n    generic_name character varying(255), -- generic chemical name\n    manufacturer character varying(100), -- drug manufacturer\n    ndc_code character varying(20) UNIQUE, -- National Drug Code (optional but useful)\n    description text, -- description of the medication\n    PRIMARY KEY (medication_id)\n)\nCREATE TABLE healthcare.insurance_plans (\n    plan_id character varying(64) NOT NULL, -- unique identifier for the insurance plan\n    plan_name character varying(200) NOT NULL, -- name of the insurance plan\n    insurance_provider character varying(100) NOT NULL, -- name of the insurance company\n    plan_type character varying(50), -- e.g., PPO, HMO, EPO\n    contact_phone character varying(20), -- provider contact number\n    website character varying(255), -- provider website\n    PRIMARY KEY (plan_id)\n)\nCREATE TABLE healthcare.patient_insurance (\n    patient_insurance_id character varying(64) NOT NULL, -- unique identifier for this patient-plan link\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    plan_id character varying(64) NOT NULL, -- FK to insurance_plans table\n    policy_number character varying(100) NOT NULL, -- patient's policy number\n    group_number character varying(100), -- group number, if applicable\n    subscriber_name character varying(200), -- name of the primary policy holder\n    effective_date date NOT NULL, -- date the coverage begins\n    expiration_date date, -- date the coverage ends (if known)\n    is_primary boolean NOT NULL DEFAULT true, -- indicates if this is the primary insurance\n    PRIMARY KEY (patient_insurance_id),\n    UNIQUE (patient_id, plan_id, policy_number) -- ensure a patient doesn't have the same policy twice\n)\n"}
{"conversations": [{"role": "user", "content": "List the count of events for each contract deployed by address '0x123abc...'"}, {"role": "assistant", "content": "SELECT c.address, COUNT(e.event_id) FROM web3.contracts c JOIN web3.events e ON c.contract_id = e.contract_id WHERE c.deployer_address = '0x123abc...' GROUP BY c.address;"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nCREATE TABLE web3.contracts ( contract_id 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 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.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 ( 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 web3.users ( user_id character varying(64) NOT NULL, username character varying(128) NOT NULL, email character varying(128) NOT NULL, password_hash text NOT NULL, created_at timestamp NOT NULL, PRIMARY KEY (user_id) )\n"}
{"conversations": [{"role": "user", "content": "Show 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": "Find the security name and ticker symbol for all securities that have a market data entry with a trading volume greater than 5,000,000."}, {"role": "assistant", "content": "SELECT DISTINCT T1.security_name, T1.ticker_symbol FROM financial_services.securities AS T1 JOIN financial_services.market_data AS T2 ON T1.security_id = T2.security_id WHERE T2.volume > 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 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 )\n"}
{"conversations": [{"role": "user", "content": "Show me all nodes that were last seen in the last 7 days, along with their IP addresses and ports."}, {"role": "assistant", "content": "SELECT node_id, ip_address, port, last_seen FROM blockchain.nodes WHERE last_seen >= CURRENT_DATE - INTERVAL '7 days';"}, {"role": "user", "content": "Now filter these results to only show nodes with port numbers between 8000 and 9000."}, {"role": "assistant", "content": "SELECT node_id, ip_address, port, last_seen FROM blockchain.nodes WHERE last_seen >= CURRENT_DATE - INTERVAL '7 days' AND port BETWEEN 8000 AND 9000;"}], "system": "You are an SQL statement expert. Given the table structure 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, ip_address text, port integer, last_seen timestamp )\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)\n"}
{"conversations": [{"role": "user", "content": "List pairs of game titles in the same genre but developed by different developers."}, {"role": "assistant", "content": "SELECT g1.title AS game1_title,\n       g2.title AS game2_title,\n       g1.genre\nFROM gaming_technology.games g1\nJOIN gaming_technology.games g2\n  ON g1.genre = g2.genre\n  AND g1.developer_id <> g2.developer_id\n  AND g1.game_id < g2.game_id;"}, {"role": "user", "content": "Only include pairs where the genre is 'RPG' or 'Action'."}, {"role": "assistant", "content": "SELECT g1.title AS game1_title,\n       g2.title AS game2_title,\n       g1.genre\nFROM gaming_technology.games g1\nJOIN gaming_technology.games g2\n  ON g1.genre = g2.genre\n  AND g1.developer_id <> g2.developer_id\n  AND g1.game_id < g2.game_id\nWHERE g1.genre IN ('RPG', 'Action');"}, {"role": "user", "content": "Limit to pairs where both games were released after 2020."}, {"role": "assistant", "content": "SELECT g1.title AS game1_title,\n       g2.title AS game2_title,\n       g1.genre\nFROM gaming_technology.games g1\nJOIN gaming_technology.games g2\n  ON g1.genre = g2.genre\n  AND g1.developer_id <> g2.developer_id\n  AND g1.game_id < g2.game_id\nWHERE g1.genre IN ('RPG', 'Action')\n  AND g1.release_date > '2020-01-01'\n  AND g2.release_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 gaming_technology.games ( game_id.uuid, title.text, developer_id.uuid, publisher_id.uuid, genre.text, release_date.date, description.text, platform.text, engine.text, website.text )\n"}
{"conversations": [{"role": "user", "content": "List all ERC20 tokens where the price is between $1 and $10, including their names, symbols, and contract addresses."}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address FROM token_metas tm JOIN token_prices_latest tpl ON tm.contract_address = tpl.contract_address WHERE tm.is_erc20 = 1 AND tpl.price BETWEEN 1 AND 10;"}, {"role": "user", "content": "I think there's an error in your query - the token_prices_latest table isn't in the schema. Can you modify it to use the token_balances table instead?"}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address FROM token_metas tm JOIN token_balances tb ON tm.contract_address = tb.wallet_address WHERE tm.is_erc20 = 1 AND CAST(tb.amount AS decimal) BETWEEN 1 AND 10;"}, {"role": "user", "content": "That doesn't seem right either. Let's just get the basic ERC20 token information without price filtering for now."}, {"role": "assistant", "content": "SELECT name, symbol, contract_address FROM token_metas WHERE is_erc20 = 1 LIMIT 100;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp.timestamp, block_number.bigint, transaction_hash.text, transaction_index.bigint, from_address.text, contract_address.text, symbol.text, total_supply.text, name.text, decimals.bigint, is_erc20.integer, is_erc721.integer, is_erc1155.integer, is_proxy.integer, extra_info.text, pk.integer )\nCREATE TABLE erc1155_approval_for_all ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar(66) NOT NULL, log_index integer NOT NULL, contract_address varchar(42) NOT NULL )\nCREATE TABLE erc20_balances ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE erc20_balances_historical ( block_number bigint, contract_address text, wallet_address text, amount text, pk integer )\nCREATE TABLE nft_holders ( block_number bigint, contract_address text, wallet_address text, token_id text, contract_type text, amount text, pk text )\nCREATE TABLE nft_holder_historical ( block_number.bigint, contract_address.text, wallet_address.text, token_id.text, contract_type.text, amount.text, pk.integer )\nCREATE TABLE sui_nfts ( object_id text, status text, collection_type text, package_id text, previous_transaction text, display text, owner text, name text )\nCREATE TABLE nft_collections ( blockchain text, contract_address text, name text, symbol text, deploy_block_number bigint, deploy_block_time bigint, erc_type text, owner text, traits text, description text, slug text, media_info text, image_url text, banner_image_url text, updated_at bigint, banner text, token_count bigint, floor_price text, floor_price_symbol text, floor_price_contract text, pk integer )\nCREATE TABLE erc20_approval ( block_number bigint NOT NULL, block_timestamp timestamp(6) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar NOT NULL, log_index integer NOT NULL, contract_address varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_balances ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply decimal, amount decimal )\nCREATE TABLE token_info (\n    block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n    block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n    tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n    tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n    tick varchar NOT NULL, -- Token tick\n    max_supply decimal(38,0) NOT NULL, -- Max supply\n    lim decimal(38,0) NOT NULL, -- Limit of each mint\n    wlim decimal(38,0) NOT NULL, -- Limit of each address can maximum mint\n    dec integer NOT NULL, -- Decimal for minimum divie\n    creator varchar(42) NOT NULL  -- Address originating the inscription (matches from_address in transactions table)\n)\nCREATE TABLE token_activities ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\nCREATE TABLE mud_holesky_redstone ( address varchar NOT NULL, table_id varchar NOT NULL, key_bytes varchar NOT NULL, key0 varchar NOT NULL, key1 varchar NOT NULL, static_data varchar NOT NULL, encoded_lengths varchar NOT NULL, dynamic_data varchar NOT NULL, is_deleted boolean NOT NULL, block_number bigint NOT NULL, log_index bigint NOT NULL )\nCREATE TABLE token_balances_bitcoin ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply varchar, amount varchar )\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar )\nCREATE TABLE token_activities_avalanche ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\nCREATE TABLE token_balances_avalanche (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n    tick varchar(20) NOT NULL, -- Ticker: Identifier of the inscription\n    wallet_address varchar(42) NOT NULL, -- Address of owner\n    total_supply decimal(38,0) NOT NULL, -- Max supply: Set max supply of the inscription\n    amount decimal(38,0) NOT NULL  -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id varchar )\n"}
{"conversations": [{"role": "user", "content": "List 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 all transactions over 10,000 USD that are not marked as 'REVERSED'."}, {"role": "assistant", "content": "SELECT transaction_id, account_id, amount, currency, status, transaction_date\nFROM financial_services.transactions\nWHERE amount > 10000 AND currency = 'USD' AND status != 'REVERSED';"}, {"role": "user", "content": "Include the related_account_id and the transaction_type in the result, and order by amount descending."}, {"role": "assistant", "content": "SELECT transaction_id, account_id, related_account_id, transaction_type, amount, currency, status, transaction_date\nFROM financial_services.transactions\nWHERE amount > 10000 AND currency = 'USD' AND status != 'REVERSED'\nORDER BY amount DESC;"}, {"role": "user", "content": "Add a filter to only include transactions that happened in the last 60 days."}, {"role": "assistant", "content": "SELECT transaction_id, account_id, related_account_id, transaction_type, amount, currency, status, transaction_date\nFROM financial_services.transactions\nWHERE amount > 10000 AND currency = 'USD' AND status != 'REVERSED' AND transaction_date >= NOW() - INTERVAL '60 days'\nORDER BY amount DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.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.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 bigserial NOT NULL, security_id character varying(64) NOT NULL, data_timestamp timestamp NOT NULL, open_price numeric(19, 8), high_price numeric(19, 8), low_price numeric(19, 8), close_price numeric(19, 8) NOT NULL, adjusted_close_price numeric(19, 8), volume bigint, source character varying(50), PRIMARY KEY (data_point_id), UNIQUE (security_id, data_timestamp), FOREIGN KEY (security_id) REFERENCES financial_services.securities(security_id) )\nCREATE TABLE financial_services.employees (\n    employee_id character varying(64) NOT NULL,  -- unique identifier for the employee\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    job_title character varying(100) NOT NULL, -- e.g., Teller, Branch Manager, Financial Advisor, Analyst\n    department character varying(100), -- e.g., Retail Banking, Wealth Management, IT\n    branch_id character varying(64), -- Identifier for the branch they work at (if applicable)\n    email character varying(128) NOT NULL UNIQUE,\n    phone_extension character varying(20),\n    hire_date date NOT NULL,\n    termination_date date, -- Date of termination, null if currently employed\n    manager_id character varying(64), -- Self-referencing key for manager relationship\n    status character varying(32) NOT NULL, -- e.g., Active, Terminated, On Leave\n    PRIMARY KEY (employee_id),\n    FOREIGN KEY (branch_id) REFERENCES financial_services.branches(branch_id), -- Assuming a branches table exists\n    FOREIGN KEY (manager_id) REFERENCES financial_services.employees(employee_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List all patients who have an active prescription for a medication manufactured by 'AstraZeneca', along with their policy number and the prescription ID."}, {"role": "assistant", "content": "SELECT p.patient_id, pi.policy_number, pr.prescription_id\nFROM healthcare.prescriptions pr\nJOIN healthcare.medications m ON pr.medication_id = m.medication_id\nJOIN healthcare.patient_insurance pi ON pr.patient_id = pi.patient_id\nWHERE m.manufacturer = 'AstraZeneca'\n  AND (pr.end_date IS NULL OR pr.end_date > CURRENT_DATE)\n  AND (pi.expiration_date IS NULL OR pi.expiration_date > CURRENT_DATE);"}, {"role": "user", "content": "Only show those patients whose insurance policy is marked as primary."}, {"role": "assistant", "content": "SELECT p.patient_id, pi.policy_number, pr.prescription_id\nFROM healthcare.prescriptions pr\nJOIN healthcare.medications m ON pr.medication_id = m.medication_id\nJOIN healthcare.patient_insurance pi ON pr.patient_id = pi.patient_id\nWHERE m.manufacturer = 'AstraZeneca'\n  AND (pr.end_date IS NULL OR pr.end_date > CURRENT_DATE)\n  AND pi.is_primary = TRUE\n  AND (pi.expiration_date IS NULL OR pi.expiration_date > CURRENT_DATE);"}, {"role": "user", "content": "Instead, I want to see the generic name of the medication and the effective date of the insurance."}, {"role": "assistant", "content": "SELECT p.patient_id, pi.policy_number, pr.prescription_id, m.generic_name, pi.effective_date\nFROM healthcare.prescriptions pr\nJOIN healthcare.medications m ON pr.medication_id = m.medication_id\nJOIN healthcare.patient_insurance pi ON pr.patient_id = pi.patient_id\nWHERE m.manufacturer = 'AstraZeneca'\n  AND (pr.end_date IS NULL OR pr.end_date > CURRENT_DATE)\n  AND pi.is_primary = TRUE\n  AND (pi.expiration_date IS NULL OR pi.expiration_date > CURRENT_DATE);"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.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.patient_insurance ( patient_insurance_id.text, patient_id.text, plan_id.text, policy_number.text, group_number.text, subscriber_name.text, effective_date.date, expiration_date.date, is_primary.boolean )\n"}
{"conversations": [{"role": "user", "content": "List the first name and last name of citizens along with the amount of payments they have made."}, {"role": "assistant", "content": "SELECT T1.first_name, T1.last_name, T2.amount FROM government_services.citizens AS T1 JOIN government_services.payments AS T2 ON T1.citizen_id = T2.citizen_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id text PRIMARY KEY, national_id_number text, first_name text, last_name text, date_of_birth date, gender text, primary_address text, contact_email text, contact_phone text, registration_date timestamp, is_verified boolean )\nCREATE TABLE government_services.services ( service_id text PRIMARY KEY, agency_id text, service_name text, description text, category text, eligibility_criteria text, standard_fee numeric, average_processing_time_days int, is_active boolean, online_application_url text )\nCREATE TABLE government_services.payments ( payment_id text PRIMARY KEY, application_id text, citizen_id text, service_id text, amount numeric, currency text, payment_method text, payment_provider_reference text, payment_timestamp timestamp, status text, notes text )\nCREATE TABLE government_services.service_locations ( location_id text PRIMARY KEY, agency_id text, location_name text, address text, city text, state text, postal_code text, latitude numeric, longitude numeric, operating_hours text, contact_phone text, is_accessible boolean )\nCREATE TABLE government_services.appointments ( appointment_id text PRIMARY KEY, citizen_id text, employee_id text, location_id text, service_id text, scheduled_start_time timestamp, scheduled_end_time timestamp, purpose text, status text, booking_method text, created_at timestamp, notes text )\n"}
{"conversations": [{"role": "user", "content": "List all medications along with the length of their description, but only include those with descriptions longer than 100 characters. Show medication_id, medication_name, and description length."}, {"role": "assistant", "content": "SELECT medication_id, medication_name, LENGTH(description) AS description_length\nFROM healthcare.medications\nWHERE LENGTH(description) > 100;"}, {"role": "user", "content": "Now include only medications where the generic_name is not null and sort by description length descending."}, {"role": "assistant", "content": "SELECT medication_id, medication_name, LENGTH(description) AS description_length\nFROM healthcare.medications\nWHERE LENGTH(description) > 100\n  AND generic_name IS NOT NULL\nORDER BY description_length 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.medications ( medication_id.text, medication_name.text, generic_name.text, manufacturer.text, ndc_code.text, description.text )\n"}
{"conversations": [{"role": "user", "content": "List all reviews for properties with a star rating of at least 4.5. Include the property_name, review_id, rating_overall, and review_date."}, {"role": "assistant", "content": "SELECT p.property_name, r.review_id, r.rating_overall, r.review_date\nFROM hospitality_technology.reviews r\nJOIN hospitality_technology.properties p ON r.property_id = p.property_id\nWHERE p.star_rating >= 4.5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.properties ( property_id text PRIMARY KEY, property_name text, address_line1 text, address_line2 text, city text, state_province text, postal_code text, country_code text, phone_number text, email_address text, property_type text, star_rating numeric, timezone text, manager_staff_id text, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.room_types ( room_type_id text, property_id text, type_name text, description text, base_rate numeric, max_occupancy integer, bed_type text, area_sqft numeric, amenities text )\nCREATE TABLE hospitality_technology.guests ( guest_id text PRIMARY KEY, first_name text, last_name text, email text, phone_number text, date_of_birth date, address_line1 text, city text, state_province text, postal_code text, country_code text, preferences text, loyalty_member_id text, communication_consent boolean, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.staff ( staff_id text, property_id text, first_name text, last_name text, position text, work_email text, work_phone text, hire_date date, termination_date date, is_active boolean, access_level integer, manager_id text, created_at timestamp )\nCREATE TABLE hospitality_technology.service_orders ( order_id.text, reservation_id.text, guest_id.text, service_id.text, staff_id_ordered.text, staff_id_delivered.text, order_timestamp.timestamp, delivery_timestamp.timestamp, quantity.integer, unit_price.numeric, total_price.numeric, status.text, notes.text, bill_id.text )\nCREATE TABLE hospitality_technology.payments (\n    payment_id character varying(64) NOT NULL,  -- unique identifier for the payment transaction\n    reservation_id character varying(64), -- FK to reservations (if payment is for a stay)\n    guest_id character varying(64) NOT NULL, -- FK to guests (who paid)\n    bill_id character varying(64), -- FK to bills/invoices this payment applies to\n    amount numeric(12,2) NOT NULL, -- amount of the payment\n    currency_code character varying(3) NOT NULL, -- ISO currency code (e.g., USD, EUR)\n    payment_method character varying(50) NOT NULL, -- e.g., CreditCard, Cash, BankTransfer, Points, Voucher\n    card_type character varying(50), -- e.g., Visa, MasterCard, Amex (if CC)\n    card_last_four character varying(4), -- last 4 digits of CC (if CC)\n    transaction_ref character varying(128), -- reference ID from payment gateway or processor\n    payment_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, -- when the payment occurred\n    status character varying(50) NOT NULL, -- e.g., Pending, Succeeded, Failed, Refunded, Disputed\n    staff_id_processed character varying(64), -- FK to staff (who processed the payment)\n    notes text, -- notes about the payment\n    PRIMARY KEY (payment_id),\n    FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id),\n    FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id),\n    FOREIGN KEY (staff_id_processed) REFERENCES hospitality_technology.staff(staff_id)\n)\nCREATE TABLE hospitality_technology.reviews ( review_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, reservation_id character varying(64) UNIQUE, guest_id character varying(64) NOT NULL, rating_overall integer, rating_cleanliness integer, rating_service integer, rating_location integer, rating_value integer, comment text, review_source character varying(100), review_date timestamp with time zone NOT NULL DEFAULT current_timestamp, is_public boolean DEFAULT true, staff_response text, response_staff_id character varying(64), response_date timestamp with time zone, PRIMARY KEY (review_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (response_staff_id) REFERENCES hospitality_technology.staff(staff_id) )\n"}
