{"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": "What is the history of incidents or accidents that occurred on platform 5 at station GHI?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information about the history of incidents or accidents on platform 5 at station GHI. My data is limited to the structural and operational details of the platforms, such as platform ID, station ID, and status. For incident history, you may need to consult a different database or contact the relevant authorities."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.platforms ( platform_id.text, station_id.text, platform_number.text, track_number.text, status.text, length_meters.numeric, accessible.boolean )\n"} {"conversations": [{"role": "user", "content": "Which chain has the highest total USD inflow from buy transactions (type=1), and how many distinct tokens were involved in that inflow?"}, {"role": "assistant", "content": "SELECT chain, SUM(usd_value) AS total_inflow, COUNT(DISTINCT token_symbol) AS distinct_tokens\nFROM smart_money_token_inflow\nWHERE type = 1\nGROUP BY chain\nORDER BY total_inflow DESC\nLIMIT 1;"}, {"role": "user", "content": "I also want to see the average price at which those tokens were bought for that chain."}, {"role": "assistant", "content": "WITH inflow AS (\n SELECT chain, SUM(usd_value) AS total_inflow\n FROM smart_money_token_inflow\n WHERE type = 1\n GROUP BY chain\n), top_chain AS (\n SELECT chain FROM inflow ORDER BY total_inflow DESC LIMIT 1\n)\nSELECT i.chain, AVG(i.avg_price) AS avg_buy_price\nFROM smart_money_token_inflow i\nJOIN top_chain t ON i.chain = t.chain\nWHERE i.type = 1;"}, {"role": "user", "content": "Actually, filter to narratives where the total USD inflow is above 50000."}, {"role": "assistant", "content": "SELECT narrative, SUM(usd_value) AS total_inflow, COUNT(DISTINCT token_symbol) AS distinct_tokens\nFROM smart_money_token_inflow\nWHERE type = 1\nGROUP BY narrative\nHAVING SUM(usd_value) > 50000;"}, {"role": "user", "content": "Please order the results by average price descending and show the top 2 chains."}, {"role": "assistant", "content": "SELECT chain, SUM(usd_value) AS total_inflow, COUNT(DISTINCT token_symbol) AS distinct_tokens, AVG(avg_price) AS avg_buy_price\nFROM smart_money_token_inflow\nWHERE type = 1\nGROUP BY chain\nORDER BY avg_buy_price DESC\nLIMIT 2;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE smart_money_token_inflow ( token_address text, token_symbol text, token_amount numeric, usd_value numeric, avg_price numeric, type numeric, address_amount numeric, narrative text, chain text )\n"} {"conversations": [{"role": "user", "content": "For each user, find the previous user by registration time. List current user_id and username, previous user_id and username, and the time difference in minutes between their registrations."}, {"role": "assistant", "content": "SELECT u.user_id AS current_user_id,\n u.username AS current_username,\n p.user_id AS previous_user_id,\n p.username AS previous_username,\n EXTRACT(EPOCH FROM (u.created_at - p.created_at)) / 60 AS diff_minutes\nFROM web3.users u\nJOIN web3.users p\n ON p.created_at = (\n SELECT MAX(created_at)\n FROM web3.users\n WHERE created_at < u.created_at\n )\nORDER BY u.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.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": "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": "Can you provide the total number of fuel refueling events and the sum of total_cost at each fueling location, including the location name and city?"}, {"role": "assistant", "content": "SELECT l.location_id, l.name, l.city, COUNT(fl.fuel_log_id) AS num_refuels, SUM(fl.total_cost) AS total_cost\nFROM transportation.fuel_logs fl\nJOIN transportation.locations l ON fl.location_id = l.location_id\nGROUP BY l.location_id, l.name, l.city;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles ( 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.fuel_logs ( fuel_log_id.text, vehicle_id.text, trip_id.text, log_timestamp.timestamp, fuel_type.text, quantity.numeric, unit.text, cost_per_unit.numeric, total_cost.numeric, odometer_reading.integer, location_id.text )\nCREATE TABLE transportation.bookings ( booking_id.text, passenger_id.text, trip_id.text, seat_number.text, booking_time.timestamp, status.text, fare.numeric, payment_transaction_id.text, special_requests.text )\n"} {"conversations": [{"role": "user", "content": "Find the names of service locations where services categorized as 'Licensing' have had appointments scheduled."}, {"role": "assistant", "content": "SELECT DISTINCT T1.location_name FROM service_locations AS T1 JOIN appointments AS T2 ON T1.location_id = T2.location_id JOIN services AS T3 ON T2.service_id = T3.service_id WHERE T3.category = 'Licensing';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.services (\n service_id character varying(64) NOT NULL, -- unique identifier for the service\n agency_id character varying(64) NOT NULL, -- FK to agencies table\n service_name character varying(255) NOT NULL, -- name of the service (e.g., Driver's License Renewal)\n description text,\n category character varying(100), -- e.g., Licensing, Benefits, Taxation, Permits\n eligibility_criteria text, -- description of who is eligible\n standard_fee numeric(10, 2) DEFAULT 0.00, -- typical fee for the service\n average_processing_time_days integer, -- estimated processing time\n is_active boolean DEFAULT true, -- whether the service is currently offered\n online_application_url character varying(255),\n PRIMARY KEY (service_id)\n)\nCREATE TABLE government_services.service_locations (\n location_id character varying(64) NOT NULL, -- unique identifier for the physical location\n agency_id character varying(64) NOT NULL, -- FK to agencies table\n location_name character varying(200), -- e.g., Downtown DMV Office\n address text NOT NULL,\n city character varying(100),\n state character varying(50),\n postal_code character varying(20),\n latitude numeric(9, 6),\n longitude numeric(9, 6),\n operating_hours text, -- description of opening times\n contact_phone character varying(32),\n is_accessible boolean, -- accessibility information (e.g., wheelchair access)\n PRIMARY KEY (location_id)\n)\nCREATE TABLE government_services.appointments (\n appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment\n citizen_id character varying(64) NOT NULL, -- FK to citizens table\n employee_id character varying(64), -- FK to employees table (optional, if assigned)\n location_id character varying(64), -- FK to service_locations table (if physical)\n service_id character varying(64), -- FK to services table (optional, if related to specific service)\n scheduled_start_time timestamp NOT NULL,\n scheduled_end_time timestamp,\n purpose text NOT NULL, -- reason for the appointment\n status character varying(30) NOT NULL, -- e.g., Scheduled, Completed, Cancelled, No-Show\n booking_method character varying(50), -- e.g., Online, Phone, In-Person\n created_at timestamp NOT NULL, -- when the appointment was booked\n notes text,\n PRIMARY KEY (appointment_id)\n)\n"} {"conversations": [{"role": "user", "content": "Find all pairs of different insurance records that share the same group_number, and show group_number, the patient_insurance_id of both records, and their corresponding patient_ids."}, {"role": "assistant", "content": "SELECT a.group_number,\n a.patient_insurance_id AS pi_id1,\n a.patient_id AS patient1_id,\n b.patient_insurance_id AS pi_id2,\n b.patient_id AS patient2_id\nFROM healthcare.patient_insurance a\nJOIN healthcare.patient_insurance b\n ON a.group_number = b.group_number\n AND a.patient_insurance_id < b.patient_insurance_id\nWHERE a.group_number IS NOT NULL;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id text, patient_id text, plan_id text, policy_number text, group_number text, subscriber_name text, effective_date date, expiration_date date, is_primary boolean )\n"} {"conversations": [{"role": "user", "content": "What is the average ROI and average realized_ratio for each chain?"}, {"role": "assistant", "content": "SELECT chain,\n AVG(roi) AS avg_roi,\n AVG(realized_ratio) AS avg_realized_ratio\nFROM smart_money_token_performance\nGROUP BY chain;"}, {"role": "user", "content": "Now filter to only include chains where average ROI is above 0.5."}, {"role": "assistant", "content": "WITH stats AS (\n SELECT chain,\n AVG(roi) AS avg_roi,\n AVG(realized_ratio) AS avg_realized_ratio\n FROM smart_money_token_performance\n GROUP BY chain\n)\nSELECT chain, avg_roi, avg_realized_ratio\nFROM stats\nWHERE avg_roi > 0.5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE smart_money_token_performance ( token_address text, token_symbol text, pnl numeric, net_flow numeric, avg_cost numeric, price numeric, realized_ratio numeric, roi numeric, chain text )\n"} {"conversations": [{"role": "user", "content": "List all patients who have insurance plans with group numbers, showing their patient IDs and the count of such plans per patient."}, {"role": "assistant", "content": "SELECT patient_id, COUNT(*) AS plan_count FROM healthcare.patient_insurance WHERE group_number IS NOT NULL GROUP BY patient_id;"}, {"role": "user", "content": "Actually, I only need patients who have more than 2 such plans."}, {"role": "assistant", "content": "SELECT patient_id, COUNT(*) AS plan_count FROM healthcare.patient_insurance WHERE group_number IS NOT NULL GROUP BY patient_id HAVING COUNT(*) > 2;"}, {"role": "user", "content": "Can you also include the earliest effective date among these plans for each patient?"}, {"role": "assistant", "content": "SELECT patient_id, COUNT(*) AS plan_count, MIN(effective_date) AS earliest_effective_date FROM healthcare.patient_insurance WHERE group_number IS NOT NULL GROUP BY patient_id HAVING COUNT(*) > 2;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patient_insurance (\n patient_insurance_id character varying(64) NOT NULL, -- unique identifier for this patient-plan link\n patient_id character varying(64) NOT NULL, -- FK to patients table\n plan_id character varying(64) NOT NULL, -- FK to insurance_plans table\n policy_number character varying(100) NOT NULL, -- patient's policy number\n group_number character varying(100), -- group number, if applicable\n subscriber_name character varying(200), -- name of the primary policy holder\n effective_date date NOT NULL, -- date the coverage begins\n expiration_date date, -- date the coverage ends (if known)\n is_primary boolean NOT NULL DEFAULT true, -- indicates if this is the primary insurance\n PRIMARY KEY (patient_insurance_id),\n UNIQUE (patient_id, plan_id, policy_number) -- ensure a patient doesn't have the same policy twice\n)\n"} {"conversations": [{"role": "user", "content": "List the full name (first name and last name) of all citizens who have uploaded documents whose expiry date is in the past."}, {"role": "assistant", "content": "SELECT DISTINCT T1.first_name, T1.last_name FROM government_services.citizens AS T1 INNER JOIN government_services.documents AS T2 ON T1.citizen_id = T2.citizen_id WHERE T2.expiry_date < CURRENT_DATE;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id text PRIMARY KEY, national_id_number text, first_name text, last_name text, date_of_birth date, gender text, primary_address text, contact_email text, contact_phone text, registration_date timestamp, is_verified boolean )\nCREATE TABLE government_services.agencies ( agency_id text PRIMARY KEY, agency_name text, jurisdiction_level text, primary_contact_email text, main_phone_number text, website_url text, established_date date, parent_agency_id text )\nCREATE TABLE government_services.documents ( document_id text PRIMARY KEY, application_id text, citizen_id text, document_type text, file_reference text, upload_timestamp timestamp, expiry_date date, verification_status text, verified_by_employee_id text, verification_timestamp timestamp )\nCREATE TABLE government_services.payments ( payment_id text PRIMARY KEY, application_id text, citizen_id text, service_id text, amount numeric, currency text, payment_method text, payment_provider_reference text, payment_timestamp timestamp, status text, notes text )\nCREATE TABLE government_services.service_locations ( location_id text PRIMARY KEY, agency_id text, location_name text, address text, city text, state text, postal_code text, latitude numeric, longitude numeric, operating_hours text, contact_phone text, is_accessible boolean )\nCREATE TABLE government_services.appointments ( appointment_id text PRIMARY KEY, citizen_id text, employee_id text, location_id text, service_id text, scheduled_start_time timestamp, scheduled_end_time timestamp, purpose text, status text, booking_method text, created_at timestamp, notes text )\n"} {"conversations": [{"role": "user", "content": "Show 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": "List all payments for reservations made at properties with a star rating of 5.0. Include the payment amount, guest ID, reservation ID, and property name."}, {"role": "assistant", "content": "SELECT T1.amount, T1.guest_id, T1.reservation_id, T3.property_name FROM hospitality_technology.payments AS T1 JOIN hospitality_technology.reservations AS T2 ON T1.reservation_id = T2.reservation_id JOIN hospitality_technology.properties AS T3 ON T2.property_id = T3.property_id WHERE T3.star_rating = 5.0"}], "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 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.reservations ( reservation_id text, property_id text, guest_id text, room_id text, room_type_id text, check_in_date date, check_out_date date, actual_check_in_ts timestamp, actual_check_out_ts timestamp, num_adults integer, num_children integer, status text, booking_source text, rate_plan_id text, total_amount numeric, amount_paid numeric, special_requests text, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.staff ( staff_id text, property_id text, first_name text, last_name text, position text, work_email text, work_phone text, hire_date date, termination_date date, is_active boolean, access_level integer, manager_id text, created_at timestamp )\nCREATE TABLE hospitality_technology.services ( service_id text, property_id text, service_name text, description text, category text, price numeric, unit text, is_available boolean, department text )\nCREATE TABLE hospitality_technology.payments ( payment_id text, reservation_id text, guest_id text, bill_id text, amount numeric, currency_code text, payment_method text, card_type text, card_last_four text, transaction_ref text, payment_timestamp timestamp, status text, staff_id_processed text, notes text )\nCREATE TABLE hospitality_technology.reviews ( review_id text, property_id text, reservation_id text, guest_id text, rating_overall integer, rating_cleanliness integer, rating_service integer, rating_location integer, rating_value integer, comment text, review_source text, review_date timestamp, is_public boolean, staff_response text, response_staff_id text, response_date timestamp )\n"} {"conversations": [{"role": "user", "content": "For each service location, find its nearest accessible location by geographic distance."}, {"role": "assistant", "content": "SELECT sl.location_id,\n sl.location_name,\n nearest.location_id AS nearest_location_id,\n nearest.location_name AS nearest_location_name\nFROM government_services.service_locations sl\nJOIN LATERAL (\n SELECT sl2.location_id,\n sl2.location_name\n FROM government_services.service_locations sl2\n WHERE sl2.is_accessible = TRUE\n AND sl2.location_id <> sl.location_id\n ORDER BY ((sl.latitude - sl2.latitude)^2 + (sl.longitude - sl2.longitude)^2) ASC\n LIMIT 1\n) AS nearest ON TRUE;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.service_locations ( location_id.text, agency_id.text, location_name.text, address.text, city.text, state.text, postal_code.text, latitude.numeric, longitude.numeric, operating_hours.text, contact_phone.text, is_accessible.boolean )\n"} {"conversations": [{"role": "user", "content": "Which routes have their origin and destination in the same city? Show the route number, description, and the origin and destination location IDs."}, {"role": "assistant", "content": "SELECT r.route_number, r.description, r.origin_location_id, r.destination_location_id\nFROM transportation.routes r\nJOIN transportation.routes r2 ON r.origin_location_id = r2.destination_location_id AND r.route_id = r2.route_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.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": "Show me the average market cap and average 24-hour price change percentage for tokens on each chain."}, {"role": "assistant", "content": "SELECT chain, AVG(market_cap) AS average_market_cap, AVG(price_change_percentage_24h) AS average_price_change_24h FROM token_basic_info GROUP BY chain;"}, {"role": "user", "content": "Now, only show chains where the average market cap is greater than 1,000,000,000."}, {"role": "assistant", "content": "SELECT chain, AVG(market_cap) AS average_market_cap, AVG(price_change_percentage_24h) AS average_price_change_24h FROM token_basic_info GROUP BY chain HAVING AVG(market_cap) > 1000000000;"}, {"role": "user", "content": "Also, order the results by average market cap in descending order."}, {"role": "assistant", "content": "SELECT chain, AVG(market_cap) AS average_market_cap, AVG(price_change_percentage_24h) AS average_price_change_24h FROM token_basic_info GROUP BY chain HAVING AVG(market_cap) > 1000000000 ORDER BY average_market_cap DESC;"}, {"role": "user", "content": "Can you also include the total number of tokens for each of these chains?"}, {"role": "assistant", "content": "SELECT chain, COUNT(*) AS number_of_tokens, AVG(market_cap) AS average_market_cap, AVG(price_change_percentage_24h) AS average_price_change_24h FROM token_basic_info GROUP BY chain HAVING AVG(market_cap) > 1000000000 ORDER BY average_market_cap 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 token_basic_info ( coin_id character varying(100) NOT NULL, token_name character varying(100) NOT NULL, token_symbol character varying(100) NOT NULL, token_address character varying(100) NOT NULL, chain text, price double precision, price_change_percentage_1h double precision, price_change_percentage_24h double precision, price_change_percentage_7d double precision, highest_price_24h double precision, lowest_price_24h double precision, market_cap double precision, market_cap_rank bigint, market_cap_change_percentage_24h text, total_volume text, narrative text, trend_rank bigint )\n"} {"conversations": [{"role": "user", "content": "Show me the wallet addresses holding the ERC20 token with contract address '0xabcdeffedcba9876543210abcdefedcba9876'. Include the amount they hold."}, {"role": "assistant", "content": "SELECT wallet_address, amount FROM erc20_balances WHERE contract_address = '0xabcdeffedcba9876543210abcdefedcba9876';"}, {"role": "user", "content": "Instead of contract address, can you do this for a token symbol like 'USDC'?"}, {"role": "assistant", "content": "SELECT eb.wallet_address, eb.amount FROM erc20_balances eb JOIN token_metas tm ON eb.contract_address = tm.contract_address WHERE tm.symbol = 'USDC' AND tm.is_erc20 = 1;"}, {"role": "user", "content": "Filter the results to only show wallets holding more than 1000 of this token."}, {"role": "assistant", "content": "SELECT eb.wallet_address, eb.amount FROM erc20_balances eb JOIN token_metas tm ON eb.contract_address = tm.contract_address WHERE tm.symbol = 'USDC' AND tm.is_erc20 = 1 AND CAST(eb.amount AS DECIMAL) > 1000;"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nCREATE TABLE token_metas ( block_timestamp timestamp, block_number bigint, transaction_hash text, transaction_index bigint, from_address text, contract_address text, symbol text, total_supply text, name text, decimals bigint, is_erc20 integer, is_erc721 integer, is_erc1155 integer, is_proxy integer, extra_info text, pk integer )\nCREATE TABLE erc1155_approval_for_all ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash text, log_index integer, contract_address text )\nCREATE TABLE erc20_balances ( block_number bigint, contract_address text, wallet_address text, amount text, pk text )\nCREATE TABLE erc20_balances_historical ( block_number bigint, contract_address text, wallet_address text, amount text, pk integer )\nCREATE TABLE nft_holders ( block_number bigint, contract_address text, wallet_address text, token_id text, contract_type text, amount text, pk text )\nCREATE TABLE sui_coins_metadata ( object_id text, coin_type text, status text, decimals bigint, description text, icon_url text, symbol text, name text )\nCREATE TABLE sui_nfts ( object_id text, status text, collection_type text, package_id text, previous_transaction text, display text, owner text, name text )\nCREATE TABLE nft_metadata ( blockchain text, contract_address text, token_id text, contract_name text, erc_type text, amount bigint, minter text, owner text, mint_block_number bigint, mint_time bigint, mint_transaction_hash text, mint_price text, token_uri text, metadata text, name text, image_uri text, traits text, updated_at bigint, status text, rarity_score real, rarity_rank integer, unique_attribute_count integer, pk integer )\nCREATE TABLE nft_collections ( blockchain text, contract_address text, name text, symbol text, deploy_block_number bigint, deploy_block_time bigint, erc_type text, owner text, traits text, description text, slug text, media_info text, image_url text, banner_image_url text, updated_at bigint, banner text, token_count bigint, floor_price text, floor_price_symbol text, floor_price_contract text, pk integer )\nCREATE TABLE token_prices_latest ( blockchain text, address text, decimals bigint, symbol text, price real, timestamp timestamp )\nCREATE TABLE token_info ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text )\nCREATE TABLE token_activities ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE mud_holesky_redstone ( address text, table_id text, key_bytes text, key0 text, key1 text, static_data text, encoded_lengths text, dynamic_data text, is_deleted boolean, block_number bigint, log_index bigint )\nCREATE TABLE token_balances_bitcoin ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply text, amount text )\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id text )\n"} {"conversations": [{"role": "user", "content": "Show each asset's symbol and the number of unique addresses that have UTXOs associated with it."}, {"role": "assistant", "content": "SELECT a.symbol, COUNT(DISTINCT u.address) AS unique_addresses\nFROM trading_platform.assets a\nJOIN trading_platform.utxos u ON a.asset_id = u.transaction_id\nGROUP BY a.asset_id, a.symbol;"}, {"role": "user", "content": "Now show only assets with more than 5 unique addresses."}, {"role": "assistant", "content": "SELECT a.symbol, COUNT(DISTINCT u.address) AS unique_addresses\nFROM trading_platform.assets a\nJOIN trading_platform.utxos u ON a.asset_id = u.transaction_id\nGROUP BY a.asset_id, a.symbol\nHAVING COUNT(DISTINCT u.address) > 5;"}, {"role": "user", "content": "Please also include the total amount for each asset in the result."}, {"role": "assistant", "content": "SELECT a.symbol, COUNT(DISTINCT u.address) AS unique_addresses, COALESCE(SUM(u.amount), 0) AS total_amount\nFROM trading_platform.assets a\nJOIN trading_platform.utxos u ON a.asset_id = u.transaction_id\nGROUP BY a.asset_id, a.symbol\nHAVING COUNT(DISTINCT u.address) > 5;"}, {"role": "user", "content": "Order the results by total_amount ascending and limit to the top 3."}, {"role": "assistant", "content": "SELECT a.symbol, COUNT(DISTINCT u.address) AS unique_addresses, COALESCE(SUM(u.amount), 0) AS total_amount\nFROM trading_platform.assets a\nJOIN trading_platform.utxos u ON a.asset_id = u.transaction_id\nGROUP BY a.asset_id, a.symbol\nHAVING COUNT(DISTINCT u.address) > 5\nORDER BY total_amount ASC\nLIMIT 3;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.users (\n user_id character varying(64) NOT NULL, -- unique identifier for the user\n username character varying(128) NOT NULL, -- username of the user\n email character varying(128) NOT NULL, -- email address of the user\n password_hash text NOT NULL, -- hashed password of the user\n created_at timestamp NOT NULL, -- time when the user account was created\n PRIMARY KEY (user_id)\n)\nCREATE TABLE trading_platform.assets ( asset_id text, name text, symbol text, type text )\nCREATE TABLE trading_platform.utxos ( utxo_id text PRIMARY KEY, transaction_id text, output_index int, address text, amount numeric, spent boolean )\nCREATE TABLE trading_platform.metadata ( metadata_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, key character varying(128) NOT NULL, value text NOT NULL, PRIMARY KEY (metadata_id) )\n"} {"conversations": [{"role": "user", "content": "Show me all contracts deployed on the 'ethereum' network along with their deployer addresses and deployment timestamps, sorted by the most recent deployments first."}, {"role": "assistant", "content": "SELECT address, deployer_address, deployed_at FROM web3.contracts WHERE network_id = 'ethereum' ORDER BY deployed_at DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.contracts ( contract_id text, address text, abi text, bytecode text, deployer_address text, deployed_at timestamp, network_id text, status text )\n"} {"conversations": [{"role": "user", "content": "For each vehicle, show the first and last fueling events including their timestamps and the quantities refueled."}, {"role": "assistant", "content": "WITH first_last AS (\n SELECT\n vehicle_id,\n MIN(log_timestamp) AS first_time,\n MAX(log_timestamp) AS last_time\n FROM transportation.fuel_logs\n GROUP BY vehicle_id\n)\nSELECT\n f1.vehicle_id,\n f1.log_timestamp AS first_refuel_time,\n f1.quantity AS first_quantity,\n f2.log_timestamp AS last_refuel_time,\n f2.quantity AS last_quantity\nFROM first_last fl\nJOIN transportation.fuel_logs f1\n ON fl.vehicle_id = f1.vehicle_id\n AND fl.first_time = f1.log_timestamp\nJOIN transportation.fuel_logs f2\n ON fl.vehicle_id = f2.vehicle_id\n AND fl.last_time = f2.log_timestamp;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.fuel_logs (\n fuel_log_id character varying(64) NOT NULL, -- unique identifier for the fuel log entry\n vehicle_id character varying(64) NOT NULL, -- identifier of the vehicle fueled\n trip_id character varying(64), -- optional: identifier of the trip during which fueling occurred\n log_timestamp timestamp with time zone NOT NULL, -- time when fueling occurred\n fuel_type character varying(32) NOT NULL, -- type of fuel added (matches vehicle's fuel type)\n quantity numeric(10, 3) NOT NULL, -- amount of fuel added (e.g., Liters, Gallons, kWh)\n unit character varying(16) NOT NULL, -- unit of quantity (e.g., L, gal, kWh)\n cost_per_unit numeric(8, 4), -- price per unit of fuel\n total_cost numeric(10, 2) NOT NULL, -- total cost of the fuel purchase\n odometer_reading integer, -- vehicle mileage at time of fueling\n location_id character varying(64), -- identifier of the fueling station/location\n PRIMARY KEY (fuel_log_id)\n)\n"} {"conversations": [{"role": "user", "content": "Find all patients who have been prescribed medications with dosage greater than 50mg, along with their medication details and prescribing doctor's name."}, {"role": "assistant", "content": "SELECT p.patient_id, p.first_name, p.last_name, pr.dosage, pr.medication_id, pr.start_date, doc.first_name AS doctor_first_name, doc.last_name AS doctor_last_name FROM healthcare.patients p JOIN healthcare.prescriptions pr ON p.patient_id = pr.patient_id JOIN healthcare.doctors doc ON pr.doctor_id = doc.doctor_id WHERE CAST(SUBSTRING_INDEX(pr.dosage, 'mg', 1) AS UNSIGNED) > 50;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id.text, first_name.text, last_name.text, date_of_birth.date, gender.text, address.text, phone_number.text, email.text, emergency_contact_name.text, emergency_contact_phone.text, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE healthcare.appointments ( appointment_id.text, patient_id.text, doctor_id.text, appointment_time.timestamp, duration_minutes.integer, reason.text, status.text, location_id.text, notes.text, created_at.timestamp )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id.text, record_id.text, patient_id.text, doctor_id.text, diagnosis_code.text, code_type.text, description.text, diagnosis_date.date, status.text, is_chronic.boolean )\nCREATE TABLE healthcare.prescriptions ( prescription_id.text, record_id.text, patient_id.text, doctor_id.text, medication_id.text, dosage.text, frequency.text, route.text, start_date.date, end_date.date, quantity_dispensed.numeric, refills_allowed.integer, prescription_date.timestamp )\nCREATE TABLE healthcare.insurance_plans ( plan_id.text, plan_name.text, insurance_provider.text, plan_type.text, contact_phone.text, website.text )\n"} {"conversations": [{"role": "user", "content": "What is the schedule of trains arriving at station with ID 'ST789' tomorrow?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide the train schedule for station ID 'ST789' as this information is not available in the current database. The table only contains details about station attributes such as name, location, and number of platforms. For train schedules, please refer to the relevant train service provider or timetable database."}], "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": "Calculate the average payment amount for all completed payments associated with services categorized as 'Healthcare'."}, {"role": "assistant", "content": "SELECT AVG(T1.amount) FROM government_services.payments AS T1 INNER JOIN government_services.applications AS T2 ON T1.application_id = T2.application_id INNER JOIN government_services.services AS T3 ON T2.service_id = T3.service_id WHERE T1.status = 'Completed' AND T3.category = 'Healthcare';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id.text, national_id_number.text, first_name.text, last_name.text, date_of_birth.date, gender.text, primary_address.text, contact_email.text, contact_phone.text, registration_date.timestamp, is_verified.boolean )\nCREATE TABLE government_services.agencies ( agency_id.text, agency_name.text, jurisdiction_level.text, primary_contact_email.text, main_phone_number.text, website_url.text, established_date.date, parent_agency_id.text )\nCREATE TABLE government_services.services ( service_id.text, agency_id.text, service_name.text, description.text, category.text, eligibility_criteria.text, standard_fee.numeric, average_processing_time_days.integer, is_active.boolean, online_application_url.text )\nCREATE TABLE government_services.applications ( application_id.text, citizen_id.text, service_id.text, submitted_at.timestamp, status.text, last_updated_at.timestamp, assigned_employee_id.text, decision_date.date, notes.text, reference_number.text )\nCREATE TABLE government_services.payments ( payment_id.text, application_id.text, citizen_id.text, service_id.text, amount.numeric, currency.text, payment_method.text, payment_provider_reference.text, payment_timestamp.timestamp, status.text, notes.text )\nCREATE TABLE government_services.employees ( employee_id.text, agency_id.text, first_name.text, last_name.text, job_title.text, department.text, work_email.text, work_phone.text, hire_date.date, termination_date.date, access_level.text, manager_employee_id.text )\nCREATE TABLE government_services.notifications ( notification_id.text, citizen_id.text, application_id.text, message_subject.text, message_body.text, channel.text, sent_at.timestamp, status.text, related_entity_type.text, related_entity_id.text )\n"} {"conversations": [{"role": "user", "content": "Find all chronic diagnoses made by Cardiology doctors in the last year, including patient ID, diagnosis description, and doctor's full name."}, {"role": "assistant", "content": "SELECT di.patient_id, di.description, d.first_name || ' ' || d.last_name AS doctor_name, di.diagnosis_date FROM healthcare.diagnoses di JOIN healthcare.doctors d ON di.doctor_id = d.doctor_id WHERE di.is_chronic = true AND d.specialty = 'Cardiology' AND di.diagnosis_date >= CURRENT_DATE - INTERVAL '1 year' ORDER BY di.diagnosis_date DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.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": "Show me all prescriptions made by doctors who have issued diagnoses described as 'Hypertension'. Include the doctor's ID, prescription ID, medication ID, and prescription date."}, {"role": "assistant", "content": "SELECT p.doctor_id, p.prescription_id, p.medication_id, p.prescription_date\nFROM healthcare.prescriptions p\nJOIN healthcare.diagnoses d ON p.doctor_id = d.doctor_id\nWHERE d.description = 'Hypertension';"}, {"role": "user", "content": "Change it to only include those prescriptions that started after January 1st, 2024."}, {"role": "assistant", "content": "SELECT p.doctor_id, p.prescription_id, p.medication_id, p.prescription_date\nFROM healthcare.prescriptions p\nJOIN healthcare.diagnoses d ON p.doctor_id = d.doctor_id\nWHERE d.description = 'Hypertension' AND p.start_date > '2024-01-01';"}, {"role": "user", "content": "Actually, also include the patient ID and only show results where the doctor's diagnosis of 'Hypertension' happened before the prescription start date."}, {"role": "assistant", "content": "SELECT p.doctor_id, p.patient_id, p.prescription_id, p.medication_id, p.prescription_date\nFROM healthcare.prescriptions p\nJOIN healthcare.diagnoses d ON p.doctor_id = d.doctor_id AND p.patient_id = d.patient_id\nWHERE d.description = 'Hypertension' AND p.start_date > '2024-01-01' AND d.diagnosis_date < p.start_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.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.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": "Show me claims reported in 2024, including the claim ID, incident date, estimated loss, and the full name of the agent who handled it."}, {"role": "assistant", "content": "SELECT T1.claim_id, T1.incident_date, T1.estimated_loss, T2.first_name, T2.last_name FROM insurance.claims AS T1 JOIN insurance.agents AS T2 ON T1.claim_handler_id = T2.agent_id WHERE STRFTIME('%Y', T1.reported_date) = '2024';"}, {"role": "user", "content": "Could you also include the status of the agent who handled each claim?"}, {"role": "assistant", "content": "SELECT T1.claim_id, T1.incident_date, T1.estimated_loss, T2.first_name, T2.last_name, T2.status FROM insurance.claims AS T1 JOIN insurance.agents AS T2 ON T1.claim_handler_id = T2.agent_id WHERE STRFTIME('%Y', T1.reported_date) = '2024';"}, {"role": "user", "content": "Actually, only show records where the claim status is 'Open'."}, {"role": "assistant", "content": "SELECT T1.claim_id, T1.incident_date, T1.estimated_loss, T2.first_name, T2.last_name, T2.status FROM insurance.claims AS T1 JOIN insurance.agents AS T2 ON T1.claim_handler_id = T2.agent_id WHERE STRFTIME('%Y', T1.reported_date) = '2024' AND T1.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 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.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 patient_id, first_name, last_name, and date_of_birth for all patients older than 65 years."}, {"role": "assistant", "content": "SELECT patient_id, first_name, last_name, date_of_birth\nFROM healthcare.patients\nWHERE date_of_birth < CURRENT_DATE - INTERVAL '65 years';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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.appointments ( appointment_id.text, patient_id.text, doctor_id.text, appointment_time.timestamp, duration_minutes.integer, reason.text, status.text, location_id.text, notes.text, created_at.timestamp )\nCREATE TABLE healthcare.medical_records ( record_id text PRIMARY KEY, patient_id text, appointment_id text, doctor_id text, record_date timestamp, chief_complaint text, present_illness_history text, past_medical_history text, physical_examination_notes text, assessment text, treatment_plan text, vitals text, created_at timestamp )\nCREATE TABLE healthcare.diagnoses (\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 PRIMARY KEY, 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 )\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": "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": "I need to find all bookings for a specific schedule with schedule_id 'sched_1122' and include the passenger and ticket details."}, {"role": "assistant", "content": "SMEMBERS schedule:sched_1122:bookings\nHGETALL booking:book_*\nHGETALL passenger:pass_*\nSMEMBERS booking:book_*:tickets\nHGETALL ticket:tkt_*"}, {"role": "user", "content": "Can you filter the tickets to show only those that are not checked in?"}, {"role": "assistant", "content": "SMEMBERS schedule:sched_1122:bookings\nHGETALL booking:book_*\nHGETALL passenger:pass_*\nSMEMBERS booking:book_*:tickets\nHGET ticket:tkt_* is_checked_in\nIF is_checked_in == 0 THEN\nHGETALL ticket:tkt_*\nENDIF"}, {"role": "user", "content": "Can you also include the car details for each ticket?"}, {"role": "assistant", "content": "SMEMBERS schedule:sched_1122:bookings\nHGETALL booking:book_*\nHGETALL passenger:pass_*\nSMEMBERS booking:book_*:tickets\nHGET ticket:tkt_* is_checked_in\nIF is_checked_in == 0 THEN\nHGETALL ticket:tkt_*\nHGET ticket:tkt_* car_id\nHGETALL car:car_*\nENDIF"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\n// Use Hashes for platform details. Key format: platform:\n// HSET platform:plat_123 platform_id \"plat_123\" station_id \"station_xyz\" platform_number \"1A\" track_number \"T1\" status \"Operational\" length_meters 250.50 accessible 1\n\n// To link platforms to stations (optional):\n// SADD station:station_xyz:platforms platform:plat_123 platform:plat_456\n// Use Hashes for train details. Key format: train:\n// HSET train:train_789 train_id \"train_789\" train_number \"Acela 2151\" model \"Siemens Velaro\" ... status \"Active\" ...\n\n// To find train by train_number (optional index):\n// SET train_number:\"Acela 2151\" train:train_789\n// Use Hashes for car details. Key format: car:\n// HSET car:car_abc car_id \"car_abc\" train_id \"train_789\" car_number \"C3\" car_type \"Passenger\" class \"Business\" capacity 60 features \"WiFi,Power Outlet\"\n\n// To link cars to trains (optional):\n// SADD train:train_789:cars car:car_abc car:car_def\n// Use Hashes for details. Key format: route_station:\n// HSET route_station:rs_ne_1 route_station_id \"rs_ne_1\" route_id \"route_ne_corr\" station_id \"station_bos\" sequence_order 1 ...\n\n// To find stops for a route, use a Sorted Set (score by sequence_order):\n// ZADD route:route_ne_corr:stops 1 route_station:rs_ne_1\n// ZADD route:route_ne_corr:stops 2 route_station:rs_ne_2\n// Use Hashes for schedule details. Key format: schedule:\n// HSET schedule:sched_1122 schedule_id \"sched_1122\" train_id \"train_789\" route_id \"route_ne_corr\" departure_datetime \"2024-05-10T08:00:00-04:00\" ... status \"Scheduled\"\n// Use Hashes for details. Key format: schedule_stop:\n// HSET schedule_stop:stop_sched1122_1 stop_id \"stop_sched1122_1\" schedule_id \"sched_1122\" station_id \"station_bos\" ...\n\n// To find stops for a schedule, use a Sorted Set (score by sequence_order):\n// ZADD schedule:sched_1122:stops 1 schedule_stop:stop_sched1122_1\n// ZADD schedule:sched_1122:stops 2 schedule_stop:stop_sched1122_2\n// Use Hashes for passenger details. Key format: passenger:\n// HSET passenger:pass_pqr passenger_id \"pass_pqr\" first_name \"Alice\" last_name \"Smith\" email \"alice.smith@example.com\" ...\n\n// To find passenger by email (optional index):\n// SET passenger_email:\"alice.smith@example.com\" passenger:pass_pqr\n// Use Hashes for booking details. Key format: booking:\n// HSET booking:book_zyx booking_id \"book_zyx\" passenger_id \"pass_pqr\" schedule_id \"sched_1122\" ... status \"Confirmed\" ...\n\n// To link bookings to passengers/schedules (optional):\n// SADD passenger:pass_pqr:bookings booking:book_zyx\n// SADD schedule:sched_1122:bookings booking:book_zyx\n// Use Hashes for ticket details. Key format: ticket:\n// HSET ticket:tkt_1a2b ticket_id \"tkt_1a2b\" booking_id \"book_zyx\" car_id \"car_abc\" seat_number \"12A\" ... is_checked_in 0 ...\n\n// To link tickets to bookings (optional):\n// SADD booking:book_zyx:tickets ticket:tkt_1a2b\n// Use Hashes for staff details. Key format: staff:\n// HSET staff:staff_mno staff_id \"staff_mno\" first_name \"Bob\" ... employee_number \"E12345\" ... is_active 1\n\n// To find staff by employee number (optional index):\n// SET staff_employee_number:\"E12345\" staff:staff_mno\n// Use Hashes for maintenance record details. Key format: maintenance_record:\n// HSET maintenance_record:maint_rec_001 record_id \"maint_rec_001\" asset_id \"train_789\" asset_type \"Train\" ... status \"Completed\"\n\n// To link records to assets (optional):\n// SADD train:train_789:maintenance maintenance_record:maint_rec_001\n// SADD platform:plat_123:maintenance maintenance_record:maint_rec_002\n"} {"conversations": [{"role": "user", "content": "List all unique actions that have been logged in the system."}, {"role": "assistant", "content": "SELECT DISTINCT action FROM trading_platform.logs;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.users ( user_id.text, username.text, email.text, password_hash.text, created_at.timestamp )\nCREATE TABLE trading_platform.wallets ( wallet_id text, user_id text, address text, private_key text, created_at timestamp )\nCREATE TABLE trading_platform.orders ( order_id text, user_id text, wallet_id text, asset_id text, order_type text, quantity numeric, price numeric, status text, created_at timestamp )\nCREATE TABLE trading_platform.trades ( trade_id character varying(64) NOT NULL, order_id character varying(64) NOT NULL, buyer_id character varying(64) NOT NULL, seller_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, quantity numeric(38,14) NOT NULL, price numeric(38,14) NOT NULL, traded_at timestamp NOT NULL, PRIMARY KEY (trade_id) )\nCREATE TABLE trading_platform.assets ( asset_id text, name text, symbol text, type text )\nCREATE TABLE trading_platform.dapps ( dapp_id text, name text, description text, url text )\nCREATE TABLE trading_platform.peers ( peer_id.text, ip_address.text, port.integer, last_seen.timestamp )\nCREATE TABLE trading_platform.metadata ( metadata_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, key character varying(128) NOT NULL, value text NOT NULL, PRIMARY KEY (metadata_id) )\nCREATE TABLE trading_platform.kyc_audit ( kyc_audit_id.text, user_id.text, status.text, reviewed_at.timestamp )\nCREATE TABLE trading_platform.logs ( log_id text PRIMARY KEY, user_id text, action text, details text, logged_at timestamp )\nCREATE TABLE trading_platform.notifications ( notification_id text, user_id text, message text, sent_at timestamp, read_at timestamp )\n"} {"conversations": [{"role": "user", "content": "List all tokens with a price below $1 and a 24-hour trading volume over $5 million."}, {"role": "assistant", "content": "SELECT token_name, token_symbol, price, total_volume FROM token_basic_info WHERE price < 1 AND total_volume::numeric > 5000000;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_basic_info ( coin_id character varying(100) NOT NULL, token_name character varying(100) NOT NULL, token_symbol character varying(100) NOT NULL, token_address character varying(100) NOT NULL, chain text, price double precision, price_change_percentage_1h double precision, price_change_percentage_24h double precision, price_change_percentage_7d double precision, highest_price_24h double precision, lowest_price_24h double precision, market_cap double precision, market_cap_rank bigint, market_cap_change_percentage_24h text, total_volume text, narrative text, trend_rank bigint )\n"} {"conversations": [{"role": "user", "content": "Provide a count of citizens registered per calendar year."}, {"role": "assistant", "content": "SELECT CAST(EXTRACT(YEAR FROM registration_date) AS INTEGER) AS registration_year, COUNT(*) AS citizen_count FROM government_services.citizens GROUP BY 1 ORDER BY 1;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens (\n citizen_id character varying(64) NOT NULL, -- unique identifier for the citizen\n national_id_number character varying(128) NOT NULL UNIQUE, -- official national identification number\n first_name character varying(100) NOT NULL,\n last_name character varying(100) NOT NULL,\n date_of_birth date NOT NULL,\n gender character varying(20),\n primary_address text NOT NULL, -- full primary residential address\n contact_email character varying(128) UNIQUE,\n contact_phone character varying(32),\n registration_date timestamp NOT NULL, -- when the citizen profile was created\n is_verified boolean DEFAULT false, -- whether identity has been officially verified\n PRIMARY KEY (citizen_id)\n)\n"} {"conversations": [{"role": "user", "content": "List every diagnosis description paired with every insurance plan's website."}, {"role": "assistant", "content": "SELECT T1.description, T2.website FROM healthcare.diagnoses AS T1 CROSS JOIN healthcare.insurance_plans AS T2;"}, {"role": "user", "content": "Only include chronic diagnoses and plans whose website ends with '.org'."}, {"role": "assistant", "content": "SELECT T1.description, T2.website FROM healthcare.diagnoses AS T1 CROSS JOIN healthcare.insurance_plans AS T2 WHERE T1.is_chronic = true AND T2.website LIKE '%.org';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.diagnoses ( diagnosis_id character varying(64) NOT NULL, record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, doctor_id character varying(64) NOT NULL, diagnosis_code character varying(20) NOT NULL, code_type character varying(10) NOT NULL DEFAULT 'ICD-10', description text, diagnosis_date date NOT NULL, status character varying(32) NOT NULL, is_chronic boolean DEFAULT false, PRIMARY KEY (diagnosis_id) )\nCREATE TABLE healthcare.insurance_plans ( plan_id text PRIMARY KEY, plan_name text, insurance_provider text, plan_type text, contact_phone text, website text )\n"} {"conversations": [{"role": "user", "content": "List the first name, last name, prescription ID, diagnosis code, and diagnosis description for patients who have both an ongoing prescription and an active chronic diagnosis."}, {"role": "assistant", "content": "SELECT DISTINCT T1.first_name, T1.last_name, T2.prescription_id, T3.diagnosis_code, T3.description FROM healthcare.patients AS T1 JOIN healthcare.prescriptions AS T2 ON T1.patient_id = T2.patient_id JOIN healthcare.diagnoses AS T3 ON T1.patient_id = T3.patient_id WHERE (T2.end_date IS NULL OR T2.end_date > CURRENT_DATE) AND T3.is_chronic IS TRUE AND T3.status = 'Active';"}, {"role": "user", "content": "Refine the results to include only those cases where the prescription started within 30 days before or on the diagnosis date."}, {"role": "assistant", "content": "SELECT DISTINCT T1.first_name, T1.last_name, T2.prescription_id, T3.diagnosis_code, T3.description FROM healthcare.patients AS T1 JOIN healthcare.prescriptions AS T2 ON T1.patient_id = T2.patient_id JOIN healthcare.diagnoses AS T3 ON T1.patient_id = T3.patient_id WHERE (T2.end_date IS NULL OR T2.end_date > CURRENT_DATE) AND T3.is_chronic IS TRUE AND T3.status = 'Active' AND T2.start_date BETWEEN T3.diagnosis_date - INTERVAL '30 days' AND T3.diagnosis_date;"}, {"role": "user", "content": "Add the full names of the doctor who wrote the prescription and the doctor who made the diagnosis to the results."}, {"role": "assistant", "content": "SELECT DISTINCT T1.first_name, T1.last_name, T2.prescription_id, T3.diagnosis_code, T3.description, T4.first_name AS prescribing_doctor_first_name, T4.last_name AS prescribing_doctor_last_name, T5.first_name AS diagnosing_doctor_first_name, T5.last_name AS diagnosing_doctor_last_name FROM healthcare.patients AS T1 JOIN healthcare.prescriptions AS T2 ON T1.patient_id = T2.patient_id JOIN healthcare.diagnoses AS T3 ON T1.patient_id = T3.patient_id JOIN healthcare.doctors AS T4 ON T2.doctor_id = T4.doctor_id JOIN healthcare.doctors AS T5 ON T3.doctor_id = T5.doctor_id WHERE (T2.end_date IS NULL OR T2.end_date > CURRENT_DATE) AND T3.is_chronic IS TRUE AND T3.status = 'Active' AND T2.start_date BETWEEN T3.diagnosis_date - INTERVAL '30 days' AND T3.diagnosis_date;"}, {"role": "user", "content": "Filter the results to only include diagnoses with a code type of 'ICD-9' and where either the prescribing or diagnosing doctor has a specialty in 'Cardiology'."}, {"role": "assistant", "content": "SELECT DISTINCT T1.first_name, T1.last_name, T2.prescription_id, T3.diagnosis_code, T3.description, T4.first_name AS prescribing_doctor_first_name, T4.last_name AS prescribing_doctor_last_name, T5.first_name AS diagnosing_doctor_first_name, T5.last_name AS diagnosing_doctor_last_name FROM healthcare.patients AS T1 JOIN healthcare.prescriptions AS T2 ON T1.patient_id = T2.patient_id JOIN healthcare.diagnoses AS T3 ON T1.patient_id = T3.patient_id JOIN healthcare.doctors AS T4 ON T2.doctor_id = T4.doctor_id JOIN healthcare.doctors AS T5 ON T3.doctor_id = T5.doctor_id WHERE (T2.end_date IS NULL OR T2.end_date > CURRENT_DATE) AND T3.is_chronic IS TRUE AND T3.status = 'Active' AND T2.start_date BETWEEN T3.diagnosis_date - INTERVAL '30 days' AND T3.diagnosis_date AND T3.code_type = 'ICD-9' AND (T4.specialty = 'Cardiology' OR T5.specialty = 'Cardiology');"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.doctors ( doctor_id text, first_name text, last_name text, specialty text, license_number text, phone_number text, email text, hospital_affiliation_id text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.appointments (\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 )\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 each insurance product's name and type, along with the number of active policies and the total premium_amount collected for those policies. Only include products that have at least one active policy."}, {"role": "assistant", "content": "SELECT p.product_name,\n p.product_type,\n COUNT(pl.policy_id) AS active_policy_count,\n SUM(pl.premium_amount) AS total_premium\nFROM insurance.insurance_products p\nJOIN insurance.policies pl ON p.product_id = pl.product_id\nWHERE pl.status = 'Active'\nGROUP BY p.product_name, p.product_type\nHAVING COUNT(pl.policy_id) > 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 insurance.customers ( customer_id text PRIMARY KEY, first_name text, last_name text, date_of_birth date, ssn_hash text, address_line1 text, address_line2 text, city text, state text, zip_code text, country text, phone_number text, email text, created_at timestamp, updated_at timestamp, status text )\nCREATE TABLE insurance.policies ( policy_id text 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 )\nCREATE TABLE insurance.claims ( claim_id text PRIMARY KEY, policy_id text, customer_id text, incident_date timestamp, reported_date timestamp, description text, estimated_loss numeric, status text, settlement_amount numeric, settlement_date date, claim_handler_id text, police_report_number text )\nCREATE TABLE insurance.insurance_products ( product_id text PRIMARY KEY, product_name text, product_type text, description text, base_premium numeric, coverage_details text, underwriting_rules text, is_active boolean, created_at timestamp, updated_at timestamp )\nCREATE TABLE insurance.premium_payments ( payment_id text PRIMARY KEY, policy_id text, customer_id text, payment_date timestamp, amount_paid numeric, payment_method text, transaction_reference text, due_date date, payment_period_start date, payment_period_end date, status text )\nCREATE TABLE insurance.claim_documents ( document_id text 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 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": "How many diagnoses does each status have grouped by is_chronic flag?"}, {"role": "assistant", "content": "SELECT is_chronic, status, COUNT(*) AS count FROM healthcare.diagnoses GROUP BY is_chronic, status;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.diagnoses ( diagnosis_id text, record_id text, patient_id text, doctor_id text, diagnosis_code text, code_type text, description text, diagnosis_date date, status text, is_chronic boolean )\n"} {"conversations": [{"role": "user", "content": "Provide a count of appointments grouped by the booking method."}, {"role": "assistant", "content": "SELECT booking_method, COUNT(*) AS appointment_count FROM government_services.appointments GROUP BY booking_method;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.documents (\n document_id character varying(64) NOT NULL, -- unique identifier for the document instance\n application_id character varying(64), -- FK to applications table (optional, could be linked to citizen directly)\n citizen_id character varying(64) NOT NULL, -- FK to citizens table\n document_type character varying(100) NOT NULL, -- e.g., Passport Scan, Proof of Address, Birth Certificate\n file_reference text NOT NULL, -- reference to the stored file (e.g., S3 URL, internal path)\n upload_timestamp timestamp NOT NULL,\n expiry_date date,\n verification_status character varying(30) DEFAULT 'Pending', -- e.g., Pending, Verified, Rejected\n verified_by_employee_id character varying(64), -- FK to employees table\n verification_timestamp timestamp,\n PRIMARY KEY (document_id)\n)\nCREATE TABLE government_services.employees (\n employee_id character varying(64) NOT NULL, -- unique identifier for the government employee\n agency_id character varying(64) NOT NULL, -- FK to agencies table\n first_name character varying(100) NOT NULL,\n last_name character varying(100) NOT NULL,\n job_title character varying(150) NOT NULL,\n department character varying(100),\n work_email character varying(128) NOT NULL UNIQUE,\n work_phone character varying(32),\n hire_date date NOT NULL,\n termination_date date, -- null if currently employed\n access_level character varying(50), -- Role or permission level\n manager_employee_id character varying(64), -- FK to self for reporting structure\n PRIMARY KEY (employee_id)\n)\nCREATE TABLE government_services.appointments (\n appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment\n citizen_id character varying(64) NOT NULL, -- FK to citizens table\n employee_id character varying(64), -- FK to employees table (optional, if assigned)\n location_id character varying(64), -- FK to service_locations table (if physical)\n service_id character varying(64), -- FK to services table (optional, if related to specific service)\n scheduled_start_time timestamp NOT NULL,\n scheduled_end_time timestamp,\n purpose text NOT NULL, -- reason for the appointment\n status character varying(30) NOT NULL, -- e.g., Scheduled, Completed, Cancelled, No-Show\n booking_method character varying(50), -- e.g., Online, Phone, In-Person\n created_at timestamp NOT NULL, -- when the appointment was booked\n notes text,\n PRIMARY KEY (appointment_id)\n)\nCREATE TABLE government_services.notifications (\n notification_id character varying(64) NOT NULL, -- unique identifier for the notification\n citizen_id character varying(64) NOT NULL, -- FK to citizens table\n application_id character varying(64), -- FK to applications table (optional)\n message_subject character varying(255),\n message_body text NOT NULL,\n channel character varying(30) NOT NULL, -- e.g., Email, SMS, Portal Message, Mail\n sent_at timestamp NOT NULL,\n status character varying(30) NOT NULL, -- e.g., Queued, Sent, Delivered, Failed, Read\n related_entity_type character varying(50), -- e.g., Application, Appointment, Document Request\n related_entity_id character varying(64), -- ID of the related entity\n PRIMARY KEY (notification_id)\n)\n"} {"conversations": [{"role": "user", "content": "I need to know the total USD value of all ERC-20 holdings by each wallet. Calculate the sum of (amount * price) using the latest token prices from token_prices_latest, grouped by wallet_address."}, {"role": "assistant", "content": "SELECT eb.wallet_address,\n SUM(CAST(eb.amount AS numeric) * tpl.price) AS total_usd_value\nFROM erc20_balances eb\nJOIN token_prices_latest tpl\n ON lower(eb.contract_address) = lower(tpl.address)\nGROUP BY eb.wallet_address;"}, {"role": "user", "content": "Actually, only include tokens where the price is greater than 0.5 USD and limit to the top 10 wallets by total_usd_value."}, {"role": "assistant", "content": "SELECT eb.wallet_address,\n SUM(CAST(eb.amount AS numeric) * tpl.price) AS total_usd_value\nFROM erc20_balances eb\nJOIN token_prices_latest tpl\n ON lower(eb.contract_address) = lower(tpl.address)\nWHERE tpl.price > 0.5\nGROUP BY eb.wallet_address\nORDER BY total_usd_value DESC\nLIMIT 10;"}, {"role": "user", "content": "Also show me the count of distinct token contracts held by each wallet as distinct_tokens."}, {"role": "assistant", "content": "SELECT eb.wallet_address,\n SUM(CAST(eb.amount AS numeric) * tpl.price) AS total_usd_value,\n COUNT(DISTINCT lower(eb.contract_address)) AS distinct_tokens\nFROM erc20_balances eb\nJOIN token_prices_latest tpl\n ON lower(eb.contract_address) = lower(tpl.address)\nWHERE tpl.price > 0.5\nGROUP BY eb.wallet_address\nORDER BY total_usd_value DESC\nLIMIT 10;"}, {"role": "user", "content": "Finally, filter out wallets that hold fewer than 2 distinct tokens."}, {"role": "assistant", "content": "SELECT eb.wallet_address,\n SUM(CAST(eb.amount AS numeric) * tpl.price) AS total_usd_value,\n COUNT(DISTINCT lower(eb.contract_address)) AS distinct_tokens\nFROM erc20_balances eb\nJOIN token_prices_latest tpl\n ON lower(eb.contract_address) = lower(tpl.address)\nWHERE tpl.price > 0.5\nGROUP BY eb.wallet_address\nHAVING COUNT(DISTINCT lower(eb.contract_address)) >= 2\nORDER BY total_usd_value DESC\nLIMIT 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE erc20_balances ( block_number.bigint, contract_address.text, wallet_address.text, amount.text, pk.text )\nCREATE TABLE nft_holders (\n block_number bigint NOT NULL, -- Block number containing the transaction\n contract_address varchar NOT NULL, -- Event contract address\n wallet_address varchar NOT NULL, -- The wallet address for the contract(with bloom filter)\n token_id varchar NOT NULL, -- NFT token id\n contract_type varchar NOT NULL, -- NFT contract type\n amount varchar NOT NULL, -- Number of held NFTs\n pk varchar NOT NULL -- The last string partition of the contract.\n)\nCREATE TABLE sui_nfts ( object_id varchar, status varchar, collection_type varchar, package_id varchar, previous_transaction varchar, display varchar, owner varchar, name varchar )\nCREATE TABLE token_prices ( uuid varchar, blockchain varchar, address varchar, decimals bigint, symbol varchar, price real, timestamp timestamp )\nCREATE TABLE token_prices_latest (\n blockchain varchar(36) NOT NULL, -- blockchain fields for the functionType in contract\n address varchar(42) NOT NULL, -- address fields for the functionType in contract\n decimals bigint NOT NULL, -- decimals fields for the functionType in contract\n symbol varchar(36) NOT NULL, -- symbol fields for the functionType in contract\n price real NOT NULL, -- price fields for the functionType in contract\n timestamp timestamp(6) NOT NULL -- timestamp fields for the functionType in contract\n)\nCREATE TABLE erc20_approval ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash text, log_index integer, contract_address text, pk integer )\nCREATE TABLE token_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_info_bitcoin ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar(255) NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar(20) NOT NULL, tick varchar(255) NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(42) NOT NULL, to_address varchar(42) NOT NULL )\nCREATE TABLE token_balances_avalanche ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply decimal, amount decimal )\n"} {"conversations": [{"role": "user", "content": "I want to see, for each guest, the total number of payments they have made and the timestamp of their latest payment."}, {"role": "assistant", "content": "SELECT p.guest_id,\n COUNT(p.payment_id) AS payment_count,\n t.last_ts\nFROM hospitality_technology.payments p\nJOIN (\n SELECT guest_id,\n MAX(payment_timestamp) AS last_ts\n FROM hospitality_technology.payments\n GROUP BY guest_id\n) t ON p.guest_id = t.guest_id\nGROUP BY p.guest_id, t.last_ts;"}, {"role": "user", "content": "Only include guests whose latest payment status was 'Succeeded' and who have made at least 5 successful payments."}, {"role": "assistant", "content": "SELECT p.guest_id,\n COUNT(p.payment_id) AS payment_count,\n t.last_ts\nFROM hospitality_technology.payments p\nJOIN (\n SELECT guest_id,\n MAX(payment_timestamp) AS last_ts,\n COUNT(*) AS cnt\n FROM hospitality_technology.payments\n WHERE status = 'Succeeded'\n GROUP BY guest_id\n HAVING COUNT(*) >= 5\n) t ON p.guest_id = t.guest_id\nGROUP BY p.guest_id, t.last_ts;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.payments ( payment_id character varying(64) NOT NULL, reservation_id character varying(64), guest_id character varying(64) NOT NULL, bill_id character varying(64), amount numeric(12,2) NOT NULL, currency_code character varying(3) NOT NULL, payment_method character varying(50) NOT NULL, card_type character varying(50), card_last_four character varying(4), transaction_ref character varying(128), payment_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, status character varying(50) NOT NULL, staff_id_processed character varying(64), notes text, PRIMARY KEY (payment_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (staff_id_processed) REFERENCES hospitality_technology.staff(staff_id) )\n"} {"conversations": [{"role": "user", "content": "Show me all wallet addresses that hold more than 1000 of any ERC1155 token, along with the token ID and contract address."}, {"role": "assistant", "content": "SELECT wallet_address, token_id, contract_address FROM nft_holders WHERE contract_type = 'ERC1155' AND CAST(amount AS decimal) > 1000;"}, {"role": "user", "content": "Can you join this with the nft_metadata table to include the name and image_uri of each token?"}, {"role": "assistant", "content": "SELECT nh.wallet_address, nh.token_id, nh.contract_address, nm.name, nm.image_uri FROM nft_holders nh JOIN nft_metadata nm ON nh.contract_address = nm.contract_address AND nh.token_id = nm.token_id WHERE nh.contract_type = 'ERC1155' AND CAST(nh.amount AS decimal) > 1000;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas (\n block_timestamp timestamp(6) NOT NULL, -- Timestamp of the block when token metadata was recorded\n block_number bigint NOT NULL, -- Block number uniquely identifying the block\n transaction_hash varchar NOT NULL, -- Hash value of the transaction\n transaction_index bigint NOT NULL, -- Index of the transaction within the block\n from_address varchar NOT NULL, -- Address from which the transaction originated\n contract_address varchar NOT NULL, -- Address of the token contract\n symbol varchar NOT NULL, -- Symbol of the token\n total_supply varchar NOT NULL, -- erc20 contract total supply\n name varchar NOT NULL, -- Name of the token\n decimals bigint NOT NULL, -- Number of decimal places for the token\n is_erc20 integer NOT NULL, -- Flag indicating if the token is an ERC-20 token (0 or 1)\n is_erc721 integer NOT NULL, -- Flag indicating if the token is an ERC-721 token (0 or 1)\n is_erc1155 integer NOT NULL, -- Flag indicating if the token is an ERC-1155 token (0 or 1)\n is_proxy integer NOT NULL, -- Flag indicating if the token is a proxy (0 or 1)\n extra_info varchar NOT NULL, -- Additional information about the token\n pk integer NOT NULL -- Partition key for the table(floor(block_number / 5760))\n)\nCREATE TABLE erc1155_approval_for_all (\n block_number bigint NOT NULL, -- Block number containing the transaction\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the transaction\n transaction_index integer NOT NULL, -- Index of the transaction within the block\n transaction_hash varchar(66) NOT NULL, -- Transaction hash\n log_index integer NOT NULL, -- Log index\n contract_address varchar(42) NOT NULL -- Event contract address\n)\nCREATE TABLE erc20_balances ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE erc20_balances_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_holders (\n block_number bigint NOT NULL, -- Block number containing the transaction\n contract_address varchar NOT NULL, -- Event contract address\n wallet_address varchar NOT NULL, -- The wallet address for the contract(with bloom filter)\n token_id varchar NOT NULL, -- NFT token id\n contract_type varchar NOT NULL, -- NFT contract type\n amount varchar NOT NULL, -- Number of held NFTs\n pk varchar NOT NULL -- The last string partition of the contract.\n)\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_nfts ( object_id text, status text, collection_type text, package_id text, previous_transaction text, display text, owner text, name text )\nCREATE TABLE nft_metadata ( blockchain text, contract_address text, token_id text, contract_name text, erc_type text, amount bigint, minter text, owner text, mint_block_number bigint, mint_time bigint, mint_transaction_hash text, mint_price text, token_uri text, metadata text, name text, image_uri text, traits text, updated_at bigint, status text, rarity_score real, rarity_rank integer, unique_attribute_count integer, pk integer )\nCREATE TABLE erc20_approval ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash text, log_index integer, contract_address text, pk integer )\nCREATE TABLE token_info (\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n tick varchar NOT NULL, -- Token tick\n max_supply decimal(38,0) NOT NULL, -- Max supply\n lim decimal(38,0) NOT NULL, -- Limit of each mint\n wlim decimal(38,0) NOT NULL, -- Limit of each address can maximum mint\n dec integer NOT NULL, -- Decimal for minimum divie\n creator varchar(42) NOT NULL -- Address originating the inscription (matches from_address in transactions table)\n)\nCREATE TABLE token_activities (\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n log_index integer NOT NULL, -- Index of the log within the transaction\n type varchar NOT NULL, -- mint | transfer | burn\n tick varchar NOT NULL, -- Token tick\n id varchar(255) NOT NULL, -- Unique identifier of the inscription\n amt decimal(38,0) NOT NULL, -- Mint amount\n from_address varchar(42) NOT NULL, -- Address sending the inscription (matches from_address in transactions table)\n to_address varchar(42) NOT NULL -- Address receiving the inscription (match to_address in transactions table)\n)\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_activities_avalanche ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\n"} {"conversations": [{"role": "user", "content": "特定のプラットフォームID 'plat_123' に関連するメンテナンス記録を取得するのを手伝っていただけますか？また、記録のステータスも含めてください。"}, {"role": "assistant", "content": "SMEMBERS platform:plat_123:maintenance\nHGETALL maintenance_record:"}, {"role": "user", "content": "ステータスが 'Completed' の記録だけを表示するようにフィルタリングしていただけますか？"}, {"role": "assistant", "content": "SMEMBERS platform:plat_123:maintenance\nHGET maintenance_record: status\nHGETALL maintenance_record: (only if status = 'Completed')"}, {"role": "user", "content": "関連する資産タイプも結果に含めていただけますか？"}, {"role": "assistant", "content": "SMEMBERS platform:plat_123:maintenance\nHGET maintenance_record: status\nHGETALL maintenance_record: (only if status = 'Completed')"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\n// Use Hashes for ticket details. Key format: ticket:\n// HSET ticket:tkt_1a2b ticket_id \"tkt_1a2b\" booking_id \"book_zyx\" car_id \"car_abc\" seat_number \"12A\" ... is_checked_in 0 ...\n\n// To link tickets to bookings (optional):\n// SADD booking:book_zyx:tickets ticket:tkt_1a2b\n// Use Hashes for maintenance record details. Key format: maintenance_record:\n// HSET maintenance_record:maint_rec_001 record_id \"maint_rec_001\" asset_id \"train_789\" asset_type \"Train\" ... status \"Completed\"\n\n// To link records to assets (optional):\n// SADD train:train_789:maintenance maintenance_record:maint_rec_001\n// SADD platform:plat_123:maintenance maintenance_record:maint_rec_002\n"} {"conversations": [{"role": "user", "content": "Show the first name, last name, relationship, and percentage share for all policy beneficiaries added after January 1st, 2024."}, {"role": "assistant", "content": "SELECT first_name, last_name, relationship, percentage_share FROM insurance.policy_beneficiaries WHERE added_at >= '2024-01-01';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.policies ( policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, product_id character varying(64) NOT NULL, agent_id character varying(64), policy_number character varying(100) NOT NULL UNIQUE, start_date date NOT NULL, end_date date NOT NULL, premium_amount numeric(12, 2) NOT NULL, coverage_limit numeric(15, 2) NOT NULL, deductible numeric(10, 2) NOT NULL, status character varying(30) NOT NULL, issued_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, cancellation_date date, cancellation_reason text, PRIMARY KEY (policy_id) )\nCREATE TABLE insurance.agents ( agent_id.text, first_name.text, last_name.text, agency_name.text, license_number.text, license_state.text, contact_email.text, contact_phone.text, hire_date.date, termination_date.date, status.text, commission_rate.numeric, manager_id.text )\nCREATE TABLE insurance.claim_documents ( document_id.text, claim_id.text, document_type.text, file_name.text, file_path.text, file_size_bytes.integer, mime_type.text, uploaded_by.text, uploaded_at.timestamp, description.text )\nCREATE TABLE insurance.policy_beneficiaries (\n beneficiary_id character varying(64) NOT NULL, -- unique identifier for the beneficiary entry\n policy_id character varying(64) NOT NULL, -- identifier of the life/relevant policy (FK to policies)\n customer_id character varying(64) NOT NULL, -- identifier of the beneficiary (could be FK to customers or store info directly)\n first_name character varying(100) NOT NULL, -- beneficiary first name (if not linking to customers table)\n last_name character varying(100) NOT NULL, -- beneficiary last name\n relationship character varying(50) NOT NULL, -- relationship to the policyholder (e.g., Spouse, Child, Parent)\n percentage_share numeric(5, 2) NOT NULL CHECK (percentage_share > 0 AND percentage_share <= 100), -- percentage of payout\n contact_info text, -- contact details for the beneficiary\n added_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n PRIMARY KEY (beneficiary_id),\n UNIQUE (policy_id, customer_id) -- Ensure a person is listed only once per policy\n)\n"} {"conversations": [{"role": "user", "content": "Find the total amount paid for all premium payments made in the last 30 days."}, {"role": "assistant", "content": "SELECT SUM(amount_paid) FROM insurance.premium_payments WHERE payment_date >= CURRENT_DATE - INTERVAL '30 day';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.policies (\n policy_id character varying(64) NOT NULL, -- unique identifier for the policy\n customer_id character varying(64) NOT NULL, -- identifier for the policyholder (FK to customers)\n product_id character varying(64) NOT NULL, -- identifier for the insurance product (FK to insurance_products)\n agent_id character varying(64), -- identifier for the agent who sold the policy (FK to agents)\n policy_number character varying(100) NOT NULL UNIQUE, -- customer-facing policy number\n start_date date NOT NULL, -- date the policy coverage begins\n end_date date NOT NULL, -- date the policy coverage ends\n premium_amount numeric(12, 2) NOT NULL, -- total premium for the policy term\n coverage_limit numeric(15, 2) NOT NULL, -- maximum amount covered\n deductible numeric(10, 2) NOT NULL, -- amount customer pays before coverage kicks in\n status character varying(30) NOT NULL, -- e.g., Active, Expired, Cancelled, Pending\n issued_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the policy was issued\n cancellation_date date,\n cancellation_reason text,\n PRIMARY KEY (policy_id)\n)\nCREATE TABLE insurance.insurance_products (\n product_id character varying(64) NOT NULL, -- unique identifier for the insurance product\n product_name character varying(150) NOT NULL, -- name of the insurance product (e.g., 'Comprehensive Auto Insurance')\n product_type character varying(50) NOT NULL, -- category like 'Auto', 'Home', 'Life', 'Health', 'Travel'\n description text, -- detailed description of the product\n base_premium numeric(10, 2) NOT NULL, -- starting premium before adjustments\n coverage_details text, -- details about what is covered (could be JSON or structured text)\n underwriting_rules text, -- rules used for assessing risk and eligibility\n is_active boolean NOT NULL DEFAULT true, -- whether the product is currently offered\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n updated_at timestamp,\n PRIMARY KEY (product_id)\n)\nCREATE TABLE insurance.premium_payments (\n payment_id character varying(64) NOT NULL, -- unique identifier for the payment\n policy_id character varying(64) NOT NULL, -- identifier of the policy the payment is for (FK to policies)\n customer_id character varying(64) NOT NULL, -- identifier of the customer making the payment (FK to customers)\n payment_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- date the payment was received\n amount_paid numeric(12, 2) NOT NULL, -- amount of the payment\n payment_method character varying(50), -- e.g., Credit Card, Bank Transfer, Check\n transaction_reference character varying(128) UNIQUE, -- reference from payment processor\n due_date date, -- due date for this payment installment\n payment_period_start date, -- start date of the period this payment covers\n payment_period_end date, -- end date of the period this payment covers\n status character varying(30) NOT NULL DEFAULT 'Completed', -- e.g., Completed, Pending, Failed, Refunded\n PRIMARY KEY (payment_id)\n)\n"} {"conversations": [{"role": "user", "content": "List all vehicles and their last maintenance service date along with the odometer reading, including only those that have not had a fuel refill in the past 30 days."}, {"role": "assistant", "content": "SELECT m.vehicle_id,\n m.last_service_date,\n m.last_odometer\nFROM (\n SELECT l.vehicle_id,\n MAX(l.service_date) AS last_service_date,\n (SELECT odometer_reading\n FROM transportation.maintenance_logs\n WHERE vehicle_id = l.vehicle_id\n ORDER BY service_date DESC\n LIMIT 1) AS last_odometer\n FROM transportation.maintenance_logs l\n GROUP BY l.vehicle_id\n) AS m\nLEFT JOIN (\n SELECT fl.vehicle_id,\n MAX(fl.log_timestamp) AS last_fuel_date\n FROM transportation.fuel_logs fl\n GROUP BY fl.vehicle_id\n) AS f ON m.vehicle_id = f.vehicle_id\nWHERE COALESCE(f.last_fuel_date, '1900-01-01'::timestamp) < NOW() - INTERVAL '30 days';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.routes ( route_id character varying(64) NOT NULL, route_number character varying(32) NOT NULL UNIQUE, description text, origin_location_id character varying(64) NOT NULL, destination_location_id character varying(64) NOT NULL, distance_km numeric(10, 2), estimated_duration_minutes integer, type character varying(32) NOT NULL, PRIMARY KEY (route_id) )\nCREATE TABLE transportation.trips ( trip_id character varying(64) NOT NULL, route_id character varying(64), vehicle_id character varying(64) NOT NULL, driver_id character varying(64) NOT NULL, scheduled_departure timestamp with time zone NOT NULL, actual_departure timestamp with time zone, scheduled_arrival timestamp with time zone NOT NULL, actual_arrival timestamp with time zone, origin_location_id character varying(64) NOT NULL, destination_location_id character varying(64) NOT NULL, status character varying(32) NOT NULL, passenger_count integer, cargo_manifest_id character varying(64), PRIMARY KEY (trip_id) )\nCREATE TABLE transportation.locations ( location_id character varying(64) NOT NULL, name character varying(255) NOT NULL, type character varying(64) NOT NULL, address_line1 character varying(255), city character varying(128), state_province character varying(128), postal_code character varying(32), country character varying(64) NOT NULL, latitude numeric(9, 6), longitude numeric(9, 6), timezone character varying(64), PRIMARY KEY (location_id) )\nCREATE TABLE transportation.maintenance_logs ( log_id character varying(64) NOT NULL, vehicle_id character varying(64) NOT NULL, service_date date NOT NULL, odometer_reading integer, service_type character varying(128) NOT NULL, description text NOT NULL, cost numeric(10, 2), mechanic_name character varying(128), next_service_due_date date, PRIMARY KEY (log_id) )\nCREATE TABLE transportation.fuel_logs ( fuel_log_id character varying(64) NOT NULL, vehicle_id character varying(64) NOT NULL, trip_id character varying(64), log_timestamp timestamp with time zone NOT NULL, fuel_type character varying(32) NOT NULL, quantity numeric(10, 3) NOT NULL, unit character varying(16) NOT NULL, cost_per_unit numeric(8, 4), total_cost numeric(10, 2) NOT NULL, odometer_reading integer, location_id character varying(64), PRIMARY KEY (fuel_log_id) )\nCREATE TABLE transportation.passengers ( passenger_id character varying(64) NOT NULL, first_name character varying(128) NOT NULL, last_name character varying(128) NOT NULL, email character varying(128) UNIQUE, phone_number character varying(32) UNIQUE, date_of_birth date, loyalty_program_id character varying(64), created_at timestamp with time zone NOT NULL, PRIMARY KEY (passenger_id) )\nCREATE TABLE transportation.bookings ( booking_id character varying(64) NOT NULL, passenger_id character varying(64) NOT NULL, trip_id character varying(64) NOT NULL, seat_number character varying(16), booking_time timestamp with time zone NOT NULL, status character varying(32) NOT NULL, fare numeric(10, 2) NOT NULL, payment_transaction_id character varying(128), special_requests text, PRIMARY KEY (booking_id) )\n"} {"conversations": [{"role": "user", "content": "List all ERC20 tokens where the price is between $1 and $10, including their names, symbols, and contract addresses."}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address FROM token_metas tm JOIN token_prices_latest tpl ON tm.contract_address = tpl.contract_address WHERE tm.is_erc20 = 1 AND tpl.price BETWEEN 1 AND 10;"}, {"role": "user", "content": "I think there's an error in your query - the token_prices_latest table isn't in the schema. Can you modify it to use the token_balances table instead?"}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address FROM token_metas tm JOIN token_balances tb ON tm.contract_address = tb.wallet_address WHERE tm.is_erc20 = 1 AND CAST(tb.amount AS decimal) BETWEEN 1 AND 10;"}, {"role": "user", "content": "That doesn't seem right either. Let's just get the basic ERC20 token information without price filtering for now."}, {"role": "assistant", "content": "SELECT name, symbol, contract_address FROM token_metas WHERE is_erc20 = 1 LIMIT 100;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp.timestamp, block_number.bigint, transaction_hash.text, transaction_index.bigint, from_address.text, contract_address.text, symbol.text, total_supply.text, name.text, decimals.bigint, is_erc20.integer, is_erc721.integer, is_erc1155.integer, is_proxy.integer, extra_info.text, pk.integer )\nCREATE TABLE erc1155_approval_for_all ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar(66) NOT NULL, log_index integer NOT NULL, contract_address varchar(42) NOT NULL )\nCREATE TABLE erc20_balances ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE erc20_balances_historical ( block_number bigint, contract_address text, wallet_address text, amount text, pk integer )\nCREATE TABLE nft_holders ( block_number bigint, contract_address text, wallet_address text, token_id text, contract_type text, amount text, pk text )\nCREATE TABLE nft_holder_historical ( block_number.bigint, contract_address.text, wallet_address.text, token_id.text, contract_type.text, amount.text, pk.integer )\nCREATE TABLE sui_nfts ( object_id text, status text, collection_type text, package_id text, previous_transaction text, display text, owner text, name text )\nCREATE TABLE nft_collections ( blockchain text, contract_address text, name text, symbol text, deploy_block_number bigint, deploy_block_time bigint, erc_type text, owner text, traits text, description text, slug text, media_info text, image_url text, banner_image_url text, updated_at bigint, banner text, token_count bigint, floor_price text, floor_price_symbol text, floor_price_contract text, pk integer )\nCREATE TABLE erc20_approval ( block_number bigint NOT NULL, block_timestamp timestamp(6) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar NOT NULL, log_index integer NOT NULL, contract_address varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_balances ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply decimal, amount decimal )\nCREATE TABLE token_info (\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n tick varchar NOT NULL, -- Token tick\n max_supply decimal(38,0) NOT NULL, -- Max supply\n lim decimal(38,0) NOT NULL, -- Limit of each mint\n wlim decimal(38,0) NOT NULL, -- Limit of each address can maximum mint\n dec integer NOT NULL, -- Decimal for minimum divie\n creator varchar(42) NOT NULL -- Address originating the inscription (matches from_address in transactions table)\n)\nCREATE TABLE token_activities ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\nCREATE TABLE mud_holesky_redstone ( address varchar NOT NULL, table_id varchar NOT NULL, key_bytes varchar NOT NULL, key0 varchar NOT NULL, key1 varchar NOT NULL, static_data varchar NOT NULL, encoded_lengths varchar NOT NULL, dynamic_data varchar NOT NULL, is_deleted boolean NOT NULL, block_number bigint NOT NULL, log_index bigint NOT NULL )\nCREATE TABLE token_balances_bitcoin ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply varchar, amount varchar )\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar )\nCREATE TABLE token_activities_avalanche ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\nCREATE TABLE token_balances_avalanche (\n block_number bigint NOT NULL, -- Block number containing the transaction\n block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n tick varchar(20) NOT NULL, -- Ticker: Identifier of the inscription\n wallet_address varchar(42) NOT NULL, -- Address of owner\n total_supply decimal(38,0) NOT NULL, -- Max supply: Set max supply of the inscription\n amount decimal(38,0) NOT NULL -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id varchar )\n"} {"conversations": [{"role": "user", "content": "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": "What is the performance review score for employee with ID 'EMP456' for the last quarter?"}, {"role": "assistant", "content": "I'm sorry, but I can't assist with information about performance review scores as this data is not included in the employees table."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE manufacturing.employees ( employee_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, job_title character varying(128) NOT NULL, skill_certifications text, hire_date date NOT NULL, assigned_line_id character varying(64), employment_status character varying(50) NOT NULL, supervisor_employee_id character varying(64), PRIMARY KEY (employee_id) )\n"} {"conversations": [{"role": "user", "content": "Show 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": "Show me all room types with a base rate over $200 and max occupancy of at least 4, along with their property IDs and amenities."}, {"role": "assistant", "content": "SELECT room_type_id, property_id, type_name, base_rate, max_occupancy, amenities FROM hospitality_technology.room_types WHERE base_rate > 200 AND max_occupancy >= 4;"}, {"role": "user", "content": "Now, join this with the guests table to show only room types from properties where the guest's country code is 'USA'."}, {"role": "assistant", "content": "SELECT rt.room_type_id, rt.property_id, rt.type_name, rt.base_rate, rt.max_occupancy, rt.amenities FROM hospitality_technology.room_types rt JOIN hospitality_technology.guests g ON rt.property_id = g.property_id WHERE rt.base_rate > 200 AND rt.max_occupancy >= 4 AND g.country_code = 'USA';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.room_types ( room_type_id text PRIMARY KEY, property_id text, type_name text, description text, base_rate numeric, max_occupancy int, bed_type text, area_sqft numeric, amenities text )\nCREATE TABLE hospitality_technology.guests ( guest_id text, first_name text, last_name text, email text, phone_number text, date_of_birth date, address_line1 text, city text, state_province text, postal_code text, country_code text, preferences text, loyalty_member_id text, communication_consent boolean, created_at timestamp, updated_at timestamp )\n"} {"conversations": [{"role": "user", "content": "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": "What are the qualifications or training history of the staff member who performed the maintenance with record_id 'REC123'?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information about the qualifications or training history of staff members as this data is not stored in the maintenance_records table. This table only contains details about maintenance activities, such as asset information, maintenance type, dates, and costs. If you have another question or need assistance with data available in this 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 train_station_management.maintenance_records (\n record_id character varying(64) NOT NULL, -- Unique identifier for the maintenance record\n asset_id character varying(64) NOT NULL, -- ID of the asset being maintained (train_id, car_id, platform_id, etc.)\n asset_type character varying(32) NOT NULL, -- Type of asset ('Train', 'Car', 'Platform', 'Track')\n maintenance_type character varying(128) NOT NULL, -- e.g., 'Scheduled Inspection', 'Repair', 'Cleaning'\n staff_id character varying(64), -- Staff member performing/overseeing maintenance\n start_datetime timestamp NOT NULL, -- When maintenance started\n end_datetime timestamp, -- When maintenance completed (nullable if ongoing)\n description text NOT NULL, -- Details of the maintenance performed\n cost numeric(12, 2), -- Cost associated with the maintenance\n status character varying(32) NOT NULL DEFAULT 'Completed', -- e.g., 'Scheduled', 'In Progress', 'Completed', 'Cancelled'\n PRIMARY KEY (record_id),\n FOREIGN KEY (staff_id) REFERENCES train_station_management.staff(staff_id)\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 me the number of players registered in each country, along with the number of different games available for each country."}, {"role": "assistant", "content": "SELECT p.country_code, COUNT(DISTINCT p.player_id) AS player_count, COUNT(DISTINCT g.game_id) AS game_count\nFROM gaming_technology.players p\nCROSS JOIN gaming_technology.games g\nGROUP BY p.country_code;"}, {"role": "user", "content": "This doesn't make sense; the game count should be the number of games, not all possible combinations. Can you fix it to just show the count of players per country?"