{"conversations": [{"role": "user", "content": "Which doctors have issued prescriptions with a route of 'Oral'? Please show doctor_id and the number of such prescriptions they have written."}, {"role": "assistant", "content": "SELECT doctor_id, COUNT(*) AS oral_prescription_count\nFROM healthcare.prescriptions\nWHERE route = 'Oral'\nGROUP BY doctor_id;"}, {"role": "user", "content": "Now, only include doctors who have written more than 10 oral prescriptions and sort the list by oral_prescription_count descending."}, {"role": "assistant", "content": "SELECT doctor_id, COUNT(*) AS oral_prescription_count\nFROM healthcare.prescriptions\nWHERE route = 'Oral'\nGROUP BY doctor_id\nHAVING COUNT(*) > 10\nORDER BY oral_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.prescriptions (\n    prescription_id character varying(64) NOT NULL, -- unique identifier for the prescription\n    record_id character varying(64) NOT NULL, -- FK linking to the medical record where it was prescribed\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    doctor_id character varying(64) NOT NULL, -- FK to prescribing doctor\n    medication_id character varying(64) NOT NULL, -- FK to medications table\n    dosage character varying(100) NOT NULL, -- e.g., '100mg', '1 tablet'\n    frequency character varying(100) NOT NULL, -- e.g., 'Once daily', 'Twice a day with meals'\n    route character varying(50), -- e.g., 'Oral', 'Topical', 'Intravenous'\n    start_date date NOT NULL, -- date prescription begins\n    end_date date, -- date prescription ends (if applicable)\n    quantity_dispensed numeric(10,2), -- amount dispensed (e.g., number of tablets)\n    refills_allowed integer NOT NULL DEFAULT 0, -- number of allowed refills\n    prescription_date timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (prescription_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List the full names and dates of birth for all patients who do not have a phone number on record."}, {"role": "assistant", "content": "SELECT first_name, last_name, date_of_birth FROM healthcare.patients WHERE phone_number IS NULL OR TRIM(phone_number) = '';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, gender character varying(10), address text, phone_number character varying(20), email character varying(128) UNIQUE, emergency_contact_name character varying(200), emergency_contact_phone character varying(20), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (patient_id) )\nCREATE TABLE healthcare.appointments ( appointment_id.text, patient_id.text, doctor_id.text, appointment_time.timestamp, duration_minutes.integer, reason.text, status.text, location_id.text, notes.text, created_at.timestamp )\nCREATE TABLE healthcare.diagnoses (\n    diagnosis_id character varying(64) NOT NULL, -- unique identifier for the diagnosis entry\n    record_id character varying(64) NOT NULL, -- FK linking to the specific medical record entry\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    doctor_id character varying(64) NOT NULL, -- FK to doctors table (diagnosing doctor)\n    diagnosis_code character varying(20) NOT NULL, -- standard code (e.g., ICD-10)\n    code_type character varying(10) NOT NULL DEFAULT 'ICD-10', -- type of code used\n    description text, -- textual description of the diagnosis\n    diagnosis_date date NOT NULL, -- date the diagnosis was made\n    status character varying(32) NOT NULL, -- e.g., Active, Resolved, Ruled Out\n    is_chronic boolean DEFAULT false, -- flag for chronic conditions\n    PRIMARY KEY (diagnosis_id)\n)\nCREATE TABLE healthcare.prescriptions ( prescription_id text, record_id text, patient_id text, doctor_id text, medication_id text, dosage text, frequency text, route text, start_date date, end_date date, quantity_dispensed numeric, refills_allowed integer, prescription_date timestamp )\nCREATE TABLE healthcare.insurance_plans ( plan_id text, plan_name text, insurance_provider text, plan_type text, contact_phone text, website text )\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id.text, patient_id.text, plan_id.text, policy_number.text, group_number.text, subscriber_name.text, effective_date.date, expiration_date.date, is_primary.boolean )\n"}
{"conversations": [{"role": "user", "content": "Show me the top 5 narratives by market cap, along with their 24-hour trading volume and 7-day price change percentage."}, {"role": "assistant", "content": "SELECT narrative.text, volume_24h.numeric, price_change_percentage_7d.numeric FROM narrative_info ORDER BY market_cap.numeric DESC LIMIT 5;"}, {"role": "user", "content": "Can you also include the top 3 coins for each of these narratives?"}, {"role": "assistant", "content": "SELECT narrative.text, volume_24h.numeric, price_change_percentage_7d.numeric, top_3_coins.text FROM narrative_info ORDER BY market_cap.numeric DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE narrative_info ( narrative.text, top_3_coins.text, price_change_percentage_1h.numeric, price_change_percentage_24h.numeric, price_change_percentage_7d.numeric, market_cap.numeric, volume_24h.numeric, trend_rank.numeric, token_num.numeric )\n"}
{"conversations": [{"role": "user", "content": "List the number of bookings for each day."}, {"role": "assistant", "content": "SELECT DATE(booking_time) AS booking_date, COUNT(*) AS booking_count\nFROM transportation.bookings\nGROUP BY DATE(booking_time);\n"}, {"role": "user", "content": "Now only include days where booking_count > 10."}, {"role": "assistant", "content": "SELECT DATE(booking_time) AS booking_date, COUNT(*) AS booking_count\nFROM transportation.bookings\nGROUP BY DATE(booking_time)\nHAVING COUNT(*) > 10;\n"}, {"role": "user", "content": "Also include the total fare collected for those days."}, {"role": "assistant", "content": "SELECT DATE(booking_time) AS booking_date,\n       COUNT(*) AS booking_count,\n       SUM(fare) AS total_fare\nFROM transportation.bookings\nGROUP BY DATE(booking_time)\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 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 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 each citizen's first and last name along with the first and last name of another citizen who shares the same last name. Show each pair only once."}, {"role": "assistant", "content": "SELECT c1.first_name || ' ' || c1.last_name AS citizen_name,\n       c2.first_name || ' ' || c2.last_name AS other_citizen_name\nFROM government_services.citizens c1\nJOIN government_services.citizens c2\n  ON c1.last_name = c2.last_name\n AND c1.citizen_id < c2.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 (\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": "Find all pairs of drivers who share the same status. Include both driver_ids, full names, and the shared status."}, {"role": "assistant", "content": "SELECT d1.driver_id AS driver1_id, d1.first_name || ' ' || d1.last_name AS driver1_name, d2.driver_id AS driver2_id, d2.first_name || ' ' || d2.last_name AS driver2_name, d1.status FROM transportation.drivers d1 JOIN transportation.drivers d2 ON d1.status = d2.status AND d1.driver_id < d2.driver_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.drivers ( driver_id text PRIMARY KEY, employee_id text, first_name text, last_name text, license_number text, license_expiry_date date, contact_number text, email text, hire_date date, status text )\n"}
{"conversations": [{"role": "user", "content": "Count the number of policies issued in each calendar year, and show the year and the count."}, {"role": "assistant", "content": "SELECT EXTRACT(YEAR FROM issued_at), COUNT(*) FROM insurance.policies WHERE issued_at IS NOT NULL GROUP BY 1 ORDER BY 1;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.customers ( customer_id text, first_name text, last_name text, date_of_birth date, ssn_hash text, address_line1 text, address_line2 text, city text, state text, zip_code text, country text, phone_number text, email text, created_at timestamp, updated_at timestamp, status text )\nCREATE TABLE insurance.policies ( policy_id text, customer_id text, product_id text, agent_id text, policy_number text, start_date date, end_date date, premium_amount numeric, coverage_limit numeric, deductible numeric, status text, issued_at timestamp, cancellation_date date, cancellation_reason text )\nCREATE TABLE insurance.insurance_products ( product_id text, product_name text, product_type text, description text, base_premium numeric, coverage_details text, underwriting_rules text, is_active boolean, created_at timestamp, updated_at timestamp )\nCREATE TABLE insurance.agents ( agent_id text, first_name text, last_name text, agency_name text, license_number text, license_state text, contact_email text, contact_phone text, hire_date date, termination_date date, status text, commission_rate numeric, manager_id text )\nCREATE TABLE insurance.policy_beneficiaries ( beneficiary_id text, policy_id text, customer_id text, first_name text, last_name text, relationship text, percentage_share numeric, contact_info text, added_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show me the usernames and email addresses of users who commented on any post tagged with the hashtag 'H777'."}, {"role": "assistant", "content": "SELECT DISTINCT u.username, u.email\nFROM social_media.comments c\nJOIN social_media.users u ON c.user_id = u.user_id\nJOIN social_media.post_hashtags ph ON c.post_id = ph.post_id\nWHERE ph.hashtag_id = 'H777';"}, {"role": "user", "content": "Please also include the comment content and when each comment was created."}, {"role": "assistant", "content": "SELECT DISTINCT u.username, u.email, c.content, c.created_at\nFROM social_media.comments c\nJOIN social_media.users u ON c.user_id = u.user_id\nJOIN social_media.post_hashtags ph ON c.post_id = ph.post_id\nWHERE ph.hashtag_id = 'H777';"}, {"role": "user", "content": "Now, only include comments created after April 1, 2024."}, {"role": "assistant", "content": "SELECT DISTINCT u.username, u.email, c.content, c.created_at\nFROM social_media.comments c\nJOIN social_media.users u ON c.user_id = u.user_id\nJOIN social_media.post_hashtags ph ON c.post_id = ph.post_id\nWHERE ph.hashtag_id = 'H777'\n  AND c.created_at > '2024-04-01';"}, {"role": "user", "content": "Instead of email, show the user's full name, and sort by comment creation time descending."}, {"role": "assistant", "content": "SELECT DISTINCT u.username, u.full_name, c.content, c.created_at\nFROM social_media.comments c\nJOIN social_media.users u ON c.user_id = u.user_id\nJOIN social_media.post_hashtags ph ON c.post_id = ph.post_id\nWHERE ph.hashtag_id = 'H777'\n  AND c.created_at > '2024-04-01'\nORDER BY c.created_at DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id character varying(64) NOT NULL, username character varying(50) NOT NULL UNIQUE, email character varying(128) NOT NULL UNIQUE, password_hash text NOT NULL, full_name character varying(100), profile_picture_url text, bio text, location character varying(100), created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, is_verified boolean NOT NULL DEFAULT false, PRIMARY KEY (user_id) )\nCREATE TABLE social_media.comments ( comment_id text, post_id text, user_id text, parent_comment_id text, content text, created_at timestamp, updated_at timestamp )\nCREATE TABLE social_media.hashtags ( hashtag_id text, tag_name text, created_at timestamp )\nCREATE TABLE social_media.notifications (\n    notification_id character varying(64) NOT NULL, -- unique identifier for the notification\n    recipient_user_id character varying(64) NOT NULL, -- user receiving the notification (FK to users.user_id)\n    sender_user_id character varying(64), -- user triggering the notification (FK to users.user_id, can be null for system notifications)\n    notification_type character varying(30) NOT NULL, -- type of notification ('like', 'comment', 'follow', 'mention', 'message')\n    target_entity_id character varying(64), -- ID of the related entity (post_id, comment_id, user_id, conversation_id)\n    target_entity_type character varying(20), -- type of the related entity ('post', 'comment', 'user', 'conversation')\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp notification was created\n    read_at timestamp, -- timestamp notification was marked as read\n    PRIMARY KEY (notification_id)\n)\nCREATE TABLE social_media.user_settings ( setting_id text PRIMARY KEY, user_id text, theme text, email_notifications_enabled bool, push_notifications_enabled bool, private_profile bool, updated_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show me all savings accounts (account_id, account_number, balance) with an interest rate above 2.5%, along with the security details (ticker_symbol, issuer_name) for securities in the same currency as the account."}, {"role": "assistant", "content": "SELECT a.account_id, a.account_number, a.balance, s.ticker_symbol, s.issuer_name FROM financial_services.accounts a JOIN financial_services.securities s ON a.currency = s.currency WHERE a.account_type = 'Savings' AND a.interest_rate > 0.025"}], "system": "You are an SQL statement expert. Given the table structure 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 character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, account_number character varying(128) NOT NULL UNIQUE, account_type character varying(50) NOT NULL, balance numeric(19, 4) NOT NULL DEFAULT 0.00, currency character varying(3) NOT NULL, opened_date date NOT NULL, status character varying(32) NOT NULL, interest_rate numeric(5, 4), last_updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (account_id), FOREIGN KEY (customer_id) REFERENCES financial_services.customers(customer_id) )\nCREATE TABLE financial_services.securities ( security_id 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 )\n"}
{"conversations": [{"role": "user", "content": "Find pairs of locations that are in the same state or province but are in different cities. Show their names, cities, and the state/province."}, {"role": "assistant", "content": "SELECT\n  l1.name AS location1_name,\n  l2.name AS location2_name,\n  l1.city AS location1_city,\n  l2.city AS location2_city,\n  l1.state_province\nFROM transportation.locations AS l1\nJOIN transportation.locations AS l2\n  ON l1.state_province = l2.state_province AND l1.city != l2.city AND l1.location_id < l2.location_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.locations ( location_id.text, name.text, type.text, address_line1.text, city.text, state_province.text, postal_code.text, country.text, latitude.numeric, longitude.numeric, timezone.text )\n"}
{"conversations": [{"role": "user", "content": "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": "Show all token symbols along with the contract address where the token was created."}, {"role": "assistant", "content": "SELECT token_symbol, contract_address FROM web3.tokens;"}, {"role": "user", "content": "Can you also include the deployer address for each of these contracts?"}, {"role": "assistant", "content": "SELECT T1.token_symbol, T1.contract_address, T2.deployer_address FROM web3.tokens AS T1 JOIN web3.contracts AS T2 ON T1.contract_address = T2.address;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.contracts ( contract_id.text, address.text, abi.text, bytecode.text, deployer_address.text, deployed_at.timestamp, network_id.text, status.text )\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.token_transfers (\n    transfer_id character varying(64) NOT NULL,  -- unique identifier for the transfer\n    token_id character varying(64) NOT NULL, -- identifier of the token being transferred\n    from_address character varying(128) NOT NULL, -- address of the sender\n    to_address character varying(128) NOT NULL, -- address of the receiver\n    value numeric(38,14) NOT NULL, -- amount of tokens transferred\n    transaction_id character varying(64) NOT NULL, -- identifier of the transaction containing the transfer\n    log_index integer NOT NULL, -- index of the transfer log in the transaction\n    PRIMARY KEY (transfer_id)\n)\nCREATE TABLE web3.wallets ( 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": "List pairs of citizens who share the same email domain."}, {"role": "assistant", "content": "SELECT c1.first_name AS first1,\n       c1.last_name AS last1,\n       c2.first_name AS first2,\n       c2.last_name AS last2,\n       SPLIT_PART(c1.contact_email, '@', 2) AS domain\nFROM government_services.citizens c1\nJOIN government_services.citizens c2\n  ON SPLIT_PART(c1.contact_email, '@', 2) = SPLIT_PART(c2.contact_email, '@', 2)\n AND c1.citizen_id < c2.citizen_id\nWHERE c1.contact_email IS NOT NULL\n  AND c2.contact_email IS NOT NULL;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens (\n    citizen_id character varying(64) NOT NULL,  -- unique identifier for the citizen\n    national_id_number character varying(128) NOT NULL UNIQUE, -- official national identification number\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    date_of_birth date NOT NULL,\n    gender character varying(20),\n    primary_address text NOT NULL, -- full primary residential address\n    contact_email character varying(128) UNIQUE,\n    contact_phone character varying(32),\n    registration_date timestamp NOT NULL, -- when the citizen profile was created\n    is_verified boolean DEFAULT false, -- whether identity has been officially verified\n    PRIMARY KEY (citizen_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List all time entries along with the case number they belong to and the full name of the lawyer who logged them."}, {"role": "assistant", "content": "SELECT T1.entry_id, T2.case_number, T3.first_name, T3.last_name FROM time_entries AS T1 JOIN cases AS T2 ON T1.case_id = T2.case_id JOIN lawyers AS T3 ON T1.lawyer_id = T3.lawyer_id"}, {"role": "user", "content": "Only include entries worked after June 1st, 2024, that are billable but have not yet been billed."}, {"role": "assistant", "content": "SELECT T1.entry_id, T2.case_number, T3.first_name, T3.last_name FROM time_entries AS T1 JOIN cases AS T2 ON T1.case_id = T2.case_id JOIN lawyers AS T3 ON T1.lawyer_id = T3.lawyer_id WHERE T1.date_worked > '2024-06-01' AND T1.is_billable = TRUE AND T1.is_billed = 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 legal_services.lawyers ( lawyer_id.text, first_name.text, last_name.text, bar_number.text, firm_id.text, email.text, phone.text, specialization.text, hire_date.timestamp, is_partner.boolean )\nCREATE TABLE legal_services.law_firms ( firm_id.text, firm_name.text, address.text, phone.text, website.text, founded_date.date, managing_partner_id.text )\nCREATE TABLE legal_services.cases ( case_id.text, case_number.text, case_name.text, client_id.text, lead_lawyer_id.text, case_type.text, status.text, date_opened.timestamp, date_closed.timestamp, description.text, court_jurisdiction.text )\nCREATE TABLE legal_services.time_entries ( entry_id.text, case_id.text, lawyer_id.text, date_worked.date, hours_spent.numeric, billing_rate.numeric, description.text, is_billable.boolean, is_billed.boolean, invoice_id.text, created_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "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;"}, {"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.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 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.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.staff (\n    staff_id character varying(64) NOT NULL,  -- unique identifier for the staff member\n    property_id character varying(64) NOT NULL, -- FK to properties table (primary property)\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    position character varying(100) NOT NULL, -- e.g., Front Desk Agent, Housekeeper, Manager, Concierge\n    work_email character varying(255) UNIQUE, -- staff member's work email\n    work_phone character varying(30),\n    hire_date date NOT NULL,\n    termination_date date, -- date employment ended (if applicable)\n    is_active boolean NOT NULL DEFAULT true, -- currently employed flag\n    access_level integer NOT NULL, -- permission level within systems (e.g., 1=basic, 5=admin)\n    manager_id character varying(64), -- FK to staff table (self-referencing for supervisor)\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (staff_id),\n    FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n    FOREIGN KEY (manager_id) REFERENCES hospitality_technology.staff(staff_id)\n)\nCREATE TABLE hospitality_technology.services ( service_id text PRIMARY KEY, property_id text, service_name text, description text, category text, price numeric, unit text, is_available boolean, department text )\nCREATE TABLE hospitality_technology.service_orders ( order_id character varying(64) NOT NULL, reservation_id character varying(64), guest_id character varying(64) NOT NULL, service_id character varying(64) NOT NULL, staff_id_ordered character varying(64), staff_id_delivered character varying(64), order_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, delivery_timestamp timestamp with time zone, quantity integer NOT NULL DEFAULT 1, unit_price numeric(10, 2) NOT NULL, total_price numeric(12, 2) NOT NULL, status character varying(50) NOT NULL, notes text, bill_id character varying(64), PRIMARY KEY (order_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (service_id) REFERENCES hospitality_technology.services(service_id), FOREIGN KEY (staff_id_ordered) REFERENCES hospitality_technology.staff(staff_id), FOREIGN KEY (staff_id_delivered) REFERENCES hospitality_technology.staff(staff_id) )\nCREATE TABLE hospitality_technology.payments ( payment_id text, reservation_id text, guest_id text, bill_id text, amount numeric, currency_code text, payment_method text, card_type text, card_last_four text, transaction_ref text, payment_timestamp timestamp, status text, staff_id_processed text, notes text )\n"}
{"conversations": [{"role": "user", "content": "List document names and versions for documents that share the same case_id, showing each pair of versions."}, {"role": "assistant", "content": "SELECT d1.case_id, d1.document_name AS doc_name_v1, d1.version AS version1, d2.document_name AS doc_name_v2, d2.version AS version2 FROM legal_services.documents d1 JOIN legal_services.documents d2 ON d1.case_id = d2.case_id AND d1.version < d2.version;"}, {"role": "user", "content": "Actually, I only want to compare the highest version against the second highest version per case."}, {"role": "assistant", "content": "SELECT d_prev.case_id, d_prev.document_name AS prev_doc, d_prev.version AS prev_version, d_latest.document_name AS latest_doc, d_latest.version AS latest_version FROM legal_services.documents d_latest JOIN legal_services.documents d_prev ON d_latest.case_id = d_prev.case_id AND d_prev.version = d_latest.version - 1 WHERE d_latest.version = (SELECT MAX(version) FROM legal_services.documents d WHERE d.case_id = d_latest.case_id);"}, {"role": "user", "content": "Also include the upload timestamps and restrict to cases with at least three versions."}, {"role": "assistant", "content": "SELECT d_latest.case_id, d_prev.document_name AS prev_doc, d_prev.upload_timestamp AS prev_upload, d_latest.document_name AS latest_doc, d_latest.upload_timestamp AS latest_upload FROM legal_services.documents d_latest JOIN legal_services.documents d_prev ON d_latest.case_id = d_prev.case_id AND d_prev.version = d_latest.version - 1 WHERE d_latest.version = (SELECT MAX(version) FROM legal_services.documents d WHERE d.case_id = d_latest.case_id) AND (SELECT COUNT(*) FROM legal_services.documents d2 WHERE d2.case_id = d_latest.case_id) >= 3;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.documents (\n    document_id character varying(64) NOT NULL,  -- unique identifier for the document\n    case_id character varying(64) NOT NULL, -- FK to cases table\n    document_name character varying(255) NOT NULL, -- name of the document file\n    document_type character varying(100), -- e.g., Pleading, Contract, Evidence, Correspondence\n    storage_path text NOT NULL, -- path or reference to the document storage location\n    uploaded_by_lawyer_id character varying(64), -- FK to lawyers table (who uploaded it)\n    upload_timestamp timestamp NOT NULL, -- time the document was uploaded\n    version integer DEFAULT 1, -- document version number\n    description text, -- brief description or notes about the document\n    PRIMARY KEY (document_id)\n)\n"}
{"conversations": [{"role": "user", "content": "What is the total count of game sessions recorded?"}, {"role": "assistant", "content": "SELECT count(*) FROM gaming_technology.game_sessions;"}, {"role": "user", "content": "Now, only count sessions that lasted longer than 1 hour."}, {"role": "assistant", "content": "SELECT count(*) FROM gaming_technology.game_sessions WHERE duration_seconds > 3600;"}], "system": "You are an SQL statement expert. Given the table structure 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 ( session_id uuid, player_id uuid, game_id uuid, server_id uuid, start_time timestamp with time zone, end_time timestamp with time zone, duration_seconds integer, score integer, session_data jsonb )\nCREATE TABLE gaming_technology.servers ( server_id uuid, game_id uuid, server_name text, region text, ip_address text, port integer, current_players integer, max_players integer, status text, last_heartbeat timestamp with time zone )\nCREATE TABLE gaming_technology.in_game_items (\n    item_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the item definition\n    game_id uuid NOT NULL, -- FK linking to the game this item belongs to\n    item_name character varying(150) NOT NULL, -- name of the item\n    item_type character varying(50) NOT NULL, -- type (e.g., Cosmetic, Consumable, Weapon, Armor)\n    description text, -- description of the item\n    rarity character varying(30), -- item rarity (e.g., Common, Rare, Epic, Legendary)\n    cost_currency character varying(10), -- currency code if purchasable (e.g., USD, EUR, GOLD)\n    cost_amount numeric(12, 2), -- price if purchasable\n    attributes jsonb, -- flexible field for item stats or properties\n    PRIMARY KEY (item_id)\n    -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id)\n)\n"}