}, {"role": "assistant", "content": "SELECT p.country_code, COUNT(*) AS player_count\nFROM gaming_technology.players p\nGROUP BY p.country_code;"}, {"role": "user", "content": "Now add in the total number of servers located in each country, based on the players' country code matching the server's region."}, {"role": "assistant", "content": "SELECT p.country_code, COUNT(*) AS player_count,\n (SELECT COUNT(*) FROM gaming_technology.servers s WHERE s.region = p.country_code) AS server_count\nFROM gaming_technology.players p\nGROUP BY p.country_code;"}, {"role": "user", "content": "Show only countries where there are at least 5 servers."}, {"role": "assistant", "content": "SELECT p.country_code, COUNT(*) AS player_count,\n (SELECT COUNT(*) FROM gaming_technology.servers s WHERE s.region = p.country_code) AS server_count\nFROM gaming_technology.players p\nGROUP BY p.country_code\nHAVING (SELECT COUNT(*) FROM gaming_technology.servers s WHERE s.region = p.country_code) >= 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.players ( player_id.uuid, username.text, email.text, password_hash.text, registration_date.timestamptz, last_login.timestamptz, country_code.text, status.text, profile_data.jsonb )\nCREATE TABLE gaming_technology.games (\n game_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game\n title character varying(200) NOT NULL, -- official title of the game\n developer_id uuid NOT NULL, -- FK linking to the developers table\n publisher_id uuid, -- FK linking to a potential publishers table (optional)\n genre character varying(100), -- primary genre (e.g., RPG, FPS, Strategy)\n release_date date, -- official release date\n description text, -- short description or synopsis of the game\n platform character varying(50) NOT NULL, -- primary platform (e.g., PC, PlayStation 5, Xbox Series X, Mobile)\n engine character varying(100), -- game engine used (e.g., Unreal Engine 5, Unity)\n website character varying(255), -- official website URL\n PRIMARY KEY (game_id)\n -- FOREIGN KEY (developer_id) REFERENCES gaming_technology.developers(developer_id) -- Example FK constraint\n)\nCREATE TABLE gaming_technology.servers ( server_id uuid NOT NULL DEFAULT gen_random_uuid(), game_id uuid NOT NULL, server_name character varying(150), region character varying(50) NOT NULL, ip_address character varying(45), port integer, current_players integer NOT NULL DEFAULT 0, max_players integer NOT NULL, status character varying(30) NOT NULL DEFAULT 'offline', last_heartbeat timestamp with time zone, PRIMARY KEY (server_id) )\nCREATE TABLE gaming_technology.achievements ( achievement_id uuid, game_id uuid, name text, description text, icon_url text, points integer, hidden boolean )\nCREATE TABLE gaming_technology.in_game_items ( item_id uuid NOT NULL DEFAULT gen_random_uuid(), game_id uuid NOT NULL, item_name character varying(150) NOT NULL, item_type character varying(50) NOT NULL, description text, rarity character varying(30), cost_currency character varying(10), cost_amount numeric(12, 2), attributes jsonb, PRIMARY KEY (item_id) )\n"} {"conversations": [{"role": "user", "content": "What is the average processing time in days for each service category?"}, {"role": "assistant", "content": "SELECT category, AVG(average_processing_time_days) AS avg_processing_time\nFROM government_services.services\nGROUP BY category;"}, {"role": "user", "content": "Only include categories where the average_processing_time_days is greater than 5."}, {"role": "assistant", "content": "SELECT category, AVG(average_processing_time_days) AS avg_processing_time\nFROM government_services.services\nGROUP BY category\nHAVING AVG(average_processing_time_days) > 5;"}, {"role": "user", "content": "Also include only active services in the calculation."}, {"role": "assistant", "content": "SELECT category, AVG(average_processing_time_days) AS avg_processing_time\nFROM government_services.services\nWHERE is_active = TRUE\nGROUP BY category\nHAVING AVG(average_processing_time_days) > 5;"}, {"role": "user", "content": "Sort the results by avg_processing_time in descending order."}, {"role": "assistant", "content": "SELECT category, AVG(average_processing_time_days) AS avg_processing_time\nFROM government_services.services\nWHERE is_active = TRUE\nGROUP BY category\nHAVING AVG(average_processing_time_days) > 5\nORDER BY avg_processing_time DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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 )\n"} {"conversations": [{"role": "user", "content": "Find employees who work in the same department as their manager. Display the employee's full name, the manager's full name, and the department they share."}, {"role": "assistant", "content": "SELECT e.first_name || ' ' || e.last_name AS employee_full_name, m.first_name || ' ' || m.last_name AS manager_full_name, e.department FROM government_services.employees AS e JOIN government_services.employees AS m ON e.manager_employee_id = m.employee_id WHERE e.department = m.department;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.employees (\n employee_id character varying(64) NOT NULL, -- unique identifier for the government employee\n agency_id character varying(64) NOT NULL, -- FK to agencies table\n first_name character varying(100) NOT NULL,\n last_name character varying(100) NOT NULL,\n job_title character varying(150) NOT NULL,\n department character varying(100),\n work_email character varying(128) NOT NULL UNIQUE,\n work_phone character varying(32),\n hire_date date NOT NULL,\n termination_date date, -- null if currently employed\n access_level character varying(50), -- Role or permission level\n manager_employee_id character varying(64), -- FK to self for reporting structure\n PRIMARY KEY (employee_id)\n)\n"} {"conversations": [{"role": "user", "content": "List lawyers who have any unbilled time entries. Show their first name, last name, and the count of their unbilled entries."}, {"role": "assistant", "content": "SELECT T1.first_name, T1.last_name, COUNT(T2.entry_id) FROM lawyers AS T1 JOIN time_entries AS T2 ON T1.lawyer_id = T2.lawyer_id WHERE T2.is_billed = false GROUP BY T1.lawyer_id, T1.first_name, T1.last_name;"}, {"role": "user", "content": "Modify that query to only include entries marked as billable, and instead show the total hours spent rather than the count."}, {"role": "assistant", "content": "SELECT T1.first_name, T1.last_name, SUM(T2.hours_spent) FROM lawyers AS T1 JOIN time_entries AS T2 ON T1.lawyer_id = T2.lawyer_id WHERE T2.is_billed = false AND T2.is_billable = true GROUP BY T1.lawyer_id, T1.first_name, T1.last_name;"}, {"role": "user", "content": "Now, only show lawyers with more than 10 unbilled billable hours in total, and sort the results by the total hours descending."}, {"role": "assistant", "content": "SELECT T1.first_name, T1.last_name, SUM(T2.hours_spent) FROM lawyers AS T1 JOIN time_entries AS T2 ON T1.lawyer_id = T2.lawyer_id WHERE T2.is_billed = false AND T2.is_billable = true GROUP BY T1.lawyer_id, T1.first_name, T1.last_name HAVING SUM(T2.hours_spent) > 10 ORDER BY SUM(T2.hours_spent) DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.lawyers ( lawyer_id text PRIMARY KEY, first_name text, last_name text, bar_number text UNIQUE, firm_id text, email text UNIQUE, phone text, specialization text, hire_date timestamp, is_partner bool )\nCREATE TABLE legal_services.law_firms ( firm_id text PRIMARY KEY, firm_name text, address text, phone text, website text, founded_date date, managing_partner_id text )\nCREATE TABLE legal_services.documents ( document_id text PRIMARY KEY, case_id text, document_name text, document_type text, storage_path text, uploaded_by_lawyer_id text, upload_timestamp timestamp, version int, description text )\nCREATE TABLE legal_services.time_entries ( entry_id text PRIMARY KEY, case_id text, lawyer_id text, date_worked date, hours_spent numeric, billing_rate numeric, description text, is_billable bool, is_billed bool, invoice_id text, created_at timestamp )\nCREATE TABLE legal_services.invoices ( invoice_id text PRIMARY KEY, invoice_number text UNIQUE, client_id text, case_id text, issue_date date, due_date date, total_amount numeric, amount_paid numeric, status text, payment_date timestamp, notes text, created_at timestamp )\nCREATE TABLE legal_services.appointments ( appointment_id text PRIMARY KEY, client_id text, lawyer_id text, case_id text, start_time timestamp, end_time timestamp, location text, subject text, notes text, status text, created_at timestamp )\n"} {"conversations": [{"role": "user", "content": "List all pairs of service orders that share the same bill_id, showing order1_id, order2_id, and the bill_id."}, {"role": "assistant", "content": "SELECT s1.order_id AS order1_id,\n s2.order_id AS order2_id,\n s1.bill_id\nFROM hospitality_technology.service_orders s1\nJOIN hospitality_technology.service_orders s2\n ON s1.bill_id = s2.bill_id\n AND s1.order_id < s2.order_id;"}, {"role": "user", "content": "Exclude pairs where bill_id is null."}, {"role": "assistant", "content": "SELECT s1.order_id AS order1_id,\n s2.order_id AS order2_id,\n s1.bill_id\nFROM hospitality_technology.service_orders s1\nJOIN hospitality_technology.service_orders s2\n ON s1.bill_id = s2.bill_id\n AND s1.order_id < s2.order_id\nWHERE s1.bill_id IS NOT NULL;"}, {"role": "user", "content": "Also include only those pairs where the first order's total_price is greater than the second order's total_price."}, {"role": "assistant", "content": "SELECT s1.order_id AS order1_id,\n s2.order_id AS order2_id,\n s1.bill_id\nFROM hospitality_technology.service_orders s1\nJOIN hospitality_technology.service_orders s2\n ON s1.bill_id = s2.bill_id\n AND s1.order_id < s2.order_id\nWHERE s1.bill_id IS NOT NULL\n AND s1.total_price > s2.total_price;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.service_orders ( order_id.text, reservation_id.text, guest_id.text, service_id.text, staff_id_ordered.text, staff_id_delivered.text, order_timestamp.timestamp, delivery_timestamp.timestamp, quantity.integer, unit_price.numeric, total_price.numeric, status.text, notes.text, bill_id.text )\n"} {"conversations": [{"role": "user", "content": "What is the fuel efficiency of the train car with car_id 'TC456'?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to information about the fuel efficiency of specific train cars. The data available in the train_cars table only includes details such as car_id, train_id, car_number, car_type, class, capacity, and features. If you have another question or need assistance with something else, I'm happy to help."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.train_cars ( car_id.text, train_id.text, car_number.text, car_type.text, class.text, capacity.integer, features.text )\n"} {"conversations": [{"role": "user", "content": "Show me 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": "Show me all claims with police reports that were filed in the last 3 months, along with the policy details and customer information."}, {"role": "assistant", "content": "SELECT c.claim_id, c.policy_id, c.customer_id, c.incident_date, c.reported_date, c.description, c.estimated_loss, c.status, c.settlement_amount, c.settlement_date, c.police_report_number, pp.payment_date, pp.amount_paid, pp.payment_method FROM insurance.claims c JOIN insurance.premium_payments pp ON c.policy_id = pp.policy_id WHERE c.police_report_number IS NOT NULL AND c.reported_date >= CURRENT_DATE - INTERVAL '3 months';"}, {"role": "user", "content": "I also want to see how many documents were submitted for each of these claims."}, {"role": "assistant", "content": "SELECT c.claim_id, c.policy_id, c.customer_id, COUNT(cd.document_id) AS document_count FROM insurance.claims c LEFT JOIN insurance.claim_documents cd ON c.claim_id = cd.claim_id WHERE c.police_report_number IS NOT NULL AND c.reported_date >= CURRENT_DATE - INTERVAL '3 months' GROUP BY c.claim_id, c.policy_id, c.customer_id;"}, {"role": "user", "content": "Now filter to only show claims where the estimated loss is above $10,000."}, {"role": "assistant", "content": "SELECT c.claim_id, c.policy_id, c.customer_id, COUNT(cd.document_id) AS document_count FROM insurance.claims c LEFT JOIN insurance.claim_documents cd ON c.claim_id = cd.claim_id WHERE c.police_report_number IS NOT NULL AND c.reported_date >= CURRENT_DATE - INTERVAL '3 months' AND c.estimated_loss > 10000 GROUP BY c.claim_id, c.policy_id, c.customer_id;"}, {"role": "user", "content": "Finally, order the results by the highest estimated loss first."}, {"role": "assistant", "content": "SELECT c.claim_id, c.policy_id, c.customer_id, COUNT(cd.document_id) AS document_count, c.estimated_loss FROM insurance.claims c LEFT JOIN insurance.claim_documents cd ON c.claim_id = cd.claim_id WHERE c.police_report_number IS NOT NULL AND c.reported_date >= CURRENT_DATE - INTERVAL '3 months' AND c.estimated_loss > 10000 GROUP BY c.claim_id, c.policy_id, c.customer_id, c.estimated_loss ORDER BY c.estimated_loss 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 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.premium_payments ( payment_id.text, policy_id.text, customer_id.text, payment_date.timestamp, amount_paid.numeric, payment_method.text, transaction_reference.text, due_date.date, payment_period_start.date, payment_period_end.date, status.text )\nCREATE TABLE insurance.claim_documents ( document_id text, claim_id text, document_type text, file_name text, file_path text, file_size_bytes integer, mime_type text, uploaded_by text, uploaded_at timestamp, description text )\n"} {"conversations": [{"role": "user", "content": "List all 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": "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": "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": "List the name of each agency and the total number of service locations it operates in New York State."}, {"role": "assistant", "content": "SELECT a.agency_name, COUNT(sl.location_id) AS location_count\nFROM government_services.agencies a\nLEFT JOIN government_services.service_locations sl ON a.agency_id = sl.agency_id\nWHERE sl.state = 'NY'\nGROUP BY a.agency_name;"}, {"role": "user", "content": "Actually, only include those service locations that are accessible."}, {"role": "assistant", "content": "SELECT a.agency_name, COUNT(sl.location_id) AS location_count\nFROM government_services.agencies a\nLEFT JOIN government_services.service_locations sl ON a.agency_id = sl.agency_id\nWHERE sl.state = 'NY' AND sl.is_accessible = TRUE\nGROUP BY a.agency_name;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.agencies ( agency_id 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.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.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 room types that offer 'WiFi' in their amenities."}, {"role": "assistant", "content": "SELECT room_type_id, property_id, type_name, amenities FROM hospitality_technology.room_types WHERE amenities LIKE '%WiFi%';"}, {"role": "user", "content": "Only include those with a base rate below 100 and return the results sorted by base_rate ascending."}, {"role": "assistant", "content": "SELECT room_type_id, property_id, type_name, amenities, base_rate FROM hospitality_technology.room_types WHERE amenities LIKE '%WiFi%' AND base_rate < 100 ORDER BY base_rate ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.room_types ( room_type_id.text, property_id.text, type_name.text, description.text, base_rate.numeric, max_occupancy.integer, bed_type.text, area_sqft.numeric, amenities.text )\n"} {"conversations": [{"role": "user", "content": "Now, sort the results by the date opened, oldest first, and show only the top 10."}, {"role": "assistant", "content": "SELECT case_name, case_number, date_opened FROM legal_services.cases WHERE lead_lawyer_id = 'lawyer_abc' AND status = 'Open' AND case_type = 'Criminal' ORDER BY date_opened ASC LIMIT 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.cases ( case_id.text, case_number.text, case_name.text, client_id.text, lead_lawyer_id.text, case_type.text, status.text, date_opened.timestamp, date_closed.timestamp, description.text, court_jurisdiction.text )\n"} {"conversations": [{"role": "user", "content": "For each user, list all pairs of read and unread notifications, showing the recipient_user_id, the unread notification_id and type, and the read notification_id and type."}, {"role": "assistant", "content": "SELECT\n n_unread.recipient_user_id,\n n_unread.notification_id AS unread_id,\n n_unread.notification_type AS unread_type,\n n_read.notification_id AS read_id,\n n_read.notification_type AS read_type\nFROM social_media.notifications n_unread\nJOIN social_media.notifications n_read\n ON n_unread.recipient_user_id = n_read.recipient_user_id\nWHERE n_unread.read_at IS NULL\n AND n_read.read_at IS NOT NULL;"}, {"role": "user", "content": "Actually, only include pairs where the unread notification_type is 'message'."}, {"role": "assistant", "content": "SELECT\n n_unread.recipient_user_id,\n n_unread.notification_id AS unread_id,\n n_unread.notification_type AS unread_type,\n n_read.notification_id AS read_id,\n n_read.notification_type AS read_type\nFROM social_media.notifications n_unread\nJOIN social_media.notifications n_read\n ON n_unread.recipient_user_id = n_read.recipient_user_id\nWHERE n_unread.read_at IS NULL\n AND n_read.read_at IS NOT NULL\n AND n_unread.notification_type = 'message';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.notifications ( notification_id character varying(64) NOT NULL, recipient_user_id character varying(64) NOT NULL, sender_user_id character varying(64), notification_type character varying(30) NOT NULL, target_entity_id character varying(64), target_entity_type character varying(20), created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, read_at timestamp, PRIMARY KEY (notification_id) )\n"} {"conversations": [{"role": "user", "content": "Show me the number of distinct room types offered by each property, including the property name and the count."}, {"role": "assistant", "content": "SELECT T1.property_name, COUNT(DISTINCT T2.room_type_id) FROM hospitality_technology.properties AS T1 JOIN hospitality_technology.room_types AS T2 ON T1.property_id = T2.property_id GROUP BY T1.property_id;"}, {"role": "user", "content": "Now, only show properties that offer more than 5 distinct room types."}, {"role": "assistant", "content": "SELECT T1.property_name, COUNT(DISTINCT T2.room_type_id) FROM hospitality_technology.properties AS T1 JOIN hospitality_technology.room_types AS T2 ON T1.property_id = T2.property_id GROUP BY T1.property_id HAVING COUNT(DISTINCT T2.room_type_id) > 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.properties (\n property_id character varying(64) NOT NULL, -- unique identifier for the property (hotel, resort, etc.)\n property_name character varying(255) NOT NULL, -- name of the property\n address_line1 character varying(255) NOT NULL, -- primary address line\n address_line2 character varying(255), -- secondary address line\n city character varying(100) NOT NULL, -- city\n state_province character varying(100), -- state or province\n postal_code character varying(20) NOT NULL, -- zip or postal code\n country_code character varying(3) NOT NULL, -- ISO country code (e.g., USA, CAN)\n phone_number character varying(30), -- main contact phone\n email_address character varying(255), -- main contact email\n property_type character varying(50) NOT NULL, -- e.g., Hotel, Resort, B&B, Motel\n star_rating numeric(2,1), -- star rating (e.g., 4.5)\n timezone character varying(64) NOT NULL, -- IANA timezone ID (e.g., America/New_York)\n manager_staff_id character varying(64), -- FK to staff table for the general manager\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, -- record creation time\n updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, -- record last update time\n PRIMARY KEY (property_id)\n)\nCREATE TABLE hospitality_technology.rooms ( room_id.text, property_id.text, room_number.text, room_type_id.text, floor.integer, status.text, is_smoking.boolean, features.text, current_condition.text, last_cleaned_at.timestamp )\nCREATE TABLE hospitality_technology.room_types ( room_type_id text PRIMARY KEY, property_id text, type_name text, description text, base_rate numeric, max_occupancy int, bed_type text, area_sqft numeric, amenities text )\nCREATE TABLE hospitality_technology.guests ( guest_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, email character varying(255) UNIQUE, phone_number character varying(30), date_of_birth date, address_line1 character varying(255), city character varying(100), state_province character varying(100), postal_code character varying(20), country_code character varying(3), preferences text, loyalty_member_id character varying(64) UNIQUE, communication_consent boolean DEFAULT true, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (guest_id) )\nCREATE TABLE hospitality_technology.reservations ( reservation_id text PRIMARY KEY, property_id text, guest_id text, room_id text, room_type_id text, check_in_date date, check_out_date date, actual_check_in_ts timestamp, actual_check_out_ts timestamp, num_adults int, num_children int, status text, booking_source text, rate_plan_id text, total_amount numeric, amount_paid numeric, special_requests text, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.services ( service_id.text, property_id.text, service_name.text, description.text, category.text, price.numeric, unit.text, is_available.boolean, department.text )\nCREATE TABLE hospitality_technology.reviews ( review_id text, property_id text, reservation_id text, guest_id text, rating_overall integer, rating_cleanliness integer, rating_service integer, rating_location integer, rating_value integer, comment text, review_source text, review_date timestamp, is_public boolean, staff_response text, response_staff_id text, response_date timestamp )\n"} {"conversations": [{"role": "user", "content": "I need to find patients who received prescriptions within 7 days after their latest appointment. Show patient_id, first and last name, appointment_time, prescription_date, and medication_name."}, {"role": "assistant", "content": "WITH latest_appt AS (\n SELECT patient_id, MAX(appointment_time) AS latest_time\n FROM healthcare.appointments\n GROUP BY patient_id\n)\nSELECT p.patient_id,\n p.first_name,\n p.last_name,\n la.latest_time AS appointment_time,\n pr.prescription_date,\n m.medication_name\nFROM latest_appt la\nJOIN healthcare.patients p\n ON p.patient_id = la.patient_id\nJOIN healthcare.prescriptions pr\n ON pr.patient_id = la.patient_id\n AND pr.prescription_date BETWEEN la.latest_time AND la.latest_time + INTERVAL '7 days'\nJOIN healthcare.medications m\n ON m.medication_id = pr.medication_id"}, {"role": "user", "content": "Actually, restrict it to prescriptions where dosage contains 'mg'."}, {"role": "assistant", "content": "WITH latest_appt AS (\n SELECT patient_id, MAX(appointment_time) AS latest_time\n FROM healthcare.appointments\n GROUP BY patient_id\n)\nSELECT p.patient_id,\n p.first_name,\n p.last_name,\n la.latest_time AS appointment_time,\n pr.prescription_date,\n m.medication_name\nFROM latest_appt la\nJOIN healthcare.patients p\n ON p.patient_id = la.patient_id\nJOIN healthcare.prescriptions pr\n ON pr.patient_id = la.patient_id\n AND pr.prescription_date BETWEEN la.latest_time AND la.latest_time + INTERVAL '7 days'\n AND pr.dosage LIKE '%mg%'\nJOIN healthcare.medications m\n ON m.medication_id = pr.medication_id"}, {"role": "user", "content": "Also, sort the results by prescription_date descending and limit to 5."}, {"role": "assistant", "content": "WITH latest_appt AS (\n SELECT patient_id, MAX(appointment_time) AS latest_time\n FROM healthcare.appointments\n GROUP BY patient_id\n)\nSELECT p.patient_id,\n p.first_name,\n p.last_name,\n la.latest_time AS appointment_time,\n pr.prescription_date,\n m.medication_name\nFROM latest_appt la\nJOIN healthcare.patients p\n ON p.patient_id = la.patient_id\nJOIN healthcare.prescriptions pr\n ON pr.patient_id = la.patient_id\n AND pr.prescription_date BETWEEN la.latest_time AND la.latest_time + INTERVAL '7 days'\n AND pr.dosage LIKE '%mg%'\nJOIN healthcare.medications m\n ON m.medication_id = pr.medication_id\nORDER BY pr.prescription_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 text, first_name text, last_name text, date_of_birth date, gender text, address text, phone_number text, email text, emergency_contact_name text, emergency_contact_phone text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.appointments ( appointment_id text, patient_id text, doctor_id text, appointment_time timestamp, duration_minutes integer, reason text, status text, location_id text, notes text, created_at timestamp )\nCREATE TABLE healthcare.medical_records ( record_id text, patient_id text, appointment_id text, doctor_id text, record_date timestamp, chief_complaint text, present_illness_history text, past_medical_history text, physical_examination_notes text, assessment text, treatment_plan text, vitals text, created_at timestamp )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id text, record_id text, patient_id text, doctor_id text, diagnosis_code text, code_type text, description text, diagnosis_date date, status text, is_chronic boolean )\nCREATE TABLE healthcare.medications ( medication_id text, medication_name text, generic_name text, manufacturer text, ndc_code text, description text )\nCREATE TABLE healthcare.prescriptions ( prescription_id text, record_id text, patient_id text, doctor_id text, medication_id text, dosage text, frequency text, route text, start_date date, end_date date, quantity_dispensed numeric, refills_allowed integer, prescription_date timestamp )\nCREATE TABLE healthcare.insurance_plans ( plan_id text, plan_name text, insurance_provider text, plan_type text, contact_phone text, website text )\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id text, patient_id text, plan_id text, policy_number text, group_number text, subscriber_name text, effective_date date, expiration_date date, is_primary boolean )\n"} {"conversations": [{"role": "user", "content": "Show all medical records with the record_id, record_date, the patient's insurance policy_number, and the doctor's ID, for records linked to a currently active insurance policy."}, {"role": "assistant", "content": "SELECT mr.record_id, mr.record_date, pi.policy_number, mr.doctor_id\nFROM healthcare.medical_records mr\nINNER JOIN healthcare.patient_insurance pi ON mr.patient_id = pi.patient_id\nWHERE pi.expiration_date IS NULL OR pi.expiration_date >= CURRENT_DATE;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.appointments ( appointment_id.text, patient_id.text, doctor_id.text, appointment_time.timestamp, duration_minutes.integer, reason.text, status.text, location_id.text, notes.text, created_at.timestamp )\nCREATE TABLE healthcare.medical_records ( record_id.text, patient_id.text, appointment_id.text, doctor_id.text, record_date.timestamp, chief_complaint.text, present_illness_history.text, past_medical_history.text, physical_examination_notes.text, assessment.text, treatment_plan.text, vitals.json, created_at.timestamp )\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id text, patient_id text, plan_id text, policy_number text, group_number text, subscriber_name text, effective_date date, expiration_date date, is_primary boolean )\n"} {"conversations": [{"role": "user", "content": "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": "What is the average balance of all addresses in the database?"}, {"role": "assistant", "content": "SELECT AVG(balance) as average_balance FROM blockchain.addresses;"}, {"role": "user", "content": "Can you break this down by the first 3 characters of the address_id?"}, {"role": "assistant", "content": "SELECT SUBSTRING(address_id, 1, 3) as address_prefix, AVG(balance) as average_balance FROM blockchain.addresses GROUP BY SUBSTRING(address_id, 1, 3);"}, {"role": "user", "content": "Now show only address prefixes where the average balance is greater than 1000."}, {"role": "assistant", "content": "SELECT SUBSTRING(address_id, 1, 3) as address_prefix, AVG(balance) as average_balance FROM blockchain.addresses GROUP BY SUBSTRING(address_id, 1, 3) HAVING AVG(balance) > 1000;"}, {"role": "user", "content": "Can you order these results by the average balance in descending order?"}, {"role": "assistant", "content": "SELECT SUBSTRING(address_id, 1, 3) as address_prefix, AVG(balance) as average_balance FROM blockchain.addresses GROUP BY SUBSTRING(address_id, 1, 3) HAVING AVG(balance) > 1000 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 blockchain.addresses ( address_id.text, public_key.text, balance.numeric )\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": "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": "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": "List active policies where the premium amount is greater than the base premium of the linked insurance product. Show policy number, policy premium, product name, and product base premium."}, {"role": "assistant", "content": "SELECT T1.policy_number, T1.premium_amount, T2.product_name, T2.base_premium FROM insurance.policies AS T1 JOIN insurance.insurance_products AS T2 ON T1.product_id = T2.product_id WHERE T1.status = 'active' AND T1.premium_amount > T2.base_premium;"}, {"role": "user", "content": "Also, only include policies that were issued in the year 2023."}, {"role": "assistant", "content": "SELECT T1.policy_number, T1.premium_amount, T2.product_name, T2.base_premium FROM insurance.policies AS T1 JOIN insurance.insurance_products AS T2 ON T1.product_id = T2.product_id WHERE T1.status = 'active' AND T1.premium_amount > T2.base_premium AND EXTRACT(YEAR FROM T1.issued_at) = 2023;"}, {"role": "user", "content": "Could you sort the results by policy premium in descending order and limit to the top 10?"}, {"role": "assistant", "content": "SELECT T1.policy_number, T1.premium_amount, T2.product_name, T2.base_premium FROM insurance.policies AS T1 JOIN insurance.insurance_products AS T2 ON T1.product_id = T2.product_id WHERE T1.status = 'active' AND T1.premium_amount > T2.base_premium AND EXTRACT(YEAR FROM T1.issued_at) = 2023 ORDER BY T1.premium_amount 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 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": "For each user, show the most recently created wallet address and the wallet creation timestamp."}, {"role": "assistant", "content": "SELECT w1.user_id, w1.address, w1.created_at\nFROM web3.wallets w1\nJOIN (\n SELECT user_id, MAX(created_at) AS max_created_at\n FROM web3.wallets\n GROUP BY user_id\n) w2 ON w1.user_id = w2.user_id AND w1.created_at = w2.max_created_at;"}, {"role": "user", "content": "Can you also include the wallet_id of the most recent wallet for each user in the result?"}, {"role": "assistant", "content": "SELECT w1.user_id, w1.wallet_id, w1.address, w1.created_at\nFROM web3.wallets w1\nJOIN (\n SELECT user_id, MAX(created_at) AS max_created_at\n FROM web3.wallets\n GROUP BY user_id\n) w2 ON w1.user_id = w2.user_id AND w1.created_at = w2.max_created_at;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.wallets ( wallet_id text PRIMARY KEY, user_id text, address text, private_key text, created_at timestamp )\n"} {"conversations": [{"role": "user", "content": "List all agencies that do not have a website URL specified. Return their agency_id, agency_name, and main_phone_number."}, {"role": "assistant", "content": "SELECT agency_id, agency_name, main_phone_number FROM government_services.agencies WHERE website_url IS NULL OR website_url = '';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.agencies ( agency_id character varying(64) NOT NULL, agency_name character varying(255) NOT NULL, jurisdiction_level character varying(50) NOT NULL, primary_contact_email character varying(128), main_phone_number character varying(32), website_url character varying(255), established_date date, parent_agency_id character varying(64), PRIMARY KEY (agency_id) )\n"} {"conversations": [{"role": "user", "content": "Show the symbol, name, and total supply for all SUI coins with status 'active'."}, {"role": "assistant", "content": "SELECT scm.symbol, scm.name, scm.coin_type, scm.total_supply\nFROM sui_coins_metadata scm\nWHERE scm.status = 'active';"}, {"role": "user", "content": "I received an error that column 'total_supply' doesn't exist in sui_coins_metadata."}, {"role": "assistant", "content": "SELECT scm.symbol, scm.name, scm.coin_type\nFROM sui_coins_metadata scm\nWHERE scm.status = 'active';"}, {"role": "user", "content": "Now, join with sui_coins to add up the total balance across all owners for each coin_type."}, {"role": "assistant", "content": "SELECT scm.symbol, scm.name, scm.coin_type, SUM(CAST(sc.balance AS NUMERIC)) AS total_balance\nFROM sui_coins_metadata scm\nJOIN sui_coins sc ON scm.coin_type = sc.coin_type\nWHERE scm.status = 'active'\nGROUP BY scm.symbol, scm.name, scm.coin_type;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp timestamp, block_number bigint, transaction_hash text, transaction_index bigint, from_address text, contract_address text, symbol text, total_supply text, name text, decimals bigint, is_erc20 integer, is_erc721 integer, is_erc1155 integer, is_proxy integer, extra_info text, pk integer )\nCREATE TABLE erc1155_approval_for_all ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash text, log_index integer, contract_address text )\nCREATE TABLE erc20_balances ( block_number bigint, contract_address text, wallet_address text, amount text, pk text )\nCREATE TABLE erc20_balances_historical ( block_number bigint, contract_address text, wallet_address text, amount text, pk integer )\nCREATE TABLE nft_holders ( block_number bigint, contract_address text, wallet_address text, token_id text, contract_type text, amount text, pk text )\nCREATE TABLE nft_holder_historical ( block_number bigint, contract_address text, wallet_address text, token_id text, contract_type text, amount text, pk integer )\nCREATE TABLE sui_coins ( object_id text, status text, coin_type text, balance text, owner text )\nCREATE TABLE sui_coins_metadata ( object_id text, coin_type text, status text, decimals bigint, description text, icon_url text, symbol text, name text )\nCREATE TABLE sui_nfts ( object_id text, status text, collection_type text, package_id text, previous_transaction text, display text, owner text, name text )\nCREATE TABLE nft_metadata ( blockchain text, contract_address text, token_id text, contract_name text, erc_type text, amount bigint, minter text, owner text, mint_block_number bigint, mint_time bigint, mint_transaction_hash text, mint_price text, token_uri text, metadata text, name text, image_uri text, traits text, updated_at bigint, status text, rarity_score real, rarity_rank integer, unique_attribute_count integer, pk integer )\nCREATE TABLE nft_collections ( blockchain text, contract_address text, name text, symbol text, deploy_block_number bigint, deploy_block_time bigint, erc_type text, owner text, traits text, description text, slug text, media_info text, image_url text, banner_image_url text, updated_at bigint, banner text, token_count bigint, floor_price text, floor_price_symbol text, floor_price_contract text, pk integer )\nCREATE TABLE token_prices ( uuid text, blockchain text, address text, decimals bigint, symbol text, price real, timestamp timestamp )\nCREATE TABLE token_prices_latest ( blockchain text, address text, decimals bigint, symbol text, price real, timestamp timestamp )\nCREATE TABLE erc20_approval ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash text, log_index integer, contract_address text, pk integer )\nCREATE TABLE token_balances ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply decimal, amount decimal )\nCREATE TABLE token_info ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text )\nCREATE TABLE token_activities ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE mud_holesky_redstone ( address text, table_id text, key_bytes text, key0 text, key1 text, static_data text, encoded_lengths text, dynamic_data text, is_deleted boolean, block_number bigint, log_index bigint )\nCREATE TABLE token_balances_bitcoin ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply text, amount text )\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_balances_avalanche ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply decimal, amount decimal )\n"} {"conversations": [{"role": "user", "content": "What is the detailed repair history of the equipment used by the staff with staff_id 'STAFF123' during maintenance tasks?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information on the detailed repair history of equipment used by staff members. The data in the maintenance_records table only includes information about maintenance tasks, such as record_id, asset_id, maintenance type, and staff_id, but does not cover equipment repair histories."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.maintenance_records ( record_id.text, asset_id.text, asset_type.text, maintenance_type.text, staff_id.text, start_datetime.timestamp, end_datetime.timestamp, description.text, cost.numeric, status.text )\n"} {"conversations": [{"role": "user", "content": "Show each account's number and type, along with the date it was opened and its interest rate."}, {"role": "assistant", "content": "SELECT account_number, account_type, opened_date, interest_rate FROM financial_services.accounts;"}, {"role": "user", "content": "Only show accounts with an interest rate higher than 2%."}, {"role": "assistant", "content": "SELECT account_number, account_type, opened_date, interest_rate FROM financial_services.accounts WHERE interest_rate > 0.02;"}], "system": "You are an SQL statement expert. Given the table structure 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) )\n"} {"conversations": [{"role": "user", "content": "List all Sui NFT collections where the owner is not null, including their name and collection_type."}, {"role": "assistant", "content": "SELECT name, collection_type FROM sui_nfts WHERE owner IS NOT NULL;"}, {"role": "user", "content": "Can you filter these results to only show collections with 'art' in their collection_type and add the display field?"}, {"role": "assistant", "content": "SELECT name, collection_type, display FROM sui_nfts WHERE owner IS NOT NULL AND collection_type LIKE '%art%';"}, {"role": "user", "content": "Now sort these results by name in ascending order and limit to the top 10."}, {"role": "assistant", "content": "SELECT name, collection_type, display FROM sui_nfts WHERE owner IS NOT NULL AND collection_type LIKE '%art%' ORDER BY name 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 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 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 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 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 )\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar(20) NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL, minted decimal(38,0) NOT NULL, holders decimal(38,0) NOT NULL, txs decimal(38,0) NOT NULL, updated_timestamp timestamp(3) NOT NULL, completed_timestamp timestamp(3) NOT NULL, id varchar(255) NOT NULL )\n"} {"conversations": [{"role": "user", "content": "List all tokens with a market cap rank under 100 and a negative 1-hour price change percentage."}, {"role": "assistant", "content": "SELECT token_name, token_symbol, market_cap_rank, price_change_percentage_1h FROM token_basic_info WHERE market_cap_rank < 100 AND price_change_percentage_1h < 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_basic_info ( coin_id character varying(100) NOT NULL, token_name character varying(100) NOT NULL, token_symbol character varying(100) NOT NULL, token_address character varying(100) NOT NULL, chain text, price double precision, price_change_percentage_1h double precision, price_change_percentage_24h double precision, price_change_percentage_7d double precision, highest_price_24h double precision, lowest_price_24h double precision, market_cap double precision, market_cap_rank bigint, market_cap_change_percentage_24h text, total_volume text, narrative text, trend_rank bigint )\n"} {"conversations": [{"role": "user", "content": "Find all pairs of transactions that occurred in the same block and were sent to the same address. Show both transaction IDs, the shared recipient address, and the block number."}, {"role": "assistant", "content": "SELECT t1.transaction_id AS tx1,\n t2.transaction_id AS tx2,\n t1.to_address,\n t1.block_number\nFROM transactions t1\nJOIN transactions t2\n ON t1.to_address = t2.to_address\n AND t1.block_number = t2.block_number\n AND t1.transaction_id < t2.transaction_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.transactions ( transaction_id text, from_address text, to_address text, value numeric, gas_used integer, gas_price numeric, block_number integer, timestamp timestamp, input_data text, status text, nonce integer )\n"} {"conversations": [{"role": "user", "content": "Could you list the trip ID, scheduled and actual arrival times, and the associated vehicle's make and model for all trips where the actual arrival was more than 30 minutes later than scheduled?"}, {"role": "assistant", "content": "SELECT T1.trip_id, T1.scheduled_arrival, T1.actual_arrival, T2.make, T2.model FROM transportation.trips AS T1 JOIN transportation.vehicles AS T2 ON T1.vehicle_id = T2.vehicle_id WHERE T1.actual_arrival IS NOT NULL AND T1.scheduled_arrival IS NOT NULL AND T1.actual_arrival > T1.scheduled_arrival + INTERVAL '30 minutes';"}, {"role": "user", "content": "Now, filter this list to only include trips that were completed within the last 6 months."}, {"role": "assistant", "content": "SELECT T1.trip_id, T1.scheduled_arrival, T1.actual_arrival, T2.make, T2.model FROM transportation.trips AS T1 JOIN transportation.vehicles AS T2 ON T1.vehicle_id = T2.vehicle_id WHERE T1.actual_arrival IS NOT NULL AND T1.scheduled_arrival IS NOT NULL AND T1.actual_arrival > T1.scheduled_arrival + INTERVAL '30 minutes' AND T1.actual_arrival >= NOW() - INTERVAL '6 months';"}], "system": "You are an SQL statement expert. Given the table structure 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 )\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.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 )\n"} {"conversations": [{"role": "user", "content": "Which vehicles have a total maintenance cost exceeding 10000 across all their maintenance logs?"}, {"role": "assistant", "content": "SELECT vehicle_id, SUM(cost) AS total_maintenance_cost FROM transportation.maintenance_logs GROUP BY vehicle_id HAVING SUM(cost) > 10000;"}, {"role": "user", "content": "For these vehicles, also show the count of maintenance logs and the average cost per log."}, {"role": "assistant", "content": "SELECT vehicle_id, COUNT(log_id) AS maintenance_log_count, AVG(cost) AS average_maintenance_cost FROM transportation.maintenance_logs GROUP BY vehicle_id HAVING SUM(cost) > 10000;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles ( vehicle_id character varying(64) NOT NULL, license_plate character varying(32) NOT NULL UNIQUE, vin character varying(17) UNIQUE, make character varying(64) NOT NULL, model character varying(64) NOT NULL, year integer NOT NULL, type character varying(32) NOT NULL, capacity integer, fuel_type character varying(32) NOT NULL, status character varying(32) NOT NULL, depot_id character varying(64), acquisition_date date, PRIMARY KEY (vehicle_id) )\nCREATE TABLE transportation.trips ( trip_id character varying(64) NOT NULL, route_id character varying(64), vehicle_id character varying(64) NOT NULL, driver_id character varying(64) NOT NULL, scheduled_departure timestamp with time zone NOT NULL, actual_departure timestamp with time zone, scheduled_arrival timestamp with time zone NOT NULL, actual_arrival timestamp with time zone, origin_location_id character varying(64) NOT NULL, destination_location_id character varying(64) NOT NULL, status character varying(32) NOT NULL, passenger_count integer, cargo_manifest_id character varying(64), PRIMARY KEY (trip_id) )\nCREATE TABLE transportation.locations ( location_id character varying(64) NOT NULL, name character varying(255) NOT NULL, type character varying(64) NOT NULL, address_line1 character varying(255), city character varying(128), state_province character varying(128), postal_code character varying(32), country character varying(64) NOT NULL, latitude numeric(9, 6), longitude numeric(9, 6), timezone character varying(64), PRIMARY KEY (location_id) )\nCREATE TABLE transportation.maintenance_logs ( log_id character varying(64) NOT NULL, vehicle_id character varying(64) NOT NULL, service_date date NOT NULL, odometer_reading integer, service_type character varying(128) NOT NULL, description text NOT NULL, cost numeric(10, 2), mechanic_name character varying(128), next_service_due_date date, PRIMARY KEY (log_id) )\nCREATE TABLE transportation.fuel_logs ( fuel_log_id character varying(64) NOT NULL, vehicle_id character varying(64) NOT NULL, trip_id character varying(64), log_timestamp timestamp with time zone NOT NULL, fuel_type character varying(32) NOT NULL, quantity numeric(10, 3) NOT NULL, unit character varying(16) NOT NULL, cost_per_unit numeric(8, 4), total_cost numeric(10, 2) NOT NULL, odometer_reading integer, location_id character varying(64), PRIMARY KEY (fuel_log_id) )\nCREATE TABLE transportation.passengers ( passenger_id character varying(64) NOT NULL, first_name character varying(128) NOT NULL, last_name character varying(128) NOT NULL, email character varying(128) UNIQUE, phone_number character varying(32) UNIQUE, date_of_birth date, loyalty_program_id character varying(64), created_at timestamp with time zone NOT NULL, PRIMARY KEY (passenger_id) )\n"} {"conversations": [{"role": "user", "content": "How many customers are there for each status?"}, {"role": "assistant", "content": "SELECT status, COUNT(*) FROM financial_services.customers GROUP BY status"}, {"role": "user", "content": "Only show statuses where the count is greater than 50."}, {"role": "assistant", "content": "SELECT status, COUNT(*) FROM financial_services.customers GROUP BY status HAVING COUNT(*) > 50"}, {"role": "user", "content": "Sort the results by the count in descending order."}, {"role": "assistant", "content": "SELECT status, COUNT(*) FROM financial_services.customers GROUP BY status HAVING COUNT(*) > 50 ORDER BY COUNT(*) DESC"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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": "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": "List all medical record entries where the treatment_plan mentions a medication name. Return patient_id, record_id, and the matching medication_name."}, {"role": "assistant", "content": "SELECT mr.patient_id,\n mr.record_id,\n m.medication_name\nFROM healthcare.medical_records AS mr\nJOIN healthcare.medications AS m\n ON mr.treatment_plan ILIKE '%' || m.medication_name || '%';"}, {"role": "user", "content": "Actually, only include medications manufactured by 'Pfizer'."}, {"role": "assistant", "content": "SELECT mr.patient_id,\n mr.record_id,\n m.medication_name\nFROM healthcare.medical_records AS mr\nJOIN healthcare.medications AS m\n ON mr.treatment_plan ILIKE '%' || m.medication_name || '%'\nWHERE m.manufacturer = 'Pfizer';"}, {"role": "user", "content": "Also sort the results by record_date descending."}, {"role": "assistant", "content": "SELECT mr.patient_id,\n mr.record_id,\n m.medication_name\nFROM healthcare.medical_records AS mr\nJOIN healthcare.medications AS m\n ON mr.treatment_plan ILIKE '%' || m.medication_name || '%'\nWHERE m.manufacturer = 'Pfizer'\nORDER BY mr.record_date DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients (\n patient_id character varying(64) NOT NULL, -- unique identifier for the patient\n first_name character varying(100) NOT NULL, -- patient's first name\n last_name character varying(100) NOT NULL, -- patient's last name\n date_of_birth date NOT NULL, -- patient's date of birth\n gender character varying(10), -- patient's gender (e.g., Male, Female, Other)\n address text, -- patient's home address\n phone_number character varying(20), -- patient's phone number\n email character varying(128) UNIQUE, -- patient's email address\n emergency_contact_name character varying(200), -- name of emergency contact\n emergency_contact_phone character varying(20), -- phone number of emergency contact\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, -- record creation time\n updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, -- record last update time\n PRIMARY KEY (patient_id)\n)\nCREATE TABLE healthcare.doctors (\n doctor_id character varying(64) NOT NULL, -- unique identifier for the doctor\n first_name character varying(100) NOT NULL, -- doctor's first name\n last_name character varying(100) NOT NULL, -- doctor's last name\n specialty character varying(100) NOT NULL, -- doctor's medical specialty\n license_number character varying(50) UNIQUE NOT NULL, -- doctor's medical license number\n phone_number character varying(20), -- doctor's contact phone\n email character varying(128) UNIQUE, -- doctor's contact email\n hospital_affiliation_id character varying(64), -- FK to hospitals table (optional)\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n PRIMARY KEY (doctor_id)\n)\nCREATE TABLE healthcare.appointments (\n appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment\n patient_id character varying(64) NOT NULL, -- FK to patients table\n doctor_id character varying(64) NOT NULL, -- FK to doctors table\n appointment_time timestamp with time zone NOT NULL, -- date and time of the appointment\n duration_minutes integer NOT NULL, -- expected duration in minutes\n reason text, -- reason for the visit\n status character varying(32) NOT NULL, -- e.g., Scheduled, Completed, Cancelled, No-show\n location_id character varying(64), -- FK to a potential locations/clinics table\n notes text, -- notes related to scheduling\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n PRIMARY KEY (appointment_id)\n)\nCREATE TABLE healthcare.medical_records (\n record_id character varying(64) NOT NULL, -- unique identifier for the medical record entry\n patient_id character varying(64) NOT NULL, -- FK to patients table\n appointment_id character varying(64) UNIQUE, -- FK to appointments table (can be null if record not tied to specific appt)\n doctor_id character varying(64) NOT NULL, -- FK to doctors table (doctor creating the record)\n record_date timestamp with time zone NOT NULL, -- date the record/observation was made\n chief_complaint text, -- patient's primary reason for visit\n present_illness_history text, -- detailed history of the current issue\n past_medical_history text, -- relevant past conditions/surgeries\n physical_examination_notes text, -- findings from the physical exam\n assessment text, -- doctor's assessment/diagnosis summary\n treatment_plan text, -- planned course of action\n vitals jsonb, -- store vitals like BP, HR, Temp as structured JSON\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n PRIMARY KEY (record_id)\n)\nCREATE TABLE healthcare.medications (\n medication_id character varying(64) NOT NULL, -- unique identifier for the medication type\n medication_name character varying(255) NOT NULL, -- common or brand name\n generic_name character varying(255), -- generic chemical name\n manufacturer character varying(100), -- drug manufacturer\n ndc_code character varying(20) UNIQUE, -- National Drug Code (optional but useful)\n description text, -- description of the medication\n PRIMARY KEY (medication_id)\n)\nCREATE TABLE healthcare.insurance_plans (\n plan_id character varying(64) NOT NULL, -- unique identifier for the insurance plan\n plan_name character varying(200) NOT NULL, -- name of the insurance plan\n insurance_provider character varying(100) NOT NULL, -- name of the insurance company\n plan_type character varying(50), -- e.g., PPO, HMO, EPO\n contact_phone character varying(20), -- provider contact number\n website character varying(255), -- provider website\n PRIMARY KEY (plan_id)\n)\nCREATE TABLE healthcare.patient_insurance (\n patient_insurance_id character varying(64) NOT NULL, -- unique identifier for this patient-plan link\n patient_id character varying(64) NOT NULL, -- FK to patients table\n plan_id character varying(64) NOT NULL, -- FK to insurance_plans table\n policy_number character varying(100) NOT NULL, -- patient's policy number\n group_number character varying(100), -- group number, if applicable\n subscriber_name character varying(200), -- name of the primary policy holder\n effective_date date NOT NULL, -- date the coverage begins\n expiration_date date, -- date the coverage ends (if known)\n is_primary boolean NOT NULL DEFAULT true, -- indicates if this is the primary insurance\n PRIMARY KEY (patient_insurance_id),\n UNIQUE (patient_id, plan_id, policy_number) -- ensure a patient doesn't have the same policy twice\n)\n"} {"conversations": [{"role": "user", "content": "Show me 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": "Can you list each server along with its game title and how many players it can still accommodate (max_players - current_players)?"}, {"role": "assistant", "content": "SELECT s.server_id,\n s.server_name,\n g.title AS game_title,\n (s.max_players - s.current_players) AS available_slots\nFROM gaming_technology.servers s\nJOIN gaming_technology.games g ON s.game_id = g.game_id;"}, {"role": "user", "content": "Only include servers that are currently 'online' or 'idle'."}, {"role": "assistant", "content": "SELECT s.server_id,\n s.server_name,\n g.title AS game_title,\n (s.max_players - s.current_players) AS available_slots\nFROM gaming_technology.servers s\nJOIN gaming_technology.games g ON s.game_id = g.game_id\nWHERE s.status IN ('online', 'idle');"}, {"role": "user", "content": "Now show only those with available_slots greater than 10, sorted by available_slots descending."}, {"role": "assistant", "content": "SELECT s.server_id,\n s.server_name,\n g.title AS game_title,\n (s.max_players - s.current_players) AS available_slots\nFROM gaming_technology.servers s\nJOIN gaming_technology.games g ON s.game_id = g.game_id\nWHERE s.status IN ('online', 'idle')\n AND (s.max_players - s.current_players) > 10\nORDER BY available_slots DESC;"}, {"role": "user", "content": "Finally, include the game's release_date and only for games released after 2022-01-01."}, {"role": "assistant", "content": "SELECT s.server_id,\n s.server_name,\n g.title AS game_title,\n g.release_date,\n (s.max_players - s.current_players) AS available_slots\nFROM gaming_technology.servers s\nJOIN gaming_technology.games g ON s.game_id = g.game_id\nWHERE s.status IN ('online', 'idle')\n AND (s.max_players - s.current_players) > 10\n AND g.release_date > '2022-01-01'\nORDER BY available_slots DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.games ( game_id uuid NOT NULL DEFAULT gen_random_uuid(), title character varying(200) NOT NULL, developer_id uuid NOT NULL, publisher_id uuid, genre character varying(100), release_date date, description text, platform character varying(50) NOT NULL, engine character varying(100), website character varying(255), PRIMARY KEY (game_id) )\nCREATE TABLE gaming_technology.servers ( server_id.uuid, game_id.uuid, server_name.text, region.text, ip_address.text, port.integer, current_players.integer, max_players.integer, status.text, last_heartbeat.timestamptz )\nCREATE TABLE gaming_technology.player_achievements ( player_achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), player_id uuid NOT NULL, achievement_id uuid NOT NULL, unlocked_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (player_achievement_id), UNIQUE (player_id, achievement_id) )\nCREATE TABLE gaming_technology.player_inventory ( inventory_id uuid NOT NULL DEFAULT gen_random_uuid(), player_id uuid NOT NULL, item_id uuid NOT NULL, quantity integer NOT NULL DEFAULT 1, acquired_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, instance_data jsonb, PRIMARY KEY (inventory_id) )\n"} {"conversations": [{"role": "user", "content": "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": "List all ERC20 tokens where the price is between $1 and $10, including their names, symbols, and contract addresses."}, {"role": "assistant", "content": "SELECT name, symbol, address FROM token_prices_latest WHERE price BETWEEN 1 AND 10 AND blockchain = 'ethereum';"}, {"role": "user", "content": "I think there's an error in your query - it should be joining with sui_coins_metadata on coin_type not address. Also, can you add the current price to the results?"}, {"role": "assistant", "content": "SELECT scm.name, scm.symbol, scm.coin_type, tpl.price FROM sui_coins_metadata scm JOIN token_prices_latest tpl ON scm.coin_type = tpl.address WHERE tpl.price BETWEEN 1 AND 10;"}, {"role": "user", "content": "Now filter these results to only show tokens with decimals equal to 18 and sort by name alphabetically."}, {"role": "assistant", "content": "SELECT scm.name, scm.symbol, scm.coin_type, tpl.price FROM sui_coins_metadata scm JOIN token_prices_latest tpl ON scm.coin_type = tpl.address WHERE tpl.price BETWEEN 1 AND 10 AND scm.decimals = 18 ORDER BY scm.name ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE erc1155_approval_for_all (\n block_number bigint NOT NULL, -- Block number containing the transaction\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the transaction\n transaction_index integer NOT NULL, -- Index of the transaction within the block\n transaction_hash varchar(66) NOT NULL, -- Transaction hash\n log_index integer NOT NULL, -- Log index\n contract_address varchar(42) NOT NULL -- Event contract address\n)\nCREATE TABLE nft_holder_historical (\n block_number bigint NOT NULL, -- Block number containing the transaction\n contract_address varchar NOT NULL, -- Event contract address\n wallet_address varchar NOT NULL, -- The wallet address for the contract(with bloom filter)\n token_id varchar NOT NULL, -- NFT token id\n contract_type varchar NOT NULL, -- NFT contract type\n amount varchar NOT NULL, -- The quantity held in the wallet\n pk integer NOT NULL -- Partition key for the table(floor(block_number / 7200))\n)\nCREATE TABLE sui_coins_metadata ( object_id varchar, coin_type varchar, status varchar, decimals bigint, description varchar, icon_url varchar, symbol varchar, name varchar )\nCREATE TABLE sui_nfts (\n object_id varchar NOT NULL, -- object id of the nft\n status varchar NOT NULL, -- status of the package, exists or deleted\n collection_type varchar NOT NULL, -- collection type of the nft, eg. 0x...123::avatars::Avatar\n package_id varchar NOT NULL, -- which package the nft belongs to, eg. 0x...123::avatars belongs to 0x...123\n previous_transaction varchar NOT NULL, -- previous transaction of the nft\n display varchar NOT NULL, -- nft metadata json object\n owner varchar NOT NULL, -- nft owner\n name varchar NOT NULL -- nft name\n)\nCREATE TABLE nft_metadata (\n blockchain varchar NOT NULL, -- blockchain fields for the functionType in contract\n contract_address varchar NOT NULL, -- Contract address(with bloom filter)\n token_id varchar NOT NULL, -- The number of the token\n contract_name varchar NOT NULL, -- contract_name fields for the functionType in contract\n erc_type varchar NOT NULL, -- The type of token\n amount bigint NOT NULL, -- amount fields for the functionType in contract\n minter varchar NOT NULL, -- minter fields for the functionType in contract\n owner varchar NOT NULL, -- owner fields for the functionType in contract\n mint_block_number bigint NOT NULL, -- mint_block_number fields for the functionType in contract\n mint_time bigint NOT NULL, -- mint_time fields for the functionType in contract\n mint_transaction_hash varchar NOT NULL, -- mint_transaction_hash fields for the functionType in contract\n mint_price varchar NOT NULL, -- mint_price fields for the functionType in contract\n token_uri varchar NOT NULL, -- token_uri fields for the functionType in contract\n metadata varchar NOT NULL, -- metadata fields for the functionType in contract\n name varchar NOT NULL, -- name fields for the functionType in contract\n image_uri varchar NOT NULL, -- image_uri fields for the functionType in contract\n traits varchar NOT NULL, -- traits fields for the functionType in contract\n updated_at bigint NOT NULL, -- updated_at fields for the functionType in contract\n status varchar NOT NULL, -- status fields for the functionType in contract\n rarity_score real NOT NULL, -- rarity_score fields for the functionType in contract\n rarity_rank integer NOT NULL, -- rarity_rank fields for the functionType in contract\n unique_attribute_count integer NOT NULL, -- unique_attribute_count fields for the functionType in contract\n pk integer NOT NULL -- Partition key for the table(floor(mint_time / 1000 / 86400 / 30))\n)\nCREATE TABLE token_prices ( uuid varchar(36) NOT NULL, blockchain varchar(36) NOT NULL, address varchar(42) NOT NULL, decimals bigint NOT NULL, symbol varchar(36) NOT NULL, price real NOT NULL, timestamp timestamp(6) NOT NULL )\nCREATE TABLE token_prices_latest ( blockchain varchar, address varchar, decimals bigint, symbol varchar, price real, timestamp timestamp )\nCREATE TABLE token_balances (\n block_number bigint NOT NULL, -- Block number containing the transaction\n block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n tick varchar NOT NULL, -- Token tick\n wallet_address varchar(42) NOT NULL, -- Address of owner\n total_supply decimal(38,0) NOT NULL, -- Max supply\n amount decimal(38,0) NOT NULL -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_balances_bitcoin ( block_number.bigint, block_timestamp.timestamp, tick.text, wallet_address.text, total_supply.text, amount.text )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar(20) NOT NULL, tick varchar(255) NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(42) NOT NULL, to_address varchar(42) NOT NULL )\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id text )\n"} {"conversations": [{"role": "user", "content": "Show me all passengers who have made more than 3 bookings, along with their total fare spent and booking count."}, {"role": "assistant", "content": "SELECT p.passenger_id, p.first_name, p.last_name, COUNT(b.booking_id) AS booking_count, SUM(b.fare) AS total_fare FROM transportation.passengers p JOIN transportation.bookings b ON p.passenger_id = b.passenger_id GROUP BY p.passenger_id, p.first_name, p.last_name HAVING COUNT(b.booking_id) > 3"}, {"role": "user", "content": "Can you filter these results to only show passengers whose total fare exceeds $500 and include their email addresses?"}, {"role": "assistant", "content": "SELECT p.passenger_id, p.first_name, p.last_name, p.email, COUNT(b.booking_id) AS booking_count, SUM(b.fare) AS total_fare FROM transportation.passengers p JOIN transportation.bookings b ON p.passenger_id = b.passenger_id GROUP BY p.passenger_id, p.first_name, p.last_name, p.email HAVING COUNT(b.booking_id) > 3 AND SUM(b.fare) > 500"}, {"role": "user", "content": "Now order the results by total fare in descending order and limit to the top 10 passengers."}, {"role": "assistant", "content": "SELECT p.passenger_id, p.first_name, p.last_name, p.email, COUNT(b.booking_id) AS booking_count, SUM(b.fare) AS total_fare FROM transportation.passengers p JOIN transportation.bookings b ON p.passenger_id = b.passenger_id GROUP BY p.passenger_id, p.first_name, p.last_name, p.email HAVING COUNT(b.booking_id) > 3 AND SUM(b.fare) > 500 ORDER BY total_fare DESC LIMIT 10"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.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 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 (\n log_id character varying(64) NOT NULL, -- unique identifier for the maintenance record\n vehicle_id character varying(64) NOT NULL, -- identifier of the vehicle serviced\n service_date date NOT NULL, -- date the service was performed\n odometer_reading integer, -- vehicle mileage at time of service\n service_type character varying(128) NOT NULL, -- type of service (e.g., Oil Change, Tire Rotation, Engine Repair)\n description text NOT NULL, -- detailed description of work done\n cost numeric(10, 2), -- cost of the service\n mechanic_name character varying(128), -- name or ID of the mechanic/shop\n next_service_due_date date, -- recommended date for next service\n PRIMARY KEY (log_id)\n)\nCREATE TABLE transportation.fuel_logs ( 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 (\n passenger_id character varying(64) NOT NULL, -- unique identifier for the passenger\n first_name character varying(128) NOT NULL, -- passenger's first name\n last_name character varying(128) NOT NULL, -- passenger's last name\n email character varying(128) UNIQUE, -- email address\n phone_number character varying(32) UNIQUE, -- phone number\n date_of_birth date, -- passenger's date of birth\n loyalty_program_id character varying(64), -- identifier for loyalty program membership\n created_at timestamp with time zone NOT NULL, -- time when the passenger record was created\n PRIMARY KEY (passenger_id)\n)\nCREATE TABLE transportation.bookings ( booking_id.text, passenger_id.text, trip_id.text, seat_number.text, booking_time.timestamp, status.text, fare.numeric, payment_transaction_id.text, special_requests.text )\n"} {"conversations": [{"role": "user", "content": "Which projects raised funds in January 2022?"}, {"role": "assistant", "content": "SELECT project_name, rounds_name, investment_value, investment_date FROM project_fundraising_record WHERE investment_date >= '2022-01-01' AND investment_date < '2022-02-01';"}, {"role": "user", "content": "Please also show their introductions."}, {"role": "assistant", "content": "SELECT project_name, rounds_name, investment_value, investment_date, introduction FROM project_fundraising_record WHERE investment_date >= '2022-01-01' AND investment_date < '2022-02-01';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE project_fundraising_record ( id.text, project_id.text, project_name.text, rounds_name.text, investment_value.numeric, investment_date.text, introduction.text, valuation.numeric )\n"} {"conversations": [{"role": "user", "content": "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": "How many addresses have a realized_ratio below 0.5?"}, {"role": "assistant", "content": "SELECT COUNT(*) AS address_count FROM smart_money_profit WHERE realized_ratio < 0.5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE smart_money_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": "Find staff who both started and left their position in the same calendar year. Show their staff_id, full name, hire date, and termination date."}, {"role": "assistant", "content": "SELECT staff_id, CONCAT(first_name, ' ', last_name) AS full_name, hire_date, termination_date\nFROM hospitality_technology.staff\nWHERE termination_date IS NOT NULL AND EXTRACT(YEAR FROM hire_date) = EXTRACT(YEAR FROM termination_date);"}, {"role": "user", "content": "Please add the property_id to the result."}, {"role": "assistant", "content": "SELECT staff_id, CONCAT(first_name, ' ', last_name) AS full_name, property_id, hire_date, termination_date\nFROM hospitality_technology.staff\nWHERE termination_date IS NOT NULL AND EXTRACT(YEAR FROM hire_date) = EXTRACT(YEAR FROM termination_date);"}, {"role": "user", "content": "Also, only show those whose access_level is at least 3 and order the result by hire_date descending."}, {"role": "assistant", "content": "SELECT staff_id, CONCAT(first_name, ' ', last_name) AS full_name, property_id, hire_date, termination_date\nFROM hospitality_technology.staff\nWHERE termination_date IS NOT NULL\n AND EXTRACT(YEAR FROM hire_date) = EXTRACT(YEAR FROM termination_date)\n AND access_level >= 3\nORDER BY hire_date DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.staff (\n staff_id character varying(64) NOT NULL, -- unique identifier for the staff member\n property_id character varying(64) NOT NULL, -- FK to properties table (primary property)\n first_name character varying(100) NOT NULL,\n last_name character varying(100) NOT NULL,\n position character varying(100) NOT NULL, -- e.g., Front Desk Agent, Housekeeper, Manager, Concierge\n work_email character varying(255) UNIQUE, -- staff member's work email\n work_phone character varying(30),\n hire_date date NOT NULL,\n termination_date date, -- date employment ended (if applicable)\n is_active boolean NOT NULL DEFAULT true, -- currently employed flag\n access_level integer NOT NULL, -- permission level within systems (e.g., 1=basic, 5=admin)\n manager_id character varying(64), -- FK to staff table (self-referencing for supervisor)\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n PRIMARY KEY (staff_id),\n FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n FOREIGN KEY (manager_id) REFERENCES hospitality_technology.staff(staff_id)\n)\n"} {"conversations": [{"role": "user", "content": "What are the safety ratings or crash statistics for the Boeing 787 Dreamliner?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to safety ratings or crash statistics for specific aircraft models like the Boeing 787 Dreamliner. My data is limited to the information in the aircraft_models table, which includes details such as model name, manufacturer, passenger capacity, and technical specifications. For safety-related information, I recommend consulting official aviation authorities or safety reports."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE manufacturing.aircraft_models ( model_id text, model_name text, manufacturer text, passenger_capacity integer, max_range_km integer, engine_type text, wingspan_m numeric, status text, first_flight_date date )\n"} {"conversations": [{"role": "user", "content": "What are the specific tools or equipment used during the maintenance with record_id 'REC456'?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information about the specific tools or equipment used during a maintenance record. The data in the maintenance_records table does not include details about tools or equipment used."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.maintenance_records ( record_id text PRIMARY KEY, asset_id text, asset_type text, maintenance_type text, staff_id text, start_datetime timestamp, end_datetime timestamp, description text, cost numeric, status text )\n"} {"conversations": [{"role": "user", "content": "Find pairs of insurance plans that are offered by the same insurance provider. Show the provider name, and the names of the two plans."}, {"role": "assistant", "content": "SELECT p1.insurance_provider, p1.plan_name, p2.plan_name FROM healthcare.insurance_plans p1 JOIN healthcare.insurance_plans p2 ON p1.insurance_provider = p2.insurance_provider AND p1.plan_id < p2.plan_id ORDER BY p1.insurance_provider, p1.plan_name;"}, {"role": "user", "content": "Only show pairs where the provider name starts with 'B'."}, {"role": "assistant", "content": "SELECT p1.insurance_provider, p1.plan_name, p2.plan_name FROM healthcare.insurance_plans p1 JOIN healthcare.insurance_plans p2 ON p1.insurance_provider = p2.insurance_provider AND p1.plan_id < p2.plan_id WHERE p1.insurance_provider LIKE 'B%' ORDER BY p1.insurance_provider, p1.plan_name;"}, {"role": "user", "content": "Further filter to include only pairs where both plans have a website listed."}, {"role": "assistant", "content": "SELECT p1.insurance_provider, p1.plan_name, p2.plan_name FROM healthcare.insurance_plans p1 JOIN healthcare.insurance_plans p2 ON p1.insurance_provider = p2.insurance_provider AND p1.plan_id < p2.plan_id WHERE p1.insurance_provider LIKE 'B%' AND p1.website IS NOT NULL AND p2.website IS NOT NULL ORDER BY p1.insurance_provider, p1.plan_name;"}, {"role": "user", "content": "Also, include the plan type for both plans in the result."}, {"role": "assistant", "content": "SELECT p1.insurance_provider, p1.plan_name, p1.plan_type, p2.plan_name, p2.plan_type FROM healthcare.insurance_plans p1 JOIN healthcare.insurance_plans p2 ON p1.insurance_provider = p2.insurance_provider AND p1.plan_id < p2.plan_id WHERE p1.insurance_provider LIKE 'B%' AND p1.website IS NOT NULL AND p2.website IS NOT NULL ORDER BY p1.insurance_provider, p1.plan_name;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.insurance_plans ( plan_id character varying(64) NOT NULL, plan_name character varying(200) NOT NULL, insurance_provider character varying(100) NOT NULL, plan_type character varying(50), contact_phone character varying(20), website character varying(255), PRIMARY KEY (plan_id) )\n"} {"conversations": [{"role": "user", "content": "For each address, show the total amount contained in UTXOs that have been spent."}, {"role": "assistant", "content": "SELECT address, SUM(amount) FROM utxos WHERE spent = TRUE GROUP BY address;"}, {"role": "user", "content": "Only include addresses where this total spent amount is greater than 500 and order the results by the total amount descending."}, {"role": "assistant", "content": "SELECT address, SUM(amount) FROM utxos WHERE spent = TRUE GROUP BY address HAVING SUM(amount) > 500 ORDER BY SUM(amount) DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.utxos (\n utxo_id character varying(64) NOT NULL, -- unique identifier for the UTXO\n transaction_id character varying(64) NOT NULL, -- identifier of the transaction that created the UTXO\n output_index integer NOT NULL, -- index of the output in the transaction\n address character varying(128) NOT NULL, -- address that can spend the UTXO\n amount numeric(38,14) NOT NULL, -- amount of the asset in the UTXO\n spent boolean NOT NULL, -- whether the UTXO has been spent\n PRIMARY KEY (utxo_id)\n)\n"} {"conversations": [{"role": "user", "content": "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": "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": "List all users and the total quantity of orders they have placed for 'buy' orders."}, {"role": "assistant", "content": "SELECT t1.username, SUM(t2.quantity) FROM trading_platform.users AS t1 JOIN trading_platform.orders AS t2 ON t1.user_id = t2.user_id WHERE t2.order_type = 'buy' GROUP BY t1.username;"}, {"role": "user", "content": "Filter this list to only include users whose total buy quantity is greater than 100."}, {"role": "assistant", "content": "SELECT t1.username, SUM(t2.quantity) FROM trading_platform.users AS t1 JOIN trading_platform.orders AS t2 ON t1.user_id = t2.user_id WHERE t2.order_type = 'buy' GROUP BY t1.username HAVING SUM(t2.quantity) > 100;"}, {"role": "user", "content": "For those users, what is the average price of their 'buy' orders? Show username and average price."}, {"role": "assistant", "content": "SELECT t1.username, AVG(t2.price) FROM trading_platform.users AS t1 JOIN trading_platform.orders AS t2 ON t1.user_id = t2.user_id WHERE t2.order_type = 'buy' GROUP BY t1.username HAVING SUM(t2.quantity) > 100;"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nCREATE TABLE trading_platform.users ( user_id.text, username.text, email.text, password_hash.text, created_at.timestamp )\nCREATE TABLE trading_platform.orders ( order_id.text, user_id.text, wallet_id.text, asset_id.text, order_type.text, quantity.numeric, price.numeric, status.text, created_at.timestamp )\nCREATE TABLE trading_platform.assets ( asset_id.text, name.text, symbol.text, type.text )\nCREATE TABLE trading_platform.dapps ( dapp_id.text, name.text, description.text, url.text )\nCREATE TABLE trading_platform.kyc_audit ( kyc_audit_id.text, user_id.text, status.text, reviewed_at.timestamp )\nCREATE TABLE trading_platform.notifications ( notification_id.text, user_id.text, message.text, sent_at.timestamp, read_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "What is the 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": "For each achievement, show its name, the game_id it belongs to, and the number of distinct players who have played a session for that game."}, {"role": "assistant", "content": "SELECT a.name, a.game_id, COUNT(DISTINCT gs.player_id) AS players_with_sessions\nFROM gaming_technology.achievements a\nLEFT JOIN gaming_technology.game_sessions gs ON a.game_id = gs.game_id\nGROUP BY a.achievement_id, a.name, a.game_id;"}, {"role": "user", "content": "Now, filter to only include achievements for games that have at least 50 players who have played a session."}, {"role": "assistant", "content": "SELECT a.name, a.game_id, COUNT(DISTINCT gs.player_id) AS players_with_sessions\nFROM gaming_technology.achievements a\nLEFT JOIN gaming_technology.game_sessions gs ON a.game_id = gs.game_id\nGROUP BY a.achievement_id, a.name, a.game_id\nHAVING COUNT(DISTINCT gs.player_id) >= 50;"}, {"role": "user", "content": "Please also include the number of times each achievement has been unlocked by unique players, labeled as unique_unlocks."}, {"role": "assistant", "content": "SELECT a.name, a.game_id, COUNT(DISTINCT gs.player_id) AS players_with_sessions,\n (SELECT COUNT(DISTINCT gs2.player_id)\n FROM gaming_technology.game_sessions gs2\n WHERE gs2.game_id = a.game_id) AS unique_unlocks\nFROM gaming_technology.achievements a\nLEFT JOIN gaming_technology.game_sessions gs ON a.game_id = gs.game_id\nGROUP BY a.achievement_id, a.name, a.game_id\nHAVING COUNT(DISTINCT gs.player_id) >= 50;"}, {"role": "user", "content": "I think unique_unlocks should be the count of distinct players who have unlocked each specific achievement, not just played a session. Can you correct that?"}, {"role": "assistant", "content": "-- With the provided tables, there is no direct record of players unlocking a specific achievement, unless unlocking is inferred elsewhere. If you have an achievement unlocks table, you could join it here. Otherwise, only possible to count sessions per game."}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.players ( player_id.uuid, username.text, email.text, password_hash.text, registration_date.timestamptz, last_login.timestamptz, country_code.text, status.text, profile_data.jsonb )\nCREATE TABLE gaming_technology.developers ( developer_id.uuid, name.text, country.text, founded_year.integer, website.text, created_at.timestamptz )\nCREATE TABLE gaming_technology.game_sessions ( session_id.uuid, player_id.uuid, game_id.uuid, server_id.uuid, start_time.timestamptz, end_time.timestamptz, duration_seconds.integer, score.integer, session_data.jsonb )\nCREATE TABLE gaming_technology.achievements ( achievement_id.uuid, game_id.uuid, name.text, description.text, icon_url.text, points.integer, hidden.boolean )\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": "Find all wallet addresses that don't have an associated user_id."}, {"role": "assistant", "content": "SELECT address_id FROM blockchain.wallets WHERE user_id IS NULL;"}, {"role": "user", "content": "Now show me these addresses along with their private_key, and join with another table to see if they have any transactions."}, {"role": "assistant", "content": "SELECT w.address_id, w.private_key FROM blockchain.wallets w WHERE w.user_id IS NULL;"}, {"role": "user", "content": "Actually, I want to see the count of such wallet addresses grouped by the first 3 characters of their address_id."}, {"role": "assistant", "content": "SELECT SUBSTRING(address_id, 1, 3) as address_prefix, COUNT(*) as address_count FROM blockchain.wallets WHERE user_id IS NULL GROUP BY SUBSTRING(address_id, 1, 3);"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE blockchain.wallets ( wallet_id.text, user_id.text, address_id.text, private_key.text )\n"} {"conversations": [{"role": "user", "content": "Show me all insurance plans that cover more than 10 patients as their primary insurance, along with the provider name and contact information."}, {"role": "assistant", "content": "SELECT ip.plan_name, ip.insurance_provider, ip.contact_phone, ip.website, COUNT(pi.patient_id) AS patient_count FROM healthcare.insurance_plans ip JOIN healthcare.patient_insurance pi ON ip.plan_id = pi.plan_id WHERE pi.is_primary = true GROUP BY ip.plan_id HAVING COUNT(pi.patient_id) > 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients (\n patient_id character varying(64) NOT NULL, -- unique identifier for the patient\n first_name character varying(100) NOT NULL, -- patient's first name\n last_name character varying(100) NOT NULL, -- patient's last name\n date_of_birth date NOT NULL, -- patient's date of birth\n gender character varying(10), -- patient's gender (e.g., Male, Female, Other)\n address text, -- patient's home address\n phone_number character varying(20), -- patient's phone number\n email character varying(128) UNIQUE, -- patient's email address\n emergency_contact_name character varying(200), -- name of emergency contact\n emergency_contact_phone character varying(20), -- phone number of emergency contact\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, -- record creation time\n updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, -- record last update time\n PRIMARY KEY (patient_id)\n)\nCREATE TABLE healthcare.doctors (\n doctor_id character varying(64) NOT NULL, -- unique identifier for the doctor\n first_name character varying(100) NOT NULL, -- doctor's first name\n last_name character varying(100) NOT NULL, -- doctor's last name\n specialty character varying(100) NOT NULL, -- doctor's medical specialty\n license_number character varying(50) UNIQUE NOT NULL, -- doctor's medical license number\n phone_number character varying(20), -- doctor's contact phone\n email character varying(128) UNIQUE, -- doctor's contact email\n hospital_affiliation_id character varying(64), -- FK to hospitals table (optional)\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n PRIMARY KEY (doctor_id)\n)\nCREATE TABLE healthcare.appointments (\n appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment\n patient_id character varying(64) NOT NULL, -- FK to patients table\n doctor_id character varying(64) NOT NULL, -- FK to doctors table\n appointment_time timestamp with time zone NOT NULL, -- date and time of the appointment\n duration_minutes integer NOT NULL, -- expected duration in minutes\n reason text, -- reason for the visit\n status character varying(32) NOT NULL, -- e.g., Scheduled, Completed, Cancelled, No-show\n location_id character varying(64), -- FK to a potential locations/clinics table\n notes text, -- notes related to scheduling\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n PRIMARY KEY (appointment_id)\n)\nCREATE TABLE healthcare.diagnoses (\n diagnosis_id character varying(64) NOT NULL, -- unique identifier for the diagnosis entry\n record_id character varying(64) NOT NULL, -- FK linking to the specific medical record entry\n patient_id character varying(64) NOT NULL, -- FK to patients table\n doctor_id character varying(64) NOT NULL, -- FK to doctors table (diagnosing doctor)\n diagnosis_code character varying(20) NOT NULL, -- standard code (e.g., ICD-10)\n code_type character varying(10) NOT NULL DEFAULT 'ICD-10', -- type of code used\n description text, -- textual description of the diagnosis\n diagnosis_date date NOT NULL, -- date the diagnosis was made\n status character varying(32) NOT NULL, -- e.g., Active, Resolved, Ruled Out\n is_chronic boolean DEFAULT false, -- flag for chronic conditions\n PRIMARY KEY (diagnosis_id)\n)\nCREATE TABLE healthcare.medications (\n medication_id character varying(64) NOT NULL, -- unique identifier for the medication type\n medication_name character varying(255) NOT NULL, -- common or brand name\n generic_name character varying(255), -- generic chemical name\n manufacturer character varying(100), -- drug manufacturer\n ndc_code character varying(20) UNIQUE, -- National Drug Code (optional but useful)\n description text, -- description of the medication\n PRIMARY KEY (medication_id)\n)\nCREATE TABLE healthcare.prescriptions (\n prescription_id character varying(64) NOT NULL, -- unique identifier for the prescription\n record_id character varying(64) NOT NULL, -- FK linking to the medical record where it was prescribed\n patient_id character varying(64) NOT NULL, -- FK to patients table\n doctor_id character varying(64) NOT NULL, -- FK to prescribing doctor\n medication_id character varying(64) NOT NULL, -- FK to medications table\n dosage character varying(100) NOT NULL, -- e.g., '100mg', '1 tablet'\n frequency character varying(100) NOT NULL, -- e.g., 'Once daily', 'Twice a day with meals'\n route character varying(50), -- e.g., 'Oral', 'Topical', 'Intravenous'\n start_date date NOT NULL, -- date prescription begins\n end_date date, -- date prescription ends (if applicable)\n quantity_dispensed numeric(10,2), -- amount dispensed (e.g., number of tablets)\n refills_allowed integer NOT NULL DEFAULT 0, -- number of allowed refills\n prescription_date timestamp with time zone NOT NULL DEFAULT current_timestamp,\n PRIMARY KEY (prescription_id)\n)\nCREATE TABLE healthcare.insurance_plans (\n plan_id character varying(64) NOT NULL, -- unique identifier for the insurance plan\n plan_name character varying(200) NOT NULL, -- name of the insurance plan\n insurance_provider character varying(100) NOT NULL, -- name of the insurance company\n plan_type character varying(50), -- e.g., PPO, HMO, EPO\n contact_phone character varying(20), -- provider contact number\n website character varying(255), -- provider website\n PRIMARY KEY (plan_id)\n)\nCREATE TABLE healthcare.patient_insurance (\n patient_insurance_id character varying(64) NOT NULL, -- unique identifier for this patient-plan link\n patient_id character varying(64) NOT NULL, -- FK to patients table\n plan_id character varying(64) NOT NULL, -- FK to insurance_plans table\n policy_number character varying(100) NOT NULL, -- patient's policy number\n group_number character varying(100), -- group number, if applicable\n subscriber_name character varying(200), -- name of the primary policy holder\n effective_date date NOT NULL, -- date the coverage begins\n expiration_date date, -- date the coverage ends (if known)\n is_primary boolean NOT NULL DEFAULT true, -- indicates if this is the primary insurance\n PRIMARY KEY (patient_insurance_id),\n UNIQUE (patient_id, plan_id, policy_number) -- ensure a patient doesn't have the same policy twice\n)\n"} {"conversations": [{"role": "user", "content": "What are the maintenance costs for a specific aircraft model like the Airbus A320?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to data regarding maintenance costs for specific aircraft models such as the Airbus A320. The information in the database is limited to details like model name, manufacturer, passenger capacity, and technical specifications. For maintenance cost information, you may need to consult with the manufacturer or a maintenance service provider."