{"conversations": [{"role": "user", "content": "For each reservation, list the guest ID, property name, and the total amount booked. Only include reservations where the total amount is greater than 300."}, {"role": "assistant", "content": "SELECT r.reservation_id, r.guest_id, p.property_name, r.total_amount\nFROM hospitality_technology.reservations r\nJOIN hospitality_technology.properties p ON r.property_id = p.property_id\nWHERE r.total_amount > 300;"}], "system": "You are an SQL statement expert. Given the table structure 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.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.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 me all patients who have been prescribed medications with dosage greater than 100mg, along with their full names and the medication details, including the prescribing doctor's last name."}, {"role": "assistant", "content": "SELECT p.first_name, p.last_name, m.medication_name, m.generic_name, pr.dosage, d.last_name AS doctor_last_name FROM healthcare.patients p JOIN healthcare.prescriptions pr ON p.patient_id = pr.patient_id JOIN healthcare.medications m ON pr.medication_id = m.medication_id JOIN healthcare.doctors d ON pr.doctor_id = d.doctor_id WHERE pr.dosage LIKE '%100mg%' OR CAST(SUBSTRING(pr.dosage FROM '([0-9]+)') AS INTEGER) > 100;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.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.medical_records (\n    record_id character varying(64) NOT NULL,  -- unique identifier for the medical record entry\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    appointment_id character varying(64) UNIQUE, -- FK to appointments table (can be null if record not tied to specific appt)\n    doctor_id character varying(64) NOT NULL, -- FK to doctors table (doctor creating the record)\n    record_date timestamp with time zone NOT NULL, -- date the record/observation was made\n    chief_complaint text, -- patient's primary reason for visit\n    present_illness_history text, -- detailed history of the current issue\n    past_medical_history text, -- relevant past conditions/surgeries\n    physical_examination_notes text, -- findings from the physical exam\n    assessment text, -- doctor's assessment/diagnosis summary\n    treatment_plan text, -- planned course of action\n    vitals jsonb, -- store vitals like BP, HR, Temp as structured JSON\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (record_id)\n)\nCREATE TABLE healthcare.diagnoses (\n    diagnosis_id character varying(64) NOT NULL, -- unique identifier for the diagnosis entry\n    record_id character varying(64) NOT NULL, -- FK linking to the specific medical record entry\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    doctor_id character varying(64) NOT NULL, -- FK to doctors table (diagnosing doctor)\n    diagnosis_code character varying(20) NOT NULL, -- standard code (e.g., ICD-10)\n    code_type character varying(10) NOT NULL DEFAULT 'ICD-10', -- type of code used\n    description text, -- textual description of the diagnosis\n    diagnosis_date date NOT NULL, -- date the diagnosis was made\n    status character varying(32) NOT NULL, -- e.g., Active, Resolved, Ruled Out\n    is_chronic boolean DEFAULT false, -- flag for chronic conditions\n    PRIMARY KEY (diagnosis_id)\n)\nCREATE TABLE healthcare.medications (\n    medication_id character varying(64) NOT NULL, -- unique identifier for the medication type\n    medication_name character varying(255) NOT NULL, -- common or brand name\n    generic_name character varying(255), -- generic chemical name\n    manufacturer character varying(100), -- drug manufacturer\n    ndc_code character varying(20) UNIQUE, -- National Drug Code (optional but useful)\n    description text, -- description of the medication\n    PRIMARY KEY (medication_id)\n)\nCREATE TABLE healthcare.prescriptions (\n    prescription_id character varying(64) NOT NULL, -- unique identifier for the prescription\n    record_id character varying(64) NOT NULL, -- FK linking to the medical record where it was prescribed\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    doctor_id character varying(64) NOT NULL, -- FK to prescribing doctor\n    medication_id character varying(64) NOT NULL, -- FK to medications table\n    dosage character varying(100) NOT NULL, -- e.g., '100mg', '1 tablet'\n    frequency character varying(100) NOT NULL, -- e.g., 'Once daily', 'Twice a day with meals'\n    route character varying(50), -- e.g., 'Oral', 'Topical', 'Intravenous'\n    start_date date NOT NULL, -- date prescription begins\n    end_date date, -- date prescription ends (if applicable)\n    quantity_dispensed numeric(10,2), -- amount dispensed (e.g., number of tablets)\n    refills_allowed integer NOT NULL DEFAULT 0, -- number of allowed refills\n    prescription_date timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (prescription_id)\n)\nCREATE TABLE healthcare.insurance_plans (\n    plan_id character varying(64) NOT NULL, -- unique identifier for the insurance plan\n    plan_name character varying(200) NOT NULL, -- name of the insurance plan\n    insurance_provider character varying(100) NOT NULL, -- name of the insurance company\n    plan_type character varying(50), -- e.g., PPO, HMO, EPO\n    contact_phone character varying(20), -- provider contact number\n    website character varying(255), -- provider website\n    PRIMARY KEY (plan_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List all claims (claim ID, incident date, status) for policies where at least one beneficiary has a percentage share greater than 50%. Also include the policy number."}, {"role": "assistant", "content": "SELECT DISTINCT T1.claim_id, T1.incident_date, T1.status, T1.policy_id FROM insurance.claims AS T1 JOIN insurance.policies AS T2 ON T1.policy_id = T2.policy_id JOIN insurance.policy_beneficiaries AS T3 ON T2.policy_id = T3.policy_id WHERE T3.percentage_share > 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 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.agents ( agent_id.text, first_name.text, last_name.text, agency_name.text, license_number.text, license_state.text, contact_email.text, contact_phone.text, hire_date.date, termination_date.date, status.text, commission_rate.numeric, manager_id.text )\nCREATE TABLE insurance.premium_payments ( 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 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 )\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 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": "List all job titles of employees who work in the 'Finance' department."}, {"role": "assistant", "content": "SELECT DISTINCT job_title\nFROM government_services.employees\nWHERE department = 'Finance';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.agencies ( agency_id character varying(64) NOT NULL, agency_name character varying(255) NOT NULL, jurisdiction_level character varying(50) NOT NULL, primary_contact_email character varying(128), main_phone_number character varying(32), website_url character varying(255), established_date date, parent_agency_id character varying(64), PRIMARY KEY (agency_id) )\nCREATE TABLE government_services.services ( 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.employees (\n    employee_id character varying(64) NOT NULL, -- unique identifier for the government employee\n    agency_id character varying(64) NOT NULL, -- FK to agencies table\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    job_title character varying(150) NOT NULL,\n    department character varying(100),\n    work_email character varying(128) NOT NULL UNIQUE,\n    work_phone character varying(32),\n    hire_date date NOT NULL,\n    termination_date date, -- null if currently employed\n    access_level character varying(50), -- Role or permission level\n    manager_employee_id character varying(64), -- FK to self for reporting structure\n    PRIMARY KEY (employee_id)\n)\nCREATE TABLE government_services.service_locations ( location_id text, 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.notifications (\n    notification_id character varying(64) NOT NULL, -- unique identifier for the notification\n    citizen_id character varying(64) NOT NULL, -- FK to citizens table\n    application_id character varying(64), -- FK to applications table (optional)\n    message_subject character varying(255),\n    message_body text NOT NULL,\n    channel character varying(30) NOT NULL, -- e.g., Email, SMS, Portal Message, Mail\n    sent_at timestamp NOT NULL,\n    status character varying(30) NOT NULL, -- e.g., Queued, Sent, Delivered, Failed, Read\n    related_entity_type character varying(50), -- e.g., Application, Appointment, Document Request\n    related_entity_id character varying(64), -- ID of the related entity\n    PRIMARY KEY (notification_id)\n)\n"}
{"conversations": [{"role": "user", "content": "List the product ID and product name of all insurance products created in 2024."}, {"role": "assistant", "content": "SELECT product_id, product_name\nFROM insurance.insurance_products\nWHERE created_at >= '2024-01-01' AND created_at < '2025-01-01';"}, {"role": "user", "content": "Can you also include their product type and base premium in the results?"}, {"role": "assistant", "content": "SELECT product_id, product_name, product_type, base_premium\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\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\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 ( 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": "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 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": "Show me the top 5 NFT collections with the highest number of unique owners, along with their names and contract addresses."}, {"role": "assistant", "content": "SELECT nc.name, nc.contract_address, COUNT(DISTINCT nh.wallet_address) AS unique_owners FROM nft_collections nc JOIN nft_holders nh ON nc.contract_address = nh.contract_address GROUP BY nc.name, nc.contract_address ORDER BY unique_owners DESC LIMIT 5;"}, {"role": "user", "content": "Can you modify the query to also include the floor price and filter to only show collections with more than 1000 unique owners?"}, {"role": "assistant", "content": "SELECT nc.name, nc.contract_address, nc.floor_price, COUNT(DISTINCT nh.wallet_address) AS unique_owners FROM nft_collections nc JOIN nft_holders nh ON nc.contract_address = nh.contract_address GROUP BY nc.name, nc.contract_address, nc.floor_price HAVING COUNT(DISTINCT nh.wallet_address) > 1000 ORDER BY unique_owners DESC LIMIT 5;"}, {"role": "user", "content": "Now 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, COUNT(DISTINCT nh.wallet_address) AS unique_owners, AVG(nm.rarity_score) AS avg_rarity_score FROM nft_collections nc JOIN nft_holders nh ON nc.contract_address = nh.contract_address JOIN nft_metadata nm ON nc.contract_address = nm.contract_address GROUP BY nc.name, nc.contract_address, nc.floor_price HAVING COUNT(DISTINCT nh.wallet_address) > 1000 ORDER BY unique_owners 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 erc20_balances_historical ( block_number bigint, contract_address varchar, wallet_address varchar, amount varchar, pk integer )\nCREATE TABLE nft_holders ( block_number bigint, contract_address varchar, wallet_address varchar, token_id varchar, contract_type varchar, amount varchar, pk varchar )\nCREATE TABLE nft_holder_historical ( block_number bigint, contract_address varchar, wallet_address varchar, token_id varchar, contract_type varchar, amount varchar, pk integer )\nCREATE TABLE sui_coins_metadata ( object_id varchar, coin_type varchar, status varchar, decimals bigint, description varchar, icon_url varchar, symbol varchar, name varchar )\nCREATE TABLE sui_nfts ( object_id varchar, status varchar, collection_type varchar, package_id varchar, previous_transaction varchar, display varchar, owner varchar, name varchar )\nCREATE TABLE nft_metadata ( blockchain varchar, contract_address varchar, token_id varchar, contract_name varchar, erc_type varchar, amount bigint, minter varchar, owner varchar, mint_block_number bigint, mint_time bigint, mint_transaction_hash varchar, mint_price varchar, token_uri varchar, metadata varchar, name varchar, image_uri varchar, traits varchar, updated_at bigint, status varchar, rarity_score real, rarity_rank integer, unique_attribute_count integer, pk integer )\nCREATE TABLE nft_collections ( blockchain varchar, contract_address varchar, name varchar, symbol varchar, deploy_block_number bigint, deploy_block_time bigint, erc_type varchar, owner varchar, traits varchar, description varchar, slug varchar, media_info varchar, image_url varchar, banner_image_url varchar, updated_at bigint, banner varchar, token_count bigint, floor_price varchar, floor_price_symbol varchar, floor_price_contract varchar, pk integer )\nCREATE TABLE token_prices ( uuid varchar, blockchain varchar, address varchar, decimals bigint, symbol varchar, price real, timestamp timestamp )\nCREATE TABLE token_prices_latest ( blockchain varchar, address varchar, decimals bigint, symbol varchar, price real, timestamp timestamp )\nCREATE TABLE erc20_approval ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash varchar, log_index integer, contract_address varchar, pk integer )\nCREATE TABLE token_info ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar )\nCREATE TABLE token_activities ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\nCREATE TABLE mud_holesky_redstone ( address varchar, table_id varchar, key_bytes varchar, key0 varchar, key1 varchar, static_data varchar, encoded_lengths varchar, dynamic_data varchar, is_deleted boolean, block_number bigint, log_index bigint )\nCREATE TABLE token_balances_avalanche ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply decimal, amount decimal )\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id varchar )\n"}
{"conversations": [{"role": "user", "content": "Show me the top 5 NFT collections with the highest floor price on Ethereum, along with their names and contract addresses."}, {"role": "assistant", "content": "SELECT name, contract_address, floor_price FROM nft_collections WHERE blockchain = 'ethereum' ORDER BY CAST(floor_price AS decimal) DESC LIMIT 5;"}, {"role": "user", "content": "Can you also include the banner image URL and filter to only show ERC721 collections?"}, {"role": "assistant", "content": "SELECT name, contract_address, floor_price, banner_image_url FROM nft_collections WHERE blockchain = 'ethereum' AND erc_type = 'ERC721' ORDER BY CAST(floor_price AS decimal) DESC LIMIT 5;"}, {"role": "user", "content": "I think there's a typo in your query - it should be 'nft_collections' not 'nft_collections'. Also, can you join this with the nft_metadata table to include the average rarity score for these collections?"}, {"role": "assistant", "content": "SELECT nc.name, nc.contract_address, nc.floor_price, nc.banner_image_url, AVG(nm.rarity_score) as avg_rarity_score FROM nft_collections nc JOIN nft_metadata nm ON nc.contract_address = nm.contract_address WHERE nc.blockchain = 'ethereum' AND nc.erc_type = 'ERC721' GROUP BY nc.name, nc.contract_address, nc.floor_price, nc.banner_image_url ORDER BY CAST(nc.floor_price AS decimal) DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE erc1155_approval_for_all (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the transaction\n    transaction_index integer NOT NULL, -- Index of the transaction within the block\n    transaction_hash varchar(66) NOT NULL, -- Transaction hash\n    log_index integer NOT NULL, -- Log index\n    contract_address varchar(42) NOT NULL  -- Event contract address\n)\nCREATE TABLE erc20_balances ( block_number.bigint, contract_address.text, wallet_address.text, amount.text, pk.text )\nCREATE TABLE erc20_balances_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_metadata (\n    blockchain varchar NOT NULL, -- blockchain fields for the functionType  in contract\n    contract_address varchar NOT NULL, -- Contract address(with bloom filter)\n    token_id varchar NOT NULL, -- The number of the token\n    contract_name varchar NOT NULL, -- contract_name fields for the functionType  in contract\n    erc_type varchar NOT NULL, -- The type of token\n    amount bigint NOT NULL, -- amount fields for the functionType  in contract\n    minter varchar NOT NULL, -- minter fields for the functionType  in contract\n    owner varchar NOT NULL, -- owner fields for the functionType  in contract\n    mint_block_number bigint NOT NULL, -- mint_block_number fields for the functionType  in contract\n    mint_time bigint NOT NULL, -- mint_time fields for the functionType  in contract\n    mint_transaction_hash varchar NOT NULL, -- mint_transaction_hash fields for the functionType  in contract\n    mint_price varchar NOT NULL, -- mint_price fields for the functionType  in contract\n    token_uri varchar NOT NULL, -- token_uri fields for the functionType  in contract\n    metadata varchar NOT NULL, -- metadata fields for the functionType  in contract\n    name varchar NOT NULL, -- name fields for the functionType  in contract\n    image_uri varchar NOT NULL, -- image_uri fields for the functionType  in contract\n    traits varchar NOT NULL, -- traits fields for the functionType  in contract\n    updated_at bigint NOT NULL, -- updated_at fields for the functionType  in contract\n    status varchar NOT NULL, -- status fields for the functionType  in contract\n    rarity_score real NOT NULL, -- rarity_score fields for the functionType  in contract\n    rarity_rank integer NOT NULL, -- rarity_rank fields for the functionType  in contract\n    unique_attribute_count integer NOT NULL, -- unique_attribute_count fields for the functionType  in contract\n    pk integer NOT NULL  -- Partition key for the table(floor(mint_time / 1000 / 86400 / 30))\n)\nCREATE TABLE nft_collections ( blockchain.text, contract_address.text, name.text, symbol.text, deploy_block_number.bigint, deploy_block_time.bigint, erc_type.text, owner.text, traits.text, description.text, slug.text, media_info.text, image_url.text, banner_image_url.text, updated_at.bigint, banner.text, token_count.bigint, floor_price.text, floor_price_symbol.text, floor_price_contract.text, pk.integer )\nCREATE TABLE token_prices ( uuid varchar(36) NOT NULL, blockchain varchar(36) NOT NULL, address varchar(42) NOT NULL, decimals bigint NOT NULL, symbol varchar(36) NOT NULL, price real NOT NULL, timestamp timestamp(6) NOT NULL )\nCREATE TABLE erc20_approval ( block_number bigint NOT NULL, block_timestamp timestamp(6) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar NOT NULL, log_index integer NOT NULL, contract_address varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_info ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE mud_holesky_redstone (\n    address varchar NOT NULL, -- address fields for the functionType  in contract\n    table_id varchar NOT NULL, -- table_id fields for the functionType  in contract\n    key_bytes varchar NOT NULL, -- key_bytes fields for the functionType  in contract\n    key0 varchar NOT NULL, -- key0 fields for the functionType  in contract\n    key1 varchar NOT NULL, -- key1 fields for the functionType  in contract\n    static_data varchar NOT NULL, -- static_data fields for the functionType  in contract\n    encoded_lengths varchar NOT NULL, -- encoded_lengths fields for the functionType  in contract\n    dynamic_data varchar NOT NULL, -- dynamic_data fields for the functionType  in contract\n    is_deleted boolean NOT NULL, -- is_deleted fields for the functionType  in contract\n    block_number bigint NOT NULL, -- Block number uniquely identifying the block\n    log_index bigint NOT NULL  -- Index of the log within the transaction\n)\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar )\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id text )\n"}
{"conversations": [{"role": "user", "content": "Show the full name of each manager and the average commission rate of the agents who report directly to them. Only include managers who have at least one reporting agent."}, {"role": "assistant", "content": "SELECT T2.first_name AS manager_first_name, T2.last_name AS manager_last_name, AVG(T1.commission_rate) AS average_agent_commission_rate FROM insurance.agents AS T1 JOIN insurance.agents AS T2 ON T1.manager_id = T2.agent_id GROUP BY T2.agent_id, T2.first_name, T2.last_name"}, {"role": "user", "content": "Filter the results to only show managers whose average agent commission rate is above 0.12."}, {"role": "assistant", "content": "SELECT T2.first_name AS manager_first_name, T2.last_name AS manager_last_name, AVG(T1.commission_rate) AS average_agent_commission_rate FROM insurance.agents AS T1 JOIN insurance.agents AS T2 ON T1.manager_id = T2.agent_id GROUP BY T2.agent_id, T2.first_name, T2.last_name HAVING AVG(T1.commission_rate) > 0.12"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.agents ( agent_id.text, first_name.text, last_name.text, agency_name.text, license_number.text, license_state.text, contact_email.text, contact_phone.text, hire_date.date, termination_date.date, status.text, commission_rate.numeric, manager_id.text )\n"}
{"conversations": [{"role": "user", "content": "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, end_date FROM insurance.policies WHERE status = 'expired' AND end_date >= CURRENT_DATE - INTERVAL '60 days' ORDER BY end_date DESC;"}, {"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, end_date FROM insurance.policies WHERE status = 'expired' AND end_date >= CURRENT_DATE - INTERVAL '60 days' AND deductible >= 1000 ORDER BY end_date DESC;"}, {"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 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 average_premium FROM insurance.policies WHERE status = 'expired' AND end_date >= CURRENT_DATE - INTERVAL '60 days' AND deductible >= 1000 GROUP BY product_id ORDER BY average_premium DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.policies ( policy_id text PRIMARY KEY, customer_id text, product_id text, agent_id text, policy_number text, start_date date, end_date date, premium_amount numeric, coverage_limit numeric, deductible numeric, status text, issued_at timestamp, cancellation_date date, cancellation_reason text )\n"}
{"conversations": [{"role": "user", "content": "List all doctors who were created in the year 2022. Show their doctor ID, first name, and last name."}, {"role": "assistant", "content": "SELECT doctor_id, first_name, last_name FROM healthcare.doctors WHERE EXTRACT(YEAR FROM created_at) = 2022"}, {"role": "user", "content": "From that list, only show doctors whose specialty is 'Neurology'."}, {"role": "assistant", "content": "SELECT doctor_id, first_name, last_name FROM healthcare.doctors WHERE EXTRACT(YEAR FROM created_at) = 2022 AND specialty = 'Neurology'"}], "system": "You are an SQL statement expert. Given the table structure 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 PRIMARY KEY, first_name text, last_name text, specialty text, license_number text, phone_number text, email text, hospital_affiliation_id text, created_at timestamp, updated_at timestamp )\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 users who have wallets but have never placed any orders, along with their wallet addresses."}, {"role": "assistant", "content": "SELECT u.user_id, u.username, u.email, w.address FROM trading_platform.users u JOIN trading_platform.wallets w ON u.user_id = w.user_id LEFT JOIN trading_platform.orders o ON u.user_id = o.user_id WHERE o.order_id IS NULL;"}, {"role": "user", "content": "Now modify the query to only include users who created their wallets in the last 6 months."}, {"role": "assistant", "content": "SELECT u.user_id, u.username, u.email, w.address FROM trading_platform.users u JOIN trading_platform.wallets w ON u.user_id = w.user_id LEFT JOIN trading_platform.orders o ON u.user_id = o.user_id WHERE o.order_id IS NULL AND w.created_at >= NOW() - INTERVAL '6 months';"}, {"role": "user", "content": "Actually, I want to see the count of such users grouped by the month they created their wallets."}, {"role": "assistant", "content": "SELECT DATE_TRUNC('month', w.created_at) AS month_created, COUNT(DISTINCT u.user_id) AS user_count FROM trading_platform.users u JOIN trading_platform.wallets w ON u.user_id = w.user_id LEFT JOIN trading_platform.orders o ON u.user_id = o.user_id WHERE o.order_id IS NULL GROUP BY month_created ORDER BY month_created;"}], "system": "You are an SQL statement expert. Given the table structure 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, user_id text, wallet_id text, asset_id text, order_type text, quantity numeric, price numeric, status text, created_at timestamp )\nCREATE TABLE trading_platform.trades ( trade_id text, order_id text, buyer_id text, seller_id text, asset_id text, quantity numeric, price numeric, traded_at timestamp )\nCREATE TABLE trading_platform.dapps ( dapp_id text PRIMARY KEY, name text, description text, url text )\nCREATE TABLE trading_platform.peers ( peer_id text PRIMARY KEY, ip_address text, port int, last_seen timestamp )\nCREATE TABLE trading_platform.notifications ( notification_id.text, user_id.text, message.text, sent_at.timestamp, read_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show me the top 3 tokens with the highest 7-day price change percentage. Display their symbol, chain, and 7d price change."}, {"role": "assistant", "content": "SELECT token_symbol, chain, price_change_percentage_7d\nFROM token_basic_info\nORDER BY price_change_percentage_7d DESC\nLIMIT 3"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE project_fundraising_record ( id.text, project_id.text, project_name.text, rounds_name.text, investment_value.numeric, investment_date.text, introduction.text, valuation.numeric )\nCREATE TABLE token_basic_info ( coin_id.text, token_name.text, token_symbol.text, token_address.text, chain.text, price.numeric, price_change_percentage_1h.numeric, price_change_percentage_24h.numeric, price_change_percentage_7d.numeric, highest_price_24h.numeric, lowest_price_24h.numeric, market_cap.numeric, market_cap_rank.numeric, market_cap_change_percentage_24h.text, total_volume.text, narrative.text, trend_rank.numeric )\nCREATE TABLE 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 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": "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": "List all tokens on the 'BSC' chain with a trend rank between 6 and 20 (inclusive), along with their symbol, price, and liquidity."}, {"role": "assistant", "content": "SELECT t.token_symbol, t.price, d.liquidity\nFROM token_basic_info t\nJOIN token_dexpool_info d ON lower(t.token_symbol) = lower(d.token_symbol) AND t.chain = d.chain\nWHERE t.chain = 'BSC' AND t.trend_rank BETWEEN 6 AND 20;"}, {"role": "user", "content": "Could you also show their 24-hour trading volume and only include tokens with a positive 24-hour price change percentage?"}, {"role": "assistant", "content": "SELECT t.token_symbol, t.price, d.liquidity, d.volume_24h\nFROM token_basic_info t\nJOIN token_dexpool_info d ON lower(t.token_symbol) = lower(d.token_symbol) AND t.chain = d.chain\nWHERE t.chain = 'BSC' AND t.trend_rank BETWEEN 6 AND 20 AND t.price_change_percentage_24h > 0;"}, {"role": "user", "content": "Add the narrative for each token and order the results by liquidity descending, showing only the top 5."}, {"role": "assistant", "content": "SELECT t.token_symbol, t.price, d.liquidity, d.volume_24h, t.narrative\nFROM token_basic_info t\nJOIN token_dexpool_info d ON lower(t.token_symbol) = lower(d.token_symbol) AND t.chain = d.chain\nWHERE t.chain = 'BSC' AND t.trend_rank BETWEEN 6 AND 20 AND t.price_change_percentage_24h > 0\nORDER BY d.liquidity 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, project_id character varying(32) NOT NULL, project_name character varying(128) NOT NULL, rounds_name character varying(32), investment_value numeric(38,14), investment_date character varying(128), introduction character varying(128), valuation numeric(38,14) )\nCREATE TABLE token_basic_info ( coin_id text, token_name text, token_symbol text, token_address text, chain text, price numeric, price_change_percentage_1h numeric, price_change_percentage_24h numeric, price_change_percentage_7d numeric, highest_price_24h numeric, lowest_price_24h numeric, market_cap numeric, market_cap_rank numeric, market_cap_change_percentage_24h text, total_volume text, narrative text, trend_rank numeric )\nCREATE TABLE token_dexpool_info ( pair_address character varying(512) NOT NULL, -- the id of dexpool token_name character varying(100) NOT NULL, -- the name of the token in the dexpool token_symbol character varying(100) NOT NULL, -- the token's symbol chain text, -- the chain that the dexpool resides price double precision, -- the current price of the token price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour price_change_percentage_6h double precision, -- change in value divided by the absolute price value of the original token price in 6 hours price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours makers_24h double precision, -- the makers of the dex pool in 24 hours volume_24h double precision, -- the trade volume of the dex pool in 24 hours liquidity double precision, -- the liquidity of the dex pool market_cap double precision, -- the market cap of the token trend_rank bigint, -- the rank of token in the dex pool of recent trending, value 1 expresses the most popular token. ,PRIMARY KEY (pair_address, chain) )\nCREATE TABLE smart_money_profit ( address character varying(100) NOT NULL, -- the user's address rank INT, -- the rank of the address in trade performance, value 1 expresses the best address. profit numeric(38,6), -- the profit user made in a month roi numeric(38,2), -- the roi of the user in a month realized_ratio numeric(38,2), -- the percentage of the user's realized profit most_profit_token character varying(100), -- the token symbol of the user's most profitable trade last_trade_time character varying(100), -- the last trade time of the user chain character varying(100), -- the chain that the address resides PRIMARY KEY (address, chain) )\nCREATE TABLE smart_money_token_inflow ( token_address text, token_symbol text, token_amount numeric, usd_value numeric, avg_price numeric, type numeric, address_amount numeric, narrative text, chain text )\n"}
{"conversations": [{"role": "user", "content": "For 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": "Show me the top 5 most recent medical records with a fever recorded. Return record_id, patient_id, record_date, and the temperature value from vitals."}, {"role": "assistant", "content": "SELECT record_id,\n       patient_id,\n       record_date,\n       vitals->>'temperature' AS temperature\nFROM healthcare.medical_records\nWHERE (vitals->>'temperature')::numeric > 38\nORDER BY record_date DESC\nLIMIT 5;"}, {"role": "user", "content": "Actually, include only records where assessment is not empty."}, {"role": "assistant", "content": "SELECT record_id,\n       patient_id,\n       record_date,\n       vitals->>'temperature' AS temperature\nFROM healthcare.medical_records\nWHERE (vitals->>'temperature')::numeric > 38\n  AND assessment IS NOT NULL\n  AND assessment <> ''\nORDER BY record_date 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 healthcare.patients ( patient_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, gender character varying(10), address text, phone_number character varying(20), email character varying(128) UNIQUE, emergency_contact_name character varying(200), emergency_contact_phone character varying(20), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (patient_id) )\nCREATE TABLE healthcare.appointments ( appointment_id text, patient_id text, doctor_id text, appointment_time timestamp, duration_minutes integer, reason text, status text, location_id text, notes text, created_at timestamp )\nCREATE TABLE healthcare.medical_records ( record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, appointment_id character varying(64) UNIQUE, doctor_id character varying(64) NOT NULL, record_date timestamp with time zone NOT NULL, chief_complaint text, present_illness_history text, past_medical_history text, physical_examination_notes text, assessment text, treatment_plan text, vitals jsonb, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (record_id) )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id text PRIMARY KEY, record_id text, patient_id text, doctor_id text, diagnosis_code text, code_type text, description text, diagnosis_date date, status text, is_chronic boolean )\nCREATE TABLE healthcare.medications ( medication_id text, medication_name text, generic_name text, manufacturer text, ndc_code text, description text )\nCREATE TABLE healthcare.prescriptions ( prescription_id.text, record_id.text, patient_id.text, doctor_id.text, medication_id.text, dosage.text, frequency.text, route.text, start_date.date, end_date.date, quantity_dispensed.numeric, refills_allowed.integer, prescription_date.timestamp )\nCREATE TABLE healthcare.insurance_plans ( plan_id.text, plan_name.text, insurance_provider.text, plan_type.text, contact_phone.text, website.text )\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, plan_id character varying(64) NOT NULL, policy_number character varying(100) NOT NULL, group_number character varying(100), subscriber_name character varying(200), effective_date date NOT NULL, expiration_date date, is_primary boolean NOT NULL DEFAULT true, PRIMARY KEY (patient_insurance_id), UNIQUE (patient_id, plan_id, policy_number) )\n"}
{"conversations": [{"role": "user", "content": "List all users and the count of wallets they own."}, {"role": "assistant", "content": "SELECT u.username, COUNT(w.wallet_id) AS wallet_count FROM blockchain.users u JOIN blockchain.wallets w ON u.user_id = w.user_id GROUP BY u.user_id, u.username;"}, {"role": "user", "content": "Filter the previous list to only include users who own more than 2 wallets."}, {"role": "assistant", "content": "SELECT u.username, COUNT(w.wallet_id) AS wallet_count FROM blockchain.users u JOIN blockchain.wallets w ON u.user_id = w.user_id GROUP BY u.user_id, u.username HAVING COUNT(w.wallet_id) > 2;"}, {"role": "user", "content": "Now, for those users, also include the total sum of balances across all addresses associated with their wallets."}, {"role": "assistant", "content": "SELECT u.username, COUNT(DISTINCT w.wallet_id) AS wallet_count, SUM(a.balance) AS total_balance FROM blockchain.users u JOIN blockchain.wallets w ON u.user_id = w.user_id JOIN blockchain.addresses a ON w.address_id = a.address_id GROUP BY u.user_id, u.username HAVING COUNT(DISTINCT w.wallet_id) > 2;"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nCREATE TABLE blockchain.addresses ( address_id character varying(128) NOT NULL, public_key text NOT NULL, balance numeric(38,14) NOT NULL, PRIMARY KEY (address_id) )\nCREATE TABLE blockchain.nodes ( node_id character varying(64) NOT NULL, ip_address character varying(15) NOT NULL, port integer NOT NULL, last_seen timestamp NOT NULL, PRIMARY KEY (node_id) )\nCREATE TABLE blockchain.wallets ( wallet_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, address_id character varying(128) NOT NULL, private_key text NOT NULL, PRIMARY KEY (wallet_id) )\nCREATE TABLE blockchain.users ( user_id character varying(64) NOT NULL, username character varying(128) NOT NULL, email character varying(128) NOT NULL, password_hash text NOT NULL, PRIMARY KEY (user_id) )\n"}
{"conversations": [{"role": "user", "content": "Show me the top 5 smart money addresses by profit on the Ethereum chain, along with their most profitable token and ROI."}, {"role": "assistant", "content": "SELECT address, most_profit_token, roi FROM smart_money_profit WHERE chain = 'Ethereum' ORDER BY profit DESC LIMIT 5;"}, {"role": "user", "content": "Now filter these results to only include addresses with an ROI greater than 50%."}, {"role": "assistant", "content": "SELECT address, most_profit_token, roi FROM smart_money_profit WHERE chain = 'Ethereum' AND roi > 50 ORDER BY profit 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 smart_money_profit ( address character varying(100) NOT NULL, -- the user's address rank INT, -- the rank of the address in trade performance, value 1 expresses the best address. profit numeric(38,6), -- the profit user made in a month roi numeric(38,2), -- the roi of the user in a month realized_ratio numeric(38,2), -- the percentage of the user's realized profit most_profit_token character varying(100), -- the token symbol of the user's most profitable trade last_trade_time character varying(100), -- the last trade time of the user chain character varying(100), -- the chain that the address resides PRIMARY KEY (address, chain) )\n"}
{"conversations": [{"role": "user", "content": "For each 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": "Show me all rooms with their room number, the type name, and the maximum occupancy for each room."}, {"role": "assistant", "content": "SELECT r.room_id, r.room_number, rt.type_name, rt.max_occupancy\nFROM hospitality_technology.rooms r\nJOIN hospitality_technology.room_types rt ON r.room_type_id = rt.room_type_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.rooms (\n    room_id character varying(64) NOT NULL,  -- unique identifier for the room\n    property_id character varying(64) NOT NULL, -- FK to properties table\n    room_number character varying(10) NOT NULL, -- room number identifier (e.g., '101', 'Suite 2B')\n    room_type_id character varying(64) NOT NULL, -- FK to room_types table\n    floor integer, -- floor number the room is on\n    status character varying(50) NOT NULL, -- e.g., Available, Occupied, Cleaning, OutOfOrder, Maintenance\n    is_smoking boolean NOT NULL DEFAULT false, -- smoking allowed flag\n    features text, -- description of features (e.g., Balcony, Sea View, Jacuzzi)\n    current_condition text, -- notes on room condition\n    last_cleaned_at timestamp with time zone, -- timestamp of last cleaning\n    PRIMARY KEY (room_id),\n    FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n    FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id)\n)\nCREATE TABLE hospitality_technology.room_types ( room_type_id text, property_id text, type_name text, description text, base_rate numeric, max_occupancy integer, bed_type text, area_sqft numeric, amenities text )\nCREATE TABLE hospitality_technology.guests ( guest_id text PRIMARY KEY, first_name text, last_name text, email text, phone_number text, date_of_birth date, address_line1 text, city text, state_province text, postal_code text, country_code text, preferences text, loyalty_member_id text, communication_consent boolean, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.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)\n"}
{"conversations": [{"role": "user", "content": "For each transaction, list the total value transferred and the number of different addresses involved (either as sender or receiver)."}, {"role": "assistant", "content": "SELECT transaction_id, SUM(value) AS total_value_transferred, COUNT(DISTINCT addr) AS num_addresses_involved\nFROM (\n    SELECT transaction_id, from_address AS addr, value FROM web3.token_transfers\n    UNION ALL\n    SELECT transaction_id, to_address AS addr, 0 as value FROM web3.token_transfers\n) t\nGROUP BY transaction_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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": "List all beneficiaries added in the last 6 months with a percentage share greater than 25%. Include their beneficiary ID, policy ID, customer ID, first name, last name, relationship, and percentage share. Order the results by the date they were added, oldest first."}, {"role": "assistant", "content": "SELECT beneficiary_id, policy_id, customer_id, first_name, last_name, relationship, percentage_share FROM insurance.policy_beneficiaries WHERE added_at >= CURRENT_DATE - INTERVAL '6 months' AND percentage_share > 25 ORDER BY added_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 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": "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": "Find the location name, address, and city for all accessible service locations located in the state of 'California'. Order the results by city."}, {"role": "assistant", "content": "SELECT location_name, address, city FROM government_services.service_locations WHERE is_accessible = TRUE AND state = 'California' ORDER BY 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 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": "Can you list the invoice numbers, issue dates, and due dates for all invoices, sorted by issue date ascending?"}, {"role": "assistant", "content": "SELECT invoice_number, issue_date, due_date FROM legal_services.invoices ORDER BY issue_date ASC;"}, {"role": "user", "content": "I only want to see invoices with a due date in May 2024. Please modify the query."}, {"role": "assistant", "content": "SELECT invoice_number, issue_date, due_date FROM legal_services.invoices WHERE due_date >= '2024-05-01' AND due_date < '2024-06-01' ORDER BY issue_date ASC;"}, {"role": "user", "content": "Also, only include invoices that have not been paid in full yet (amount_paid < total_amount)."}, {"role": "assistant", "content": "SELECT invoice_number, issue_date, due_date FROM legal_services.invoices WHERE due_date >= '2024-05-01' AND due_date < '2024-06-01' AND amount_paid < total_amount ORDER BY issue_date ASC;"}, {"role": "user", "content": "Add the status column and sort the results by due_date descending."}, {"role": "assistant", "content": "SELECT invoice_number, issue_date, due_date, status FROM legal_services.invoices WHERE due_date >= '2024-05-01' AND due_date < '2024-06-01' AND amount_paid < total_amount ORDER BY due_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": "Show me all properties in California with a star rating above 4.0, along with the names of their managers and the count of active staff members at each property."}, {"role": "assistant", "content": "SELECT p.property_name, p.star_rating, s.first_name || ' ' || s.last_name AS manager_name, COUNT(st.staff_id) AS active_staff_count FROM hospitality_technology.properties p JOIN hospitality_technology.staff s ON p.manager_staff_id = s.staff_id JOIN hospitality_technology.staff st ON p.property_id = st.property_id WHERE p.state_province = 'California' AND p.star_rating > 4.0 AND st.is_active = true GROUP BY p.property_name, p.star_rating, manager_name ORDER BY active_staff_count DESC;"}, {"role": "user", "content": "Now, include only properties with more than 5 active staff members and show the average star rating of reviews for each property."}, {"role": "assistant", "content": "SELECT p.property_name, p.star_rating, s.first_name || ' ' || s.last_name AS manager_name, COUNT(st.staff_id) AS active_staff_count, AVG(r.rating_overall) AS avg_review_rating FROM hospitality_technology.properties p JOIN hospitality_technology.staff s ON p.manager_staff_id = s.staff_id JOIN hospitality_technology.staff st ON p.property_id = st.property_id LEFT JOIN hospitality_technology.reviews r ON p.property_id = r.property_id WHERE p.state_province = 'California' AND p.star_rating > 4.0 AND st.is_active = true GROUP BY p.property_name, p.star_rating, manager_name HAVING COUNT(st.staff_id) > 5 ORDER BY active_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.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.guests ( guest_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, email character varying(255) UNIQUE, phone_number character varying(30), date_of_birth date, address_line1 character varying(255), city character varying(100), state_province character varying(100), postal_code character varying(20), country_code character varying(3), preferences text, loyalty_member_id character varying(64) UNIQUE, communication_consent boolean DEFAULT true, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (guest_id) )\nCREATE TABLE hospitality_technology.staff ( staff_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, position character varying(100) NOT NULL, work_email character varying(255) UNIQUE, work_phone character varying(30), hire_date date NOT NULL, termination_date date, is_active boolean NOT NULL DEFAULT true, access_level integer NOT NULL, manager_id character varying(64), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (staff_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (manager_id) REFERENCES hospitality_technology.staff(staff_id) )\nCREATE TABLE hospitality_technology.services ( service_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, service_name character varying(150) NOT NULL, description text, category character varying(100), price numeric(10, 2) NOT NULL, unit character varying(30), is_available boolean NOT NULL DEFAULT true, department character varying(100), PRIMARY KEY (service_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id) )\nCREATE TABLE hospitality_technology.service_orders ( order_id character varying(64) NOT NULL, reservation_id character varying(64), guest_id character varying(64) NOT NULL, service_id character varying(64) NOT NULL, staff_id_ordered character varying(64), staff_id_delivered character varying(64), order_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, delivery_timestamp timestamp with time zone, quantity integer NOT NULL DEFAULT 1, unit_price numeric(10, 2) NOT NULL, total_price numeric(12, 2) NOT NULL, status character varying(50) NOT NULL, notes text, bill_id character varying(64), PRIMARY KEY (order_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (service_id) REFERENCES hospitality_technology.services(service_id), FOREIGN KEY (staff_id_ordered) REFERENCES hospitality_technology.staff(staff_id), FOREIGN KEY (staff_id_delivered) REFERENCES hospitality_technology.staff(staff_id) )\nCREATE TABLE hospitality_technology.payments ( payment_id character varying(64) NOT NULL, reservation_id character varying(64), guest_id character varying(64) NOT NULL, bill_id character varying(64), amount numeric(12,2) NOT NULL, currency_code character varying(3) NOT NULL, payment_method character varying(50) NOT NULL, card_type character varying(50), card_last_four character varying(4), transaction_ref character varying(128), payment_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, status character varying(50) NOT NULL, staff_id_processed character varying(64), notes text, PRIMARY KEY (payment_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (staff_id_processed) REFERENCES hospitality_technology.staff(staff_id) )\nCREATE TABLE hospitality_technology.reviews ( review_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, reservation_id character varying(64) UNIQUE, guest_id character varying(64) NOT NULL, rating_overall integer, rating_cleanliness integer, rating_service integer, rating_location integer, rating_value integer, comment text, review_source character varying(100), review_date timestamp with time zone NOT NULL DEFAULT current_timestamp, is_public boolean DEFAULT true, staff_response text, response_staff_id character varying(64), response_date timestamp with time zone, PRIMARY KEY (review_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (response_staff_id) REFERENCES hospitality_technology.staff(staff_id) )\n"}
{"conversations": [{"role": "user", "content": "Find cases where an address received tokens in one transfer and then sent tokens in another. List the receive transfer_id, the send transfer_id, the address, and both transfer values."}, {"role": "assistant", "content": "SELECT recv.transfer_id AS receive_transfer_id,\n       send.transfer_id AS send_transfer_id,\n       recv.to_address AS address,\n       recv.value       AS received_value,\n       send.value       AS sent_value\nFROM web3.token_transfers recv\nJOIN web3.token_transfers send\n  ON recv.to_address = send.from_address;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.token_transfers (\n    transfer_id character varying(64) NOT NULL,  -- unique identifier for the transfer\n    token_id character varying(64) NOT NULL, -- identifier of the token being transferred\n    from_address character varying(128) NOT NULL, -- address of the sender\n    to_address character varying(128) NOT NULL, -- address of the receiver\n    value numeric(38,14) NOT NULL, -- amount of tokens transferred\n    transaction_id character varying(64) NOT NULL, -- identifier of the transaction containing the transfer\n    log_index integer NOT NULL, -- index of the transfer log in the transaction\n    PRIMARY KEY (transfer_id)\n)\n"}