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE manufacturing.aircraft_models ( model_id character varying(64) NOT NULL, model_name character varying(128) NOT NULL, manufacturer character varying(128) NOT NULL, passenger_capacity integer, max_range_km integer, engine_type character varying(100), wingspan_m numeric(6,2), status character varying(50) NOT NULL, first_flight_date date, PRIMARY KEY (model_id) )\n"} {"conversations": [{"role": "user", "content": "List all users who performed more than 10 'view' actions in the logs, along with their action counts."}, {"role": "assistant", "content": "SELECT user_id, COUNT(log_id) AS view_action_count FROM trading_platform.logs WHERE action = 'view' GROUP BY user_id HAVING COUNT(log_id) > 10 ORDER BY view_action_count DESC;"}, {"role": "user", "content": "Now include only users who performed these actions on cryptocurrency assets."}, {"role": "assistant", "content": "SELECT l.user_id, COUNT(l.log_id) AS view_action_count FROM trading_platform.logs l JOIN trading_platform.assets a ON l.details->>'asset_id' = a.asset_id WHERE l.action = 'view' AND a.type = 'cryptocurrency' GROUP BY l.user_id HAVING COUNT(l.log_id) > 10 ORDER BY view_action_count DESC;"}, {"role": "user", "content": "Actually, I want to see the most recent timestamp of their last view action as well."}, {"role": "assistant", "content": "SELECT l.user_id, COUNT(l.log_id) AS view_action_count, MAX(l.logged_at) AS last_view_time FROM trading_platform.logs l JOIN trading_platform.assets a ON l.details->>'asset_id' = a.asset_id WHERE l.action = 'view' AND a.type = 'cryptocurrency' GROUP BY l.user_id HAVING COUNT(l.log_id) > 10 ORDER BY view_action_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.assets ( asset_id text, name text, symbol text, type text )\nCREATE TABLE trading_platform.logs ( log_id text, user_id text, action text, details text, logged_at timestamp )\n"} {"conversations": [{"role": "user", "content": "List all documents that have multiple versions, including document_name, case_id, and the count of versions."}, {"role": "assistant", "content": "SELECT document_name,\n case_id,\n COUNT(*) AS version_count\nFROM legal_services.documents\nGROUP BY document_name, case_id\nHAVING COUNT(*) > 1;"}, {"role": "user", "content": "Actually, I only want to include those with at least three versions."}, {"role": "assistant", "content": "SELECT document_name,\n case_id,\n COUNT(*) AS version_count\nFROM legal_services.documents\nGROUP BY document_name, case_id\nHAVING COUNT(*) >= 3;"}, {"role": "user", "content": "Also include the lawyer ID who uploaded the latest version for each document."}, {"role": "assistant", "content": "SELECT d.document_name,\n d.case_id,\n m.version_count,\n d.uploaded_by_lawyer_id\nFROM legal_services.documents d\nJOIN (\n SELECT document_name,\n case_id,\n COUNT(*) AS version_count,\n MAX(version) AS max_version\n FROM legal_services.documents\n GROUP BY document_name, case_id\n HAVING COUNT(*) >= 3\n) m\n ON d.document_name = m.document_name\n AND d.case_id = m.case_id\n AND d.version = m.max_version;"}], "system": "You are an SQL statement expert. Given the table structure 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": "How many documents are there for each document_type? Show document_type and count ordered by the count in descending order."}, {"role": "assistant", "content": "SELECT document_type,\n COUNT(*) AS count\nFROM legal_services.documents\nGROUP BY document_type\nORDER BY count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.documents ( document_id.text, case_id.text, document_name.text, document_type.text, storage_path.text, uploaded_by_lawyer_id.text, upload_timestamp.timestamp, version.integer, description.text )\n"} {"conversations": [{"role": "user", "content": "List 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": "Which NFTs minted in the past 14 days on Ethereum have a rarity_score above 70? For each, show contract address, token ID, name, and minter."}, {"role": "assistant", "content": "SELECT contract_address, token_id, name, minter\nFROM nft_metadata\nWHERE blockchain = 'Ethereum'\n AND mint_time >= (extract(epoch from now()) - 14*24*60*60)\n AND rarity_score > 70;"}, {"role": "user", "content": "For these NFTs, can you also include the collection name and symbol by joining with the nft_collections table?"}, {"role": "assistant", "content": "SELECT nm.contract_address, nm.token_id, nm.name, nm.minter, nc.name AS collection_name, nc.symbol\nFROM nft_metadata nm\nJOIN nft_collections nc\n ON nm.blockchain = nc.blockchain AND nm.contract_address = nc.contract_address\nWHERE nm.blockchain = 'Ethereum'\n AND nm.mint_time >= (extract(epoch from now()) - 14*24*60*60)\n AND nm.rarity_score > 70;"}, {"role": "user", "content": "Can you filter only those collections where the erc_type is 'ERC1155'?"}, {"role": "assistant", "content": "SELECT nm.contract_address, nm.token_id, nm.name, nm.minter, nc.name AS collection_name, nc.symbol\nFROM nft_metadata nm\nJOIN nft_collections nc\n ON nm.blockchain = nc.blockchain AND nm.contract_address = nc.contract_address\nWHERE nm.blockchain = 'Ethereum'\n AND nm.mint_time >= (extract(epoch from now()) - 14*24*60*60)\n AND nm.rarity_score > 70\n AND nc.erc_type = 'ERC1155';"}, {"role": "user", "content": "Now, also include the owner for each NFT, and order the results by rarity_rank ascending."}, {"role": "assistant", "content": "SELECT nm.contract_address, nm.token_id, nm.name, nm.minter, nm.owner, nc.name AS collection_name, nc.symbol\nFROM nft_metadata nm\nJOIN nft_collections nc\n ON nm.blockchain = nc.blockchain AND nm.contract_address = nc.contract_address\nWHERE nm.blockchain = 'Ethereum'\n AND nm.mint_time >= (extract(epoch from now()) - 14*24*60*60)\n AND nm.rarity_score > 70\n AND nc.erc_type = 'ERC1155'\nORDER BY nm.rarity_rank ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE nft_holders ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, token_id varchar NOT NULL, contract_type varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_coins_metadata (\n object_id varchar NOT NULL, -- object id of the coin metadata object\n coin_type varchar NOT NULL, -- coin type, eg. 0x...66::reap_token::REAP_TOKEN\n status varchar NOT NULL, -- coin status, eg. exists, deleted\n decimals bigint NOT NULL, -- decimals of the coin\n description varchar NOT NULL, -- description of the coin\n icon_url varchar NOT NULL, -- icon url of the coin\n symbol varchar NOT NULL, -- symbol of the coin\n name varchar NOT NULL -- name of the coin\n)\nCREATE TABLE sui_nfts ( object_id text, status text, collection_type text, package_id text, previous_transaction text, display text, owner text, name text )\nCREATE TABLE nft_metadata ( blockchain text, contract_address text, token_id text, contract_name text, erc_type text, amount bigint, minter text, owner text, mint_block_number bigint, mint_time bigint, mint_transaction_hash text, mint_price text, token_uri text, metadata text, name text, image_uri text, traits text, updated_at bigint, status text, rarity_score real, rarity_rank integer, unique_attribute_count integer, pk integer )\nCREATE TABLE nft_collections ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, name varchar NOT NULL, symbol varchar NOT NULL, deploy_block_number bigint NOT NULL, deploy_block_time bigint NOT NULL, erc_type varchar NOT NULL, owner varchar NOT NULL, traits varchar NOT NULL, description varchar NOT NULL, slug varchar NOT NULL, media_info varchar NOT NULL, image_url varchar NOT NULL, banner_image_url varchar NOT NULL, updated_at bigint NOT NULL, banner varchar NOT NULL, token_count bigint NOT NULL, floor_price varchar NOT NULL, floor_price_symbol varchar NOT NULL, floor_price_contract varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_prices ( uuid text, blockchain text, address text, decimals bigint, symbol text, price real, timestamp timestamp )\nCREATE TABLE token_prices_latest (\n blockchain varchar(36) NOT NULL, -- blockchain fields for the functionType in contract\n address varchar(42) NOT NULL, -- address fields for the functionType in contract\n decimals bigint NOT NULL, -- decimals fields for the functionType in contract\n symbol varchar(36) NOT NULL, -- symbol fields for the functionType in contract\n price real NOT NULL, -- price fields for the functionType in contract\n timestamp timestamp(6) NOT NULL -- timestamp fields for the functionType in contract\n)\nCREATE TABLE erc20_approval ( block_number bigint NOT NULL, block_timestamp timestamp(6) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar NOT NULL, log_index integer NOT NULL, contract_address varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_balances ( block_number.bigint, block_timestamp.timestamp, tick.text, wallet_address.text, total_supply.decimal, amount.decimal )\nCREATE TABLE token_info (\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n tick varchar NOT NULL, -- Token tick\n max_supply decimal(38,0) NOT NULL, -- Max supply\n lim decimal(38,0) NOT NULL, -- Limit of each mint\n wlim decimal(38,0) NOT NULL, -- Limit of each address can maximum mint\n dec integer NOT NULL, -- Decimal for minimum divie\n creator varchar(42) NOT NULL -- Address originating the inscription (matches from_address in transactions table)\n)\nCREATE TABLE mud_holesky_redstone (\n address varchar NOT NULL, -- address fields for the functionType in contract\n table_id varchar NOT NULL, -- table_id fields for the functionType in contract\n key_bytes varchar NOT NULL, -- key_bytes fields for the functionType in contract\n key0 varchar NOT NULL, -- key0 fields for the functionType in contract\n key1 varchar NOT NULL, -- key1 fields for the functionType in contract\n static_data varchar NOT NULL, -- static_data fields for the functionType in contract\n encoded_lengths varchar NOT NULL, -- encoded_lengths fields for the functionType in contract\n dynamic_data varchar NOT NULL, -- dynamic_data fields for the functionType in contract\n is_deleted boolean NOT NULL, -- is_deleted fields for the functionType in contract\n block_number bigint NOT NULL, -- Block number uniquely identifying the block\n log_index bigint NOT NULL -- Index of the log within the transaction\n)\nCREATE TABLE token_info_bitcoin ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, tick.text, max_supply.decimal, lim.decimal, wlim.decimal, dec.integer, creator.text )\nCREATE TABLE token_activities_avalanche (\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n log_index integer NOT NULL, -- Index of the log within the transaction\n type varchar(20) NOT NULL, -- Operation: Type of event (deploy, mint, transfer, list)\n tick varchar(255) NOT NULL, -- Ticker: Identifier of the inscription\n id varchar(255) NOT NULL, -- Unique identifier of the inscription\n amt decimal(38,0) NOT NULL, -- Amount to mint: States the amount of the inscription to operation. When operation is mint, has to be less or equal to \"lim\"\n from_address varchar(42) NOT NULL, -- Address sending the inscription\n to_address varchar(42) NOT NULL -- Address receiving the inscription\n)\nCREATE TABLE token_balances_avalanche ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply decimal, amount decimal )\n"} {"conversations": [{"role": "user", "content": "能否帮我查询特定路线(route_id 为 'route_ne_corr')上的所有车站信息，并包含每个车站的平台数量？"}, {"role": "assistant", "content": "ZRANGE route:route_ne_corr:stops 0 -1\nHGETALL route_station: for each route_station_id in result\nHGETALL station: for each station_id in result\nSCARD station::platforms for each station_id in result"}, {"role": "user", "content": "能否将结果按照车站的顺序(sequence_order)进行排序？"}, {"role": "assistant", "content": "ZRANGE route:route_ne_corr:stops 0 -1 WITHSCORES\nHGETALL route_station: for each route_station_id in result\nHGETALL station: for each station_id in result\nSCARD station::platforms for each station_id in result\nSort results by sequence_order (score from ZRANGE)"}, {"role": "user", "content": "能否只显示有超过5个平台的车站信息？"}, {"role": "assistant", "content": "ZRANGE route:route_ne_corr:stops 0 -1 WITHSCORES\nHGETALL route_station: for each route_station_id in result\nHGETALL station: for each station_id in result\nSCARD station::platforms for each station_id in result\nFilter results where SCARD result > 5\nSort results by sequence_order (score from ZRANGE)"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\n// Use Hashes to store station details. Key format: station:\n// Example:\n// HSET station:station_xyz station_id \"station_xyz\" station_name \"Grand Central Terminal\" city \"New York\" state_province \"NY\" country_code \"USA\" address \"89 E 42nd St...\" timezone \"America/New_York\" number_of_platforms 44 created_at \"2023-01-15T10:00:00Z\" last_updated_at \"2023-10-28T15:30:00Z\"\n\n// To quickly find stations by city (optional index):\n// SADD stations:city:NewYork station:station_xyz\n// Use Hashes for platform details. Key format: platform:\n// HSET platform:plat_123 platform_id \"plat_123\" station_id \"station_xyz\" platform_number \"1A\" track_number \"T1\" status \"Operational\" length_meters 250.50 accessible 1\n\n// To link platforms to stations (optional):\n// SADD station:station_xyz:platforms platform:plat_123 platform:plat_456\n// Use Hashes for train details. Key format: train:\n// HSET train:train_789 train_id \"train_789\" train_number \"Acela 2151\" model \"Siemens Velaro\" ... status \"Active\" ...\n\n// To find train by train_number (optional index):\n// SET train_number:\"Acela 2151\" train:train_789\n// Use Hashes for car details. Key format: car:\n// HSET car:car_abc car_id \"car_abc\" train_id \"train_789\" car_number \"C3\" car_type \"Passenger\" class \"Business\" capacity 60 features \"WiFi,Power Outlet\"\n\n// To link cars to trains (optional):\n// SADD train:train_789:cars car:car_abc car:car_def\n// Use Hashes for route details. Key format: route:\n// HSET route:route_ne_corr route_id \"route_ne_corr\" route_name \"Northeast Corridor\" ... origin_station_id \"station_bos\" ... is_active 1\n// Use Hashes for details. Key format: route_station:\n// HSET route_station:rs_ne_1 route_station_id \"rs_ne_1\" route_id \"route_ne_corr\" station_id \"station_bos\" sequence_order 1 ...\n\n// To find stops for a route, use a Sorted Set (score by sequence_order):\n// ZADD route:route_ne_corr:stops 1 route_station:rs_ne_1\n// ZADD route:route_ne_corr:stops 2 route_station:rs_ne_2\n// Use Hashes for passenger details. Key format: passenger:\n// HSET passenger:pass_pqr passenger_id \"pass_pqr\" first_name \"Alice\" last_name \"Smith\" email \"alice.smith@example.com\" ...\n\n// To find passenger by email (optional index):\n// SET passenger_email:\"alice.smith@example.com\" passenger:pass_pqr\n// Use Hashes for booking details. Key format: booking:\n// HSET booking:book_zyx booking_id \"book_zyx\" passenger_id \"pass_pqr\" schedule_id \"sched_1122\" ... status \"Confirmed\" ...\n\n// To link bookings to passengers/schedules (optional):\n// SADD passenger:pass_pqr:bookings booking:book_zyx\n// SADD schedule:sched_1122:bookings booking:book_zyx\n// Use Hashes for ticket details. Key format: ticket:\n// HSET ticket:tkt_1a2b ticket_id \"tkt_1a2b\" booking_id \"book_zyx\" car_id \"car_abc\" seat_number \"12A\" ... is_checked_in 0 ...\n\n// To link tickets to bookings (optional):\n// SADD booking:book_zyx:tickets ticket:tkt_1a2b\n"} {"conversations": [{"role": "user", "content": "Can you list all SUI coins with 'active' status and their owner addresses and balances?"}, {"role": "assistant", "content": "SELECT object_id, coin_type, owner, balance\nFROM sui_coins\nWHERE status = 'active';"}, {"role": "user", "content": "Add the coin symbol and name from the sui_coins_metadata table."}, {"role": "assistant", "content": "SELECT sc.object_id, sc.coin_type, sc.owner, sc.balance, scm.symbol, scm.name\nFROM sui_coins sc\nLEFT JOIN sui_coins_metadata scm ON sc.coin_type = scm.coin_type\nWHERE sc.status = 'active';"}, {"role": "user", "content": "Only include coins where the description mentions 'utility'."}, {"role": "assistant", "content": "SELECT sc.object_id, sc.coin_type, sc.owner, sc.balance, scm.symbol, scm.name\nFROM sui_coins sc\nLEFT JOIN sui_coins_metadata scm ON sc.coin_type = scm.coin_type\nWHERE sc.status = 'active' AND scm.description ILIKE '%utility%';"}, {"role": "user", "content": "Limit the output to the top 10 coins sorted by balance descending."}, {"role": "assistant", "content": "SELECT sc.object_id, sc.coin_type, sc.owner, sc.balance, scm.symbol, scm.name\nFROM sui_coins sc\nLEFT JOIN sui_coins_metadata scm ON sc.coin_type = scm.coin_type\nWHERE sc.status = 'active' AND scm.description ILIKE '%utility%'\nORDER BY CAST(sc.balance AS BIGINT) DESC\nLIMIT 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE erc1155_approval_for_all ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash varchar, log_index integer, contract_address varchar )\nCREATE TABLE erc20_balances_historical ( block_number bigint, contract_address varchar, wallet_address varchar, amount varchar, pk integer )\nCREATE TABLE nft_holders ( block_number bigint, contract_address varchar, wallet_address varchar, token_id varchar, contract_type varchar, amount varchar, pk varchar )\nCREATE TABLE nft_holder_historical ( block_number bigint, contract_address varchar, wallet_address varchar, token_id varchar, contract_type varchar, amount varchar, pk integer )\nCREATE TABLE sui_coins ( object_id varchar, status varchar, coin_type varchar, balance varchar, owner varchar )\nCREATE TABLE sui_coins_metadata ( object_id varchar, coin_type varchar, status varchar, decimals bigint, description varchar, icon_url varchar, symbol varchar, name varchar )\nCREATE TABLE sui_nfts ( object_id varchar, status varchar, collection_type varchar, package_id varchar, previous_transaction varchar, display varchar, owner varchar, name varchar )\nCREATE TABLE nft_metadata ( blockchain varchar, contract_address varchar, token_id varchar, contract_name varchar, erc_type varchar, amount bigint, minter varchar, owner varchar, mint_block_number bigint, mint_time bigint, mint_transaction_hash varchar, mint_price varchar, token_uri varchar, metadata varchar, name varchar, image_uri varchar, traits varchar, updated_at bigint, status varchar, rarity_score real, rarity_rank integer, unique_attribute_count integer, pk integer )\nCREATE TABLE nft_collections ( blockchain varchar, contract_address varchar, name varchar, symbol varchar, deploy_block_number bigint, deploy_block_time bigint, erc_type varchar, owner varchar, traits varchar, description varchar, slug varchar, media_info varchar, image_url varchar, banner_image_url varchar, updated_at bigint, banner varchar, token_count bigint, floor_price varchar, floor_price_symbol varchar, floor_price_contract varchar, pk integer )\nCREATE TABLE token_prices ( uuid varchar, blockchain varchar, address varchar, decimals bigint, symbol varchar, price real, timestamp timestamp )\nCREATE TABLE token_prices_latest ( blockchain varchar, address varchar, decimals bigint, symbol varchar, price real, timestamp timestamp )\nCREATE TABLE erc20_approval ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash varchar, log_index integer, contract_address varchar, pk integer )\nCREATE TABLE token_balances ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply decimal, amount decimal )\nCREATE TABLE token_info ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar )\nCREATE TABLE token_activities ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\nCREATE TABLE mud_holesky_redstone ( address varchar, table_id varchar, key_bytes varchar, key0 varchar, key1 varchar, static_data varchar, encoded_lengths varchar, dynamic_data varchar, is_deleted boolean, block_number bigint, log_index bigint )\nCREATE TABLE token_balances_bitcoin ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply varchar, amount varchar )\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\n"} {"conversations": [{"role": "user", "content": "Return the usernames and emails of users who have bios that mention the word 'travel'."}, {"role": "assistant", "content": "SELECT username, email\nFROM social_media.users\nWHERE bio ILIKE '%travel%';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id.text, username.text, email.text, password_hash.text, full_name.text, profile_picture_url.text, bio.text, location.text, created_at.timestamp, updated_at.timestamp, is_verified.boolean )\nCREATE TABLE social_media.posts ( post_id.text, user_id.text, content.text, media_url.text, media_type.text, created_at.timestamp, updated_at.timestamp, visibility.text, location_lat.numeric, location_lon.numeric )\nCREATE TABLE social_media.comments ( comment_id.text, post_id.text, user_id.text, parent_comment_id.text, content.text, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE social_media.hashtags ( hashtag_id.text, tag_name.text, created_at.timestamp )\nCREATE TABLE social_media.post_hashtags ( post_hashtag_id.text, post_id.text, hashtag_id.text )\nCREATE TABLE social_media.conversations ( conversation_id.text, created_at.timestamp, last_message_at.timestamp, is_group_chat.boolean, group_name.text )\nCREATE TABLE social_media.user_settings ( setting_id.text, user_id.text, theme.text, email_notifications_enabled.boolean, push_notifications_enabled.boolean, private_profile.boolean, updated_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "What is the schedule of trains arriving at platform 1A at station XYZ on December 25th, 2023?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information about train schedules or specific arrival times as this data is not included in the platform management table. For train schedules, please refer to the train timetable or contact the station's customer service."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.platforms (\n platform_id character varying(64) NOT NULL, -- Unique identifier for the platform\n station_id character varying(64) NOT NULL, -- Foreign key referencing stations\n platform_number character varying(10) NOT NULL, -- Platform identifier (e.g., '1A', '5')\n track_number character varying(10), -- Associated track number, if different\n status character varying(32) NOT NULL DEFAULT 'Operational', -- e.g., Operational, Maintenance, Closed\n length_meters numeric(8,2), -- Length of the platform in meters\n accessible boolean NOT NULL DEFAULT false, -- Is the platform accessible (e.g., wheelchair)?\n PRIMARY KEY (platform_id),\n FOREIGN KEY (station_id) REFERENCES train_station_management.stations(station_id)\n)\n"} {"conversations": [{"role": "user", "content": "List the first name, last name, license number, and status for all drivers whose license expires in the next 6 months."}, {"role": "assistant", "content": "SELECT\n first_name,\n last_name,\n license_number,\n status\nFROM transportation.drivers\nWHERE\n license_expiry_date BETWEEN CURRENT_DATE AND CURRENT_DATE + INTERVAL '6 month'\nORDER BY\n license_expiry_date;"}, {"role": "user", "content": "Now, count how many drivers from that list have an 'Active' status."}, {"role": "assistant", "content": "SELECT\n COUNT(*)\nFROM transportation.drivers\nWHERE\n license_expiry_date BETWEEN CURRENT_DATE AND CURRENT_DATE + INTERVAL '6 month' AND status = 'Active';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.drivers ( driver_id text PRIMARY KEY, employee_id text, first_name text, last_name text, license_number text, license_expiry_date date, contact_number text, email text, hire_date date, status text )\n"} {"conversations": [{"role": "user", "content": "Show me all reservations with their guest IDs and room IDs where the total amount is greater than $500 and the status is 'Confirmed', ordered by check-in date."}, {"role": "assistant", "content": "SELECT reservation_id, guest_id, room_id, check_in_date, total_amount FROM hospitality_technology.reservations WHERE total_amount > 500 AND status = 'Confirmed' ORDER BY check_in_date;"}, {"role": "user", "content": "Now, join this with the service_orders table to include the total price of all services ordered for each reservation."}, {"role": "assistant", "content": "SELECT r.reservation_id, r.guest_id, r.room_id, r.check_in_date, r.total_amount, SUM(so.total_price) AS total_service_price FROM hospitality_technology.reservations r LEFT JOIN hospitality_technology.service_orders so ON r.reservation_id = so.reservation_id WHERE r.total_amount > 500 AND r.status = 'Confirmed' GROUP BY r.reservation_id, r.guest_id, r.room_id, r.check_in_date, r.total_amount ORDER BY r.check_in_date;"}, {"role": "user", "content": "The query should also show the difference between the total amount and the base rate for each reservation."}, {"role": "assistant", "content": "SELECT r.reservation_id, r.guest_id, r.room_id, r.check_in_date, r.total_amount, SUM(so.total_price) AS total_service_price, (r.total_amount - rt.base_rate) AS rate_difference FROM hospitality_technology.reservations r LEFT JOIN hospitality_technology.service_orders so ON r.reservation_id = so.reservation_id LEFT JOIN hospitality_technology.room_types rt ON r.room_type_id = rt.room_type_id WHERE r.total_amount > 500 AND r.status = 'Confirmed' GROUP BY r.reservation_id, r.guest_id, r.room_id, r.check_in_date, r.total_amount, rt.base_rate ORDER BY r.check_in_date;"}, {"role": "user", "content": "Actually, I only need reservations where the total amount is at least 50% higher than the base rate, and order them by check-in date."}, {"role": "assistant", "content": "SELECT r.reservation_id, r.guest_id, r.room_id, r.check_in_date, r.total_amount, SUM(so.total_price) AS total_service_price, (r.total_amount - rt.base_rate) AS rate_difference FROM hospitality_technology.reservations r LEFT JOIN hospitality_technology.service_orders so ON r.reservation_id = so.reservation_id LEFT JOIN hospitality_technology.room_types rt ON r.room_type_id = rt.room_type_id WHERE r.total_amount > 500 AND r.status = 'Confirmed' AND r.total_amount >= rt.base_rate * 1.5 GROUP BY r.reservation_id, r.guest_id, r.room_id, r.check_in_date, r.total_amount, rt.base_rate 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 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.reservations (\n reservation_id character varying(64) NOT NULL, -- unique identifier for the booking\n property_id character varying(64) NOT NULL, -- FK to properties table\n guest_id character varying(64) NOT NULL, -- FK to guests table (primary guest)\n room_id character varying(64), -- FK to rooms table (assigned room, might be null initially)\n room_type_id character varying(64) NOT NULL, -- FK to room_types table (booked room type)\n check_in_date date NOT NULL, -- scheduled check-in date\n check_out_date date NOT NULL, -- scheduled check-out date\n actual_check_in_ts timestamp with time zone, -- actual check-in time\n actual_check_out_ts timestamp with time zone, -- actual check-out time\n num_adults integer NOT NULL, -- number of adults\n num_children integer DEFAULT 0, -- number of children\n status character varying(50) NOT NULL, -- e.g., Pending, Confirmed, CheckedIn, CheckedOut, Cancelled, NoShow\n booking_source character varying(100), -- e.g., Website, OTA (Expedia, Booking.com), Phone, WalkIn\n rate_plan_id character varying(64), -- FK to rate_plans table (optional)\n total_amount numeric(12, 2), -- estimated or final total cost\n amount_paid numeric(12, 2) DEFAULT 0.00, -- amount already paid\n special_requests text, -- specific guest requests for this booking\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n PRIMARY KEY (reservation_id),\n FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id),\n FOREIGN KEY (room_id) REFERENCES hospitality_technology.rooms(room_id),\n FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id)\n)\nCREATE TABLE hospitality_technology.staff ( staff_id text 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 (\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 ( 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 character varying(64) NOT NULL, property_id character varying(64) NOT NULL, reservation_id character varying(64) UNIQUE, guest_id character varying(64) NOT NULL, rating_overall integer, rating_cleanliness integer, rating_service integer, rating_location integer, rating_value integer, comment text, review_source character varying(100), review_date timestamp with time zone NOT NULL DEFAULT current_timestamp, is_public boolean DEFAULT true, staff_response text, response_staff_id character varying(64), response_date timestamp with time zone, PRIMARY KEY (review_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (response_staff_id) REFERENCES hospitality_technology.staff(staff_id) )\n"} {"conversations": [{"role": "user", "content": "For each citizen who has made at least one payment, show the citizen's full name, number of payments, and total amount paid, grouped by currency."}, {"role": "assistant", "content": "SELECT\n c.first_name || ' ' || c.last_name AS full_name,\n p.currency,\n COUNT(*) AS payment_count,\n SUM(p.amount) AS total_amount\nFROM government_services.citizens c\nJOIN government_services.payments p ON c.citizen_id = p.citizen_id\nGROUP BY full_name, p.currency;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id character varying(64) NOT NULL, national_id_number character varying(128) NOT NULL UNIQUE, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, gender character varying(20), primary_address text NOT NULL, contact_email character varying(128) UNIQUE, contact_phone character varying(32), registration_date timestamp NOT NULL, is_verified boolean DEFAULT false, PRIMARY KEY (citizen_id) )\nCREATE TABLE government_services.payments ( payment_id character varying(64) NOT NULL, application_id character varying(64), citizen_id character varying(64) NOT NULL, service_id character varying(64), amount numeric(12, 2) NOT NULL, currency character varying(3) NOT NULL DEFAULT 'USD', payment_method character varying(50), payment_provider_reference character varying(128), payment_timestamp timestamp NOT NULL, status character varying(30) NOT NULL, notes text, PRIMARY KEY (payment_id) )\nCREATE TABLE government_services.employees ( employee_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, job_title character varying(150) NOT NULL, department character varying(100), work_email character varying(128) NOT NULL UNIQUE, work_phone character varying(32), hire_date date NOT NULL, termination_date date, access_level character varying(50), manager_employee_id character varying(64), PRIMARY KEY (employee_id) )\nCREATE TABLE government_services.service_locations ( location_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, location_name character varying(200), address text NOT NULL, city character varying(100), state character varying(50), postal_code character varying(20), latitude numeric(9, 6), longitude numeric(9, 6), operating_hours text, contact_phone character varying(32), is_accessible boolean, PRIMARY KEY (location_id) )\nCREATE TABLE government_services.appointments ( appointment_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, employee_id character varying(64), location_id character varying(64), service_id character varying(64), scheduled_start_time timestamp NOT NULL, scheduled_end_time timestamp, purpose text NOT NULL, status character varying(30) NOT NULL, booking_method character varying(50), created_at timestamp NOT NULL, notes text, PRIMARY KEY (appointment_id) )\nCREATE TABLE government_services.notifications ( notification_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, application_id character varying(64), message_subject character varying(255), message_body text NOT NULL, channel character varying(30) NOT NULL, sent_at timestamp NOT NULL, status character varying(30) NOT NULL, related_entity_type character varying(50), related_entity_id character varying(64), PRIMARY KEY (notification_id) )\n"} {"conversations": [{"role": "user", "content": "Show the email address and the creation date for every user, ordered by their username alphabetically."}, {"role": "assistant", "content": "SELECT email, created_at FROM trading_platform.users ORDER BY username ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.users ( user_id.text, username.text, email.text, password_hash.text, created_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "Which services have 'Eligibility' mentioned in their eligibility_criteria field?"}, {"role": "assistant", "content": "SELECT service_name, eligibility_criteria\nFROM government_services.services\nWHERE eligibility_criteria ILIKE '%Eligibility%';"}], "system": "You are an SQL statement expert. Given the table structure 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": "Find cases where an address received tokens in one transfer and then sent tokens in another. List the receive transfer_id, the send transfer_id, the address, and both transfer values."}, {"role": "assistant", "content": "SELECT recv.transfer_id AS receive_transfer_id,\n send.transfer_id AS send_transfer_id,\n recv.to_address AS address,\n recv.value AS received_value,\n send.value AS sent_value\nFROM web3.token_transfers recv\nJOIN web3.token_transfers send\n ON recv.to_address = send.from_address;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.token_transfers (\n transfer_id character varying(64) NOT NULL, -- unique identifier for the transfer\n token_id character varying(64) NOT NULL, -- identifier of the token being transferred\n from_address character varying(128) NOT NULL, -- address of the sender\n to_address character varying(128) NOT NULL, -- address of the receiver\n value numeric(38,14) NOT NULL, -- amount of tokens transferred\n transaction_id character varying(64) NOT NULL, -- identifier of the transaction containing the transfer\n log_index integer NOT NULL, -- index of the transfer log in the transaction\n PRIMARY KEY (transfer_id)\n)\n"} {"conversations": [{"role": "user", "content": "Show me all prescriptions for medication with ID 'MED123' along with the patient IDs and dosages."}, {"role": "assistant", "content": "SELECT prescription_id, patient_id, dosage FROM healthcare.prescriptions WHERE medication_id = 'MED123';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.prescriptions ( prescription_id text PRIMARY KEY, record_id text, patient_id text, doctor_id text, medication_id text, dosage text, frequency text, route text, start_date date, end_date date, quantity_dispensed numeric, refills_allowed int, prescription_date timestamp )\n"} {"conversations": [{"role": "user", "content": "Show me all trades with their corresponding ticker_symbol and security_name for trades executed in the last 7 days."}, {"role": "assistant", "content": "SELECT tr.trade_id, tr.account_id, tr.trade_type, tr.quantity, tr.price_per_unit, tr.total_amount,\n tr.commission, tr.trade_timestamp,\n s.ticker_symbol, s.security_name\nFROM financial_services.trades tr\nJOIN financial_services.securities s ON tr.security_id = s.security_id\nWHERE tr.trade_timestamp >= now() - INTERVAL '7 days';"}, {"role": "user", "content": "Only include trades where commission is greater than 50 and status is 'Completed'."}, {"role": "assistant", "content": "SELECT tr.trade_id, tr.account_id, tr.trade_type, tr.quantity, tr.price_per_unit, tr.total_amount,\n tr.commission, tr.trade_timestamp,\n s.ticker_symbol, s.security_name\nFROM financial_services.trades tr\nJOIN financial_services.securities s ON tr.security_id = s.security_id\nWHERE tr.trade_timestamp >= now() - INTERVAL '7 days'\n AND tr.commission > 50\n AND tr.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 financial_services.customers ( customer_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, ssn_hash character varying(128), address text NOT NULL, city character varying(100) NOT NULL, state character varying(50) NOT NULL, zip_code character varying(20) NOT NULL, country character varying(50) NOT NULL, email character varying(128) UNIQUE, phone_number character varying(32), created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, status character varying(32) NOT NULL, risk_profile character varying(50), PRIMARY KEY (customer_id) )\nCREATE TABLE financial_services.accounts (\n account_id character varying(64) NOT NULL, -- unique identifier for the account\n customer_id character varying(64) NOT NULL, -- foreign key linking to the customer\n account_number character varying(128) NOT NULL UNIQUE, -- unique account number visible to customer\n account_type character varying(50) NOT NULL, -- e.g., Checking, Savings, Investment, Loan, Credit Card\n balance numeric(19, 4) NOT NULL DEFAULT 0.00, -- current account balance\n currency character varying(3) NOT NULL, -- currency code (e.g., USD, EUR)\n opened_date date NOT NULL, -- date the account was opened\n status character varying(32) NOT NULL, -- e.g., Open, Closed, Frozen\n interest_rate numeric(5, 4), -- annual interest rate, if applicable\n last_updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last account update\n PRIMARY KEY (account_id),\n FOREIGN KEY (customer_id) REFERENCES financial_services.customers(customer_id)\n)\nCREATE TABLE financial_services.transactions (\n transaction_id character varying(64) NOT NULL, -- unique identifier for the transaction\n account_id character varying(64) NOT NULL, -- account involved in the transaction\n related_account_id character varying(64), -- counterpart account for transfers\n transaction_type character varying(50) NOT NULL, -- e.g., Deposit, Withdrawal, Transfer, Payment, Fee, Interest\n amount numeric(19, 4) NOT NULL, -- transaction amount\n currency character varying(3) NOT NULL, -- transaction currency\n transaction_date timestamp NOT NULL, -- exact time of the transaction\n effective_date date NOT NULL, -- date the transaction affects the balance\n description text, -- description or memo of the transaction\n status character varying(32) NOT NULL, -- e.g., Pending, Completed, Failed, Reversed\n reference_number character varying(128), -- external reference if applicable (e.g., check number)\n PRIMARY KEY (transaction_id),\n FOREIGN KEY (account_id) REFERENCES financial_services.accounts(account_id),\n FOREIGN KEY (related_account_id) REFERENCES financial_services.accounts(account_id)\n)\nCREATE TABLE financial_services.securities (\n security_id character varying(64) NOT NULL, -- unique identifier for the security\n ticker_symbol character varying(20) NOT NULL UNIQUE, -- stock ticker or fund symbol\n isin_code character varying(12) UNIQUE, -- International Securities Identification Number\n cusip_code character varying(9) UNIQUE, -- CUSIP number\n security_name text NOT NULL, -- full name of the security\n security_type character varying(50) NOT NULL, -- e.g., Stock, Bond, ETF, Mutual Fund, Option, Future\n exchange character varying(50), -- primary exchange where traded (e.g., NYSE, NASDAQ)\n currency character varying(3) NOT NULL, -- currency the security is denominated in\n issuer_name character varying(255), -- name of the issuing entity\n sector character varying(100), -- industry sector\n last_updated timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n PRIMARY KEY (security_id)\n)\nCREATE TABLE financial_services.trades ( trade_id text PRIMARY KEY, account_id text, security_id text, order_id text, trade_type text, quantity numeric, price_per_unit numeric, total_amount numeric, commission numeric, trade_timestamp timestamp, settlement_date date, status text, execution_venue text )\nCREATE TABLE financial_services.market_data ( data_point_id.bigint, security_id.text, data_timestamp.timestamp, open_price.numeric, high_price.numeric, low_price.numeric, close_price.numeric, adjusted_close_price.numeric, volume.bigint, source.text )\nCREATE TABLE financial_services.employees ( employee_id text, first_name text, last_name text, job_title text, department text, branch_id text, email text, phone_extension text, hire_date date, termination_date date, manager_id text, status text )\n"} {"conversations": [{"role": "user", "content": "Show 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 contracts where the deployer address is the same as the contract address, indicating self-deployed contracts, and show their network IDs and deployment timestamps."}, {"role": "assistant", "content": "SELECT address, network_id, deployed_at FROM web3.contracts WHERE address = deployer_address;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.contracts ( contract_id character varying(64) NOT NULL, address character varying(128) NOT NULL, abi text NOT NULL, bytecode text NOT NULL, deployer_address character varying(128) NOT NULL, deployed_at timestamp NOT NULL, network_id character varying(64) NOT NULL, status character varying(32) NOT NULL, PRIMARY KEY (contract_id) )\n"} {"conversations": [{"role": "user", "content": "List the first and last names of employees and the full name of the citizens for whom they have scheduled appointments."}, {"role": "assistant", "content": "SELECT T1.first_name , T1.last_name , T3.first_name , T3.last_name FROM government_services.employees AS T1 JOIN government_services.appointments AS T2 ON T1.employee_id = T2.employee_id JOIN government_services.citizens AS T3 ON T2.citizen_id = T3.citizen_id"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id text PRIMARY KEY, national_id_number text, first_name text, last_name text, date_of_birth date, gender text, primary_address text, contact_email text, contact_phone text, registration_date timestamp, is_verified boolean )\nCREATE TABLE government_services.agencies ( agency_id text PRIMARY KEY, agency_name text, jurisdiction_level text, primary_contact_email text, main_phone_number text, website_url text, established_date date, parent_agency_id text )\nCREATE TABLE government_services.services ( service_id text PRIMARY KEY, agency_id text, service_name text, description text, category text, eligibility_criteria text, standard_fee numeric, average_processing_time_days int, is_active boolean, online_application_url text )\nCREATE TABLE government_services.applications ( application_id text PRIMARY KEY, citizen_id text, service_id text, submitted_at timestamp, status text, last_updated_at timestamp, assigned_employee_id text, decision_date date, notes text, reference_number text )\nCREATE TABLE government_services.documents ( document_id text PRIMARY KEY, application_id text, citizen_id text, document_type text, file_reference text, upload_timestamp timestamp, expiry_date date, verification_status text, verified_by_employee_id text, verification_timestamp timestamp )\nCREATE TABLE government_services.payments ( payment_id text PRIMARY KEY, application_id text, citizen_id text, service_id text, amount numeric, currency text, payment_method text, payment_provider_reference text, payment_timestamp timestamp, status text, notes text )\nCREATE TABLE government_services.employees ( employee_id text PRIMARY KEY, agency_id text, first_name text, last_name text, job_title text, department text, work_email text, work_phone text, hire_date date, termination_date date, access_level text, manager_employee_id text )\nCREATE TABLE government_services.appointments ( appointment_id text PRIMARY KEY, citizen_id text, employee_id text, location_id text, service_id text, scheduled_start_time timestamp, scheduled_end_time timestamp, purpose text, status text, booking_method text, created_at timestamp, notes text )\nCREATE TABLE government_services.notifications ( notification_id text PRIMARY KEY, citizen_id text, application_id text, message_subject text, message_body text, channel text, sent_at timestamp, status text, related_entity_type text, related_entity_id text )\n"} {"conversations": [{"role": "user", "content": "Show me each product_type along with the count of products for that type, but only include types where the average base_premium exceeds 500. Order the results by the product count in descending order."