{"conversations": [{"role": "user", "content": "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": "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": "What is the number of guests per country, grouped by country_code?"}, {"role": "assistant", "content": "SELECT country_code,\n       COUNT(*) AS guest_count\nFROM hospitality_technology.guests\nGROUP BY country_code;"}, {"role": "user", "content": "Only include countries that have at least 5 guests."}, {"role": "assistant", "content": "SELECT country_code,\n       COUNT(*) AS guest_count\nFROM hospitality_technology.guests\nGROUP BY country_code\nHAVING COUNT(*) >= 5;"}, {"role": "user", "content": "Also include the most recently registered guest in each of those countries, showing their full name and created_at."}, {"role": "assistant", "content": "WITH country_counts AS (\n  SELECT country_code,\n         COUNT(*) AS guest_count,\n         MAX(created_at) AS last_reg\n  FROM hospitality_technology.guests\n  GROUP BY country_code\n  HAVING COUNT(*) >= 5\n)\nSELECT cc.country_code,\n       cc.guest_count,\n       g.first_name || ' ' || g.last_name AS last_guest_name,\n       g.created_at          AS last_registration\nFROM country_counts cc\nJOIN hospitality_technology.guests g\n  ON g.country_code = cc.country_code\n AND g.created_at = cc.last_reg;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.guests ( guest_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, email character varying(255) UNIQUE, phone_number character varying(30), date_of_birth date, address_line1 character varying(255), city character varying(100), state_province character varying(100), postal_code character varying(20), country_code character varying(3), preferences text, loyalty_member_id character varying(64) UNIQUE, communication_consent boolean DEFAULT true, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (guest_id) )\n"}
{"conversations": [{"role": "user", "content": "Show me all users who have a wallet but do not have an entry in the KYC audit table. List their user ID and wallet address."}, {"role": "assistant", "content": "SELECT w.user_id, w.address FROM trading_platform.wallets w LEFT JOIN trading_platform.kyc_audit k ON w.user_id = k.user_id WHERE k.user_id IS NULL;"}, {"role": "user", "content": "For these users without a KYC entry, what is the average age of their wallets in days?"}, {"role": "assistant", "content": "SELECT AVG(DATE_PART('day', NOW() - w.created_at)) AS average_wallet_age_days FROM trading_platform.wallets w LEFT JOIN trading_platform.kyc_audit k ON w.user_id = k.user_id WHERE k.user_id IS NULL;"}, {"role": "user", "content": "Filter this list to only include users whose wallet is older than 365 days (1 year) and still has no KYC entry. Show their user ID and wallet creation date."}, {"role": "assistant", "content": "SELECT w.user_id, w.created_at FROM trading_platform.wallets w LEFT JOIN trading_platform.kyc_audit k ON w.user_id = k.user_id WHERE k.user_id IS NULL AND w.created_at < NOW() - INTERVAL '365 days';"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nCREATE TABLE trading_platform.wallets ( wallet_id text, user_id text, address text, private_key text, created_at timestamp )\nCREATE TABLE trading_platform.peers ( peer_id text, ip_address text, port integer, last_seen timestamp )\nCREATE TABLE trading_platform.kyc_audit ( kyc_audit_id text, user_id text, status text, reviewed_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "What is the count of securities for each security_type in the 'Financial' sector?"}, {"role": "assistant", "content": "SELECT security_type, COUNT(*) as security_count FROM financial_services.securities WHERE sector = 'Financial' GROUP BY security_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.securities ( security_id text PRIMARY KEY, ticker_symbol text, isin_code text, cusip_code text, security_name text, security_type text, exchange text, currency text, issuer_name text, sector text, last_updated timestamp )\n"}
{"conversations": [{"role": "user", "content": "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 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": "List all users whose password hash contains the substring 'abc'."}, {"role": "assistant", "content": "SELECT user_id, username, password_hash FROM blockchain.users WHERE password_hash LIKE '%abc%';"}, {"role": "user", "content": "Also include their email address."}, {"role": "assistant", "content": "SELECT user_id, username, password_hash, email FROM blockchain.users WHERE password_hash LIKE '%abc%';"}, {"role": "user", "content": "Filter to only show users whose username does *not* contain 'test'."}, {"role": "assistant", "content": "SELECT user_id, username, password_hash, email FROM blockchain.users WHERE password_hash LIKE '%abc%' AND username NOT LIKE '%test%';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE blockchain.wallets ( wallet_id.text, user_id.text, address_id.text, private_key.text )\nCREATE TABLE blockchain.users ( user_id.text, username.text, email.text, password_hash.text )\n"}
{"conversations": [{"role": "user", "content": "Show me all doctors specializing in Pediatrics along with their upcoming appointments, including the patient ID and appointment time."}, {"role": "assistant", "content": "SELECT d.doctor_id, d.first_name, d.last_name, a.patient_id, a.appointment_time FROM healthcare.doctors d JOIN healthcare.appointments a ON d.doctor_id = a.doctor_id WHERE d.specialty = 'Pediatrics' AND a.appointment_time > CURRENT_TIMESTAMP ORDER BY a.appointment_time;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.doctors ( doctor_id text PRIMARY KEY, first_name text, last_name text, specialty text, license_number text, phone_number text, email text, hospital_affiliation_id text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.appointments ( appointment_id text, patient_id text, doctor_id text, appointment_time timestamp, duration_minutes integer, reason text, status text, location_id text, notes text, created_at timestamp )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id text, record_id text, patient_id text, doctor_id text, diagnosis_code text, code_type text, description text, diagnosis_date date, status text, is_chronic boolean )\nCREATE TABLE healthcare.medications ( 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": "Retrieve the policy_number, start_date, end_date, premium_amount, and corresponding product_name for policies with a coverage_limit greater than 500000."}, {"role": "assistant", "content": "SELECT p.policy_number, p.start_date, p.end_date, p.premium_amount, ip.product_name\nFROM insurance.policies p\nJOIN insurance.insurance_products ip ON p.product_id = ip.product_id\nWHERE p.coverage_limit > 500000;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.policies ( policy_id text, customer_id text, product_id text, agent_id text, policy_number text, start_date date, end_date date, premium_amount numeric, coverage_limit numeric, deductible numeric, status text, issued_at timestamp, cancellation_date date, cancellation_reason text )\nCREATE TABLE insurance.insurance_products ( product_id text, product_name text, product_type text, description text, base_premium numeric, coverage_details text, underwriting_rules text, is_active boolean, created_at timestamp, updated_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "List all ERC20 tokens with their names and symbols where the price is greater than $10, sorted by price in descending order."}, {"role": "assistant", "content": "SELECT t.symbol, t.name, p.price FROM sui_coins_metadata t JOIN token_prices_latest p ON t.coin_type = p.address WHERE p.price > 10 ORDER BY p.price DESC;"}, {"role": "user", "content": "I think there's an error in your query - it should be t.symbol not t.symbol. Also, can you add the contract address to the results?"}, {"role": "assistant", "content": "SELECT t.symbol, t.name, p.price, p.address as contract_address FROM sui_coins_metadata t JOIN token_prices_latest p ON t.coin_type = p.address WHERE p.price > 10 ORDER BY p.price DESC;"}, {"role": "user", "content": "Now filter these results to only show tokens with decimals equal to 18."}, {"role": "assistant", "content": "SELECT t.symbol, t.name, p.price, p.address as contract_address FROM sui_coins_metadata t JOIN token_prices_latest p ON t.coin_type = p.address WHERE p.price > 10 AND t.decimals = 18 ORDER BY p.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 erc1155_approval_for_all (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the transaction\n    transaction_index integer NOT NULL, -- Index of the transaction within the block\n    transaction_hash varchar(66) NOT NULL, -- Transaction hash\n    log_index integer NOT NULL, -- Log index\n    contract_address varchar(42) NOT NULL  -- Event contract address\n)\nCREATE TABLE erc20_balances ( block_number.bigint, contract_address.text, wallet_address.text, amount.text, pk.text )\nCREATE TABLE erc20_balances_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_holders ( block_number bigint, contract_address varchar, wallet_address varchar, token_id varchar, contract_type varchar, amount varchar, pk varchar )\nCREATE TABLE sui_coins_metadata ( object_id varchar, coin_type varchar, status varchar, decimals bigint, description varchar, icon_url varchar, symbol varchar, name varchar )\nCREATE TABLE nft_metadata (\n    blockchain varchar NOT NULL, -- blockchain fields for the functionType  in contract\n    contract_address varchar NOT NULL, -- Contract address(with bloom filter)\n    token_id varchar NOT NULL, -- The number of the token\n    contract_name varchar NOT NULL, -- contract_name fields for the functionType  in contract\n    erc_type varchar NOT NULL, -- The type of token\n    amount bigint NOT NULL, -- amount fields for the functionType  in contract\n    minter varchar NOT NULL, -- minter fields for the functionType  in contract\n    owner varchar NOT NULL, -- owner fields for the functionType  in contract\n    mint_block_number bigint NOT NULL, -- mint_block_number fields for the functionType  in contract\n    mint_time bigint NOT NULL, -- mint_time fields for the functionType  in contract\n    mint_transaction_hash varchar NOT NULL, -- mint_transaction_hash fields for the functionType  in contract\n    mint_price varchar NOT NULL, -- mint_price fields for the functionType  in contract\n    token_uri varchar NOT NULL, -- token_uri fields for the functionType  in contract\n    metadata varchar NOT NULL, -- metadata fields for the functionType  in contract\n    name varchar NOT NULL, -- name fields for the functionType  in contract\n    image_uri varchar NOT NULL, -- image_uri fields for the functionType  in contract\n    traits varchar NOT NULL, -- traits fields for the functionType  in contract\n    updated_at bigint NOT NULL, -- updated_at fields for the functionType  in contract\n    status varchar NOT NULL, -- status fields for the functionType  in contract\n    rarity_score real NOT NULL, -- rarity_score fields for the functionType  in contract\n    rarity_rank integer NOT NULL, -- rarity_rank fields for the functionType  in contract\n    unique_attribute_count integer NOT NULL, -- unique_attribute_count fields for the functionType  in contract\n    pk integer NOT NULL  -- Partition key for the table(floor(mint_time / 1000 / 86400 / 30))\n)\nCREATE TABLE token_prices_latest ( blockchain varchar, address varchar, decimals bigint, symbol varchar, price real, timestamp timestamp )\nCREATE TABLE token_info ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE mud_holesky_redstone (\n    address varchar NOT NULL, -- address fields for the functionType  in contract\n    table_id varchar NOT NULL, -- table_id fields for the functionType  in contract\n    key_bytes varchar NOT NULL, -- key_bytes fields for the functionType  in contract\n    key0 varchar NOT NULL, -- key0 fields for the functionType  in contract\n    key1 varchar NOT NULL, -- key1 fields for the functionType  in contract\n    static_data varchar NOT NULL, -- static_data fields for the functionType  in contract\n    encoded_lengths varchar NOT NULL, -- encoded_lengths fields for the functionType  in contract\n    dynamic_data varchar NOT NULL, -- dynamic_data fields for the functionType  in contract\n    is_deleted boolean NOT NULL, -- is_deleted fields for the functionType  in contract\n    block_number bigint NOT NULL, -- Block number uniquely identifying the block\n    log_index bigint NOT NULL  -- Index of the log within the transaction\n)\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\nCREATE TABLE token_balances_avalanche (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n    tick varchar(20) NOT NULL, -- Ticker: Identifier of the inscription\n    wallet_address varchar(42) NOT NULL, -- Address of owner\n    total_supply decimal(38,0) NOT NULL, -- Max supply: Set max supply of the inscription\n    amount decimal(38,0) NOT NULL  -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id text )\n"}
{"conversations": [{"role": "user", "content": "Show a list of clients whose status is 'inactive', including their first and last name, email, phone, and date registered."}, {"role": "assistant", "content": "SELECT first_name, last_name, email, phone, date_registered\nFROM legal_services.clients\nWHERE status = 'inactive';"}], "system": "You are an SQL statement expert. Given the table structure 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.lawyers (\n    lawyer_id character varying(64) NOT NULL,  -- unique identifier for the lawyer\n    first_name character varying(100) NOT NULL, -- lawyer's first name\n    last_name character varying(100) NOT NULL, -- lawyer's last name\n    bar_number character varying(64) UNIQUE NOT NULL, -- lawyer's bar association number\n    firm_id character varying(64), -- FK to law_firms table\n    email character varying(128) UNIQUE NOT NULL, -- lawyer's professional email\n    phone character varying(32), -- lawyer's contact phone number\n    specialization text, -- areas of legal expertise\n    hire_date timestamp NOT NULL, -- date the lawyer was hired or joined\n    is_partner boolean DEFAULT false, -- flag indicating if the lawyer is a partner\n    PRIMARY KEY (lawyer_id)\n)\nCREATE TABLE legal_services.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 (\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.time_entries (\n    entry_id character varying(64) NOT NULL,  -- unique identifier for the time entry\n    case_id character varying(64) NOT NULL, -- FK to cases table\n    lawyer_id character varying(64) NOT NULL, -- FK to lawyers table (who performed the work)\n    date_worked date NOT NULL, -- date the work was performed\n    hours_spent numeric(5, 2) NOT NULL CHECK (hours_spent > 0), -- duration of work in hours (e.g., 1.5 for 1h 30m)\n    billing_rate numeric(10, 2) NOT NULL, -- hourly rate applied for this entry\n    description text NOT NULL, -- detailed description of the work performed\n    is_billable boolean DEFAULT true, -- whether this time entry is billable to the client\n    is_billed boolean DEFAULT false, -- whether this entry has been included in an invoice\n    invoice_id character varying(64), -- FK to invoices table (once billed)\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the entry was recorded\n    PRIMARY KEY (entry_id)\n)\nCREATE TABLE legal_services.appointments (\n    appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment\n    client_id character varying(64) NOT NULL, -- FK to clients table\n    lawyer_id character varying(64) NOT NULL, -- FK to lawyers table\n    case_id character varying(64), -- FK to cases table (optional, if related to a specific case)\n    start_time timestamp NOT NULL, -- scheduled start date and time\n    end_time timestamp NOT NULL, -- scheduled end date and time\n    location text, -- location of the meeting (address or virtual link)\n    subject character varying(255), -- subject or purpose of the appointment\n    notes text, -- additional notes for the appointment\n    status character varying(50) NOT NULL, -- e.g., Scheduled, Completed, Canceled, Rescheduled\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n    PRIMARY KEY (appointment_id)\n)\n"}
{"conversations": [{"role": "user", "content": "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": "List all unspent UTXOs with an amount greater than 10."}, {"role": "assistant", "content": "SELECT utxo_id, transaction_id, address, amount FROM utxos WHERE spent = FALSE AND amount > 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.wallets ( wallet_id.text, user_id.text, address.text, private_key.text, created_at.timestamp )\nCREATE TABLE trading_platform.trades ( trade_id.text, order_id.text, buyer_id.text, seller_id.text, asset_id.text, quantity.numeric, price.numeric, traded_at.timestamp )\nCREATE TABLE trading_platform.utxos ( utxo_id.text, transaction_id.text, output_index.integer, address.text, amount.numeric, spent.boolean )\nCREATE TABLE trading_platform.dapps ( dapp_id.text, name.text, description.text, url.text )\nCREATE TABLE trading_platform.peers ( peer_id.text, ip_address.text, port.integer, last_seen.timestamp )\nCREATE TABLE trading_platform.logs ( log_id.text, user_id.text, action.text, details.text, logged_at.timestamp )\n"}
{"conversations": [{"role": "user", "content": "Find the total number of documents uploaded by each citizen along with their first and last names."}, {"role": "assistant", "content": "SELECT c.citizen_id, c.first_name, c.last_name, COUNT(d.document_id) AS document_count\nFROM government_services.citizens c\nLEFT JOIN government_services.documents d ON c.citizen_id = d.citizen_id\nGROUP BY c.citizen_id, c.first_name, c.last_name;"}, {"role": "user", "content": "Actually, I only want to include those citizens who have uploaded documents in the last 30 days."}, {"role": "assistant", "content": "SELECT c.citizen_id, c.first_name, c.last_name, COUNT(d.document_id) AS document_count\nFROM government_services.citizens c\nJOIN government_services.documents d ON c.citizen_id = d.citizen_id\nWHERE d.upload_timestamp >= NOW() - INTERVAL '30 days'\nGROUP BY c.citizen_id, c.first_name, c.last_name;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens (\n    citizen_id character varying(64) NOT NULL,  -- unique identifier for the citizen\n    national_id_number character varying(128) NOT NULL UNIQUE, -- official national identification number\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    date_of_birth date NOT NULL,\n    gender character varying(20),\n    primary_address text NOT NULL, -- full primary residential address\n    contact_email character varying(128) UNIQUE,\n    contact_phone character varying(32),\n    registration_date timestamp NOT NULL, -- when the citizen profile was created\n    is_verified boolean DEFAULT false, -- whether identity has been officially verified\n    PRIMARY KEY (citizen_id)\n)\nCREATE TABLE government_services.services (\n    service_id character varying(64) NOT NULL, -- unique identifier for the service\n    agency_id character varying(64) NOT NULL, -- FK to agencies table\n    service_name character varying(255) NOT NULL, -- name of the service (e.g., Driver's License Renewal)\n    description text,\n    category character varying(100), -- e.g., Licensing, Benefits, Taxation, Permits\n    eligibility_criteria text, -- description of who is eligible\n    standard_fee numeric(10, 2) DEFAULT 0.00, -- typical fee for the service\n    average_processing_time_days integer, -- estimated processing time\n    is_active boolean DEFAULT true, -- whether the service is currently offered\n    online_application_url character varying(255),\n    PRIMARY KEY (service_id)\n)\nCREATE TABLE government_services.documents ( document_id text PRIMARY KEY, application_id text, citizen_id text, document_type text, file_reference text, upload_timestamp timestamp, expiry_date date, verification_status text, verified_by_employee_id text, verification_timestamp timestamp )\nCREATE TABLE government_services.payments ( payment_id text, application_id text, citizen_id text, service_id text, amount numeric, currency text, payment_method text, payment_provider_reference text, payment_timestamp timestamp, status text, notes text )\nCREATE TABLE government_services.employees (\n    employee_id character varying(64) NOT NULL, -- unique identifier for the government employee\n    agency_id character varying(64) NOT NULL, -- FK to agencies table\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    job_title character varying(150) NOT NULL,\n    department character varying(100),\n    work_email character varying(128) NOT NULL UNIQUE,\n    work_phone character varying(32),\n    hire_date date NOT NULL,\n    termination_date date, -- null if currently employed\n    access_level character varying(50), -- Role or permission level\n    manager_employee_id character varying(64), -- FK to self for reporting structure\n    PRIMARY KEY (employee_id)\n)\nCREATE TABLE government_services.appointments ( appointment_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, employee_id character varying(64), location_id character varying(64), service_id character varying(64), scheduled_start_time timestamp NOT NULL, scheduled_end_time timestamp, purpose text NOT NULL, status character varying(30) NOT NULL, booking_method character varying(50), created_at timestamp NOT NULL, notes text, PRIMARY KEY (appointment_id) )\n"}
{"conversations": [{"role": "user", "content": "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": "What is the average commission for trades executed on the 'NYSE' venue?"}, {"role": "assistant", "content": "SELECT AVG(commission) FROM financial_services.trades WHERE execution_venue = 'NYSE';"}], "system": "You are an SQL statement expert. Given the table structure 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.text, account_id.text, security_id.text, order_id.text, trade_type.text, quantity.numeric, price_per_unit.numeric, total_amount.numeric, commission.numeric, trade_timestamp.timestamp, settlement_date.date, status.text, execution_venue.text )\n"}
{"conversations": [{"role": "user", "content": "List payment records in USD including guest names and processing staff names."}, {"role": "assistant", "content": "SELECT p.payment_id,\n       p.amount,\n       p.currency_code,\n       g.guest_name,\n       s.staff_name\nFROM hospitality_technology.payments p\nJOIN hospitality_technology.guests g ON p.guest_id = g.guest_id\nJOIN hospitality_technology.staff s ON p.staff_id_processed = s.staff_id\nWHERE p.currency_code = 'USD';"}, {"role": "user", "content": "Only include payments with status 'Succeeded' made within the last 30 days."}, {"role": "assistant", "content": "SELECT p.payment_id,\n       p.amount,\n       p.currency_code,\n       g.guest_name,\n       s.staff_name\nFROM hospitality_technology.payments p\nJOIN hospitality_technology.guests g ON p.guest_id = g.guest_id\nJOIN hospitality_technology.staff s ON p.staff_id_processed = s.staff_id\nWHERE p.currency_code = 'USD'\n  AND p.status = 'Succeeded'\n  AND p.payment_timestamp >= NOW() - INTERVAL '30 days';"}, {"role": "user", "content": "Sort by payment timestamp descending and limit to 50 records."}, {"role": "assistant", "content": "SELECT p.payment_id,\n       p.amount,\n       p.currency_code,\n       g.guest_name,\n       s.staff_name\nFROM hospitality_technology.payments p\nJOIN hospitality_technology.guests g ON p.guest_id = g.guest_id\nJOIN hospitality_technology.staff s ON p.staff_id_processed = s.staff_id\nWHERE p.currency_code = 'USD'\n  AND p.status = 'Succeeded'\n  AND p.payment_timestamp >= NOW() - INTERVAL '30 days'\nORDER BY p.payment_timestamp DESC\nLIMIT 50;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.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.payments (\n    payment_id character varying(64) NOT NULL,  -- unique identifier for the payment transaction\n    reservation_id character varying(64), -- FK to reservations (if payment is for a stay)\n    guest_id character varying(64) NOT NULL, -- FK to guests (who paid)\n    bill_id character varying(64), -- FK to bills/invoices this payment applies to\n    amount numeric(12,2) NOT NULL, -- amount of the payment\n    currency_code character varying(3) NOT NULL, -- ISO currency code (e.g., USD, EUR)\n    payment_method character varying(50) NOT NULL, -- e.g., CreditCard, Cash, BankTransfer, Points, Voucher\n    card_type character varying(50), -- e.g., Visa, MasterCard, Amex (if CC)\n    card_last_four character varying(4), -- last 4 digits of CC (if CC)\n    transaction_ref character varying(128), -- reference ID from payment gateway or processor\n    payment_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, -- when the payment occurred\n    status character varying(50) NOT NULL, -- e.g., Pending, Succeeded, Failed, Refunded, Disputed\n    staff_id_processed character varying(64), -- FK to staff (who processed the payment)\n    notes text, -- notes about the payment\n    PRIMARY KEY (payment_id),\n    FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id),\n    FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id),\n    FOREIGN KEY (staff_id_processed) REFERENCES hospitality_technology.staff(staff_id)\n)\n"}
{"conversations": [{"role": "user", "content": "What is the ticket price for a journey on train number T4321?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to information about ticket prices for specific trains. The data I have is limited to train details such as model, manufacturer, capacity, and maintenance schedules. For ticket pricing, please consult the ticketing office or the official website."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.trains ( train_id text PRIMARY KEY, train_number text UNIQUE, model text, manufacturer text, year_manufactured int, capacity int, status text, last_maintenance_date date, next_maintenance_date date )\n"}
{"conversations": [{"role": "user", "content": "List all overdue premium payments with their policy IDs and due dates, sorted by due date in ascending order."}, {"role": "assistant", "content": "SELECT policy_id, due_date FROM insurance.premium_payments WHERE status = 'overdue' ORDER BY due_date ASC;"}, {"role": "user", "content": "Now include only those overdue payments where the due date was more than 60 days ago."}, {"role": "assistant", "content": "SELECT policy_id, due_date FROM insurance.premium_payments WHERE status = 'overdue' AND due_date < CURRENT_DATE - INTERVAL '60 days' ORDER BY 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 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": "How many documents of each type exist in the system? Show the document type and the count."}, {"role": "assistant", "content": "SELECT document_type, COUNT(*) AS document_count\nFROM legal_services.documents\ngroup BY document_type;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.clients ( client_id text, first_name text, last_name text, company_name text, email text, phone text, address text, date_registered timestamp, status text )\nCREATE TABLE legal_services.law_firms ( firm_id text, firm_name text, address text, phone text, website text, founded_date date, managing_partner_id text )\nCREATE TABLE legal_services.cases ( case_id text, case_number text, case_name text, client_id text, lead_lawyer_id text, case_type text, status text, date_opened timestamp, date_closed timestamp, description text, court_jurisdiction text )\nCREATE TABLE legal_services.documents ( document_id text, case_id text, document_name text, document_type text, storage_path text, uploaded_by_lawyer_id text, upload_timestamp timestamp, version integer, description text )\nCREATE TABLE legal_services.time_entries ( entry_id text, case_id text, lawyer_id text, date_worked date, hours_spent numeric, billing_rate numeric, description text, is_billable boolean, is_billed boolean, invoice_id text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show me each patient's full name along with the name of every doctor they've had an appointment with."}, {"role": "assistant", "content": "SELECT p.first_name || ' ' || p.last_name AS patient_full_name, d.first_name || ' ' || d.last_name AS doctor_full_name\nFROM healthcare.appointments a\nJOIN healthcare.patients p ON a.patient_id = p.patient_id\nJOIN healthcare.doctors d ON a.doctor_id = d.doctor_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id text PRIMARY KEY, first_name text, last_name text, date_of_birth date, gender text, address text, phone_number text, email text, emergency_contact_name text, emergency_contact_phone text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.doctors ( doctor_id text PRIMARY KEY, first_name text, last_name text, specialty text, license_number text, phone_number text, email text, hospital_affiliation_id text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.appointments ( appointment_id text PRIMARY KEY, patient_id text, doctor_id text, appointment_time timestamp, duration_minutes int, reason text, status text, location_id text, notes text, created_at timestamp )\nCREATE TABLE healthcare.medications ( medication_id text PRIMARY KEY, medication_name text, generic_name text, manufacturer text, ndc_code text, description text )\nCREATE TABLE healthcare.prescriptions ( prescription_id text PRIMARY KEY, record_id text, patient_id text, doctor_id text, medication_id text, dosage text, frequency text, route text, start_date date, end_date date, quantity_dispensed numeric, refills_allowed int, prescription_date timestamp )\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id text PRIMARY KEY, patient_id text, plan_id text, policy_number text, group_number text, subscriber_name text, effective_date date, expiration_date date, is_primary boolean )\n"}
{"conversations": [{"role": "user", "content": "Find all pairs of drivers where one driver's license_expiry_date is earlier than another's. Return each pair's driver_ids, full names, and respective expiry dates."}, {"role": "assistant", "content": "SELECT d1.driver_id AS driver1_id, d1.first_name || ' ' || d1.last_name AS driver1_name, d1.license_expiry_date AS expiry1, d2.driver_id AS driver2_id, d2.first_name || ' ' || d2.last_name AS driver2_name, d2.license_expiry_date AS expiry2 FROM transportation.drivers d1 JOIN transportation.drivers d2 ON d1.license_expiry_date < d2.license_expiry_date;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.drivers ( driver_id text PRIMARY KEY, employee_id text, first_name text, last_name text, license_number text, license_expiry_date date, contact_number text, email text, hire_date date, status text )\n"}
{"conversations": [{"role": "user", "content": "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": "Show each patient's policy number, the associated insurance plan ID, and any medications they have been prescribed, including the medication ID and prescription date."}, {"role": "assistant", "content": "SELECT pi.patient_id, pi.policy_number, pi.plan_id, pr.medication_id, pr.prescription_date\nFROM healthcare.patient_insurance pi\nJOIN healthcare.prescriptions pr ON pi.patient_id = pr.patient_id;"}, {"role": "user", "content": "Only include prescriptions that were made after the insurance policy's effective date."}, {"role": "assistant", "content": "SELECT pi.patient_id, pi.policy_number, pi.plan_id, pr.medication_id, pr.prescription_date\nFROM healthcare.patient_insurance pi\nJOIN healthcare.prescriptions pr ON pi.patient_id = pr.patient_id\nWHERE pr.prescription_date >= pi.effective_date;"}, {"role": "user", "content": "Add the expiration date of the insurance policy and only show records where the prescription was made before the policy expired."}, {"role": "assistant", "content": "SELECT pi.patient_id, pi.policy_number, pi.plan_id, pi.expiration_date, pr.medication_id, pr.prescription_date\nFROM healthcare.patient_insurance pi\nJOIN healthcare.prescriptions pr ON pi.patient_id = pr.patient_id\nWHERE pr.prescription_date >= pi.effective_date\n  AND (pi.expiration_date IS NULL OR pr.prescription_date < pi.expiration_date);"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.diagnoses ( diagnosis_id character varying(64) NOT NULL, record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, doctor_id character varying(64) NOT NULL, diagnosis_code character varying(20) NOT NULL, code_type character varying(10) NOT NULL DEFAULT 'ICD-10', description text, diagnosis_date date NOT NULL, status character varying(32) NOT NULL, is_chronic boolean DEFAULT false, PRIMARY KEY (diagnosis_id) )\nCREATE TABLE healthcare.prescriptions ( prescription_id character varying(64) NOT NULL, record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, doctor_id character varying(64) NOT NULL, medication_id character varying(64) NOT NULL, dosage character varying(100) NOT NULL, frequency character varying(100) NOT NULL, route character varying(50), start_date date NOT NULL, end_date date, quantity_dispensed numeric(10,2), refills_allowed integer NOT NULL DEFAULT 0, prescription_date timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (prescription_id) )\nCREATE TABLE healthcare.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": "How many patients have at least one medical record associated with them?"}, {"role": "assistant", "content": "SELECT COUNT(DISTINCT patient_id) FROM healthcare.medical_records;"}, {"role": "user", "content": "Now, can you show me the count of patients who do *not* have any medical records?"}, {"role": "assistant", "content": "SELECT COUNT(p.patient_id) FROM healthcare.patients p LEFT JOIN healthcare.medical_records mr ON p.patient_id = mr.patient_id WHERE mr.record_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 healthcare.patients ( patient_id text, first_name text, last_name text, date_of_birth date, gender text, address text, phone_number text, email text, emergency_contact_name text, emergency_contact_phone text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.medical_records (\n    record_id character varying(64) NOT NULL,  -- unique identifier for the medical record entry\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    appointment_id character varying(64) UNIQUE, -- FK to appointments table (can be null if record not tied to specific appt)\n    doctor_id character varying(64) NOT NULL, -- FK to doctors table (doctor creating the record)\n    record_date timestamp with time zone NOT NULL, -- date the record/observation was made\n    chief_complaint text, -- patient's primary reason for visit\n    present_illness_history text, -- detailed history of the current issue\n    past_medical_history text, -- relevant past conditions/surgeries\n    physical_examination_notes text, -- findings from the physical exam\n    assessment text, -- doctor's assessment/diagnosis summary\n    treatment_plan text, -- planned course of action\n    vitals jsonb, -- store vitals like BP, HR, Temp as structured JSON\n    created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n    PRIMARY KEY (record_id)\n)\nCREATE TABLE healthcare.diagnoses (\n    diagnosis_id character varying(64) NOT NULL, -- unique identifier for the diagnosis entry\n    record_id character varying(64) NOT NULL, -- FK linking to the specific medical record entry\n    patient_id character varying(64) NOT NULL, -- FK to patients table\n    doctor_id character varying(64) NOT NULL, -- FK to doctors table (diagnosing doctor)\n    diagnosis_code character varying(20) NOT NULL, -- standard code (e.g., ICD-10)\n    code_type character varying(10) NOT NULL DEFAULT 'ICD-10', -- type of code used\n    description text, -- textual description of the diagnosis\n    diagnosis_date date NOT NULL, -- date the diagnosis was made\n    status character varying(32) NOT NULL, -- e.g., Active, Resolved, Ruled Out\n    is_chronic boolean DEFAULT false, -- flag for chronic conditions\n    PRIMARY KEY (diagnosis_id)\n)\nCREATE TABLE healthcare.medications ( medication_id 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.text, plan_name.text, insurance_provider.text, plan_type.text, contact_phone.text, website.text )\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id.text, patient_id.text, plan_id.text, policy_number.text, group_number.text, subscriber_name.text, effective_date.date, expiration_date.date, is_primary.boolean )\n"}
{"conversations": [{"role": "user", "content": "Show me the property ID, name, and creation date for all properties created after January 1, 2022."}, {"role": "assistant", "content": "SELECT property_id, property_name, created_at FROM hospitality_technology.properties WHERE created_at >= '2022-01-01';"}, {"role": "user", "content": "Filter this list to only include properties in 'Texas' or 'Florida' and sort by creation date ascending."}, {"role": "assistant", "content": "SELECT property_id, property_name, created_at FROM hospitality_technology.properties WHERE created_at >= '2022-01-01' AND state_province IN ('TX', 'FL') ORDER BY created_at ASC;"}, {"role": "user", "content": "Actually, only show properties of type 'Resort' and limit the output to the top 10."}, {"role": "assistant", "content": "SELECT property_id, property_name, created_at FROM hospitality_technology.properties WHERE created_at >= '2022-01-01' AND state_province IN ('TX', 'FL') AND property_type = 'Resort' ORDER BY created_at 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 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 )\n"}
{"conversations": [{"role": "user", "content": "Show all rooms that are on floor 3."}, {"role": "assistant", "content": "SELECT room_id, property_id, room_number FROM hospitality_technology.rooms WHERE floor = 3;"}, {"role": "user", "content": "For these rooms, include the property name and room number."}, {"role": "assistant", "content": "SELECT r.room_number, p.property_name FROM hospitality_technology.rooms AS r JOIN hospitality_technology.properties AS p ON r.property_id = p.property_id WHERE r.floor = 3;"}, {"role": "user", "content": "Also, include the type name and current status for each room."}, {"role": "assistant", "content": "SELECT r.room_number, p.property_name, rt.type_name, r.status FROM hospitality_technology.rooms AS r JOIN hospitality_technology.properties AS p ON r.property_id = p.property_id JOIN hospitality_technology.room_types AS rt ON r.room_type_id = rt.room_type_id AND r.property_id = rt.property_id WHERE r.floor = 3;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.properties ( property_id text, property_name text, address_line1 text, address_line2 text, city text, state_province text, postal_code text, country_code text, phone_number text, email_address text, property_type text, star_rating numeric, timezone text, manager_staff_id text, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.rooms ( room_id text, property_id text, room_number text, room_type_id text, floor integer, status text, is_smoking boolean, features text, current_condition text, last_cleaned_at timestamp )\nCREATE TABLE hospitality_technology.room_types ( room_type_id text, property_id text, type_name text, description text, base_rate numeric, max_occupancy integer, bed_type text, area_sqft numeric, amenities text )\n"}
{"conversations": [{"role": "user", "content": "Find all wallet addresses that don't have an associated user_id."}, {"role": "assistant", "content": "SELECT address_id, private_key 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 LEFT JOIN blockchain.transactions t ON w.address_id = t.sender_address WHERE w.user_id IS NULL;"}, {"role": "user", "content": "This query seems incorrect because the transactions table isn't in the schema. Can you modify it to just show the wallet information?"}, {"role": "assistant", "content": "SELECT address_id, private_key FROM blockchain.wallets WHERE 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 wallet_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": "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": "List all ERC20 tokens where the total supply is between '1000000000' and '5000000000'. Show the symbol and name."}, {"role": "assistant", "content": "SELECT symbol, name FROM token_metas WHERE is_erc20 = 1 AND total_supply >= '1000000000' AND total_supply <= '5000000000'"}, {"role": "user", "content": "Also include the decimals and contract address."}, {"role": "assistant", "content": "SELECT symbol, name, decimals, contract_address FROM token_metas WHERE is_erc20 = 1 AND total_supply >= '1000000000' AND total_supply <= '5000000000'"}, {"role": "user", "content": "Filter these tokens to only include those where is_proxy is 0."}, {"role": "assistant", "content": "SELECT symbol, name, decimals, contract_address FROM token_metas WHERE is_erc20 = 1 AND total_supply >= '1000000000' AND total_supply <= '5000000000' AND is_proxy = 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 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 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 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 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_balances_avalanche ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar(20) NOT NULL, wallet_address varchar(42) NOT NULL, total_supply decimal(38,0) NOT NULL, amount decimal(38,0) NOT NULL )\n"}
{"conversations": [{"role": "user", "content": "Show me the first and last names of citizens along with their dates of birth and contact emails for all citizens who registered after January 1, 2023."}, {"role": "assistant", "content": "SELECT first_name, last_name, date_of_birth, contact_email FROM government_services.citizens WHERE registration_date > '2023-01-01';"}, {"role": "user", "content": "Only include citizens whose accounts are verified."}, {"role": "assistant", "content": "SELECT first_name, last_name, date_of_birth, contact_email FROM government_services.citizens WHERE registration_date > '2023-01-01' 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 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 )\n"}
{"conversations": [{"role": "user", "content": "How many likes were given to comments in June 2024?"}, {"role": "assistant", "content": "SELECT COUNT(*) AS comment_likes_count\nFROM social_media.likes\nWHERE comment_id IS NOT NULL \n  AND DATE_TRUNC('month', created_at) = '2024-06-01';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.comments ( comment_id character varying(64) NOT NULL, post_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, parent_comment_id character varying(64), content text NOT NULL, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (comment_id) )\nCREATE TABLE social_media.likes ( like_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, post_id character varying(64), comment_id character varying(64), created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (like_id), CONSTRAINT unique_user_like UNIQUE (user_id, post_id, comment_id), CONSTRAINT check_like_target CHECK (post_id IS NOT NULL OR comment_id IS NOT NULL) )\nCREATE TABLE social_media.post_hashtags ( post_hashtag_id character varying(64) NOT NULL, post_id character varying(64) NOT NULL, hashtag_id character varying(64) NOT NULL, PRIMARY KEY (post_hashtag_id), CONSTRAINT unique_post_hashtag UNIQUE (post_id, hashtag_id) )\nCREATE TABLE social_media.conversations ( conversation_id character varying(64) NOT NULL, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, last_message_at timestamp, is_group_chat boolean NOT NULL DEFAULT false, group_name character varying(100), PRIMARY KEY (conversation_id) )\nCREATE TABLE social_media.notifications ( notification_id character varying(64) NOT NULL, recipient_user_id character varying(64) NOT NULL, sender_user_id character varying(64), notification_type character varying(30) NOT NULL, target_entity_id character varying(64), target_entity_type character varying(20), created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, read_at timestamp, PRIMARY KEY (notification_id) )\nCREATE TABLE social_media.user_settings ( setting_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL UNIQUE, theme character varying(20) DEFAULT 'light', email_notifications_enabled boolean DEFAULT true, push_notifications_enabled boolean DEFAULT true, private_profile boolean DEFAULT false, updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (setting_id) )\n"}
{"conversations": [{"role": "user", "content": "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 group chat conversations and the number of messages in each group chat."}, {"role": "assistant", "content": "SELECT c.conversation_id,\n       c.group_name,\n       COUNT(m.message_id) AS message_count\nFROM social_media.conversations c\nJOIN social_media.messages m\n  ON c.conversation_id = m.conversation_id\nWHERE c.is_group_chat = true\nGROUP BY c.conversation_id, c.group_name;"}, {"role": "user", "content": "Actually, only include group chats with more than 10 messages and order by message_count descending."}, {"role": "assistant", "content": "SELECT c.conversation_id,\n       c.group_name,\n       COUNT(m.message_id) AS message_count\nFROM social_media.conversations c\nJOIN social_media.messages m\n  ON c.conversation_id = m.conversation_id\nWHERE c.is_group_chat = true\nGROUP BY c.conversation_id, c.group_name\nHAVING COUNT(m.message_id) > 10\nORDER BY message_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.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.follows ( follow_id.text, follower_user_id.text, following_user_id.text, created_at.timestamp )\nCREATE TABLE social_media.messages ( message_id character varying(64) NOT NULL, conversation_id character varying(64) NOT NULL, sender_user_id character varying(64) NOT NULL, content text, media_url text, media_type character varying(20), sent_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, read_at timestamp, PRIMARY KEY (message_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.user_settings ( setting_id text PRIMARY KEY, user_id text, theme text, email_notifications_enabled bool, push_notifications_enabled bool, private_profile bool, updated_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "List all pairs of tokens (show token_id for both) that share the same contract address, excluding pairs where the token_id is the same."}, {"role": "assistant", "content": "SELECT t1.token_id AS token_id1, t2.token_id AS token_id2, t1.contract_address FROM web3.tokens AS t1 JOIN web3.tokens AS t2 ON t1.contract_address = t2.contract_address WHERE t1.token_id < t2.token_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.tokens ( token_id character varying(64) NOT NULL, contract_address character varying(128) NOT NULL, token_name character varying(128) NOT NULL, token_symbol character varying(32) NOT NULL, decimals integer NOT NULL, total_supply numeric(38,14) NOT NULL, PRIMARY KEY (token_id) )\n"}
{"conversations": [{"role": "user", "content": "List the names and types of all in-game items that have a rarity of 'Epic'."}, {"role": "assistant", "content": "SELECT item_name, item_type FROM gaming_technology.in_game_items WHERE rarity = 'Epic';"}, {"role": "user", "content": "Further restrict the list to only include items of item_type 'Weapon'."}, {"role": "assistant", "content": "SELECT item_name, item_type FROM gaming_technology.in_game_items WHERE rarity = 'Epic' AND item_type = 'Weapon';"}, {"role": "user", "content": "Order these results by their cost_amount in descending order."}, {"role": "assistant", "content": "SELECT item_name, item_type FROM gaming_technology.in_game_items WHERE rarity = 'Epic' AND item_type = 'Weapon' ORDER BY cost_amount DESC;"}, {"role": "user", "content": "Please also include the cost_currency and cost_amount in the output."}, {"role": "assistant", "content": "SELECT item_name, item_type, cost_currency, cost_amount FROM gaming_technology.in_game_items WHERE rarity = 'Epic' AND item_type = 'Weapon' ORDER BY cost_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 gaming_technology.players ( player_id uuid, username text, email text, password_hash text, registration_date timestamp with time zone, last_login timestamp with time zone, country_code text, status text, profile_data jsonb )\nCREATE TABLE gaming_technology.developers ( developer_id uuid, name text, country text, founded_year integer, website text, created_at timestamp with time zone )\nCREATE TABLE gaming_technology.game_sessions ( session_id uuid, player_id uuid, game_id uuid, server_id uuid, start_time timestamp with time zone, end_time timestamp with time zone, duration_seconds integer, score integer, session_data jsonb )\nCREATE TABLE gaming_technology.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 timestamp with time zone, instance_data jsonb )\n"}