}, {"role": "assistant", "content": "SELECT product_type,\n COUNT(*) AS product_count\nFROM insurance.insurance_products\nGROUP BY product_type\nHAVING AVG(base_premium) > 500\nORDER BY product_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.insurance_products ( product_id.text, product_name.text, product_type.text, description.text, base_premium.numeric, coverage_details.text, underwriting_rules.text, is_active.boolean, created_at.timestamp, updated_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "List all securities (security_id, ticker_symbol, security_name) that have a currency of 'EUR' and were last updated within the last 30 days, along with their exchange and sector information."}, {"role": "assistant", "content": "SELECT security_id, ticker_symbol, security_name, exchange, sector FROM financial_services.securities WHERE currency = 'EUR' AND last_updated >= CURRENT_DATE - INTERVAL '30 days';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.securities (\n security_id character varying(64) NOT NULL, -- unique identifier for the security\n ticker_symbol character varying(20) NOT NULL UNIQUE, -- stock ticker or fund symbol\n isin_code character varying(12) UNIQUE, -- International Securities Identification Number\n cusip_code character varying(9) UNIQUE, -- CUSIP number\n security_name text NOT NULL, -- full name of the security\n security_type character varying(50) NOT NULL, -- e.g., Stock, Bond, ETF, Mutual Fund, Option, Future\n exchange character varying(50), -- primary exchange where traded (e.g., NYSE, NASDAQ)\n currency character varying(3) NOT NULL, -- currency the security is denominated in\n issuer_name character varying(255), -- name of the issuing entity\n sector character varying(100), -- industry sector\n last_updated timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n PRIMARY KEY (security_id)\n)\n"} {"conversations": [{"role": "user", "content": "Count the total number of comments each user has made."}, {"role": "assistant", "content": "SELECT user_id, COUNT(*) AS comment_count FROM comments 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 social_media.comments ( comment_id.text, post_id.text, user_id.text, parent_comment_id.text, content.text, created_at.timestamp, updated_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "Can you provide the total number of cars associated with a specific train with train_id 'train_789'?"}, {"role": "assistant", "content": "SCARD train:train_789:cars"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\n// Use Hashes for platform details. Key format: platform:\n// HSET platform:plat_123 platform_id \"plat_123\" station_id \"station_xyz\" platform_number \"1A\" track_number \"T1\" status \"Operational\" length_meters 250.50 accessible 1\n\n// To link platforms to stations (optional):\n// SADD station:station_xyz:platforms platform:plat_123 platform:plat_456\n// Use Hashes for train details. Key format: train:\n// HSET train:train_789 train_id \"train_789\" train_number \"Acela 2151\" model \"Siemens Velaro\" ... status \"Active\" ...\n\n// To find train by train_number (optional index):\n// SET train_number:\"Acela 2151\" train:train_789\n// Use Hashes for car details. Key format: car:\n// HSET car:car_abc car_id \"car_abc\" train_id \"train_789\" car_number \"C3\" car_type \"Passenger\" class \"Business\" capacity 60 features \"WiFi,Power Outlet\"\n\n// To link cars to trains (optional):\n// SADD train:train_789:cars car:car_abc car:car_def\n// Use Hashes for details. Key format: route_station:\n// HSET route_station:rs_ne_1 route_station_id \"rs_ne_1\" route_id \"route_ne_corr\" station_id \"station_bos\" sequence_order 1 ...\n\n// To find stops for a route, use a Sorted Set (score by sequence_order):\n// ZADD route:route_ne_corr:stops 1 route_station:rs_ne_1\n// ZADD route:route_ne_corr:stops 2 route_station:rs_ne_2\n// Use Hashes for schedule details. Key format: schedule:\n// HSET schedule:sched_1122 schedule_id \"sched_1122\" train_id \"train_789\" route_id \"route_ne_corr\" departure_datetime \"2024-05-10T08:00:00-04:00\" ... status \"Scheduled\"\n// Use Hashes for details. Key format: schedule_stop:\n// HSET schedule_stop:stop_sched1122_1 stop_id \"stop_sched1122_1\" schedule_id \"sched_1122\" station_id \"station_bos\" ...\n\n// To find stops for a schedule, use a Sorted Set (score by sequence_order):\n// ZADD schedule:sched_1122:stops 1 schedule_stop:stop_sched1122_1\n// ZADD schedule:sched_1122:stops 2 schedule_stop:stop_sched1122_2\n// Use Hashes for passenger details. Key format: passenger:\n// HSET passenger:pass_pqr passenger_id \"pass_pqr\" first_name \"Alice\" last_name \"Smith\" email \"alice.smith@example.com\" ...\n\n// To find passenger by email (optional index):\n// SET passenger_email:\"alice.smith@example.com\" passenger:pass_pqr\n// Use Hashes for booking details. Key format: booking:\n// HSET booking:book_zyx booking_id \"book_zyx\" passenger_id \"pass_pqr\" schedule_id \"sched_1122\" ... status \"Confirmed\" ...\n\n// To link bookings to passengers/schedules (optional):\n// SADD passenger:pass_pqr:bookings booking:book_zyx\n// SADD schedule:sched_1122:bookings booking:book_zyx\n// Use Hashes for ticket details. Key format: ticket:\n// HSET ticket:tkt_1a2b ticket_id \"tkt_1a2b\" booking_id \"book_zyx\" car_id \"car_abc\" seat_number \"12A\" ... is_checked_in 0 ...\n\n// To link tickets to bookings (optional):\n// SADD booking:book_zyx:tickets ticket:tkt_1a2b\n// Use Hashes for staff details. Key format: staff:\n// HSET staff:staff_mno staff_id \"staff_mno\" first_name \"Bob\" ... employee_number \"E12345\" ... is_active 1\n\n// To find staff by employee number (optional index):\n// SET staff_employee_number:\"E12345\" staff:staff_mno\n// Use Hashes for maintenance record details. Key format: maintenance_record:\n// HSET maintenance_record:maint_rec_001 record_id \"maint_rec_001\" asset_id \"train_789\" asset_type \"Train\" ... status \"Completed\"\n\n// To link records to assets (optional):\n// SADD train:train_789:maintenance maintenance_record:maint_rec_001\n// SADD platform:plat_123:maintenance maintenance_record:maint_rec_002\n"} {"conversations": [{"role": "user", "content": "List all cryptocurrency assets that have been traded at least 50 times, along with their average trade price."}, {"role": "assistant", "content": "SELECT a.asset_id, a.name, a.symbol, COUNT(t.trade_id) AS trade_count, AVG(t.price) AS avg_price FROM trading_platform.assets a JOIN trading_platform.trades t ON a.asset_id = t.asset_id WHERE a.type = 'cryptocurrency' GROUP BY a.asset_id HAVING COUNT(t.trade_id) >= 50 ORDER BY trade_count DESC;"}, {"role": "user", "content": "Now filter these results to only show assets where the average trade price is above $100."}, {"role": "assistant", "content": "SELECT a.asset_id, a.name, a.symbol, COUNT(t.trade_id) AS trade_count, AVG(t.price) AS avg_price FROM trading_platform.assets a JOIN trading_platform.trades t ON a.asset_id = t.asset_id WHERE a.type = 'cryptocurrency' GROUP BY a.asset_id HAVING COUNT(t.trade_id) >= 50 AND AVG(t.price) > 100 ORDER BY avg_price DESC;"}, {"role": "user", "content": "Can you also include the most recent trade timestamp for each asset?"}, {"role": "assistant", "content": "SELECT a.asset_id, a.name, a.symbol, COUNT(t.trade_id) AS trade_count, AVG(t.price) AS avg_price, MAX(t.traded_at) AS last_trade FROM trading_platform.assets a JOIN trading_platform.trades t ON a.asset_id = t.asset_id WHERE a.type = 'cryptocurrency' GROUP BY a.asset_id HAVING COUNT(t.trade_id) >= 50 AND AVG(t.price) > 100 ORDER BY avg_price DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.users (\n user_id character varying(64) NOT NULL, -- unique identifier for the user\n username character varying(128) NOT NULL, -- username of the user\n email character varying(128) NOT NULL, -- email address of the user\n password_hash text NOT NULL, -- hashed password of the user\n created_at timestamp NOT NULL, -- time when the user account was created\n PRIMARY KEY (user_id)\n)\nCREATE TABLE trading_platform.wallets (\n wallet_id character varying(64) NOT NULL, -- unique identifier for the wallet\n user_id character varying(64) NOT NULL, -- identifier of the user owning the wallet\n address character varying(128) NOT NULL, -- address of the wallet\n private_key text NOT NULL, -- private key of the wallet\n created_at timestamp NOT NULL, -- time when the wallet was created\n PRIMARY KEY (wallet_id)\n)\nCREATE TABLE trading_platform.orders (\n order_id character varying(64) NOT NULL, -- unique identifier for the order\n user_id character varying(64) NOT NULL, -- identifier of the user placing the order\n wallet_id character varying(64) NOT NULL, -- identifier of the wallet used for the order\n asset_id character varying(64) NOT NULL, -- identifier of the asset being traded\n order_type character varying(32) NOT NULL, -- type of the order (e.g., buy, sell)\n quantity numeric(38,14) NOT NULL, -- quantity of the asset in the order\n price numeric(38,14) NOT NULL, -- price per unit of the asset\n status character varying(32) NOT NULL, -- status of the order (e.g., open, filled, canceled)\n created_at timestamp NOT NULL, -- time when the order was created\n PRIMARY KEY (order_id)\n)\nCREATE TABLE trading_platform.trades (\n trade_id character varying(64) NOT NULL, -- unique identifier for the trade\n order_id character varying(64) NOT NULL, -- identifier of the order that led to the trade\n buyer_id character varying(64) NOT NULL, -- identifier of the buyer\n seller_id character varying(64) NOT NULL, -- identifier of the seller\n asset_id character varying(64) NOT NULL, -- identifier of the asset being traded\n quantity numeric(38,14) NOT NULL, -- quantity of the asset in the trade\n price numeric(38,14) NOT NULL, -- price per unit of the asset\n traded_at timestamp NOT NULL, -- time when the trade was executed\n PRIMARY KEY (trade_id)\n)\nCREATE TABLE trading_platform.assets (\n asset_id character varying(64) NOT NULL, -- unique identifier for the asset\n name character varying(128) NOT NULL, -- name of the asset\n symbol character varying(32) NOT NULL, -- symbol of the asset\n type character varying(32) NOT NULL, -- type of the asset (e.g., cryptocurrency, stock)\n PRIMARY KEY (asset_id)\n)\nCREATE TABLE trading_platform.dapps (\n dapp_id character varying(64) NOT NULL, -- unique identifier for the DApp\n name character varying(128) NOT NULL, -- name of the DApp\n description text NOT NULL, -- description of the DApp\n url character varying(256) NOT NULL, -- URL of the DApp\n PRIMARY KEY (dapp_id)\n)\nCREATE TABLE trading_platform.peers (\n peer_id character varying(64) NOT NULL, -- unique identifier for the peer\n ip_address character varying(15) NOT NULL, -- IP address of the peer\n port integer NOT NULL, -- port number of the peer\n last_seen timestamp NOT NULL, -- last time the peer was active\n PRIMARY KEY (peer_id)\n)\nCREATE TABLE trading_platform.metadata (\n metadata_id character varying(64) NOT NULL, -- unique identifier for the metadata\n asset_id character varying(64) NOT NULL, -- identifier of the asset the metadata is associated with\n key character varying(128) NOT NULL, -- key of the metadata\n value text NOT NULL, -- value of the metadata\n PRIMARY KEY (metadata_id)\n)\nCREATE TABLE trading_platform.kyc_audit (\n kyc_audit_id character varying(64) NOT NULL, -- unique identifier for the KYC audit\n user_id character varying(64) NOT NULL, -- identifier of the user being audited\n status character varying(32) NOT NULL, -- status of the KYC audit (e.g., pending, approved, rejected)\n reviewed_at timestamp NOT NULL, -- time when the KYC audit was reviewed\n PRIMARY KEY (kyc_audit_id)\n)\nCREATE TABLE trading_platform.logs (\n log_id character varying(64) NOT NULL, -- unique identifier for the log entry\n user_id character varying(64), -- identifier of the user associated with the log entry\n action character varying(128) NOT NULL, -- action performed\n details text NOT NULL, -- details of the action\n logged_at timestamp NOT NULL, -- time when the log entry was created\n PRIMARY KEY (log_id)\n)\n"} {"conversations": [{"role": "user", "content": "List all pairs of tokens (show token_id for both) that share the same contract address, excluding pairs where the token_id is the same."}, {"role": "assistant", "content": "SELECT t1.token_id AS token_id1, t2.token_id AS token_id2, t1.contract_address FROM web3.tokens AS t1 JOIN web3.tokens AS t2 ON t1.contract_address = t2.contract_address WHERE t1.token_id < t2.token_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.tokens ( token_id character varying(64) NOT NULL, contract_address character varying(128) NOT NULL, token_name character varying(128) NOT NULL, token_symbol character varying(32) NOT NULL, decimals integer NOT NULL, total_supply numeric(38,14) NOT NULL, PRIMARY KEY (token_id) )\n"} {"conversations": [{"role": "user", "content": "List all beneficiaries who do not have any contact information provided. Show beneficiary_id, first_name, and last_name."}, {"role": "assistant", "content": "SELECT beneficiary_id, first_name, last_name FROM insurance.policy_beneficiaries WHERE contact_info IS NULL OR contact_info = ''"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.policy_beneficiaries ( beneficiary_id text, policy_id text, customer_id text, first_name text, last_name text, relationship text, percentage_share numeric, contact_info text, added_at timestamp )\n"} {"conversations": [{"role": "user", "content": "Show me all customers who have missing contact information (either phone number or email is null), along with their state and city."}, {"role": "assistant", "content": "SELECT first_name, last_name, state, city FROM insurance.customers WHERE phone_number IS NULL OR email IS NULL;"}, {"role": "user", "content": "Now filter these to only show customers from Florida or New York who were created in the last year."}, {"role": "assistant", "content": "SELECT first_name, last_name, state, city FROM insurance.customers WHERE (phone_number IS NULL OR email IS NULL) AND state IN ('Florida', 'New York') AND created_at >= CURRENT_DATE - INTERVAL '1 year';"}, {"role": "user", "content": "I also want to see when these customers were last updated (updated_at field)."}, {"role": "assistant", "content": "SELECT first_name, last_name, state, city, updated_at FROM insurance.customers WHERE (phone_number IS NULL OR email IS NULL) AND state IN ('Florida', 'New York') AND created_at >= CURRENT_DATE - INTERVAL '1 year';"}, {"role": "user", "content": "Finally, order the results by state first, then by the most recently updated customers first."}, {"role": "assistant", "content": "SELECT first_name, last_name, state, city, updated_at FROM insurance.customers WHERE (phone_number IS NULL OR email IS NULL) AND state IN ('Florida', 'New York') AND created_at >= CURRENT_DATE - INTERVAL '1 year' ORDER BY state, updated_at DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.customers (\n customer_id character varying(64) NOT NULL, -- unique identifier for the customer\n first_name character varying(100) NOT NULL, -- customer's first name\n last_name character varying(100) NOT NULL, -- customer's last name\n date_of_birth date NOT NULL, -- customer's date of birth\n ssn_hash character varying(128), -- Hashed social security number (or national ID)\n address_line1 character varying(255) NOT NULL,\n address_line2 character varying(255),\n city character varying(100) NOT NULL,\n state character varying(50) NOT NULL,\n zip_code character varying(20) NOT NULL,\n country character varying(50) NOT NULL DEFAULT 'USA',\n phone_number character varying(30),\n email character varying(128) UNIQUE, -- unique email address\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the customer record was created\n updated_at timestamp, -- when the customer record was last updated\n status character varying(20) NOT NULL DEFAULT 'Active', -- e.g., Active, Inactive, Prospect\n PRIMARY KEY (customer_id)\n)\n"} {"conversations": [{"role": "user", "content": "For each claim, show the claim ID, incident date, and the number of documents attached to it. Only include claims that have at least 2 documents."}, {"role": "assistant", "content": "SELECT c.claim_id, c.incident_date, COUNT(d.document_id) AS document_count\nFROM insurance.claims c\nJOIN insurance.claim_documents d ON c.claim_id = d.claim_id\nGROUP BY c.claim_id, c.incident_date\nHAVING COUNT(d.document_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 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": "How many clients are registered with an active status?"}, {"role": "assistant", "content": "SELECT COUNT(*) FROM legal_services.clients WHERE status = 'active';"}, {"role": "user", "content": "Could you also tell me the average number of days since registration for these active clients?"}, {"role": "assistant", "content": "SELECT AVG(EXTRACT(EPOCH FROM (CURRENT_TIMESTAMP - date_registered)) / 86400) AS average_days_since_registration FROM legal_services.clients WHERE status = 'active';"}, {"role": "user", "content": "What about clients with a 'prospect' status? Show me the count and the average registration duration in days for them as well."}, {"role": "assistant", "content": "SELECT COUNT(*), AVG(EXTRACT(EPOCH FROM (CURRENT_TIMESTAMP - date_registered)) / 86400) AS average_days_since_registration FROM legal_services.clients WHERE status = 'prospect';"}, {"role": "user", "content": "Can you show me both statuses ('active' and 'prospect') in the same query, listing the status, count, and average duration, and order by count descending?"}, {"role": "assistant", "content": "SELECT status, COUNT(*), AVG(EXTRACT(EPOCH FROM (CURRENT_TIMESTAMP - date_registered)) / 86400) AS average_days_since_registration FROM legal_services.clients WHERE status IN ('active', 'prospect') GROUP BY status ORDER BY count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.clients (\n client_id character varying(64) NOT NULL, -- unique identifier for the client\n first_name character varying(100) NOT NULL, -- client's first name\n last_name character varying(100) NOT NULL, -- client's last name\n company_name character varying(200), -- company name if applicable\n email character varying(128) UNIQUE NOT NULL, -- client's primary email\n phone character varying(32), -- client's contact phone number\n address text, -- client's full address\n date_registered timestamp NOT NULL, -- when the client was first registered\n status character varying(32) NOT NULL, -- client status (e.g., active, inactive, prospect)\n PRIMARY KEY (client_id)\n)\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.time_entries (\n entry_id character varying(64) NOT NULL, -- unique identifier for the time entry\n case_id character varying(64) NOT NULL, -- FK to cases table\n lawyer_id character varying(64) NOT NULL, -- FK to lawyers table (who performed the work)\n date_worked date NOT NULL, -- date the work was performed\n hours_spent numeric(5, 2) NOT NULL CHECK (hours_spent > 0), -- duration of work in hours (e.g., 1.5 for 1h 30m)\n billing_rate numeric(10, 2) NOT NULL, -- hourly rate applied for this entry\n description text NOT NULL, -- detailed description of the work performed\n is_billable boolean DEFAULT true, -- whether this time entry is billable to the client\n is_billed boolean DEFAULT false, -- whether this entry has been included in an invoice\n invoice_id character varying(64), -- FK to invoices table (once billed)\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the entry was recorded\n PRIMARY KEY (entry_id)\n)\nCREATE TABLE legal_services.invoices (\n invoice_id character varying(64) NOT NULL, -- unique identifier for the invoice\n invoice_number character varying(100) UNIQUE NOT NULL, -- user-facing invoice number\n client_id character varying(64) NOT NULL, -- FK to clients table\n case_id character varying(64), -- FK to cases table (optional, could be general retainer)\n issue_date date NOT NULL, -- date the invoice was generated\n due_date date NOT NULL, -- date the payment is due\n total_amount numeric(12, 2) NOT NULL, -- total amount due on the invoice\n amount_paid numeric(12, 2) DEFAULT 0.00, -- amount already paid\n status character varying(50) NOT NULL, -- e.g., Draft, Sent, Paid, Partially Paid, Overdue, Void\n payment_date timestamp, -- date the invoice was fully paid (nullable)\n notes text, -- additional notes or terms on the invoice\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n PRIMARY KEY (invoice_id)\n)\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": "List all appointments scheduled in the next 30 days with appointment_id, client_id, case_id, and any invoice_id linked to that case."}, {"role": "assistant", "content": "SELECT\n a.appointment_id,\n a.client_id,\n a.case_id,\n i.invoice_id\nFROM legal_services.appointments AS a\nLEFT JOIN legal_services.invoices AS i\n ON a.case_id = i.case_id\nWHERE a.start_time BETWEEN CURRENT_DATE AND CURRENT_DATE + INTERVAL '30 days';"}, {"role": "user", "content": "Change to include only appointments with status 'Scheduled' and invoices that are not fully paid."}, {"role": "assistant", "content": "SELECT\n a.appointment_id,\n a.client_id,\n a.case_id,\n i.invoice_id\nFROM legal_services.appointments AS a\nLEFT JOIN legal_services.invoices AS i\n ON a.case_id = i.case_id\nWHERE a.start_time BETWEEN CURRENT_DATE AND CURRENT_DATE + INTERVAL '30 days'\n AND a.status = 'Scheduled'\n AND (i.status IS NULL OR i.status <> 'Paid');"}, {"role": "user", "content": "Also include only those where the case_type is 'Corporate'."}, {"role": "assistant", "content": "SELECT\n a.appointment_id,\n a.client_id,\n a.case_id,\n i.invoice_id\nFROM legal_services.appointments AS a\nJOIN legal_services.cases AS c\n ON a.case_id = c.case_id\nLEFT JOIN legal_services.invoices AS i\n ON a.case_id = i.case_id\nWHERE a.start_time BETWEEN CURRENT_DATE AND CURRENT_DATE + INTERVAL '30 days'\n AND a.status = 'Scheduled'\n AND (i.status IS NULL OR i.status <> 'Paid')\n AND c.case_type = 'Corporate';"}, {"role": "user", "content": "Finally, order by start_time ascending and return only the first 10 rows."}, {"role": "assistant", "content": "SELECT\n a.appointment_id,\n a.client_id,\n a.case_id,\n i.invoice_id\nFROM legal_services.appointments AS a\nJOIN legal_services.cases AS c\n ON a.case_id = c.case_id\nLEFT JOIN legal_services.invoices AS i\n ON a.case_id = i.case_id\nWHERE a.start_time BETWEEN CURRENT_DATE AND CURRENT_DATE + INTERVAL '30 days'\n AND a.status = 'Scheduled'\n AND (i.status IS NULL OR i.status <> 'Paid')\n AND c.case_type = 'Corporate'\nORDER BY a.start_time ASC\nLIMIT 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.law_firms (\n firm_id character varying(64) NOT NULL, -- unique identifier for the law firm\n firm_name character varying(200) NOT NULL, -- official name of the law firm\n address text NOT NULL, -- primary address of the firm\n phone character varying(32), -- firm's main phone number\n website character varying(255), -- firm's website URL\n founded_date date, -- date the firm was established\n managing_partner_id character varying(64), -- FK to lawyers table (optional)\n PRIMARY KEY (firm_id)\n)\nCREATE TABLE legal_services.cases (\n case_id character varying(64) NOT NULL, -- unique identifier for the case/matter\n case_number character varying(100) UNIQUE, -- official case number (court or internal)\n case_name text NOT NULL, -- descriptive name or title for the case\n client_id character varying(64) NOT NULL, -- FK to clients table\n lead_lawyer_id character varying(64) NOT NULL, -- FK to lawyers table (primary lawyer responsible)\n case_type character varying(100) NOT NULL, -- e.g., Litigation, Corporate, Family Law, IP\n status character varying(50) NOT NULL, -- e.g., Open, Closed, Pending, On Hold, Appealed\n date_opened timestamp NOT NULL, -- date the case was formally opened\n date_closed timestamp, -- date the case was closed (nullable)\n description text, -- detailed description of the case\n court_jurisdiction character varying(128), -- court or jurisdiction if applicable\n PRIMARY KEY (case_id)\n)\nCREATE TABLE legal_services.time_entries (\n entry_id character varying(64) NOT NULL, -- unique identifier for the time entry\n case_id character varying(64) NOT NULL, -- FK to cases table\n lawyer_id character varying(64) NOT NULL, -- FK to lawyers table (who performed the work)\n date_worked date NOT NULL, -- date the work was performed\n hours_spent numeric(5, 2) NOT NULL CHECK (hours_spent > 0), -- duration of work in hours (e.g., 1.5 for 1h 30m)\n billing_rate numeric(10, 2) NOT NULL, -- hourly rate applied for this entry\n description text NOT NULL, -- detailed description of the work performed\n is_billable boolean DEFAULT true, -- whether this time entry is billable to the client\n is_billed boolean DEFAULT false, -- whether this entry has been included in an invoice\n invoice_id character varying(64), -- FK to invoices table (once billed)\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the entry was recorded\n PRIMARY KEY (entry_id)\n)\nCREATE TABLE legal_services.invoices (\n invoice_id character varying(64) NOT NULL, -- unique identifier for the invoice\n invoice_number character varying(100) UNIQUE NOT NULL, -- user-facing invoice number\n client_id character varying(64) NOT NULL, -- FK to clients table\n case_id character varying(64), -- FK to cases table (optional, could be general retainer)\n issue_date date NOT NULL, -- date the invoice was generated\n due_date date NOT NULL, -- date the payment is due\n total_amount numeric(12, 2) NOT NULL, -- total amount due on the invoice\n amount_paid numeric(12, 2) DEFAULT 0.00, -- amount already paid\n status character varying(50) NOT NULL, -- e.g., Draft, Sent, Paid, Partially Paid, Overdue, Void\n payment_date timestamp, -- date the invoice was fully paid (nullable)\n notes text, -- additional notes or terms on the invoice\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n PRIMARY KEY (invoice_id)\n)\nCREATE TABLE legal_services.appointments (\n appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment\n client_id character varying(64) NOT NULL, -- FK to clients table\n lawyer_id character varying(64) NOT NULL, -- FK to lawyers table\n case_id character varying(64), -- FK to cases table (optional, if related to a specific case)\n start_time timestamp NOT NULL, -- scheduled start date and time\n end_time timestamp NOT NULL, -- scheduled end date and time\n location text, -- location of the meeting (address or virtual link)\n subject character varying(255), -- subject or purpose of the appointment\n notes text, -- additional notes for the appointment\n status character varying(50) NOT NULL, -- e.g., Scheduled, Completed, Canceled, Rescheduled\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n PRIMARY KEY (appointment_id)\n)\n"} {"conversations": [{"role": "user", "content": "Show me each service order along with the next order placed by the same guest, including both order IDs and the time difference in minutes between the two orders."}, {"role": "assistant", "content": "SELECT a.order_id,\n b.order_id AS next_order_id,\n EXTRACT(EPOCH FROM (b.order_timestamp - a.order_timestamp)) / 60 AS diff_minutes\nFROM hospitality_technology.service_orders a\nJOIN hospitality_technology.service_orders b\n ON a.guest_id = b.guest_id\n AND b.order_timestamp > a.order_timestamp;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.service_orders ( order_id.text, reservation_id.text, guest_id.text, service_id.text, staff_id_ordered.text, staff_id_delivered.text, order_timestamp.timestamp, delivery_timestamp.timestamp, quantity.integer, unit_price.numeric, total_price.numeric, status.text, notes.text, bill_id.text )\n"} {"conversations": [{"role": "user", "content": "I need to find pairs of nodes that share the same port but have different IP addresses. Can you write a query for that?"}, {"role": "assistant", "content": "SELECT n1.node_id AS node1_id,\n n2.node_id AS node2_id,\n n1.port\nFROM blockchain.nodes n1\nJOIN blockchain.nodes n2\n ON n1.port = n2.port\n AND n1.ip_address <> n2.ip_address;"}, {"role": "user", "content": "Great. Now include the time difference in hours between their last_seen timestamps."}, {"role": "assistant", "content": "SELECT n1.node_id AS node1_id,\n n2.node_id AS node2_id,\n n1.port,\n ABS(EXTRACT(EPOCH FROM (n1.last_seen - n2.last_seen)) / 3600) AS hour_diff\nFROM blockchain.nodes n1\nJOIN blockchain.nodes n2\n ON n1.port = n2.port\n AND n1.ip_address <> n2.ip_address;"}, {"role": "user", "content": "Actually, I only want those pairs where the time difference is less than 1 hour, and order the results by the smallest time difference first."}, {"role": "assistant", "content": "SELECT n1.node_id AS node1_id,\n n2.node_id AS node2_id,\n n1.port,\n ABS(EXTRACT(EPOCH FROM (n1.last_seen - n2.last_seen)) / 3600) AS hour_diff\nFROM blockchain.nodes n1\nJOIN blockchain.nodes n2\n ON n1.port = n2.port\n AND n1.ip_address <> n2.ip_address\nWHERE ABS(EXTRACT(EPOCH FROM (n1.last_seen - n2.last_seen)) / 3600) < 1\nORDER BY hour_diff ASC;"}, {"role": "user", "content": "One more thing: can you add a count of how many such pairs exist for each port?"}, {"role": "assistant", "content": "SELECT port,\n COUNT(*) AS pair_count\nFROM (\n SELECT 1\n FROM blockchain.nodes n1\n JOIN blockchain.nodes n2\n ON n1.port = n2.port\n AND n1.ip_address <> n2.ip_address\n WHERE ABS(EXTRACT(EPOCH FROM (n1.last_seen - n2.last_seen)) / 3600) < 1\n) sub\nGROUP BY port;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE blockchain.nodes ( node_id character varying(64) NOT NULL, ip_address character varying(15) NOT NULL, port integer NOT NULL, last_seen timestamp NOT NULL, PRIMARY KEY (node_id) )\n"} {"conversations": [{"role": "user", "content": "Show the names and cities of all service locations, along with the agency ID, for locations whose postal code starts with '10'."}, {"role": "assistant", "content": "SELECT location_name, city, agency_id FROM government_services.service_locations WHERE postal_code LIKE '10%';"}, {"role": "user", "content": "Actually, only include those locations that are marked as accessible."}, {"role": "assistant", "content": "SELECT location_name, city, agency_id FROM government_services.service_locations WHERE postal_code LIKE '10%' AND is_accessible = TRUE;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.service_locations (\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": "Can you help me get the total number of operational platforms across all stations?"}, {"role": "assistant", "content": "db.platforms.countDocuments({ status: 'Operational' });"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\n// db.createCollection('platforms')\n// Optional: db.platforms.createIndex({ platform_id: 1 }, { unique: true })\n// Optional: db.platforms.createIndex({ station_id: 1 })\n{\n _id: ObjectId(),\n platform_id: \"plat_123\", // String (unique)\n station_id: \"station_xyz\", // String (references stations.station_id)\n platform_number: \"1A\", // String\n track_number: \"T1\", // String\n status: \"Operational\", // String ('Operational', 'Maintenance', 'Closed')\n length_meters: 250.50, // Decimal128 or Double\n accessible: true // Boolean\n}\n// db.createCollection('routes')\n// Optional: db.routes.createIndex({ route_id: 1 }, { unique: true })\n{\n _id: ObjectId(),\n route_id: \"route_ne_corr\", // String (unique)\n route_name: \"Northeast Corridor\", // String\n description: \"High-speed rail linking Boston and Washington D.C.\", // String\n origin_station_id: \"station_bos\", // String (references stations.station_id)\n destination_station_id: \"station_was\", // String (references stations.station_id)\n is_active: true // Boolean\n}\n// db.createCollection('route_stations')\n// Optional: db.route_stations.createIndex({ route_station_id: 1 }, { unique: true })\n// Optional: db.route_stations.createIndex({ route_id: 1, sequence_order: 1 }, { unique: true })\n{\n _id: ObjectId(),\n route_station_id: \"rs_ne_1\", // String (unique)\n route_id: \"route_ne_corr\", // String (references routes.route_id)\n station_id: \"station_bos\", // String (references stations.station_id)\n sequence_order: 1, // Int32\n distance_from_previous_km: null, // Decimal128 or Double (null for first stop)\n typical_stop_duration_minutes: null // Int32 (null for origin/destination or if no stop)\n}\n// --- OR --- Embed within the Route document:\n// {\n// _id: ObjectId(), route_id: \"route_ne_corr\", ...,\n// stations: [\n// { station_id: \"station_bos\", sequence_order: 1, distance_from_previous_km: null, typical_stop_duration_minutes: null },\n// { station_id: \"station_pvd\", sequence_order: 2, distance_from_previous_km: 70.5, typical_stop_duration_minutes: 5 },\n// ...\n// ]\n// }\n// db.createCollection('schedules')\n// Optional: db.schedules.createIndex({ schedule_id: 1 }, { unique: true })\n// Optional: db.schedules.createIndex({ route_id: 1, departure_datetime: 1 })\n{\n _id: ObjectId(),\n schedule_id: \"sched_1122\", // String (unique)\n train_id: \"train_789\", // String (references trains.train_id)\n route_id: \"route_ne_corr\", // String (references routes.route_id)\n departure_datetime: ISODate(\"2024-05-10T08:00:00-04:00\"), // Date (with timezone)\n arrival_datetime: ISODate(\"2024-05-10T15:30:00-04:00\"), // Date (with timezone)\n status: \"Scheduled\", // String ('Scheduled', 'On Time', 'Delayed', 'Cancelled', 'Arrived')\n notes: \"Track work expected near Philadelphia\" // String\n}\n// db.createCollection('schedule_stops')\n// Optional: db.schedule_stops.createIndex({ stop_id: 1 }, { unique: true })\n// Optional: db.schedule_stops.createIndex({ schedule_id: 1, sequence_order: 1 }, { unique: true })\n{\n _id: ObjectId(),\n stop_id: \"stop_sched1122_1\", // String (unique)\n schedule_id: \"sched_1122\", // String (references schedules.schedule_id)\n station_id: \"station_bos\", // String (references stations.station_id)\n platform_id: \"plat_bos_3\", // String (references platforms.platform_id, nullable)\n sequence_order: 1, // Int32\n scheduled_arrival_time: null, // Date\n scheduled_departure_time: ISODate(\"2024-05-10T08:00:00-04:00\"), // Date\n actual_arrival_time: null, // Date\n actual_departure_time: ISODate(\"2024-05-10T08:01:00-04:00\"), // Date\n status: \"On Time\" // String\n}\n// --- OR --- Embed within the Schedule document using an array 'stops'\n// db.createCollection('passengers')\n// Optional: db.passengers.createIndex({ passenger_id: 1 }, { unique: true })\n// Optional: db.passengers.createIndex({ email: 1 }, { unique: true, sparse: true })\n// Optional: db.passengers.createIndex({ phone_number: 1 }, { unique: true, sparse: true })\n{\n _id: ObjectId(),\n passenger_id: \"pass_pqr\", // String (unique)\n first_name: \"Alice\", // String\n last_name: \"Smith\", // String\n email: \"alice.smith@example.com\", // String (unique, sparse)\n phone_number: \"+15551234567\", // String (unique, sparse)\n date_of_birth: ISODate(\"1990-03-20\"), // Date\n loyalty_program_id: \"LOYALTY123\", // String\n created_at: ISODate(\"2023-02-01T11:00:00Z\") // Date\n}\n// db.createCollection('staff')\n// Optional: db.staff.createIndex({ staff_id: 1 }, { unique: true })\n// Optional: db.staff.createIndex({ employee_number: 1 }, { unique: true })\n// Optional: db.staff.createIndex({ contact_email: 1 }, { unique: true, sparse: true })\n{\n _id: ObjectId(),\n staff_id: \"staff_mno\", // String (unique)\n first_name: \"Bob\", // String\n last_name: \"Jones\", // String\n role: \"Conductor\", // String\n primary_station_id: null, // String (references stations.station_id, nullable)\n employee_number: \"E12345\", // String (unique)\n hire_date: ISODate(\"2018-06-01\"), // Date\n contact_email: \"bob.jones@example-rail.com\", // String (unique, sparse)\n contact_phone: \"+15559876543\", // String\n is_active: true // Boolean\n}\n"} {"conversations": [{"role": "user", "content": "List all clients along with their case_number and case_type for cases that are currently 'Open'."}, {"role": "assistant", "content": "SELECT c.first_name, c.last_name, c.email, cs.case_number, cs.case_type\nFROM legal_services.clients AS c\nJOIN legal_services.cases AS cs\n ON c.client_id = cs.client_id\nWHERE cs.status = 'Open';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.clients ( client_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, company_name character varying(200), email character varying(128) UNIQUE NOT NULL, phone character varying(32), address text, date_registered timestamp NOT NULL, status character varying(32) NOT NULL, PRIMARY KEY (client_id) )\nCREATE TABLE legal_services.lawyers ( lawyer_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, bar_number character varying(64) UNIQUE NOT NULL, firm_id character varying(64), email character varying(128) UNIQUE NOT NULL, phone character varying(32), specialization text, hire_date timestamp NOT NULL, is_partner boolean DEFAULT false, PRIMARY KEY (lawyer_id) )\nCREATE TABLE legal_services.law_firms ( firm_id character varying(64) NOT NULL, firm_name character varying(200) NOT NULL, address text NOT NULL, phone character varying(32), website character varying(255), founded_date date, managing_partner_id character varying(64), PRIMARY KEY (firm_id) )\nCREATE TABLE legal_services.cases ( case_id character varying(64) NOT NULL, case_number character varying(100) UNIQUE, case_name text NOT NULL, client_id character varying(64) NOT NULL, lead_lawyer_id character varying(64) NOT NULL, case_type character varying(100) NOT NULL, status character varying(50) NOT NULL, date_opened timestamp NOT NULL, date_closed timestamp, description text, court_jurisdiction character varying(128), PRIMARY KEY (case_id) )\nCREATE TABLE legal_services.documents ( document_id character varying(64) NOT NULL, case_id character varying(64) NOT NULL, document_name character varying(255) NOT NULL, document_type character varying(100), storage_path text NOT NULL, uploaded_by_lawyer_id character varying(64), upload_timestamp timestamp NOT NULL, version integer DEFAULT 1, description text, PRIMARY KEY (document_id) )\nCREATE TABLE legal_services.time_entries ( entry_id character varying(64) NOT NULL, case_id character varying(64) NOT NULL, lawyer_id character varying(64) NOT NULL, date_worked date NOT NULL, hours_spent numeric(5, 2) NOT NULL CHECK (hours_spent > 0), billing_rate numeric(10, 2) NOT NULL, description text NOT NULL, is_billable boolean DEFAULT true, is_billed boolean DEFAULT false, invoice_id character varying(64), created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (entry_id) )\nCREATE TABLE legal_services.appointments ( appointment_id character varying(64) NOT NULL, client_id character varying(64) NOT NULL, lawyer_id character varying(64) NOT NULL, case_id character varying(64), start_time timestamp NOT NULL, end_time timestamp NOT NULL, location text, subject character varying(255), notes text, status character varying(50) NOT NULL, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (appointment_id) )\n"} {"conversations": [{"role": "user", "content": "Count the number of law firms founded in each decade. Show the decade (e.g., 1990s, 2000s) and the count."}, {"role": "assistant", "content": "SELECT CONCAT(FLOOR(EXTRACT(YEAR FROM founded_date) / 10) * 10, 's') AS decade, COUNT(*) AS firm_count FROM law_firms WHERE founded_date IS NOT NULL GROUP BY decade ORDER BY decade;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.clients ( client_id text PRIMARY KEY, first_name text, last_name text, company_name text, email text UNIQUE, phone text, address text, date_registered timestamp, status text )\nCREATE TABLE legal_services.law_firms ( firm_id text PRIMARY KEY, firm_name text, address text, phone text, website text, founded_date date, managing_partner_id text )\nCREATE TABLE legal_services.documents ( document_id text PRIMARY KEY, case_id text, document_name text, document_type text, storage_path text, uploaded_by_lawyer_id text, upload_timestamp timestamp, version int, description text )\n"} {"conversations": [{"role": "user", "content": "Find all users who registered with a Yahoo email address, along with their registration dates."}, {"role": "assistant", "content": "SELECT user_id, username, email, password_hash FROM blockchain.users WHERE email LIKE '%@yahoo.com';"}, {"role": "user", "content": "This query doesn't show registration dates. Can you modify it to include the registration date?"}, {"role": "assistant", "content": "I notice the users table doesn't have a registration date column. Would you like me to show other available information from the users table?"}, {"role": "user", "content": "Then just show me the count of Yahoo email users instead."}, {"role": "assistant", "content": "SELECT COUNT(*) as yahoo_user_count FROM blockchain.users WHERE email LIKE '%@yahoo.com';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE blockchain.blocks ( block_id text, previous_block_id text, timestamp timestamp, nonce integer, merkle_root text, difficulty integer )\nCREATE TABLE blockchain.transactions (\n transaction_id character varying(64) NOT NULL, -- unique identifier for the transaction\n block_id character varying(64) NOT NULL, -- identifier of the block containing the transaction\n sender_address character varying(128) NOT NULL, -- address of the sender\n receiver_address character varying(128) NOT NULL, -- address of the receiver\n amount numeric(38,14) NOT NULL, -- amount transferred\n timestamp timestamp NOT NULL, -- time when the transaction was created\n signature text NOT NULL, -- digital signature of the transaction\n PRIMARY KEY (transaction_id)\n)\nCREATE TABLE blockchain.addresses ( address_id text PRIMARY KEY, public_key text, balance numeric )\nCREATE TABLE blockchain.users ( user_id character varying(64) NOT NULL, username character varying(128) NOT NULL, email character varying(128) NOT NULL, password_hash text NOT NULL, PRIMARY KEY (user_id) )\n"} {"conversations": [{"role": "user", "content": "List all pairs of fuel log entries for the same vehicle that occurred more than 7 days apart, showing vehicle_id, first_log_id, second_log_id, and the time difference in days."}, {"role": "assistant", "content": "SELECT f1.vehicle_id,\n f1.fuel_log_id AS first_log_id,\n f2.fuel_log_id AS second_log_id,\n EXTRACT(EPOCH FROM (f2.log_timestamp - f1.log_timestamp))/86400 AS days_difference\nFROM transportation.fuel_logs f1\nJOIN transportation.fuel_logs f2\n ON f1.vehicle_id = f2.vehicle_id\n AND f2.log_timestamp > f1.log_timestamp + INTERVAL '7 days';"}, {"role": "user", "content": "Now filter to only include pairs where the quantity increased by at least 50 units."}, {"role": "assistant", "content": "SELECT f1.vehicle_id,\n f1.fuel_log_id AS first_log_id,\n f2.fuel_log_id AS second_log_id,\n EXTRACT(EPOCH FROM (f2.log_timestamp - f1.log_timestamp))/86400 AS days_difference\nFROM transportation.fuel_logs f1\nJOIN transportation.fuel_logs f2\n ON f1.vehicle_id = f2.vehicle_id\n AND f2.log_timestamp > f1.log_timestamp + INTERVAL '7 days'\nWHERE (f2.quantity - f1.quantity) >= 50;"}, {"role": "user", "content": "Also display the difference in total_cost between the two logs."