{"conversations": [{"role": "user", "content": "Show the case number, case name, and the full name of the lead lawyer, along with the total hours spent on each case."}, {"role": "assistant", "content": "SELECT c.case_number, c.case_name, CONCAT(l.first_name, ' ', l.last_name) AS lead_lawyer_name, COALESCE(SUM(te.hours_spent), 0) AS total_hours\nFROM legal_services.cases c\nLEFT JOIN legal_services.lawyers l ON c.lead_lawyer_id = l.lawyer_id\nLEFT JOIN legal_services.time_entries te ON c.case_id = te.case_id\nGROUP BY c.case_number, c.case_name, l.first_name, l.last_name;"}, {"role": "user", "content": "Could you modify the query to only include cases where more than 20 hours were spent in total?"}, {"role": "assistant", "content": "SELECT c.case_number, c.case_name, CONCAT(l.first_name, ' ', l.last_name) AS lead_lawyer_name, SUM(te.hours_spent) AS total_hours\nFROM legal_services.cases c\nLEFT JOIN legal_services.lawyers l ON c.lead_lawyer_id = l.lawyer_id\nLEFT JOIN legal_services.time_entries te ON c.case_id = te.case_id\nGROUP BY c.case_number, c.case_name, l.first_name, l.last_name\nHAVING SUM(te.hours_spent) > 20;"}, {"role": "user", "content": "Now restrict the result to cases where the lead lawyer is also a partner."}, {"role": "assistant", "content": "SELECT c.case_number, c.case_name, CONCAT(l.first_name, ' ', l.last_name) AS lead_lawyer_name, SUM(te.hours_spent) AS total_hours\nFROM legal_services.cases c\nLEFT JOIN legal_services.lawyers l ON c.lead_lawyer_id = l.lawyer_id\nLEFT JOIN legal_services.time_entries te ON c.case_id = te.case_id\nWHERE l.is_partner = TRUE\nGROUP BY c.case_number, c.case_name, l.first_name, l.last_name\nHAVING SUM(te.hours_spent) > 20;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.lawyers ( lawyer_id text PRIMARY KEY, first_name text, last_name text, bar_number text UNIQUE, firm_id text, email text UNIQUE, phone text, specialization text, hire_date timestamp, is_partner bool )\nCREATE TABLE legal_services.cases ( case_id text PRIMARY KEY, case_number text UNIQUE, case_name text, client_id text, lead_lawyer_id text, case_type text, status text, date_opened timestamp, date_closed timestamp, description text, court_jurisdiction text )\nCREATE TABLE legal_services.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": "Calculate the average number of days between when an incident occurred and when the claim was reported, but only for claims that were settled in the year 2023."}, {"role": "assistant", "content": "SELECT\n  AVG(EXTRACT(EPOCH FROM (reported_date - incident_date)) / 86400.0)::numeric(10, 2)\nFROM\n  insurance.claims\nWHERE\n  settlement_date IS NOT NULL AND EXTRACT(YEAR FROM settlement_date) = 2023;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.claims (\n    claim_id character varying(64) NOT NULL, -- unique identifier for the claim\n    policy_id character varying(64) NOT NULL, -- identifier of the policy under which the claim is made (FK to policies)\n    customer_id character varying(64) NOT NULL, -- identifier of the customer making the claim (FK to customers)\n    incident_date timestamp NOT NULL, -- date and time of the incident leading to the claim\n    reported_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- date the claim was reported\n    description text NOT NULL, -- detailed description of the incident and claim\n    estimated_loss numeric(15, 2), -- initial estimated cost of the loss\n    status character varying(30) NOT NULL, -- e.g., Filed, Processing, Under Review, Approved, Denied, Settled\n    settlement_amount numeric(15, 2), -- final amount paid out\n    settlement_date date,\n    claim_handler_id character varying(64), -- identifier for the employee handling the claim (FK to employees/adjusters)\n    police_report_number character varying(100),\n    PRIMARY KEY (claim_id)\n)\n"}
{"conversations": [{"role": "user", "content": "What are the personal contact details of the staff member associated with staff_id 'STAFF789' who worked on a specific maintenance record?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide personal contact details of staff members as this information is not stored in the maintenance_records table and is outside the scope of the available data."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.maintenance_records ( record_id text, asset_id text, asset_type text, maintenance_type text, staff_id text, start_datetime timestamp, end_datetime timestamp, description text, cost numeric, status text )\n"}
{"conversations": [{"role": "user", "content": "Show the number of reservations and the sum total_amount for each property."}, {"role": "assistant", "content": "SELECT p.property_id, p.property_name, COUNT(r.reservation_id) AS reservation_count, SUM(r.total_amount) AS total_revenue \nFROM hospitality_technology.properties p \nLEFT JOIN hospitality_technology.reservations r ON p.property_id = r.property_id \nGROUP BY p.property_id, p.property_name;"}, {"role": "user", "content": "Return only those properties with at least 50 reservations."}, {"role": "assistant", "content": "SELECT p.property_id, p.property_name, COUNT(r.reservation_id) AS reservation_count, SUM(r.total_amount) AS total_revenue \nFROM hospitality_technology.properties p \nLEFT JOIN hospitality_technology.reservations r ON p.property_id = r.property_id \nGROUP BY p.property_id, p.property_name \nHAVING COUNT(r.reservation_id) >= 50;"}, {"role": "user", "content": "Additionally, only include properties in cities that start with the letter 'S' and order by total revenue descending."}, {"role": "assistant", "content": "SELECT p.property_id, p.property_name, COUNT(r.reservation_id) AS reservation_count, SUM(r.total_amount) AS total_revenue \nFROM hospitality_technology.properties p \nLEFT JOIN hospitality_technology.reservations r ON p.property_id = r.property_id \nWHERE p.city LIKE 'S%'\nGROUP BY p.property_id, p.property_name \nHAVING COUNT(r.reservation_id) >= 50\nORDER BY total_revenue DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.properties ( property_id text, property_name text, address_line1 text, address_line2 text, city text, state_province text, postal_code text, country_code text, phone_number text, email_address text, property_type text, star_rating numeric, timezone text, manager_staff_id text, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.room_types ( room_type_id text, property_id text, type_name text, description text, base_rate numeric, max_occupancy integer, bed_type text, area_sqft numeric, amenities text )\nCREATE TABLE hospitality_technology.guests ( guest_id text, first_name text, last_name text, email text, phone_number text, date_of_birth date, address_line1 text, city text, state_province text, postal_code text, country_code text, preferences text, loyalty_member_id text, communication_consent boolean, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.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": "What is the fuel efficiency of the train car with car_id 'TC456'?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to information about the fuel efficiency of specific train cars. The data available in the train_cars table only includes details such as car_id, train_id, car_number, car_type, class, capacity, and features. If you have another question or need assistance with something else, I'm happy to help."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.train_cars ( car_id.text, train_id.text, car_number.text, car_type.text, class.text, capacity.integer, features.text )\n"}
{"conversations": [{"role": "user", "content": "List the usernames and emails of all users who registered on '2023-03-15'."}, {"role": "assistant", "content": "SELECT username, email FROM web3.users WHERE DATE(created_at) = '2023-03-15';"}, {"role": "user", "content": "Instead of the list, can you just give me the total number of users who registered on '2023-03-15'?"}, {"role": "assistant", "content": "SELECT COUNT(*) FROM web3.users WHERE DATE(created_at) = '2023-03-15';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.users ( user_id text, username text, email text, password_hash text, created_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "Show all token transfers including the token symbol and the address of the contract that created each token. List the transfer id, token id, value, transaction id, the contract address, and the token symbol."}, {"role": "assistant", "content": "SELECT tt.transfer_id, tt.token_id, tt.value, tt.transaction_id, t.contract_id AS contract_address, t.token_symbol\nFROM web3.token_transfers tt\nJOIN web3.tokens t ON tt.token_id = t.token_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.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.transactions ( transaction_id text, from_address text, to_address text, value numeric, gas_used integer, gas_price numeric, block_number integer, timestamp timestamp, input_data text, status text, nonce integer )\nCREATE TABLE web3.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": "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": "For each premium payment, list all previous payments made by the same customer. Show customer_id, previous_payment_id, previous_payment_date, current_payment_id, current_payment_date, and amount difference."}, {"role": "assistant", "content": "SELECT p1.customer_id,\n       p1.payment_id AS previous_payment_id,\n       p1.payment_date AS previous_payment_date,\n       p2.payment_id AS current_payment_id,\n       p2.payment_date AS current_payment_date,\n       p2.amount_paid - p1.amount_paid AS amount_diff\nFROM insurance.premium_payments p1\nJOIN insurance.premium_payments p2\n  ON p1.customer_id = p2.customer_id\n  AND p1.payment_date < p2.payment_date;"}, {"role": "user", "content": "Actually, only include pairs where the current payment date is in 2024."}, {"role": "assistant", "content": "SELECT p1.customer_id,\n       p1.payment_id AS previous_payment_id,\n       p1.payment_date AS previous_payment_date,\n       p2.payment_id AS current_payment_id,\n       p2.payment_date AS current_payment_date,\n       p2.amount_paid - p1.amount_paid AS amount_diff\nFROM insurance.premium_payments p1\nJOIN insurance.premium_payments p2\n  ON p1.customer_id = p2.customer_id\n  AND p1.payment_date < p2.payment_date\nWHERE p2.payment_date BETWEEN '2024-01-01' AND '2024-12-31';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.premium_payments ( payment_id text, policy_id text, customer_id text, payment_date timestamp, amount_paid numeric, payment_method text, transaction_reference text, due_date date, payment_period_start date, payment_period_end date, status text )\n"}
{"conversations": [{"role": "user", "content": "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 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": "List all contracts with status 'active' and include the number of events they've emitted in the last 30 days."}, {"role": "assistant", "content": "SELECT c.contract_id, c.address, COUNT(e.event_id) AS recent_event_count FROM web3.contracts c LEFT JOIN web3.events e ON c.contract_id = e.contract_id WHERE c.status = 'active' AND e.emitted_at >= CURRENT_DATE - INTERVAL '30 days' GROUP BY c.contract_id, c.address;"}, {"role": "user", "content": "There's a typo in your SQL, it should be 'INTERVAL' not 'INTERVAL'. Also, I need the deployer address included in the results."}, {"role": "assistant", "content": "SELECT c.contract_id, c.address, c.deployer_address, COUNT(e.event_id) AS recent_event_count FROM web3.contracts c LEFT JOIN web3.events e ON c.contract_id = e.contract_id WHERE c.status = 'active' AND e.emitted_at >= CURRENT_DATE - INTERVAL '30 days' GROUP BY c.contract_id, c.address, c.deployer_address;"}, {"role": "user", "content": "Now filter to only show contracts that have emitted at least 5 events in this period."}, {"role": "assistant", "content": "SELECT c.contract_id, c.address, c.deployer_address, COUNT(e.event_id) AS recent_event_count FROM web3.contracts c LEFT JOIN web3.events e ON c.contract_id = e.contract_id WHERE c.status = 'active' AND e.emitted_at >= CURRENT_DATE - INTERVAL '30 days' GROUP BY c.contract_id, c.address, c.deployer_address HAVING COUNT(e.event_id) >= 5;"}, {"role": "user", "content": "Actually, sort the results by the deployer address in ascending order first, then by event count in descending order."}, {"role": "assistant", "content": "SELECT c.contract_id, c.address, c.deployer_address, COUNT(e.event_id) AS recent_event_count FROM web3.contracts c LEFT JOIN web3.events e ON c.contract_id = e.contract_id WHERE c.status = 'active' AND e.emitted_at >= CURRENT_DATE - INTERVAL '30 days' GROUP BY c.contract_id, c.address, c.deployer_address HAVING COUNT(e.event_id) >= 5 ORDER BY c.deployer_address ASC, recent_event_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.contracts (\n    contract_id character varying(64) NOT NULL,  -- unique identifier for the contract\n    address character varying(128) NOT NULL, -- address of the deployed contract\n    abi text NOT NULL, -- application binary interface of the contract\n    bytecode text NOT NULL, -- bytecode of the contract\n    deployer_address character varying(128) NOT NULL, -- address of the deployer\n    deployed_at timestamp NOT NULL, -- time when the contract was deployed\n    network_id character varying(64) NOT NULL, -- identifier of the network where the contract is deployed\n    status character varying(32) NOT NULL, -- status of the contract (e.g., active, deprecated)\n    PRIMARY KEY (contract_id)\n)\nCREATE TABLE web3.events (\n    event_id character varying(64) NOT NULL,  -- unique identifier for the event\n    contract_id character varying(64) NOT NULL, -- identifier of the contract emitting the event\n    event_name character varying(128) NOT NULL, -- name of the event\n    data text NOT NULL, -- data payload of the event\n    emitted_at timestamp NOT NULL, -- time when the event was emitted\n    transaction_id character varying(64) NOT NULL, -- identifier of the transaction that triggered the event\n    log_index integer NOT NULL, -- index of the event log in the transaction\n    PRIMARY KEY (event_id)\n)\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": "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": "List all narratives with a trend rank in the top 10 and a 24-hour trading volume over $100 million."}, {"role": "assistant", "content": "SELECT narrative, trend_rank, volume_24h FROM narrative_info WHERE trend_rank <= 10 AND volume_24h > 100000000 ORDER BY trend_rank;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\n \"CREATE TABLE 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"}
{"conversations": [{"role": "user", "content": "Summarize the accounts table by account type and currency, showing the average balance for each combination."}, {"role": "assistant", "content": "SELECT account_type, currency, AVG(balance) AS average_balance, COUNT(account_id) AS account_count FROM financial_services.accounts GROUP BY account_type, currency ORDER BY account_type, currency;"}, {"role": "user", "content": "Only include combinations where the average balance is greater than 5000."}, {"role": "assistant", "content": "SELECT account_type, currency, AVG(balance) AS average_balance, COUNT(account_id) AS account_count FROM financial_services.accounts GROUP BY account_type, currency HAVING AVG(balance) > 5000 ORDER BY average_balance DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.accounts (\n    account_id character varying(64) NOT NULL, -- unique identifier for the account\n    customer_id character varying(64) NOT NULL, -- foreign key linking to the customer\n    account_number character varying(128) NOT NULL UNIQUE, -- unique account number visible to customer\n    account_type character varying(50) NOT NULL, -- e.g., Checking, Savings, Investment, Loan, Credit Card\n    balance numeric(19, 4) NOT NULL DEFAULT 0.00, -- current account balance\n    currency character varying(3) NOT NULL, -- currency code (e.g., USD, EUR)\n    opened_date date NOT NULL, -- date the account was opened\n    status character varying(32) NOT NULL, -- e.g., Open, Closed, Frozen\n    interest_rate numeric(5, 4), -- annual interest rate, if applicable\n    last_updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last account update\n    PRIMARY KEY (account_id),\n    FOREIGN KEY (customer_id) REFERENCES financial_services.customers(customer_id)\n)\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": "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": "How many hashtags have been created in March 2024?"}, {"role": "assistant", "content": "```sql\nSELECT COUNT(*) AS march_2024_hashtag_count\nFROM social_media.hashtags\nWHERE created_at >= '2024-03-01'\n  AND created_at <  '2024-04-01';\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 social_media.users ( user_id text PRIMARY KEY, username text, email text, password_hash text, full_name text, profile_picture_url text, bio text, location text, created_at timestamp, updated_at timestamp, is_verified bool )\nCREATE TABLE social_media.hashtags ( hashtag_id text PRIMARY KEY, tag_name text, created_at timestamp )\nCREATE TABLE social_media.conversation_participants ( participant_id text PRIMARY KEY, conversation_id text, user_id text, joined_at timestamp, last_read_at timestamp )\nCREATE TABLE social_media.notifications ( notification_id text PRIMARY KEY, recipient_user_id text, sender_user_id text, notification_type text, target_entity_id text, target_entity_type text, created_at timestamp, read_at timestamp )\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 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": "Which service locations do not have a contact phone specified? Show the location_id and location_name."}, {"role": "assistant", "content": "SELECT location_id, location_name\nFROM government_services.service_locations\nWHERE contact_phone IS NULL OR contact_phone = '';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.documents ( document_id character varying(64) NOT NULL, application_id character varying(64), citizen_id character varying(64) NOT NULL, document_type character varying(100) NOT NULL, file_reference text NOT NULL, upload_timestamp timestamp NOT NULL, expiry_date date, verification_status character varying(30) DEFAULT 'Pending', verified_by_employee_id character varying(64), verification_timestamp timestamp, PRIMARY KEY (document_id) )\nCREATE TABLE government_services.service_locations ( location_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, location_name character varying(200), address text NOT NULL, city character varying(100), state character varying(50), postal_code character varying(20), latitude numeric(9, 6), longitude numeric(9, 6), operating_hours text, contact_phone character varying(32), is_accessible boolean, PRIMARY KEY (location_id) )\n"}
{"conversations": [{"role": "user", "content": "Provide a count of how many peers were last seen on each distinct day recorded in the system."}, {"role": "assistant", "content": "SELECT DATE(last_seen), COUNT(*) FROM trading_platform.peers GROUP BY DATE(last_seen) ORDER BY DATE(last_seen);"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.users ( user_id text, username text, email text, password_hash text, created_at timestamp )\nCREATE TABLE trading_platform.wallets ( wallet_id text, user_id text, address text, private_key text, created_at timestamp )\nCREATE TABLE trading_platform.orders ( order_id text, user_id text, wallet_id text, asset_id text, order_type text, quantity numeric, price numeric, status text, created_at timestamp )\nCREATE TABLE trading_platform.trades ( trade_id text, order_id text, buyer_id text, seller_id text, asset_id text, quantity numeric, price numeric, traded_at timestamp )\nCREATE TABLE trading_platform.assets ( asset_id text, name text, symbol text, type text )\nCREATE TABLE trading_platform.utxos ( utxo_id text, transaction_id text, output_index integer, address text, amount numeric, spent boolean )\nCREATE TABLE trading_platform.dapps ( dapp_id text, name text, description text, url text )\nCREATE TABLE trading_platform.peers ( peer_id text, ip_address text, port integer, last_seen timestamp )\nCREATE TABLE trading_platform.kyc_audit ( kyc_audit_id text, user_id text, status text, reviewed_at timestamp )\nCREATE TABLE trading_platform.logs ( log_id text, user_id text, action text, details text, logged_at timestamp )\nCREATE TABLE trading_platform.notifications ( notification_id text, user_id text, message text, sent_at timestamp, read_at timestamp )\n"}