}, {"role": "assistant", "content": "SELECT f1.vehicle_id,\n f1.fuel_log_id AS first_log_id,\n f2.fuel_log_id AS second_log_id,\n EXTRACT(EPOCH FROM (f2.log_timestamp - f1.log_timestamp))/86400 AS days_difference,\n (f2.quantity - f1.quantity) AS quantity_difference,\n (f2.total_cost - f1.total_cost) AS cost_difference\nFROM transportation.fuel_logs f1\nJOIN transportation.fuel_logs f2\n ON f1.vehicle_id = f2.vehicle_id\n AND f2.log_timestamp > f1.log_timestamp + INTERVAL '7 days'\nWHERE (f2.quantity - f1.quantity) >= 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 transportation.fuel_logs ( fuel_log_id.text, vehicle_id.text, trip_id.text, log_timestamp.timestamp, fuel_type.text, quantity.numeric, unit.text, cost_per_unit.numeric, total_cost.numeric, odometer_reading.integer, location_id.text )\n"} {"conversations": [{"role": "user", "content": "Retrieve a list of all patient insurance policies, showing the subscriber name and the name of the insurance provider for the plan."}, {"role": "assistant", "content": "SELECT T1.subscriber_name, T2.insurance_provider FROM healthcare.patient_insurance AS T1 JOIN healthcare.insurance_plans AS T2 ON T1.plan_id = T2.plan_id;"}, {"role": "user", "content": "Refine this list to only include policies from the provider 'Aetna' and where the subscriber name contains 'Doe'."}, {"role": "assistant", "content": "SELECT T1.subscriber_name, T2.insurance_provider FROM healthcare.patient_insurance AS T1 JOIN healthcare.insurance_plans AS T2 ON T1.plan_id = T2.plan_id WHERE T2.insurance_provider = 'Aetna' AND T1.subscriber_name LIKE '%Doe%';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patient_insurance (\n patient_insurance_id character varying(64) NOT NULL, -- unique identifier for this patient-plan link\n patient_id character varying(64) NOT NULL, -- FK to patients table\n plan_id character varying(64) NOT NULL, -- FK to insurance_plans table\n policy_number character varying(100) NOT NULL, -- patient's policy number\n group_number character varying(100), -- group number, if applicable\n subscriber_name character varying(200), -- name of the primary policy holder\n effective_date date NOT NULL, -- date the coverage begins\n expiration_date date, -- date the coverage ends (if known)\n is_primary boolean NOT NULL DEFAULT true, -- indicates if this is the primary insurance\n PRIMARY KEY (patient_insurance_id),\n UNIQUE (patient_id, plan_id, policy_number) -- ensure a patient doesn't have the same policy twice\n)\n"} {"conversations": [{"role": "user", "content": "List the distinct cities where service locations are present."}, {"role": "assistant", "content": "SELECT DISTINCT city FROM government_services.service_locations;"}], "system": "You are an SQL statement expert. Given the table structure 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": "Give me the total billed amount for each invoice in 2024."}, {"role": "assistant", "content": "SELECT invoice_id, SUM(hours_spent * billing_rate) AS total_billed_amount FROM legal_services.time_entries WHERE is_billed = TRUE AND EXTRACT(YEAR FROM date_worked) = 2024 GROUP BY invoice_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.time_entries ( entry_id text PRIMARY KEY, case_id text, lawyer_id text, date_worked date, hours_spent numeric, billing_rate numeric, description text, is_billable bool, is_billed bool, invoice_id text, created_at timestamp )\n"} {"conversations": [{"role": "user", "content": "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 premium payments for policy 'POL123'. Show payment ID, payment date, amount paid, and status."}, {"role": "assistant", "content": "SELECT payment_id, payment_date, amount_paid, status FROM insurance.premium_payments WHERE policy_id = 'POL123';"}, {"role": "user", "content": "Only show payments made on or after January 1, 2024."}, {"role": "assistant", "content": "SELECT payment_id, payment_date, amount_paid, status FROM insurance.premium_payments WHERE policy_id = 'POL123' AND payment_date >= '2024-01-01';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.premium_payments (\n payment_id character varying(64) NOT NULL, -- unique identifier for the payment\n policy_id character varying(64) NOT NULL, -- identifier of the policy the payment is for (FK to policies)\n customer_id character varying(64) NOT NULL, -- identifier of the customer making the payment (FK to customers)\n payment_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- date the payment was received\n amount_paid numeric(12, 2) NOT NULL, -- amount of the payment\n payment_method character varying(50), -- e.g., Credit Card, Bank Transfer, Check\n transaction_reference character varying(128) UNIQUE, -- reference from payment processor\n due_date date, -- due date for this payment installment\n payment_period_start date, -- start date of the period this payment covers\n payment_period_end date, -- end date of the period this payment covers\n status character varying(30) NOT NULL DEFAULT 'Completed', -- e.g., Completed, Pending, Failed, Refunded\n PRIMARY KEY (payment_id)\n)\n"} {"conversations": [{"role": "user", "content": "Retrieve the agency name and the most recent notification sent date for each agency, considering only notifications related to agencies."}, {"role": "assistant", "content": "SELECT a.agency_name, MAX(n.sent_at) AS last_notification_date\nFROM government_services.agencies a\nJOIN government_services.notifications n\n ON n.related_entity_type = 'Agency'\n AND n.related_entity_id = a.agency_id\nGROUP BY a.agency_name;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.agencies ( agency_id character varying(64) NOT NULL, agency_name character varying(255) NOT NULL, jurisdiction_level character varying(50) NOT NULL, primary_contact_email character varying(128), main_phone_number character varying(32), website_url character varying(255), established_date date, parent_agency_id character varying(64), PRIMARY KEY (agency_id) )\nCREATE TABLE government_services.notifications (\n notification_id character varying(64) NOT NULL, -- unique identifier for the notification\n citizen_id character varying(64) NOT NULL, -- FK to citizens table\n application_id character varying(64), -- FK to applications table (optional)\n message_subject character varying(255),\n message_body text NOT NULL,\n channel character varying(30) NOT NULL, -- e.g., Email, SMS, Portal Message, Mail\n sent_at timestamp NOT NULL,\n status character varying(30) NOT NULL, -- e.g., Queued, Sent, Delivered, Failed, Read\n related_entity_type character varying(50), -- e.g., Application, Appointment, Document Request\n related_entity_id character varying(64), -- ID of the related entity\n PRIMARY KEY (notification_id)\n)\n"} {"conversations": [{"role": "user", "content": "Calculate the average number of days between when an incident occurred and when the claim was reported, but only for claims that were settled in the year 2023."}, {"role": "assistant", "content": "SELECT\n AVG(EXTRACT(EPOCH FROM (reported_date - incident_date)) / 86400.0)::numeric(10, 2)\nFROM\n insurance.claims\nWHERE\n settlement_date IS NOT NULL AND EXTRACT(YEAR FROM settlement_date) = 2023;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.claims (\n claim_id character varying(64) NOT NULL, -- unique identifier for the claim\n policy_id character varying(64) NOT NULL, -- identifier of the policy under which the claim is made (FK to policies)\n customer_id character varying(64) NOT NULL, -- identifier of the customer making the claim (FK to customers)\n incident_date timestamp NOT NULL, -- date and time of the incident leading to the claim\n reported_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- date the claim was reported\n description text NOT NULL, -- detailed description of the incident and claim\n estimated_loss numeric(15, 2), -- initial estimated cost of the loss\n status character varying(30) NOT NULL, -- e.g., Filed, Processing, Under Review, Approved, Denied, Settled\n settlement_amount numeric(15, 2), -- final amount paid out\n settlement_date date,\n claim_handler_id character varying(64), -- identifier for the employee handling the claim (FK to employees/adjusters)\n police_report_number character varying(100),\n PRIMARY KEY (claim_id)\n)\n"} {"conversations": [{"role": "user", "content": "List all users whose usernames start with the letter 'B'."}, {"role": "assistant", "content": "SELECT user_id, username, email, created_at FROM trading_platform.users WHERE username LIKE 'B%';"}, {"role": "user", "content": "Can you make it case-insensitive, so usernames starting with either upper or lower case 'b' are included?"}, {"role": "assistant", "content": "SELECT user_id, username, email, created_at FROM trading_platform.users WHERE username ILIKE 'b%';"}, {"role": "user", "content": "Instead of showing all details, just display the usernames in alphabetical order."}, {"role": "assistant", "content": "SELECT username FROM trading_platform.users WHERE username ILIKE 'b%' ORDER BY username ASC;"}, {"role": "user", "content": "Limit the result to only the first 3 usernames."}, {"role": "assistant", "content": "SELECT username FROM trading_platform.users WHERE username ILIKE 'b%' ORDER BY username ASC LIMIT 3;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.users (\n user_id character varying(64) NOT NULL, -- unique identifier for the user\n username character varying(128) NOT NULL, -- username of the user\n email character varying(128) NOT NULL, -- email address of the user\n password_hash text NOT NULL, -- hashed password of the user\n created_at timestamp NOT NULL, -- time when the user account was created\n PRIMARY KEY (user_id)\n)\n"} {"conversations": [{"role": "user", "content": "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": "Which pairs of routes have the same distance in kilometers but different estimated durations? Show their route numbers, distances and both estimated durations."}, {"role": "assistant", "content": "SELECT r1.route_number AS route_number_1, r2.route_number AS route_number_2, r1.distance_km, r1.estimated_duration_minutes AS estimated_duration_1, r2.estimated_duration_minutes AS estimated_duration_2\nFROM transportation.routes r1\nJOIN transportation.routes r2\n ON r1.distance_km = r2.distance_km\n AND r1.estimated_duration_minutes <> r2.estimated_duration_minutes\n AND r1.route_id < r2.route_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.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": "For each notification, list the next notification sent to the same citizen (if any). Show citizen_id, notification_id, sent_at, next_notification_id, and next_sent_at."}, {"role": "assistant", "content": "SELECT\n n1.citizen_id,\n n1.notification_id,\n n1.sent_at,\n n2.notification_id AS next_notification_id,\n n2.sent_at AS next_sent_at\nFROM government_services.notifications n1\nLEFT JOIN government_services.notifications n2\n ON n1.citizen_id = n2.citizen_id\n AND n2.sent_at = (\n SELECT MIN(sent_at)\n FROM government_services.notifications n3\n WHERE n3.citizen_id = n1.citizen_id\n AND n3.sent_at > n1.sent_at\n );"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.notifications ( notification_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, application_id character varying(64), message_subject character varying(255), message_body text NOT NULL, channel character varying(30) NOT NULL, sent_at timestamp NOT NULL, status character varying(30) NOT NULL, related_entity_type character varying(50), related_entity_id character varying(64), PRIMARY KEY (notification_id) )\n"} {"conversations": [{"role": "user", "content": "Find all 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": "Find all users whose usernames contain numbers and have email addresses from either Gmail or Yahoo."}, {"role": "assistant", "content": "SELECT username, email FROM blockchain.users WHERE (username ~ '[0-9]') AND (email LIKE '%@gmail.com' OR email LIKE '%@yahoo.com');"}, {"role": "user", "content": "Now, order these results by username length in descending order."}, {"role": "assistant", "content": "SELECT username, email FROM blockchain.users WHERE (username ~ '[0-9]') AND (email LIKE '%@gmail.com' OR email LIKE '%@yahoo.com') ORDER BY LENGTH(username) DESC;"}, {"role": "user", "content": "Can you modify this to only show the top 5 longest usernames?"}, {"role": "assistant", "content": "SELECT username, email FROM blockchain.users WHERE (username ~ '[0-9]') AND (email LIKE '%@gmail.com' OR email LIKE '%@yahoo.com') ORDER BY LENGTH(username) DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE blockchain.users ( user_id text, username text, email text, password_hash text )\n"} {"conversations": [{"role": "user", "content": "List all medical records, showing the record ID, record date, and the full name of the doctor who created the record. Include the patient ID as well."}, {"role": "assistant", "content": "SELECT mr.record_id, mr.record_date, mr.patient_id, d.first_name, d.last_name FROM healthcare.medical_records mr JOIN doctors d ON mr.doctor_id = d.doctor_id;"}, {"role": "user", "content": "Refine this to only include records where the chief_complaint is not null or empty and the doctor's specialty is 'Cardiology'."}, {"role": "assistant", "content": "SELECT mr.record_id, mr.record_date, mr.patient_id, d.first_name, d.last_name FROM healthcare.medical_records mr JOIN doctors d ON mr.doctor_id = d.doctor_id WHERE (mr.chief_complaint IS NOT NULL AND mr.chief_complaint != '') AND d.specialty = 'Cardiology';"}, {"role": "user", "content": "Also, sort the results by record_date in descending order and limit the output to the top 10 records."}, {"role": "assistant", "content": "SELECT mr.record_id, mr.record_date, mr.patient_id, d.first_name, d.last_name FROM healthcare.medical_records mr JOIN doctors d ON mr.doctor_id = d.doctor_id WHERE (mr.chief_complaint IS NOT NULL AND mr.chief_complaint != '') AND d.specialty = 'Cardiology' ORDER BY mr.record_date DESC LIMIT 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.medical_records (\n record_id character varying(64) NOT NULL, -- unique identifier for the medical record entry\n patient_id character varying(64) NOT NULL, -- FK to patients table\n appointment_id character varying(64) UNIQUE, -- FK to appointments table (can be null if record not tied to specific appt)\n doctor_id character varying(64) NOT NULL, -- FK to doctors table (doctor creating the record)\n record_date timestamp with time zone NOT NULL, -- date the record/observation was made\n chief_complaint text, -- patient's primary reason for visit\n present_illness_history text, -- detailed history of the current issue\n past_medical_history text, -- relevant past conditions/surgeries\n physical_examination_notes text, -- findings from the physical exam\n assessment text, -- doctor's assessment/diagnosis summary\n treatment_plan text, -- planned course of action\n vitals jsonb, -- store vitals like BP, HR, Temp as structured JSON\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n PRIMARY KEY (record_id)\n)\n"} {"conversations": [{"role": "user", "content": "List all reservations that have a total_amount greater than the amount_paid. Include the reservation_id, guest_id, total_amount, and amount_paid."}, {"role": "assistant", "content": "SELECT reservation_id, guest_id, total_amount, amount_paid\nFROM hospitality_technology.reservations\nWHERE total_amount > amount_paid;"}, {"role": "user", "content": "Can you also show the check_in_date and check_out_date for each of those reservations?"}, {"role": "assistant", "content": "SELECT reservation_id, guest_id, total_amount, amount_paid, check_in_date, check_out_date\nFROM hospitality_technology.reservations\nWHERE total_amount > amount_paid;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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.payments ( payment_id text PRIMARY KEY, reservation_id text, guest_id text, bill_id text, amount numeric, currency_code text, payment_method text, card_type text, card_last_four text, transaction_ref text, payment_timestamp timestamp, status text, staff_id_processed text, notes text )\n"} {"conversations": [{"role": "user", "content": "List all pairs of time entries worked by the same lawyer on the same day but billed at different rates. Include both entry IDs, the lawyer_id, the date_worked, and each billing_rate."}, {"role": "assistant", "content": "SELECT t1.entry_id AS entry1_id,\n t2.entry_id AS entry2_id,\n t1.lawyer_id,\n t1.date_worked,\n t1.billing_rate AS rate1,\n t2.billing_rate AS rate2\nFROM legal_services.time_entries t1\nJOIN legal_services.time_entries t2\n ON t1.lawyer_id = t2.lawyer_id\n AND t1.date_worked = t2.date_worked\n AND t1.billing_rate <> t2.billing_rate\n AND t1.entry_id < t2.entry_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.time_entries ( entry_id.text, case_id.text, lawyer_id.text, date_worked.date, hours_spent.numeric, billing_rate.numeric, description.text, is_billable.boolean, is_billed.boolean, invoice_id.text, created_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "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 all plan names and their contact numbers for plans of type 'HMO' offered by 'Sunrise Insurance'."}, {"role": "assistant", "content": "SELECT plan_name, contact_phone FROM healthcare.insurance_plans WHERE plan_type = 'HMO' AND insurance_provider = 'Sunrise Insurance';"}], "system": "You are an SQL statement expert. Given the table structure 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.insurance_plans ( plan_id text PRIMARY KEY, plan_name text, insurance_provider text, plan_type text, contact_phone text, website text )\n"} {"conversations": [{"role": "user", "content": "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": "How many likes were given to comments in June 2024?"}, {"role": "assistant", "content": "SELECT COUNT(*) AS comment_likes_count\nFROM social_media.likes\nWHERE comment_id IS NOT NULL \n AND DATE_TRUNC('month', created_at) = '2024-06-01';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.comments ( comment_id character varying(64) NOT NULL, post_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, parent_comment_id character varying(64), content text NOT NULL, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (comment_id) )\nCREATE TABLE social_media.likes ( like_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, post_id character varying(64), comment_id character varying(64), created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (like_id), CONSTRAINT unique_user_like UNIQUE (user_id, post_id, comment_id), CONSTRAINT check_like_target CHECK (post_id IS NOT NULL OR comment_id IS NOT NULL) )\nCREATE TABLE social_media.post_hashtags ( post_hashtag_id character varying(64) NOT NULL, post_id character varying(64) NOT NULL, hashtag_id character varying(64) NOT NULL, PRIMARY KEY (post_hashtag_id), CONSTRAINT unique_post_hashtag UNIQUE (post_id, hashtag_id) )\nCREATE TABLE social_media.conversations ( conversation_id character varying(64) NOT NULL, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, last_message_at timestamp, is_group_chat boolean NOT NULL DEFAULT false, group_name character varying(100), PRIMARY KEY (conversation_id) )\nCREATE TABLE social_media.notifications ( notification_id character varying(64) NOT NULL, recipient_user_id character varying(64) NOT NULL, sender_user_id character varying(64), notification_type character varying(30) NOT NULL, target_entity_id character varying(64), target_entity_type character varying(20), created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, read_at timestamp, PRIMARY KEY (notification_id) )\nCREATE TABLE social_media.user_settings ( setting_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL UNIQUE, theme character varying(20) DEFAULT 'light', email_notifications_enabled boolean DEFAULT true, push_notifications_enabled boolean DEFAULT true, private_profile boolean DEFAULT false, updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (setting_id) )\n"} {"conversations": [{"role": "user", "content": "Show 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": "For Sui NFTs with status 'exists', list their object_id, name, and owner."}, {"role": "assistant", "content": "SELECT object_id, name, owner\nFROM sui_nfts\nWHERE status = 'exists';"}, {"role": "user", "content": "I also need to see collection_type and package_id for each NFT."}, {"role": "assistant", "content": "SELECT object_id, name, owner, collection_type, package_id\nFROM sui_nfts\nWHERE status = 'exists';"}, {"role": "user", "content": "Please filter the result to include only NFTs where collection_type contains the word 'Genesis'."}, {"role": "assistant", "content": "SELECT object_id, name, owner, collection_type, package_id\nFROM sui_nfts\nWHERE status = 'exists' AND collection_type LIKE '%Genesis%';"}], "system": "You are an SQL statement expert. Given the table structure 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 (\n block_number bigint NOT NULL, -- Block number containing the transaction\n contract_address varchar NOT NULL, -- Event contract address\n wallet_address varchar NOT NULL, -- The wallet address for the contract\n amount varchar NOT NULL, -- Wallet's on-chain balance at the corresponding block height\n pk integer NOT NULL -- Partition key for the table(floor(block_number / 7200))\n)\nCREATE TABLE nft_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 (\n block_number bigint NOT NULL, -- Block number containing the transaction\n contract_address varchar NOT NULL, -- Event contract address\n wallet_address varchar NOT NULL, -- The wallet address for the contract(with bloom filter)\n token_id varchar NOT NULL, -- NFT token id\n contract_type varchar NOT NULL, -- NFT contract type\n amount varchar NOT NULL, -- The quantity held in the wallet\n pk integer NOT NULL -- Partition key for the table(floor(block_number / 7200))\n)\nCREATE TABLE sui_coins_metadata ( object_id.text, coin_type.text, status.text, decimals.bigint, description.text, icon_url.text, symbol.text, name.text )\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_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 (\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n tick varchar NOT NULL, -- Token tick\n max_supply decimal(38,0) NOT NULL, -- Max supply\n lim decimal(38,0) NOT NULL, -- Limit of each mint\n wlim decimal(38,0) NOT NULL, -- Limit of each address can maximum mint\n dec integer NOT NULL, -- Decimal for minimum divie\n creator varchar(42) NOT NULL -- Address originating the inscription (matches from_address in transactions table)\n)\nCREATE TABLE token_activities (\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n log_index integer NOT NULL, -- Index of the log within the transaction\n type varchar NOT NULL, -- mint | transfer | burn\n tick varchar NOT NULL, -- Token tick\n id varchar(255) NOT NULL, -- Unique identifier of the inscription\n amt decimal(38,0) NOT NULL, -- Mint amount\n from_address varchar(42) NOT NULL, -- Address sending the inscription (matches from_address in transactions table)\n to_address varchar(42) NOT NULL -- Address receiving the inscription (match to_address in transactions table)\n)\nCREATE TABLE mud_holesky_redstone ( address varchar NOT NULL, table_id varchar NOT NULL, key_bytes varchar NOT NULL, key0 varchar NOT NULL, key1 varchar NOT NULL, static_data varchar NOT NULL, encoded_lengths varchar NOT NULL, dynamic_data varchar NOT NULL, is_deleted boolean NOT NULL, block_number bigint NOT NULL, log_index bigint NOT NULL )\nCREATE TABLE token_info_bitcoin ( 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_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_balances_avalanche ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar(20) NOT NULL, wallet_address varchar(42) NOT NULL, total_supply decimal(38,0) NOT NULL, amount decimal(38,0) NOT NULL )\nCREATE TABLE token_info_avalanche (\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n tick varchar(20) NOT NULL, -- Ticker: Identifier of the inscription\n max_supply decimal(38,0) NOT NULL, -- Max supply: Set max supply of the inscription\n lim decimal(38,0) NOT NULL, -- Mint limit: limit per inscription\n wlim decimal(38,0) NOT NULL, -- Limit of each address can maximum mint\n dec integer NOT NULL, -- Decimal for minimum divie\n creator varchar(42) NOT NULL, -- Address originating the inscription (matches from_address in transactions table)\n minted decimal(38,0) NOT NULL, -- Sum of minted amount\n holders decimal(38,0) NOT NULL, -- Count of holders\n txs decimal(38,0) NOT NULL, -- Count of transactions\n updated_timestamp timestamp(3) NOT NULL, -- Timestamp of update\n completed_timestamp timestamp(3) NOT NULL, -- Timestamp of minted completed\n id varchar(255) NOT NULL -- id fields for the functionType in contract asc20\n)\n"} {"conversations": [{"role": "user", "content": "Can you write a query that retrieves each server's name, its region, and the highest current player count observed in that region?"}, {"role": "assistant", "content": "SELECT s.server_name, s.region, m.max_current_players\nFROM gaming_technology.servers s\nJOIN (\n SELECT region, MAX(current_players) AS max_current_players\n FROM gaming_technology.servers\n GROUP BY region\n) m ON s.region = m.region;"}, {"role": "user", "content": "Actually, only include regions where that maximum current player count exceeds 50."}, {"role": "assistant", "content": "SELECT s.server_name, s.region, m.max_current_players\nFROM gaming_technology.servers s\nJOIN (\n SELECT region, MAX(current_players) AS max_current_players\n FROM gaming_technology.servers\n GROUP BY region\n HAVING MAX(current_players) > 50\n) m ON s.region = m.region;"}, {"role": "user", "content": "Also, exclude any servers that are already full (where current_players equals max_players)."}, {"role": "assistant", "content": "SELECT s.server_name, s.region, m.max_current_players\nFROM gaming_technology.servers s\nJOIN (\n SELECT region, MAX(current_players) AS max_current_players\n FROM gaming_technology.servers\n GROUP BY region\n HAVING MAX(current_players) > 50\n) m ON s.region = m.region\nWHERE s.current_players < s.max_players;"}, {"role": "user", "content": "Finally, sort the results by region ascending and then by the maximum current players in descending order."}, {"role": "assistant", "content": "SELECT s.server_name, s.region, m.max_current_players\nFROM gaming_technology.servers s\nJOIN (\n SELECT region, MAX(current_players) AS max_current_players\n FROM gaming_technology.servers\n GROUP BY region\n HAVING MAX(current_players) > 50\n) m ON s.region = m.region\nWHERE s.current_players < s.max_players\nORDER BY s.region ASC, m.max_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.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) )\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 the total billed hours and total billed amount for each case that has at least one billed and billable time entry."}, {"role": "assistant", "content": "SELECT t.case_id, c.case_number, SUM(t.hours_spent) AS total_billed_hours, SUM(t.hours_spent * t.billing_rate) AS total_billed_amount\nFROM legal_services.time_entries t\nJOIN legal_services.cases c ON t.case_id = c.case_id\nWHERE t.is_billable = TRUE AND t.is_billed = TRUE\nGROUP BY t.case_id, c.case_number\nHAVING COUNT(*) >= 1;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.cases (\n case_id character varying(64) NOT NULL, -- unique identifier for the case/matter\n case_number character varying(100) UNIQUE, -- official case number (court or internal)\n case_name text NOT NULL, -- descriptive name or title for the case\n client_id character varying(64) NOT NULL, -- FK to clients table\n lead_lawyer_id character varying(64) NOT NULL, -- FK to lawyers table (primary lawyer responsible)\n case_type character varying(100) NOT NULL, -- e.g., Litigation, Corporate, Family Law, IP\n status character varying(50) NOT NULL, -- e.g., Open, Closed, Pending, On Hold, Appealed\n date_opened timestamp NOT NULL, -- date the case was formally opened\n date_closed timestamp, -- date the case was closed (nullable)\n description text, -- detailed description of the case\n court_jurisdiction character varying(128), -- court or jurisdiction if applicable\n PRIMARY KEY (case_id)\n)\nCREATE TABLE legal_services.time_entries ( entry_id text PRIMARY KEY, case_id text, lawyer_id text, date_worked date, hours_spent numeric, billing_rate numeric, description text, is_billable bool, is_billed bool, invoice_id text, created_at timestamp )\nCREATE TABLE legal_services.appointments ( appointment_id.text, client_id.text, lawyer_id.text, case_id.text, start_time.timestamp, end_time.timestamp, location.text, subject.text, notes.text, status.text, created_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "Count the number of logs for each action type."}, {"role": "assistant", "content": "SELECT action,\n COUNT(*) AS count\nFROM trading_platform.logs\nGROUP BY action;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.logs ( log_id text PRIMARY KEY, user_id text, action text, details text, logged_at timestamp )\n"} {"conversations": [{"role": "user", "content": "For each 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": "How many insurance policies does each patient have? Return patient_id and policy_count."}, {"role": "assistant", "content": "SELECT patient_id,\n COUNT(*) AS policy_count\nFROM healthcare.patient_insurance\nGROUP BY patient_id;"}, {"role": "user", "content": "Only show patients with more than 2 policies and order by policy_count descending."}, {"role": "assistant", "content": "SELECT patient_id,\n COUNT(*) AS policy_count\nFROM healthcare.patient_insurance\nGROUP BY patient_id\nHAVING COUNT(*) > 2\nORDER BY policy_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.doctors ( doctor_id.text, first_name.text, last_name.text, specialty.text, license_number.text, phone_number.text, email.text, hospital_affiliation_id.text, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE healthcare.appointments ( appointment_id.text, patient_id.text, doctor_id.text, appointment_time.timestamp, duration_minutes.integer, reason.text, status.text, location_id.text, notes.text, created_at.timestamp )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id.text, record_id.text, patient_id.text, doctor_id.text, diagnosis_code.text, code_type.text, description.text, diagnosis_date.date, status.text, is_chronic.boolean )\nCREATE TABLE healthcare.medications ( medication_id.text, medication_name.text, generic_name.text, manufacturer.text, ndc_code.text, description.text )\nCREATE TABLE healthcare.prescriptions ( prescription_id.text, record_id.text, patient_id.text, doctor_id.text, medication_id.text, dosage.text, frequency.text, route.text, start_date.date, end_date.date, quantity_dispensed.numeric, refills_allowed.integer, prescription_date.timestamp )\nCREATE TABLE healthcare.insurance_plans ( plan_id.text, plan_name.text, insurance_provider.text, plan_type.text, contact_phone.text, website.text )\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id.text, patient_id.text, plan_id.text, policy_number.text, group_number.text, subscriber_name.text, effective_date.date, expiration_date.date, is_primary.boolean )\n"} {"conversations": [{"role": "user", "content": "For each chain, which centralized exchange holds the largest total USD value in their token balance as of the most recent snapshot?"}, {"role": "assistant", "content": "WITH latest_snapshot AS (\n SELECT MAX(snapshot_time) AS max_time FROM cex_token_balance\n)\nSELECT c.chain, c.exchange, SUM(c.usd_value) AS total_usd_value\nFROM cex_token_balance c\nJOIN latest_snapshot l ON c.snapshot_time = l.max_time\nGROUP BY c.chain, c.exchange\nQUALIFY ROW_NUMBER() OVER(PARTITION BY c.chain ORDER BY SUM(c.usd_value) DESC) = 1;"}, {"role": "user", "content": "Could you also include the number of distinct tokens each exchange holds in those chains?"}, {"role": "assistant", "content": "WITH latest_snapshot AS (\n SELECT MAX(snapshot_time) AS max_time FROM cex_token_balance\n),\nexchange_totals AS (\n SELECT c.chain, c.exchange, SUM(c.usd_value) AS total_usd_value, COUNT(DISTINCT c.token_symbol) AS token_count\n FROM cex_token_balance c\n JOIN latest_snapshot l ON c.snapshot_time = l.max_time\n GROUP BY c.chain, c.exchange\n),\nranked_exchanges AS (\n SELECT *, ROW_NUMBER() OVER(PARTITION BY chain ORDER BY total_usd_value DESC) AS rn\n FROM exchange_totals\n)\nSELECT chain, exchange, total_usd_value, token_count\nFROM ranked_exchanges\nWHERE rn = 1;"}, {"role": "user", "content": "I got an error with the QUALIFY clause. Can you rewrite the query using a derived table or CTE instead?"}, {"role": "assistant", "content": "WITH latest_snapshot AS (\n SELECT MAX(snapshot_time) AS max_time FROM cex_token_balance\n),\nexchange_totals AS (\n SELECT c.chain, c.exchange, SUM(c.usd_value) AS total_usd_value, COUNT(DISTINCT c.token_symbol) AS token_count\n FROM cex_token_balance c\n JOIN latest_snapshot l ON c.snapshot_time = l.max_time\n GROUP BY c.chain, c.exchange\n),\nmax_values AS (\n SELECT chain, MAX(total_usd_value) AS max_usd_value\n FROM exchange_totals\n GROUP BY chain\n)\nSELECT e.chain, e.exchange, e.total_usd_value, e.token_count\nFROM exchange_totals e\nJOIN max_values m ON e.chain = m.chain AND e.total_usd_value = m.max_usd_value;"}, {"role": "user", "content": "Now, only show exchanges where their usd_value is above $5,000,000."}, {"role": "assistant", "content": "WITH latest_snapshot AS (\n SELECT MAX(snapshot_time) AS max_time FROM cex_token_balance\n),\nexchange_totals AS (\n SELECT c.chain, c.exchange, SUM(c.usd_value) AS total_usd_value, COUNT(DISTINCT c.token_symbol) AS token_count\n FROM cex_token_balance c\n JOIN latest_snapshot l ON c.snapshot_time = l.max_time\n GROUP BY c.chain, c.exchange\n),\nmax_values AS (\n SELECT chain, MAX(total_usd_value) AS max_usd_value\n FROM exchange_totals\n GROUP BY chain\n)\nSELECT e.chain, e.exchange, e.total_usd_value, e.token_count\nFROM exchange_totals e\nJOIN max_values m ON e.chain = m.chain AND e.total_usd_value = m.max_usd_value\nWHERE e.total_usd_value > 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 project_fundraising_record ( id character varying(32) NOT NULL, -- fundraising record id project_id character varying(32) NOT NULL, -- the invested project's id project_name character varying(128) NOT NULL, -- name of the invested project rounds_name character varying(32), -- name of the fundraising round investment_value numeric(38,14), -- amount of the fundraising in USD investment_date character varying(128), -- the date of the investment happened introduction character varying(128), -- the introduction of the invested project valuation numeric(38,14), -- the valuation of the project in USD when invested )\nCREATE TABLE token_basic_info ( coin_id character varying(100) NOT NULL, -- the id of the token token_name character varying(100) NOT NULL, -- the token's name token_symbol character varying(100) NOT NULL, -- the token's symbol token_address character varying(100) NOT NULL, -- the token's address chain text, -- the chain that the token resides price double precision, -- the current price of the token price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days highest_price_24h double precision, -- the highest price of the token in 24 hours lowest_price_24h double precision, -- the lowest price of the token in 24 hours market_cap double precision, -- the market cap of the token market_cap_rank bigint, -- the rank of the token market cap in desc market_cap_change_percentage_24h text, -- the percentage of market cap changes in 24 hours total_volume text, -- the trade volum of the token both in decentralized exchange(DEX) and centralized exchange(CEX) narrative text, -- the category or narrative of the token trend_rank biging, -- the trending rank of the token, value 1 expresses the most popular token. ,PRIMARY KEY (coin_id, chain) )\nCREATE TABLE 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 character varying(32) NOT NULL, -- the snapshot time of record, converted from original timestamp chain character varying(128) NOT NULL, -- the chain that the token resides address character varying(128) NOT NULL, -- the address that holds the assets, owned by a CEX exchange character varying(512) NOT NULL, -- a centralized exchange name token_address character varying(128) NOT NULL, -- token contract address token_symbol character varying(512), --token symbol balance numeric(38,10), -- token balance usd_value numeric(38,14), -- value of the token held in USD price double precision, --price of the token in USD ,PRIMARY KEY (snapshot_time, exchange, address, chain, token_address) )\nCREATE TABLE smart_money_profit ( address text, rank numeric, profit numeric, roi numeric, realized_ratio numeric, most_profit_token text, last_trade_time text, chain text )\n"} {"conversations": [{"role": "user", "content": "Show the number of achievements unlocked by each player per month. Display player_id, month (as YYYY-MM), and achievement_count."}, {"role": "assistant", "content": "SELECT player_id,\n TO_CHAR(unlocked_at, 'YYYY-MM') AS year_month,\n COUNT(*) AS achievement_count\nFROM gaming_technology.player_achievements\nGROUP BY player_id, TO_CHAR(unlocked_at, 'YYYY-MM');"}, {"role": "user", "content": "Filter to months where players unlocked at least 5 achievements."}, {"role": "assistant", "content": "SELECT player_id,\n TO_CHAR(unlocked_at, 'YYYY-MM') AS year_month,\n COUNT(*) AS achievement_count\nFROM gaming_technology.player_achievements\nGROUP BY player_id, TO_CHAR(unlocked_at, 'YYYY-MM')\nHAVING COUNT(*) >= 5;"}, {"role": "user", "content": "Sort the results by year_month ascending and then by achievement_count descending."}, {"role": "assistant", "content": "SELECT player_id,\n TO_CHAR(unlocked_at, 'YYYY-MM') AS year_month,\n COUNT(*) AS achievement_count\nFROM gaming_technology.player_achievements\nGROUP BY player_id, TO_CHAR(unlocked_at, 'YYYY-MM')\nHAVING COUNT(*) >= 5\nORDER BY year_month ASC, achievement_count DESC;"}, {"role": "user", "content": "Limit the results to 10 rows."}, {"role": "assistant", "content": "SELECT player_id,\n TO_CHAR(unlocked_at, 'YYYY-MM') AS year_month,\n COUNT(*) AS achievement_count\nFROM gaming_technology.player_achievements\nGROUP BY player_id, TO_CHAR(unlocked_at, 'YYYY-MM')\nHAVING COUNT(*) >= 5\nORDER BY year_month ASC, achievement_count DESC\nLIMIT 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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": "Provide each trip's ID, vehicle license plate, driver's full name, origin city, and destination city."}, {"role": "assistant", "content": "SELECT t.trip_id,\n v.license_plate,\n CONCAT(d.first_name, ' ', d.last_name) AS driver_name,\n lo.city AS origin_city,\n ld.city AS destination_city\nFROM transportation.trips t\nJOIN transportation.vehicles v ON t.vehicle_id = v.vehicle_id\nJOIN transportation.drivers d ON t.driver_id = d.driver_id\nJOIN transportation.locations lo ON t.origin_location_id = lo.location_id\nJOIN transportation.locations ld ON t.destination_location_id = ld.location_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles ( vehicle_id text PRIMARY KEY, license_plate text, vin text, make text, model text, year int, type text, capacity int, fuel_type text, status text, depot_id text, acquisition_date date )\nCREATE TABLE transportation.drivers ( driver_id text, employee_id text, first_name text, last_name text, license_number text, license_expiry_date date, contact_number text, email text, hire_date date, status text )\nCREATE TABLE transportation.routes ( route_id text PRIMARY KEY, route_number text, description text, origin_location_id text, destination_location_id text, distance_km numeric, estimated_duration_minutes int, type text )\nCREATE TABLE transportation.trips ( trip_id text PRIMARY KEY, route_id text, vehicle_id text, driver_id text, scheduled_departure timestamp, actual_departure timestamp, scheduled_arrival timestamp, actual_arrival timestamp, origin_location_id text, destination_location_id text, status text, passenger_count int, cargo_manifest_id text )\nCREATE TABLE transportation.locations ( location_id text PRIMARY KEY, name text, type text, address_line1 text, city text, state_province text, postal_code text, country text, latitude numeric, longitude numeric, timezone text )\nCREATE TABLE transportation.maintenance_logs ( log_id.text, vehicle_id.text, service_date.date, odometer_reading.integer, service_type.text, description.text, cost.numeric, mechanic_name.text, next_service_due_date.date )\nCREATE TABLE transportation.bookings ( booking_id text, passenger_id text, trip_id text, seat_number text, booking_time timestamp, status text, fare numeric, payment_transaction_id text, special_requests text )\n"} {"conversations": [{"role": "user", "content": "List 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": "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": "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": "Find receiver addresses that have received transactions from more than 5 distinct sender addresses. Show the receiver address and the count of distinct senders."}, {"role": "assistant", "content": "SELECT receiver_address, COUNT(DISTINCT sender_address) FROM blockchain.transactions GROUP BY receiver_address HAVING COUNT(DISTINCT sender_address) > 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE blockchain.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)\n"} {"conversations": [{"role": "user", "content": "Show me all pairs of cases led by the same lawyer, including both case names and the lead lawyer ID."}, {"role": "assistant", "content": "SELECT c1.lead_lawyer_id,\n c1.case_name AS case_name_1,\n c2.case_name AS case_name_2\nFROM legal_services.cases c1\nJOIN legal_services.cases c2\n ON c1.lead_lawyer_id = c2.lead_lawyer_id\n AND c1.case_id < c2.case_id;"}, {"role": "user", "content": "Actually, only include pairs where the case types are also the same."}, {"role": "assistant", "content": "SELECT c1.lead_lawyer_id,\n c1.case_name AS case_name_1,\n c2.case_name AS case_name_2\nFROM legal_services.cases c1\nJOIN legal_services.cases c2\n ON c1.lead_lawyer_id = c2.lead_lawyer_id\n AND c1.case_type = c2.case_type\n AND c1.case_id < c2.case_id;"}, {"role": "user", "content": "Also, show me the earliest opening date between the two cases for each pair."}, {"role": "assistant", "content": "SELECT c1.lead_lawyer_id,\n c1.case_name AS case_name_1,\n c2.case_name AS case_name_2,\n LEAST(c1.date_opened, c2.date_opened) AS earliest_open_date\nFROM legal_services.cases c1\nJOIN legal_services.cases c2\n ON c1.lead_lawyer_id = c2.lead_lawyer_id\n AND c1.case_type = c2.case_type\n AND c1.case_id < c2.case_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.cases ( case_id text, case_number text, case_name text, client_id text, lead_lawyer_id text, case_type text, status text, date_opened timestamp, date_closed timestamp, description text, court_jurisdiction text )\n"} {"conversations": [{"role": "user", "content": "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": "Show me all active managers along with their property IDs and the number of staff members they supervise, ordered by the number of supervised staff in descending order."}, {"role": "assistant", "content": "SELECT s.staff_id, s.property_id, s.first_name, s.last_name, COUNT(s2.staff_id) AS supervised_staff_count FROM hospitality_technology.staff s LEFT JOIN hospitality_technology.staff s2 ON s.staff_id = s2.manager_id WHERE s.position = 'Manager' AND s.is_active = true GROUP BY s.staff_id, s.property_id, s.first_name, s.last_name ORDER BY supervised_staff_count DESC;"}, {"role": "user", "content": "Now, include only managers who supervise at least 3 staff members and show their email addresses as well."