{"conversations": [{"role": "user", "content": "How many players registered in each year? Show the year and the registration count."}, {"role": "assistant", "content": "SELECT EXTRACT(YEAR FROM registration_date) AS year,\n       COUNT(*) AS registrations\nFROM gaming_technology.players\nGROUP BY year;"}, {"role": "user", "content": "Actually, only include years after 2021."}, {"role": "assistant", "content": "SELECT EXTRACT(YEAR FROM registration_date) AS year,\n       COUNT(*) AS registrations\nFROM gaming_technology.players\nWHERE EXTRACT(YEAR FROM registration_date) > 2021\nGROUP BY year;"}, {"role": "user", "content": "Also, include only active players."}, {"role": "assistant", "content": "SELECT EXTRACT(YEAR FROM registration_date) AS year,\n       COUNT(*) AS registrations\nFROM gaming_technology.players\nWHERE EXTRACT(YEAR FROM registration_date) > 2021\n  AND status = 'active'\nGROUP BY year;"}, {"role": "user", "content": "Finally, order the results by year descending."}, {"role": "assistant", "content": "SELECT EXTRACT(YEAR FROM registration_date) AS year,\n       COUNT(*) AS registrations\nFROM gaming_technology.players\nWHERE EXTRACT(YEAR FROM registration_date) > 2021\n  AND status = 'active'\nGROUP BY year\nORDER BY year DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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)\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": "Show me all active customers from New York who were born before 1980, along with their contact information."}, {"role": "assistant", "content": "SELECT first_name, last_name, phone_number, email, address_line1, city, state, zip_code FROM insurance.customers WHERE state = 'New York' AND status = 'active' AND date_of_birth < '1980-01-01';"}, {"role": "user", "content": "Now filter these results to only show customers who have provided both a phone number and an email address."}, {"role": "assistant", "content": "SELECT first_name, last_name, phone_number, email, address_line1, city, state, zip_code FROM insurance.customers WHERE state = 'New York' AND status = 'active' AND date_of_birth < '1980-01-01' AND phone_number IS NOT NULL AND email IS NOT NULL;"}, {"role": "user", "content": "I also want to see how long these customers have been in our system (difference between current date and created_at in years)."}, {"role": "assistant", "content": "SELECT first_name, last_name, phone_number, email, address_line1, city, state, zip_code, EXTRACT(YEAR FROM AGE(NOW(), created_at)) AS years_in_system FROM insurance.customers WHERE state = 'New York' AND status = 'active' AND date_of_birth < '1980-01-01' AND phone_number IS NOT NULL AND email IS NOT NULL;"}, {"role": "user", "content": "Finally, order the results by the longest tenure in our system first, then by last name alphabetically."}, {"role": "assistant", "content": "SELECT first_name, last_name, phone_number, email, address_line1, city, state, zip_code, EXTRACT(YEAR FROM AGE(NOW(), created_at)) AS years_in_system FROM insurance.customers WHERE state = 'New York' AND status = 'active' AND date_of_birth < '1980-01-01' AND phone_number IS NOT NULL AND email IS NOT NULL ORDER BY years_in_system DESC, last_name ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.customers ( 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": "I need to list the top 5 ERC20 tokens by total supply, including symbol, contract_address, and name."}, {"role": "assistant", "content": "SELECT tm.contract_address, tm.symbol, tm.name, CAST(tm.total_supply AS DECIMAL) AS total_supply\nFROM token_metas tm\nWHERE tm.is_erc20 = 1\nORDER BY CAST(tm.total_supply AS DECIMAL) DESC\nLIMIT 5;"}, {"role": "user", "content": "Also include the latest USD price for each token from token_prices using the most recent timestamp per token."}, {"role": "assistant", "content": "SELECT tm.contract_address, tm.symbol, tm.name, CAST(tm.total_supply AS DECIMAL) AS total_supply, tp.price\nFROM token_metas tm\nJOIN (\n  SELECT address, price FROM token_prices tp1\n  WHERE tp1.timestamp = (\n    SELECT MAX(tp2.timestamp) FROM token_prices tp2 WHERE tp2.address = tp1.address\n  )\n) tp ON tp.address = tm.contract_address\nWHERE tm.is_erc20 = 1\nORDER BY CAST(tm.total_supply AS DECIMAL) DESC\nLIMIT 5;"}, {"role": "user", "content": "Filter results to only include tokens where the price is greater than 2."}, {"role": "assistant", "content": "SELECT tm.contract_address, tm.symbol, tm.name, CAST(tm.total_supply AS DECIMAL) AS total_supply, tp.price\nFROM token_metas tm\nJOIN (\n  SELECT address, price FROM token_prices tp1\n  WHERE tp1.timestamp = (\n    SELECT MAX(tp2.timestamp) FROM token_prices tp2 WHERE tp2.address = tp1.address\n  )\n) tp ON tp.address = tm.contract_address\nWHERE tm.is_erc20 = 1\n  AND tp.price > 2\nORDER BY CAST(tm.total_supply AS DECIMAL) DESC\nLIMIT 5;"}, {"role": "user", "content": "Order the results by price descending and limit to 5."}, {"role": "assistant", "content": "SELECT tm.contract_address, tm.symbol, tm.name, CAST(tm.total_supply AS DECIMAL) AS total_supply, tp.price\nFROM token_metas tm\nJOIN (\n  SELECT address, price FROM token_prices tp1\n  WHERE tp1.timestamp = (\n    SELECT MAX(tp2.timestamp) FROM token_prices tp2 WHERE tp2.address = tp1.address\n  )\n) tp ON tp.address = tm.contract_address\nWHERE tm.is_erc20 = 1\n  AND tp.price > 2\nORDER BY tp.price DESC\nLIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp.timestamp, block_number.bigint, transaction_hash.text, transaction_index.bigint, from_address.text, contract_address.text, symbol.text, total_supply.text, name.text, decimals.bigint, is_erc20.integer, is_erc721.integer, is_erc1155.integer, is_proxy.integer, extra_info.text, pk.integer )\nCREATE TABLE erc1155_approval_for_all (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the transaction\n    transaction_index integer NOT NULL, -- Index of the transaction within the block\n    transaction_hash varchar(66) NOT NULL, -- Transaction hash\n    log_index integer NOT NULL, -- Log index\n    contract_address varchar(42) NOT NULL  -- Event contract address\n)\nCREATE TABLE erc20_balances ( block_number bigint, contract_address varchar, wallet_address varchar, amount varchar, pk varchar )\nCREATE TABLE nft_holders ( block_number.bigint, contract_address.text, wallet_address.text, token_id.text, contract_type.text, amount.text, pk.text )\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_coins_metadata (\n    object_id varchar NOT NULL, -- object id of the coin metadata object\n    coin_type varchar NOT NULL, -- coin type, eg. 0x...66::reap_token::REAP_TOKEN\n    status varchar NOT NULL, -- coin status, eg. exists, deleted\n    decimals bigint NOT NULL, -- decimals of the coin\n    description varchar NOT NULL, -- description of the coin\n    icon_url varchar NOT NULL, -- icon url of the coin\n    symbol varchar NOT NULL, -- symbol of the coin\n    name varchar NOT NULL  -- name of the coin\n)\nCREATE TABLE nft_collections ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, name varchar NOT NULL, symbol varchar NOT NULL, deploy_block_number bigint NOT NULL, deploy_block_time bigint NOT NULL, erc_type varchar NOT NULL, owner varchar NOT NULL, traits varchar NOT NULL, description varchar NOT NULL, slug varchar NOT NULL, media_info varchar NOT NULL, image_url varchar NOT NULL, banner_image_url varchar NOT NULL, updated_at bigint NOT NULL, banner varchar NOT NULL, token_count bigint NOT NULL, floor_price varchar NOT NULL, floor_price_symbol varchar NOT NULL, floor_price_contract varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_prices ( uuid.text, blockchain.text, address.text, decimals.bigint, symbol.text, price.real, timestamp.timestamp )\nCREATE TABLE erc20_approval ( block_number.bigint, block_timestamp.timestamp, transaction_index.integer, transaction_hash.text, log_index.integer, contract_address.text, pk.integer )\nCREATE TABLE token_balances (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n    tick varchar NOT NULL, -- Token tick\n    wallet_address varchar(42) NOT NULL, -- Address of owner\n    total_supply decimal(38,0) NOT NULL, -- Max supply\n    amount decimal(38,0) NOT NULL  -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE token_activities ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\nCREATE TABLE mud_holesky_redstone ( address text, table_id text, key_bytes text, key0 text, key1 text, static_data text, encoded_lengths text, dynamic_data text, is_deleted boolean, block_number bigint, log_index bigint )\nCREATE TABLE token_balances_bitcoin (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n    tick varchar(255) NOT NULL, -- Ticker: Identifier of the inscription\n    wallet_address varchar(42) NOT NULL, -- Address of owner\n    total_supply varchar NOT NULL, -- Max supply: Set max supply of the inscription\n    amount varchar NOT NULL  -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_balances_avalanche (\n    block_number bigint NOT NULL, -- Block number containing the transaction\n    block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n    tick varchar(20) NOT NULL, -- Ticker: Identifier of the inscription\n    wallet_address varchar(42) NOT NULL, -- Address of owner\n    total_supply decimal(38,0) NOT NULL, -- Max supply: Set max supply of the inscription\n    amount decimal(38,0) NOT NULL  -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id varchar )\n"}
{"conversations": [{"role": "user", "content": "List each achievement with the very next achievement unlocked by the same player using a self-join. Show player_id, current_ach, current_unlocked_at, next_ach, and next_unlocked_at."}, {"role": "assistant", "content": "SELECT pa1.player_id,\n       pa1.achievement_id AS current_ach,\n       pa1.unlocked_at AS current_unlocked_at,\n       pa2.achievement_id AS next_ach,\n       pa2.unlocked_at AS next_unlocked_at\nFROM gaming_technology.player_achievements pa1\nJOIN gaming_technology.player_achievements pa2\n  ON pa1.player_id = pa2.player_id\n AND pa2.unlocked_at = (\n     SELECT MIN(pa3.unlocked_at)\n     FROM gaming_technology.player_achievements pa3\n     WHERE pa3.player_id = pa1.player_id\n       AND pa3.unlocked_at > pa1.unlocked_at\n );"}, {"role": "user", "content": "Now restrict to pairs where the time difference between current_unlocked_at and next_unlocked_at is less than 48 hours."}, {"role": "assistant", "content": "SELECT pa1.player_id,\n       pa1.achievement_id AS current_ach,\n       pa1.unlocked_at AS current_unlocked_at,\n       pa2.achievement_id AS next_ach,\n       pa2.unlocked_at AS next_unlocked_at\nFROM gaming_technology.player_achievements pa1\nJOIN gaming_technology.player_achievements pa2\n  ON pa1.player_id = pa2.player_id\n AND pa2.unlocked_at = (\n     SELECT MIN(pa3.unlocked_at)\n     FROM gaming_technology.player_achievements pa3\n     WHERE pa3.player_id = pa1.player_id\n       AND pa3.unlocked_at > pa1.unlocked_at\n )\nWHERE pa2.unlocked_at - pa1.unlocked_at < INTERVAL '48 hours';"}, {"role": "user", "content": "Order the results by player_id and current_unlocked_at ascending."}, {"role": "assistant", "content": "SELECT pa1.player_id,\n       pa1.achievement_id AS current_ach,\n       pa1.unlocked_at AS current_unlocked_at,\n       pa2.achievement_id AS next_ach,\n       pa2.unlocked_at AS next_unlocked_at\nFROM gaming_technology.player_achievements pa1\nJOIN gaming_technology.player_achievements pa2\n  ON pa1.player_id = pa2.player_id\n AND pa2.unlocked_at = (\n     SELECT MIN(pa3.unlocked_at)\n     FROM gaming_technology.player_achievements pa3\n     WHERE pa3.player_id = pa1.player_id\n       AND pa3.unlocked_at > pa1.unlocked_at\n )\nWHERE pa2.unlocked_at - pa1.unlocked_at < INTERVAL '48 hours'\nORDER BY pa1.player_id ASC, pa1.unlocked_at ASC;"}, {"role": "user", "content": "Finally, limit to 20 rows."}, {"role": "assistant", "content": "SELECT pa1.player_id,\n       pa1.achievement_id AS current_ach,\n       pa1.unlocked_at AS current_unlocked_at,\n       pa2.achievement_id AS next_ach,\n       pa2.unlocked_at AS next_unlocked_at\nFROM gaming_technology.player_achievements pa1\nJOIN gaming_technology.player_achievements pa2\n  ON pa1.player_id = pa2.player_id\n AND pa2.unlocked_at = (\n     SELECT MIN(pa3.unlocked_at)\n     FROM gaming_technology.player_achievements pa3\n     WHERE pa3.player_id = pa1.player_id\n       AND pa3.unlocked_at > pa1.unlocked_at\n )\nWHERE pa2.unlocked_at - pa1.unlocked_at < INTERVAL '48 hours'\nORDER BY pa1.player_id ASC, pa1.unlocked_at ASC\nLIMIT 20;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.player_achievements ( player_achievement_id uuid, player_id uuid, achievement_id uuid, unlocked_at timestamp with time zone )\n"}
{"conversations": [{"role": "user", "content": "Find all medical records where the treatment plan includes 'physical therapy' and the patient has an active primary insurance plan, showing the patient ID, record date, and insurance provider details."}, {"role": "assistant", "content": "SELECT mr.patient_id, mr.record_date, i.provider_name, i.policy_number FROM healthcare.medical_records mr JOIN healthcare.patients p ON mr.patient_id = p.patient_id JOIN healthcare.insurance_plans i ON p.patient_id = i.patient_id WHERE mr.treatment_plan LIKE '%physical therapy%' AND i.is_primary = true AND i.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 healthcare.patients ( patient_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, gender character varying(10), address text, phone_number character varying(20), email character varying(128) UNIQUE, emergency_contact_name character varying(200), emergency_contact_phone character varying(20), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (patient_id) )\nCREATE TABLE healthcare.doctors ( doctor_id.text, first_name.text, last_name.text, specialty.text, license_number.text, phone_number.text, email.text, hospital_affiliation_id.text, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE healthcare.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 PRIMARY KEY, record_id text, patient_id text, doctor_id text, diagnosis_code text, code_type text, description text, diagnosis_date date, status text, is_chronic boolean )\nCREATE TABLE healthcare.medications (\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 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": "I would like to see a list of all medical records where the chief complaint contains the word 'cough' along with the doctor's ID and the date of the record."}, {"role": "assistant", "content": "SELECT record_id, doctor_id, record_date, chief_complaint FROM healthcare.medical_records WHERE chief_complaint ILIKE '%cough%';"}, {"role": "user", "content": "Could you expand this to show only records where the temperature in the vitals field is above 37.5°C?"}, {"role": "assistant", "content": "SELECT record_id, doctor_id, record_date, chief_complaint, vitals->>'temperature' AS temperature FROM healthcare.medical_records WHERE chief_complaint ILIKE '%cough%' AND (vitals->>'temperature')::float > 37.5;"}, {"role": "user", "content": "Now, restrict it further to only show records documented after January 1st, 2024."}, {"role": "assistant", "content": "SELECT record_id, doctor_id, record_date, chief_complaint, vitals->>'temperature' AS temperature FROM healthcare.medical_records WHERE chief_complaint ILIKE '%cough%' AND (vitals->>'temperature')::float > 37.5 AND record_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 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": "I want a list of all claims where at least one document is larger than 2 megabytes. Include the claim ID, incident date, and the file name of such documents."}, {"role": "assistant", "content": "SELECT c.claim_id, c.incident_date, d.file_name\nFROM insurance.claims c\nJOIN insurance.claim_documents d ON c.claim_id = d.claim_id\nWHERE d.file_size_bytes > 2097152;"}, {"role": "user", "content": "Actually, please also show the document type and only include documents uploaded after June 1, 2024."}, {"role": "assistant", "content": "SELECT c.claim_id, c.incident_date, d.file_name, d.document_type\nFROM insurance.claims c\nJOIN insurance.claim_documents d ON c.claim_id = d.claim_id\nWHERE d.file_size_bytes > 2097152\n  AND d.uploaded_at > '2024-06-01';"}, {"role": "user", "content": "Add the file size in kilobytes and order the results by file size descending."}, {"role": "assistant", "content": "SELECT c.claim_id, c.incident_date, d.file_name, d.document_type, (d.file_size_bytes/1024) AS file_size_kb\nFROM insurance.claims c\nJOIN insurance.claim_documents d ON c.claim_id = d.claim_id\nWHERE d.file_size_bytes > 2097152\n  AND d.uploaded_at > '2024-06-01'\nORDER BY d.file_size_bytes DESC;"}, {"role": "user", "content": "Sorry, I'm getting some records where file_size_bytes is NULL. Please exclude those from the results."}, {"role": "assistant", "content": "SELECT c.claim_id, c.incident_date, d.file_name, d.document_type, (d.file_size_bytes/1024) AS file_size_kb\nFROM insurance.claims c\nJOIN insurance.claim_documents d ON c.claim_id = d.claim_id\nWHERE d.file_size_bytes > 2097152\n  AND d.uploaded_at > '2024-06-01'\n  AND d.file_size_bytes IS NOT NULL\nORDER BY d.file_size_bytes DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.claims ( claim_id text, policy_id text, customer_id text, incident_date timestamp, reported_date timestamp, description text, estimated_loss numeric, status text, settlement_amount numeric, settlement_date date, claim_handler_id text, police_report_number text )\nCREATE TABLE insurance.claim_documents ( document_id text PRIMARY KEY, claim_id text, document_type text, file_name text, file_path text, file_size_bytes int, mime_type text, uploaded_by text, uploaded_at timestamp, description text )\n"}
{"conversations": [{"role": "user", "content": "Show me the number of game servers in each region and the average maximum number of players they can accommodate. Exclude any servers that are currently offline."}, {"role": "assistant", "content": "SELECT region, COUNT(server_id) AS server_count, AVG(max_players) AS average_max_players FROM gaming_technology.servers WHERE status != 'offline' GROUP BY region;"}, {"role": "user", "content": "Please filter the results to only include regions that have more than 5 active servers."}, {"role": "assistant", "content": "SELECT region, COUNT(server_id) AS server_count, AVG(max_players) AS average_max_players FROM gaming_technology.servers WHERE status != 'offline' GROUP BY region HAVING COUNT(server_id) > 5;"}, {"role": "user", "content": "Can you also include the total number of current players across all active servers in each of those regions?"}, {"role": "assistant", "content": "SELECT region, COUNT(server_id) AS server_count, AVG(max_players) AS average_max_players, SUM(current_players) AS total_current_players FROM gaming_technology.servers WHERE status != 'offline' GROUP BY region HAVING COUNT(server_id) > 5;"}, {"role": "user", "content": "Order the final results by the total number of current players in descending order."}, {"role": "assistant", "content": "SELECT region, COUNT(server_id) AS server_count, AVG(max_players) AS average_max_players, SUM(current_players) AS total_current_players FROM gaming_technology.servers WHERE status != 'offline' GROUP BY region HAVING COUNT(server_id) > 5 ORDER BY total_current_players DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.players (\n    player_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the player\n    username character varying(100) NOT NULL UNIQUE, -- player's chosen display name\n    email character varying(255) NOT NULL UNIQUE, -- player's email address for login/recovery\n    password_hash text NOT NULL, -- securely hashed password\n    registration_date timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the player account was created\n    last_login timestamp with time zone, -- timestamp of the last successful login\n    country_code character(2), -- player's country (ISO 3166-1 alpha-2)\n    status character varying(20) NOT NULL DEFAULT 'active', -- account status (e.g., active, banned, suspended)\n    profile_data jsonb, -- flexible field for avatar url, bio, preferences etc.\n    PRIMARY KEY (player_id)\n)\nCREATE TABLE gaming_technology.games (\n    game_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game\n    title character varying(200) NOT NULL, -- official title of the game\n    developer_id uuid NOT NULL, -- FK linking to the developers table\n    publisher_id uuid, -- FK linking to a potential publishers table (optional)\n    genre character varying(100), -- primary genre (e.g., RPG, FPS, Strategy)\n    release_date date, -- official release date\n    description text, -- short description or synopsis of the game\n    platform character varying(50) NOT NULL, -- primary platform (e.g., PC, PlayStation 5, Xbox Series X, Mobile)\n    engine character varying(100), -- game engine used (e.g., Unreal Engine 5, Unity)\n    website character varying(255), -- official website URL\n    PRIMARY KEY (game_id)\n    -- FOREIGN KEY (developer_id) REFERENCES gaming_technology.developers(developer_id) -- Example FK constraint\n)\nCREATE TABLE gaming_technology.game_sessions (\n    session_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game session\n    player_id uuid NOT NULL, -- FK linking to the players table\n    game_id uuid NOT NULL, -- FK linking to the games table\n    server_id uuid, -- FK linking to the servers table (nullable for single-player)\n    start_time timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the session began\n    end_time timestamp with time zone, -- when the session ended (null if ongoing)\n    duration_seconds integer, -- calculated duration of the session in seconds\n    score integer, -- player's score for the session, if applicable\n    session_data jsonb, -- flexible field for session-specific info (e.g., map played, character used)\n    PRIMARY KEY (session_id)\n    -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n    -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id),\n    -- FOREIGN KEY (server_id) REFERENCES gaming_technology.servers(server_id)\n)\nCREATE TABLE gaming_technology.servers (\n    server_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game server instance\n    game_id uuid NOT NULL, -- FK linking to the game this server hosts\n    server_name character varying(150), -- display name for the server\n    region character varying(50) NOT NULL, -- geographical region (e.g., us-east-1, eu-west-2)\n    ip_address character varying(45), -- IP address (IPv4 or IPv6)\n    port integer, -- network port number\n    current_players integer NOT NULL DEFAULT 0, -- number of players currently connected\n    max_players integer NOT NULL, -- maximum player capacity\n    status character varying(30) NOT NULL DEFAULT 'offline', -- server status (e.g., online, offline, maintenance)\n    last_heartbeat timestamp with time zone, -- last time the server reported its status\n    PRIMARY KEY (server_id)\n    -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id)\n)\nCREATE TABLE gaming_technology.achievements (\n    achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for an achievement definition\n    game_id uuid NOT NULL, -- FK linking to the game the achievement belongs to\n    name character varying(150) NOT NULL, -- name of the achievement\n    description text NOT NULL, -- how to unlock the achievement\n    icon_url character varying(255), -- URL for the achievement's icon\n    points integer DEFAULT 0, -- points awarded for unlocking (optional)\n    hidden boolean DEFAULT false, -- whether the achievement details are hidden until unlocked\n    PRIMARY KEY (achievement_id)\n    -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id)\n)\nCREATE TABLE gaming_technology.player_achievements (\n    player_achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for this unlock instance\n    player_id uuid NOT NULL, -- FK linking to the player who unlocked it\n    achievement_id uuid NOT NULL, -- FK linking to the achievement definition\n    unlocked_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the achievement was unlocked\n    PRIMARY KEY (player_achievement_id),\n    UNIQUE (player_id, achievement_id) -- Ensure a player can only unlock an achievement once\n    -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n    -- FOREIGN KEY (achievement_id) REFERENCES gaming_technology.achievements(achievement_id)\n)\nCREATE TABLE gaming_technology.in_game_items (\n    item_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the item definition\n    game_id uuid NOT NULL, -- FK linking to the game this item belongs to\n    item_name character varying(150) NOT NULL, -- name of the item\n    item_type character varying(50) NOT NULL, -- type (e.g., Cosmetic, Consumable, Weapon, Armor)\n    description text, -- description of the item\n    rarity character varying(30), -- item rarity (e.g., Common, Rare, Epic, Legendary)\n    cost_currency character varying(10), -- currency code if purchasable (e.g., USD, EUR, GOLD)\n    cost_amount numeric(12, 2), -- price if purchasable\n    attributes jsonb, -- flexible field for item stats or properties\n    PRIMARY KEY (item_id)\n    -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id)\n)\nCREATE TABLE gaming_technology.player_inventory (\n    inventory_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for an inventory entry\n    player_id uuid NOT NULL, -- FK linking to the player owning the item\n    item_id uuid NOT NULL, -- FK linking to the item definition\n    quantity integer NOT NULL DEFAULT 1, -- number of items held (for stackable items)\n    acquired_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the item was acquired\n    instance_data jsonb, -- data specific to this instance (e.g., weapon mods, durability)\n    PRIMARY KEY (inventory_id),\n    -- Optional unique constraint if items are non-stackable or unique instances\n    -- UNIQUE (player_id, item_id) -- Use if quantity is always 1\n    -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n    -- FOREIGN KEY (item_id) REFERENCES gaming_technology.in_game_items(item_id)\n)\n"}
{"conversations": [{"role": "user", "content": "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": "List all agents who have been terminated, showing their full name, agency name, and termination date."}, {"role": "assistant", "content": "SELECT first_name, last_name, agency_name, termination_date\nFROM insurance.agents\nWHERE status <> 'Active';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.agents ( agent_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, agency_name character varying(150), license_number character varying(100) NOT NULL UNIQUE, license_state character varying(50) NOT NULL, contact_email character varying(128) UNIQUE, contact_phone character varying(30), hire_date date, termination_date date, status character varying(20) NOT NULL DEFAULT 'Active', commission_rate numeric(5, 4) NOT NULL DEFAULT 0.05, manager_id character varying(64), PRIMARY KEY (agent_id) )\n"}