}, {"role": "assistant", "content": "SELECT s.staff_id, s.property_id, s.first_name, s.last_name, s.work_email, COUNT(s2.staff_id) AS supervised_staff_count FROM hospitality_technology.staff s LEFT JOIN hospitality_technology.staff s2 ON s.staff_id = s2.manager_id WHERE s.position = 'Manager' AND s.is_active = true GROUP BY s.staff_id, s.property_id, s.first_name, s.last_name, s.work_email HAVING COUNT(s2.staff_id) >= 3 ORDER BY supervised_staff_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.staff (\n staff_id character varying(64) NOT NULL, -- unique identifier for the staff member\n property_id character varying(64) NOT NULL, -- FK to properties table (primary property)\n first_name character varying(100) NOT NULL,\n last_name character varying(100) NOT NULL,\n position character varying(100) NOT NULL, -- e.g., Front Desk Agent, Housekeeper, Manager, Concierge\n work_email character varying(255) UNIQUE, -- staff member's work email\n work_phone character varying(30),\n hire_date date NOT NULL,\n termination_date date, -- date employment ended (if applicable)\n is_active boolean NOT NULL DEFAULT true, -- currently employed flag\n access_level integer NOT NULL, -- permission level within systems (e.g., 1=basic, 5=admin)\n manager_id character varying(64), -- FK to staff table (self-referencing for supervisor)\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n PRIMARY KEY (staff_id),\n FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n FOREIGN KEY (manager_id) REFERENCES hospitality_technology.staff(staff_id)\n)\n"} {"conversations": [{"role": "user", "content": "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": "How many users registered in each month?"}, {"role": "assistant", "content": "SELECT date_trunc('month', created_at) AS month,\n COUNT(*) AS registrations\nFROM web3.users\nGROUP BY month\nORDER BY month;"}, {"role": "user", "content": "Actually, show only those months where registrations exceed 10."}, {"role": "assistant", "content": "SELECT date_trunc('month', created_at) AS month,\n COUNT(*) AS registrations\nFROM web3.users\nGROUP BY month\nHAVING COUNT(*) > 10\nORDER BY month;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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 available spa services (category = 'Wellness') with their names and prices, ordered by price in descending order."}, {"role": "assistant", "content": "SELECT service_name, price FROM hospitality_technology.services WHERE category = 'Wellness' AND is_available = true ORDER BY price DESC;"}, {"role": "user", "content": "Now, include only services from properties with ID starting with 'PROP1' and show their property IDs as well."}, {"role": "assistant", "content": "SELECT service_name, price, property_id FROM hospitality_technology.services WHERE category = 'Wellness' AND is_available = true AND property_id LIKE 'PROP1%' ORDER BY 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.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 user, show their username and how many unique conversations they have sent at least one message in where the conversation is a group chat."}, {"role": "assistant", "content": "SELECT u.username, COUNT(DISTINCT m.conversation_id) AS group_chats_messaged_in\nFROM social_media.users u\nJOIN social_media.messages m ON u.user_id = m.sender_user_id\nJOIN social_media.conversations c ON m.conversation_id = c.conversation_id\nWHERE c.is_group_chat = TRUE\nGROUP BY u.username;"}, {"role": "user", "content": "Instead, show only users who have sent messages in more than one group chat, and include their email addresses."}, {"role": "assistant", "content": "SELECT u.username, u.email, COUNT(DISTINCT m.conversation_id) AS group_chats_messaged_in\nFROM social_media.users u\nJOIN social_media.messages m ON u.user_id = m.sender_user_id\nJOIN social_media.conversations c ON m.conversation_id = c.conversation_id\nWHERE c.is_group_chat = TRUE\nGROUP BY u.username, u.email\nHAVING COUNT(DISTINCT m.conversation_id) > 1;"}, {"role": "user", "content": "Also add the most recent message time sent by each user in these group chats."}, {"role": "assistant", "content": "SELECT u.username, u.email, COUNT(DISTINCT m.conversation_id) AS group_chats_messaged_in, MAX(m.sent_at) AS last_message_time\nFROM social_media.users u\nJOIN social_media.messages m ON u.user_id = m.sender_user_id\nJOIN social_media.conversations c ON m.conversation_id = c.conversation_id\nWHERE c.is_group_chat = TRUE\nGROUP BY u.username, u.email\nHAVING COUNT(DISTINCT m.conversation_id) > 1;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id text, username text, email text, password_hash text, full_name text, profile_picture_url text, bio text, location text, created_at timestamp, updated_at timestamp, is_verified boolean )\nCREATE TABLE social_media.posts ( post_id.text, user_id.text, content.text, media_url.text, media_type.text, created_at.timestamp, updated_at.timestamp, visibility.text, location_lat.numeric, location_lon.numeric )\nCREATE TABLE social_media.comments (\n comment_id character varying(64) NOT NULL, -- unique identifier for the comment\n post_id character varying(64) NOT NULL, -- identifier of the post being commented on (FK to posts.post_id)\n user_id character varying(64) NOT NULL, -- identifier of the user who made the comment (FK to users.user_id)\n parent_comment_id character varying(64), -- identifier of the parent comment if it's a reply (FK to comments.comment_id)\n content text NOT NULL, -- textual content of the comment\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of comment creation\n updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last comment edit\n PRIMARY KEY (comment_id)\n)\nCREATE TABLE social_media.likes ( like_id text, user_id text, post_id text, comment_id text, created_at timestamp )\nCREATE TABLE social_media.follows ( follow_id character varying(64) NOT NULL, follower_user_id character varying(64) NOT NULL, following_user_id character varying(64) NOT NULL, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (follow_id), CONSTRAINT unique_follow UNIQUE (follower_user_id, following_user_id) )\nCREATE TABLE social_media.hashtags ( hashtag_id character varying(64) NOT NULL, tag_name character varying(100) NOT NULL UNIQUE, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (hashtag_id) )\nCREATE TABLE social_media.post_hashtags ( post_hashtag_id character varying(64) NOT NULL, post_id character varying(64) NOT NULL, hashtag_id character varying(64) NOT NULL, PRIMARY KEY (post_hashtag_id), CONSTRAINT unique_post_hashtag UNIQUE (post_id, hashtag_id) )\nCREATE TABLE social_media.messages (\n message_id character varying(64) NOT NULL, -- unique identifier for the message\n conversation_id character varying(64) NOT NULL, -- identifier for the conversation thread (FK to conversations.conversation_id)\n sender_user_id character varying(64) NOT NULL, -- identifier of the sender (FK to users.user_id)\n content text, -- textual content of the message\n media_url text, -- URL to attached media (image/video)\n media_type character varying(20), -- type of media ('image', 'video', null)\n sent_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when message was sent\n read_at timestamp, -- timestamp when message was read by recipient(s)\n PRIMARY KEY (message_id)\n)\nCREATE TABLE social_media.conversations ( conversation_id text PRIMARY KEY, created_at timestamp, last_message_at timestamp, is_group_chat bool, group_name text )\nCREATE TABLE social_media.conversation_participants (\n participant_id character varying(64) NOT NULL, -- unique identifier for the participant entry\n conversation_id character varying(64) NOT NULL, -- identifier of the conversation (FK to conversations.conversation_id)\n user_id character varying(64) NOT NULL, -- identifier of the user in the conversation (FK to users.user_id)\n joined_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when user joined the conversation\n last_read_at timestamp, -- timestamp indicating up to when the user has read messages\n PRIMARY KEY (participant_id),\n CONSTRAINT unique_user_conversation UNIQUE (conversation_id, user_id) -- prevent user being added multiple times\n)\nCREATE TABLE social_media.notifications ( notification_id.text, recipient_user_id.text, sender_user_id.text, notification_type.text, target_entity_id.text, target_entity_type.text, created_at.timestamp, read_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "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": "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 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": "List all insurance products that have a base premium greater than 1000 and are currently active, showing product name, type, and base premium."}, {"role": "assistant", "content": "SELECT product_name, product_type, base_premium FROM insurance.insurance_products WHERE base_premium > 1000 AND is_active = TRUE"}, {"role": "user", "content": "Now, find policies associated with these products that were issued in 2024, showing the policy number and its premium amount."}, {"role": "assistant", "content": "SELECT p.policy_number, p.premium_amount FROM insurance.policies AS p JOIN insurance.insurance_products AS ip ON p.product_id = ip.product_id WHERE ip.base_premium > 1000 AND ip.is_active = TRUE AND date_part('year', p.issued_at) = 2024"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.policies ( policy_id text, customer_id text, product_id text, agent_id text, policy_number text, start_date date, end_date date, premium_amount numeric, coverage_limit numeric, deductible numeric, status text, issued_at timestamp, cancellation_date date, cancellation_reason text )\nCREATE TABLE insurance.insurance_products ( product_id text, product_name text, product_type text, description text, base_premium numeric, coverage_details text, underwriting_rules text, is_active boolean, created_at timestamp, updated_at timestamp )\nCREATE TABLE insurance.claim_documents ( document_id text, claim_id text, document_type text, file_name text, file_path text, file_size_bytes integer, mime_type text, uploaded_by text, uploaded_at timestamp, description text )\n"} {"conversations": [{"role": "user", "content": "List the usernames and emails of users who have sent at least one notification."}, {"role": "assistant", "content": "SELECT DISTINCT T1.username, T1.email FROM social_media.users AS T1 JOIN social_media.notifications AS T2 ON T1.user_id = T2.sender_user_id;"}, {"role": "user", "content": "Only show those who sent notifications of type 'message'."}, {"role": "assistant", "content": "SELECT DISTINCT T1.username, T1.email FROM social_media.users AS T1 JOIN social_media.notifications AS T2 ON T1.user_id = T2.sender_user_id WHERE T2.notification_type = 'message';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id text, username text, email text, password_hash text, full_name text, profile_picture_url text, bio text, location text, created_at timestamp, updated_at timestamp, is_verified boolean )\nCREATE TABLE social_media.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.notifications ( notification_id.text, recipient_user_id.text, sender_user_id.text, notification_type.text, target_entity_id.text, target_entity_type.text, created_at.timestamp, read_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "List all patient insurance entries where the subscriber name is different from the patient's last name. Include patient ID, subscriber name, and patient last name."}, {"role": "assistant", "content": "SELECT T1.patient_id, T1.subscriber_name, T2.last_name FROM healthcare.patient_insurance AS T1 JOIN healthcare.patients AS T2 ON T1.patient_id = T2.patient_id WHERE T1.subscriber_name <> T2.last_name;"}, {"role": "user", "content": "Also, only show entries where the policy is marked as primary."}, {"role": "assistant", "content": "SELECT T1.patient_id, T1.subscriber_name, T2.last_name FROM healthcare.patient_insurance AS T1 JOIN healthcare.patients AS T2 ON T1.patient_id = T2.patient_id WHERE T1.subscriber_name <> T2.last_name AND T1.is_primary = TRUE;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.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 ( 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 (\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, patient_id.text, appointment_id.text, doctor_id.text, record_date.timestamp, chief_complaint.text, present_illness_history.text, past_medical_history.text, physical_examination_notes.text, assessment.text, treatment_plan.text, vitals.json, created_at.timestamp )\nCREATE TABLE healthcare.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 text PRIMARY KEY, medication_name text, generic_name text, manufacturer text, ndc_code text, description text )\nCREATE TABLE healthcare.insurance_plans ( plan_id.text, plan_name.text, insurance_provider.text, plan_type.text, contact_phone.text, website.text )\nCREATE TABLE healthcare.patient_insurance (\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 full names of citizens who have submitted applications for services provided by agencies at the 'Federal' jurisdiction level."}, {"role": "assistant", "content": "SELECT T1.first_name, T1.last_name FROM government_services.citizens AS T1 INNER JOIN government_services.applications AS T2 ON T1.citizen_id = T2.citizen_id INNER JOIN government_services.services AS T3 ON T2.service_id = T3.service_id INNER JOIN government_services.agencies AS T4 ON T3.agency_id = T4.agency_id WHERE T4.jurisdiction_level = 'Federal';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id.text, national_id_number.text, first_name.text, last_name.text, date_of_birth.date, gender.text, primary_address.text, contact_email.text, contact_phone.text, registration_date.timestamp, is_verified.boolean )\nCREATE TABLE government_services.agencies ( agency_id.text, agency_name.text, jurisdiction_level.text, primary_contact_email.text, main_phone_number.text, website_url.text, established_date.date, parent_agency_id.text )\nCREATE TABLE government_services.services ( service_id.text, agency_id.text, service_name.text, description.text, category.text, eligibility_criteria.text, standard_fee.numeric, average_processing_time_days.integer, is_active.boolean, online_application_url.text )\nCREATE TABLE government_services.applications ( application_id.text, citizen_id.text, service_id.text, submitted_at.timestamp, status.text, last_updated_at.timestamp, assigned_employee_id.text, decision_date.date, notes.text, reference_number.text )\nCREATE TABLE government_services.payments ( payment_id.text, application_id.text, citizen_id.text, service_id.text, amount.numeric, currency.text, payment_method.text, payment_provider_reference.text, payment_timestamp.timestamp, status.text, notes.text )\nCREATE TABLE government_services.employees ( employee_id.text, agency_id.text, first_name.text, last_name.text, job_title.text, department.text, work_email.text, work_phone.text, hire_date.date, termination_date.date, access_level.text, manager_employee_id.text )\nCREATE TABLE government_services.notifications ( notification_id.text, citizen_id.text, application_id.text, message_subject.text, message_body.text, channel.text, sent_at.timestamp, status.text, related_entity_type.text, related_entity_id.text )\n"} {"conversations": [{"role": "user", "content": "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": "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 properties and the average base rate of their room types."}, {"role": "assistant", "content": "SELECT T1.property_name , AVG(T2.base_rate) FROM hospitality_technology.properties AS T1 JOIN hospitality_technology.room_types AS T2 ON T1.property_id = T2.property_id GROUP BY T1.property_name"}, {"role": "user", "content": "Filter to only show properties where the average base rate is above 250."}, {"role": "assistant", "content": "SELECT T1.property_name , AVG(T2.base_rate) FROM hospitality_technology.properties AS T1 JOIN hospitality_technology.room_types AS T2 ON T1.property_id = T2.property_id GROUP BY T1.property_name HAVING AVG(T2.base_rate) > 250"}, {"role": "user", "content": "Also, only include properties in 'New York' or 'Florida' and order by average base rate descending."}, {"role": "assistant", "content": "SELECT T1.property_name , AVG(T2.base_rate) AS avg_base_rate FROM hospitality_technology.properties AS T1 JOIN hospitality_technology.room_types AS T2 ON T1.property_id = T2.property_id WHERE T1.state IN ('New York', 'Florida') GROUP BY T1.property_name HAVING AVG(T2.base_rate) > 250 ORDER BY avg_base_rate 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 (\n room_type_id character varying(64) NOT NULL, -- unique identifier for the room type\n property_id character varying(64) NOT NULL, -- FK to properties table (type might be property-specific)\n type_name character varying(100) NOT NULL, -- e.g., Standard King, Deluxe Queen, Executive Suite\n description text, -- description of the room type\n base_rate numeric(10, 2) NOT NULL, -- standard price per night\n max_occupancy integer NOT NULL, -- maximum number of guests\n bed_type character varying(50), -- e.g., King, Queen, 2 Doubles, Twin\n area_sqft numeric(8,2), -- size of the room in square feet\n amenities text, -- comma-separated list or JSON of amenities\n PRIMARY KEY (room_type_id),\n FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id)\n)\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 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": "Count how many posts have media attachments."}, {"role": "assistant", "content": "SELECT count(*) FROM social_media.posts WHERE media_url IS NOT NULL"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id text PRIMARY KEY, username text, email text, password_hash text, full_name text, profile_picture_url text, bio text, location text, created_at timestamp, updated_at timestamp, is_verified bool )\nCREATE TABLE social_media.posts ( post_id.text, user_id.text, content.text, media_url.text, media_type.text, created_at.timestamp, updated_at.timestamp, visibility.text, location_lat.numeric, location_lon.numeric )\nCREATE TABLE social_media.comments ( comment_id text PRIMARY KEY, post_id text, user_id text, parent_comment_id text, content text, created_at timestamp, updated_at timestamp )\nCREATE TABLE social_media.follows ( follow_id text PRIMARY KEY, follower_user_id text, following_user_id text, created_at timestamp )\nCREATE TABLE social_media.hashtags ( hashtag_id.text, tag_name.text, created_at.timestamp )\nCREATE TABLE social_media.post_hashtags ( post_hashtag_id character varying(64) NOT NULL, post_id character varying(64) NOT NULL, hashtag_id character varying(64) NOT NULL, PRIMARY KEY (post_hashtag_id), CONSTRAINT unique_post_hashtag UNIQUE (post_id, hashtag_id) )\nCREATE TABLE social_media.messages ( message_id text PRIMARY KEY, conversation_id text, sender_user_id text, content text, media_url text, media_type text, sent_at timestamp, read_at timestamp )\nCREATE TABLE social_media.conversations ( conversation_id text, created_at timestamp, last_message_at timestamp, is_group_chat boolean, group_name text )\nCREATE TABLE social_media.conversation_participants ( participant_id text, conversation_id text, user_id text, joined_at timestamp, last_read_at timestamp )\nCREATE TABLE social_media.notifications (\n notification_id character varying(64) NOT NULL, -- unique identifier for the notification\n recipient_user_id character varying(64) NOT NULL, -- user receiving the notification (FK to users.user_id)\n sender_user_id character varying(64), -- user triggering the notification (FK to users.user_id, can be null for system notifications)\n notification_type character varying(30) NOT NULL, -- type of notification ('like', 'comment', 'follow', 'mention', 'message')\n target_entity_id character varying(64), -- ID of the related entity (post_id, comment_id, user_id, conversation_id)\n target_entity_type character varying(20), -- type of the related entity ('post', 'comment', 'user', 'conversation')\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp notification was created\n read_at timestamp, -- timestamp notification was marked as read\n PRIMARY KEY (notification_id)\n)\nCREATE TABLE social_media.user_settings ( setting_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL UNIQUE, theme character varying(20) DEFAULT 'light', email_notifications_enabled boolean DEFAULT true, push_notifications_enabled boolean DEFAULT true, private_profile boolean DEFAULT false, updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (setting_id) )\n"} {"conversations": [{"role": "user", "content": "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": "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": "For each player, show their player_id and the number of unique games they have played sessions on."}, {"role": "assistant", "content": "SELECT player_id, COUNT(DISTINCT game_id) AS unique_games\nFROM gaming_technology.game_sessions\nGROUP BY player_id;"}, {"role": "user", "content": "Also show the total number of sessions they have played."}, {"role": "assistant", "content": "SELECT player_id, COUNT(DISTINCT game_id) AS unique_games, COUNT(*) AS total_sessions\nFROM gaming_technology.game_sessions\nGROUP BY player_id;"}, {"role": "user", "content": "Only include players who have played on more than 2 unique games."}, {"role": "assistant", "content": "SELECT player_id, COUNT(DISTINCT game_id) AS unique_games, COUNT(*) AS total_sessions\nFROM gaming_technology.game_sessions\nGROUP BY player_id\nHAVING COUNT(DISTINCT game_id) > 2;"}, {"role": "user", "content": "For each result, include the player's username as well."}, {"role": "assistant", "content": "SELECT p.player_id, p.username, COUNT(DISTINCT gs.game_id) AS unique_games, COUNT(*) AS total_sessions\nFROM gaming_technology.players p\nJOIN gaming_technology.game_sessions gs ON p.player_id = gs.player_id\nGROUP BY p.player_id, p.username\nHAVING COUNT(DISTINCT gs.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 ( player_id.uuid, username.text, email.text, password_hash.text, registration_date.timestamptz, last_login.timestamptz, country_code.text, status.text, profile_data.jsonb )\nCREATE TABLE gaming_technology.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 ( server_id uuid NOT NULL DEFAULT gen_random_uuid(), game_id uuid NOT NULL, server_name character varying(150), region character varying(50) NOT NULL, ip_address character varying(45), port integer, current_players integer NOT NULL DEFAULT 0, max_players integer NOT NULL, status character varying(30) NOT NULL DEFAULT 'offline', last_heartbeat timestamp with time zone, PRIMARY KEY (server_id) )\nCREATE TABLE gaming_technology.achievements ( achievement_id uuid, game_id uuid, name text, description text, icon_url text, points integer, hidden boolean )\nCREATE TABLE gaming_technology.player_achievements ( player_achievement_id.uuid, player_id.uuid, achievement_id.uuid, unlocked_at.timestamptz )\nCREATE TABLE gaming_technology.in_game_items ( item_id uuid NOT NULL DEFAULT gen_random_uuid(), game_id uuid NOT NULL, item_name character varying(150) NOT NULL, item_type character varying(50) NOT NULL, description text, rarity character varying(30), cost_currency character varying(10), cost_amount numeric(12, 2), attributes jsonb, PRIMARY KEY (item_id) )\n"} {"conversations": [{"role": "user", "content": "Show all routes including their number, type, and description."}, {"role": "assistant", "content": "SELECT route_number , type , description FROM transportation.routes"}, {"role": "user", "content": "Only show routes of type 'City Bus'."}, {"role": "assistant", "content": "SELECT route_number , type , description FROM transportation.routes WHERE type = 'City Bus'"}, {"role": "user", "content": "For these 'City Bus' routes, include the origin and destination city names."}, {"role": "assistant", "content": "SELECT T1.route_number , T1.type , T1.description , T2.city AS origin_city , T3.city AS destination_city FROM transportation.routes AS T1 JOIN transportation.locations AS T2 ON T1.origin_location_id = T2.location_id JOIN transportation.locations AS T3 ON T1.destination_location_id = T3.location_id WHERE T1.type = 'City Bus'"}, {"role": "user", "content": "Order the results by route number in ascending order and limit to the first 10."}, {"role": "assistant", "content": "SELECT T1.route_number , T1.type , T1.description , T2.city AS origin_city , T3.city AS destination_city FROM transportation.routes AS T1 JOIN transportation.locations AS T2 ON T1.origin_location_id = T2.location_id JOIN transportation.locations AS T3 ON T1.destination_location_id = T3.location_id WHERE T1.type = 'City Bus' ORDER BY T1.route_number ASC LIMIT 10"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles (\n vehicle_id character varying(64) NOT NULL, -- unique identifier for the vehicle\n license_plate character varying(32) NOT NULL UNIQUE, -- vehicle license plate\n vin character varying(17) UNIQUE, -- vehicle identification number\n make character varying(64) NOT NULL, -- manufacturer of the vehicle\n model character varying(64) NOT NULL, -- model of the vehicle\n year integer NOT NULL, -- manufacturing year\n type character varying(32) NOT NULL, -- type of vehicle (e.g., Bus, Train, Truck, Car, Van)\n capacity integer, -- passenger or cargo capacity\n fuel_type character varying(32) NOT NULL, -- e.g., Diesel, Gasoline, Electric, Hydrogen\n status character varying(32) NOT NULL, -- e.g., Active, Maintenance, Decommissioned\n depot_id character varying(64), -- identifier of the home depot/base\n acquisition_date date, -- date the vehicle was acquired\n PRIMARY KEY (vehicle_id)\n)\nCREATE TABLE transportation.drivers (\n driver_id character varying(64) NOT NULL, -- unique identifier for the driver\n employee_id character varying(64) NOT NULL UNIQUE, -- employee reference number\n first_name character varying(128) NOT NULL, -- driver's first name\n last_name character varying(128) NOT NULL, -- driver's last name\n license_number character varying(64) NOT NULL UNIQUE, -- driving license number\n license_expiry_date date NOT NULL, -- expiry date of the license\n contact_number character varying(32), -- phone number\n email character varying(128) UNIQUE, -- email address\n hire_date date NOT NULL, -- date the driver was hired\n status character varying(32) NOT NULL, -- e.g., Active, On Leave, Terminated\n PRIMARY KEY (driver_id)\n)\nCREATE TABLE transportation.routes (\n route_id character varying(64) NOT NULL, -- unique identifier for the route\n route_number character varying(32) NOT NULL UNIQUE, -- public-facing route number/name\n description text, -- description of the route\n origin_location_id character varying(64) NOT NULL, -- identifier of the starting location\n destination_location_id character varying(64) NOT NULL, -- identifier of the ending location\n distance_km numeric(10, 2), -- estimated distance in kilometers\n estimated_duration_minutes integer, -- estimated travel time in minutes\n type character varying(32) NOT NULL, -- e.g., City Bus, Intercity Train, Cargo Delivery\n PRIMARY KEY (route_id)\n)\nCREATE TABLE transportation.locations (\n location_id character varying(64) NOT NULL, -- unique identifier for the location\n name character varying(255) NOT NULL, -- name of the location (e.g., Central Station, Depot Alpha, Pier 7)\n type character varying(64) NOT NULL, -- e.g., Station, Stop, Depot, Port, Airport, Customer Address\n address_line1 character varying(255), -- street address\n city character varying(128), -- city name\n state_province character varying(128), -- state or province\n postal_code character varying(32), -- postal code\n country character varying(64) NOT NULL, -- country name\n latitude numeric(9, 6), -- geographic latitude\n longitude numeric(9, 6), -- geographic longitude\n timezone character varying(64), -- IANA timezone name (e.g., America/New_York)\n PRIMARY KEY (location_id)\n)\nCREATE TABLE transportation.fuel_logs (\n fuel_log_id character varying(64) NOT NULL, -- unique identifier for the fuel log entry\n vehicle_id character varying(64) NOT NULL, -- identifier of the vehicle fueled\n trip_id character varying(64), -- optional: identifier of the trip during which fueling occurred\n log_timestamp timestamp with time zone NOT NULL, -- time when fueling occurred\n fuel_type character varying(32) NOT NULL, -- type of fuel added (matches vehicle's fuel type)\n quantity numeric(10, 3) NOT NULL, -- amount of fuel added (e.g., Liters, Gallons, kWh)\n unit character varying(16) NOT NULL, -- unit of quantity (e.g., L, gal, kWh)\n cost_per_unit numeric(8, 4), -- price per unit of fuel\n total_cost numeric(10, 2) NOT NULL, -- total cost of the fuel purchase\n odometer_reading integer, -- vehicle mileage at time of fueling\n location_id character varying(64), -- identifier of the fueling station/location\n PRIMARY KEY (fuel_log_id)\n)\n"} {"conversations": [{"role": "user", "content": "What is the current number of passengers at station with ID 'ST123' right now?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information on the current number of passengers at a station. The data I have access to only includes static details about stations such as their name, location, and number of platforms, not real-time passenger counts."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.stations (\n station_id character varying(64) NOT NULL, -- Unique identifier for the station\n station_name character varying(128) NOT NULL, -- Name of the station\n city character varying(100) NOT NULL, -- City where the station is located\n state_province character varying(100), -- State or province\n country_code character varying(3) NOT NULL, -- ISO country code\n address text, -- Full address of the station\n timezone character varying(64) NOT NULL, -- Timezone ID (e.g., 'America/New_York')\n number_of_platforms integer NOT NULL DEFAULT 0, -- Total number of platforms\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- When the station record was created\n last_updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- When the station record was last updated\n PRIMARY KEY (station_id)\n)\n"} {"conversations": [{"role": "user", "content": "List all appointments that are currently scheduled and show their appointment time."}, {"role": "assistant", "content": "SELECT appointment_id, patient_id, doctor_id, appointment_time FROM healthcare.appointments WHERE status = 'Scheduled';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, gender character varying(10), address text, phone_number character varying(20), email character varying(128) UNIQUE, emergency_contact_name character varying(200), emergency_contact_phone character varying(20), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (patient_id) )\nCREATE TABLE healthcare.appointments ( appointment_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, doctor_id character varying(64) NOT NULL, appointment_time timestamp with time zone NOT NULL, duration_minutes integer NOT NULL, reason text, status character varying(32) NOT NULL, location_id character varying(64), notes text, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (appointment_id) )\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, plan_id character varying(64) NOT NULL, policy_number character varying(100) NOT NULL, group_number character varying(100), subscriber_name character varying(200), effective_date date NOT NULL, expiration_date date, is_primary boolean NOT NULL DEFAULT true, PRIMARY KEY (patient_insurance_id), UNIQUE (patient_id, plan_id, policy_number) )\n"} {"conversations": [{"role": "user", "content": "How many lawyers who are partners were hired in each year? Show the hire year and the count."}, {"role": "assistant", "content": "SELECT strftime('%Y', hire_date) AS hire_year , count(lawyer_id) FROM legal_services.lawyers WHERE is_partner = true GROUP BY hire_year"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.lawyers (\n lawyer_id character varying(64) NOT NULL, -- unique identifier for the lawyer\n first_name character varying(100) NOT NULL, -- lawyer's first name\n last_name character varying(100) NOT NULL, -- lawyer's last name\n bar_number character varying(64) UNIQUE NOT NULL, -- lawyer's bar association number\n firm_id character varying(64), -- FK to law_firms table\n email character varying(128) UNIQUE NOT NULL, -- lawyer's professional email\n phone character varying(32), -- lawyer's contact phone number\n specialization text, -- areas of legal expertise\n hire_date timestamp NOT NULL, -- date the lawyer was hired or joined\n is_partner boolean DEFAULT false, -- flag indicating if the lawyer is a partner\n PRIMARY KEY (lawyer_id)\n)\n"} {"conversations": [{"role": "user", "content": "Show the count of applications assigned to employees, grouped by the job title of the assigned employee."}, {"role": "assistant", "content": "SELECT e.job_title, COUNT(a.application_id) AS application_count FROM government_services.applications AS a JOIN government_services.employees AS e ON a.assigned_employee_id = e.employee_id GROUP BY e.job_title"}, {"role": "user", "content": "Filter the count to include only applications with status 'Processing'."}, {"role": "assistant", "content": "SELECT e.job_title, COUNT(a.application_id) AS application_count FROM government_services.applications AS a JOIN government_services.employees AS e ON a.assigned_employee_id = e.employee_id WHERE a.status = 'Processing' GROUP BY e.job_title"}, {"role": "user", "content": "Only display job titles that have more than 10 applications with 'Processing' status assigned."}, {"role": "assistant", "content": "SELECT e.job_title, COUNT(a.application_id) AS application_count FROM government_services.applications AS a JOIN government_services.employees AS e ON a.assigned_employee_id = e.employee_id WHERE a.status = 'Processing' GROUP BY e.job_title HAVING COUNT(a.application_id) > 10"}, {"role": "user", "content": "Instead of 'Processing' status, show the count for applications with status 'Pending Info'."}, {"role": "assistant", "content": "SELECT e.job_title, COUNT(a.application_id) AS application_count FROM government_services.applications AS a JOIN government_services.employees AS e ON a.assigned_employee_id = e.employee_id WHERE a.status = 'Pending Info' GROUP BY e.job_title HAVING COUNT(a.application_id) > 10"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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.applications (\n application_id character varying(64) NOT NULL, -- unique identifier for the application\n citizen_id character varying(64) NOT NULL, -- FK to citizens table\n service_id character varying(64) NOT NULL, -- FK to services table\n submitted_at timestamp NOT NULL, -- time the application was submitted\n status character varying(50) NOT NULL, -- e.g., Submitted, Processing, Approved, Rejected, Pending Info\n last_updated_at timestamp NOT NULL, -- time the status or details last changed\n assigned_employee_id character varying(64), -- FK to employees table (optional)\n decision_date date, -- date when a final decision was made\n notes text, -- internal notes or citizen-provided comments\n reference_number character varying(100) UNIQUE, -- publicly visible reference number\n PRIMARY KEY (application_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.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": "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": "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": "What is the maintenance schedule for the platforms at the station with ID 'ST234' for the next month?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to the maintenance schedule for the platforms at any station. The data I have only includes basic station information such as station ID, name, location, and number of platforms. For maintenance schedules, you may need to contact the station management or relevant authorities."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.stations ( station_id text PRIMARY KEY, station_name text, city text, state_province text, country_code text, address text, timezone text, number_of_platforms int, created_at timestamp, last_updated_at timestamp )\n"} {"conversations": [{"role": "user", "content": "List 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": "能否帮我统计特定车站(station_id 为 'station_xyz')的所有工作人员数量？"}, {"role": "assistant", "content": "MATCH (s:Station {station_id: 'station_xyz'})<-[:BASED_AT]-(staff:Staff)\nRETURN COUNT(staff) AS total_staff"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\n// Node Label: :Station\n// Properties:\n// station_id: String (Constraint: UNIQUE)\n// station_name: String\n// city: String (Index recommended)\n// state_province: String\n// country_code: String\n// address: String\n// timezone: String\n// number_of_platforms: Integer\n// created_at: DateTime\n// last_updated_at: DateTime\n// Example Cypher CREATE:\n// CREATE (:Station {station_id: 'station_xyz', station_name: 'Grand Central Terminal', city: 'New York', ...})\n// Node Label: :Platform\n// Properties:\n// platform_id: String (Constraint: UNIQUE)\n// platform_number: String\n// track_number: String\n// status: String\n// length_meters: Float\n// accessible: Boolean\n// Relationship: (:Platform)-[:LOCATED_AT]->(:Station)\n// Example Cypher CREATE:\n// MATCH (s:Station {station_id: 'station_xyz'})\n// CREATE (p:Platform {platform_id: 'plat_123', ...})-[:LOCATED_AT]->(s)\n// Node Label: :Train\n// Properties:\n// train_id: String (Constraint: UNIQUE)\n// train_number: String (Constraint: UNIQUE)\n// model: String\n// manufacturer: String\n// year_manufactured: Integer\n// capacity: Integer\n// status: String\n// last_maintenance_date: Date\n// next_maintenance_date: Date\n// Example Cypher CREATE:\n// CREATE (:Train {train_id: 'train_789', train_number: 'Acela 2151', ...})\n// Node Label: :TrainCar\n// Properties:\n// car_id: String (Constraint: UNIQUE)\n// car_number: String\n// car_type: String\n// class: String\n// capacity: Integer\n// features: String (Or List if driver supports)\n// Relationship: (:TrainCar)-[:PART_OF_TRAIN]->(:Train)\n// Example Cypher CREATE:\n// MATCH (t:Train {train_id: 'train_789'})\n// CREATE (c:TrainCar {car_id: 'car_abc', ...})-[:PART_OF_TRAIN]->(t)\n// Node Label: :Route\n// Properties:\n// route_id: String (Constraint: UNIQUE)\n// route_name: String\n// description: String\n// is_active: Boolean\n// Relationships:\n// (:Route)-[:STARTS_AT]->(:Station)\n// (:Route)-[:ENDS_AT]->(:Station)\n// Example Cypher CREATE:\n// MATCH (origin:Station {station_id: 'station_bos'}), (dest:Station {station_id: 'station_was'})\n// CREATE (r:Route {route_id: 'route_ne_corr', ...})-[:STARTS_AT]->(origin), (r)-[:ENDS_AT]->(dest)\n// Relationship: (:Route)-[rel:HAS_STOP]->(:Station)\n// Relationship Properties on :HAS_STOP:\n// sequence_order: Integer\n// distance_from_previous_km: Float\n// typical_stop_duration_minutes: Integer\n// Example Cypher CREATE:\n// MATCH (r:Route {route_id: 'route_ne_corr'}), (s:Station {station_id: 'station_pvd'})\n// CREATE (r)-[:HAS_STOP {sequence_order: 2, distance_from_previous_km: 70.5, ...}]->(s)\n// Node Label: :ScheduledTrip (or just :Trip)\n// Properties:\n// schedule_id: String (Constraint: UNIQUE)\n// departure_datetime: DateTime\n// arrival_datetime: DateTime\n// status: String\n// notes: String\n// Relationships:\n// (:ScheduledTrip)-[:USES_TRAIN]->(:Train)\n// (:ScheduledTrip)-[:FOLLOWS_ROUTE]->(:Route)\n// Example Cypher CREATE:\n// MATCH (t:Train {train_id: 'train_789'}), (r:Route {route_id: 'route_ne_corr'})\n// CREATE (sched:ScheduledTrip {schedule_id: 'sched_1122', ...})-[:USES_TRAIN]->(t), (sched)-[:FOLLOWS_ROUTE]->(r)\n// Relationship: (:ScheduledTrip)-[rel:SCHEDULED_STOP]->(:Station)\n// Relationship Properties on :SCHEDULED_STOP:\n// sequence_order: Integer\n// platform_id: String (references Platform node if modeled, or just store ID)\n// scheduled_arrival_time: DateTime\n// scheduled_departure_time: DateTime\n// actual_arrival_time: DateTime\n// actual_departure_time: DateTime\n// status: String\n// Example Cypher CREATE:\n// MATCH (sched:ScheduledTrip {schedule_id: 'sched_1122'}), (s:Station {station_id: 'station_pvd'})\n// CREATE (sched)-[:SCHEDULED_STOP {sequence_order: 2, platform_id: 'plat_pvd_1', ...}]->(s)\n// Node Label: :Passenger\n// Properties:\n// passenger_id: String (Constraint: UNIQUE)\n// first_name: String\n// last_name: String\n// email: String (Constraint: UNIQUE, if not null)\n// phone_number: String (Constraint: UNIQUE, if not null)\n// date_of_birth: Date\n// loyalty_program_id: String\n// created_at: DateTime\n// Example Cypher CREATE:\n// CREATE (:Passenger {passenger_id: 'pass_pqr', first_name: 'Alice', ...})\n// Node Label: :Booking\n// Properties:\n// booking_id: String (Constraint: UNIQUE)\n// booking_datetime: DateTime\n// status: String\n// total_price: Float\n// currency_code: String\n// special_requests: String\n// Relationships:\n// (:Passenger)-[:MADE_BOOKING]->(:Booking)\n// (:Booking)-[:FOR_TRIP]->(:ScheduledTrip)\n// Example Cypher CREATE:\n// MATCH (p:Passenger {passenger_id: 'pass_pqr'}), (sched:ScheduledTrip {schedule_id: 'sched_1122'})\n// CREATE (p)-[:MADE_BOOKING]->(b:Booking {booking_id: 'book_zyx', ...})-[:FOR_TRIP]->(sched)\n// Node Label: :Ticket\n// Properties:\n// ticket_id: String (Constraint: UNIQUE)\n// seat_number: String\n// ticket_type: String\n// price: Float\n// is_checked_in: Boolean\n// qr_code_data: String\n// Relationships:\n// (:Ticket)-[:PART_OF_BOOKING]->(:Booking)\n// (:Ticket)-[:ASSIGNED_TO_CAR]->(:TrainCar)\n// Example Cypher CREATE:\n// MATCH (b:Booking {booking_id: 'book_zyx'}), (c:TrainCar {car_id: 'car_abc'})\n// CREATE (t:Ticket {ticket_id: 'tkt_1a2b', ...})-[:PART_OF_BOOKING]->(b), (t)-[:ASSIGNED_TO_CAR]->(c)\n// Node Label: :Staff\n// Properties:\n// staff_id: String (Constraint: UNIQUE)\n// first_name: String\n// last_name: String\n// role: String\n// employee_number: String (Constraint: UNIQUE)\n// hire_date: Date\n// contact_email: String (Constraint: UNIQUE, if not null)\n// contact_phone: String\n// is_active: Boolean\n// Relationship (Optional):\n// (:Staff)-[:BASED_AT]->(:Station)\n// Example Cypher CREATE:\n// CREATE (:Staff {staff_id: 'staff_mno', first_name: 'Bob', ...})\n// OPTIONAL MATCH (s:Station {station_id: 'station_xyz'}) // If primary_station_id exists\n// WITH s, staff_mno // Need to get the created staff node reference\n// WHERE s IS NOT NULL\n// CREATE (staff_mno)-[:BASED_AT]->(s)\n"} {"conversations": [{"role": "user", "content": "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": "For each group chat, can you show me each participant's username and the date they joined the chat?"}, {"role": "assistant", "content": "SELECT u.username, c.group_name, cp.joined_at\nFROM social_media.conversation_participants cp\nJOIN social_media.users u ON cp.user_id = u.user_id\nJOIN social_media.conversations c ON cp.conversation_id = c.conversation_id\nWHERE c.is_group_chat = true;"}, {"role": "user", "content": "Can you also include the total number of participants for each group chat in the result?"}, {"role": "assistant", "content": "SELECT u.username, c.group_name, cp.joined_at, COUNT(cp2.participant_id) AS total_participants\nFROM social_media.conversation_participants cp\nJOIN social_media.users u ON cp.user_id = u.user_id\nJOIN social_media.conversations c ON cp.conversation_id = c.conversation_id\nJOIN social_media.conversation_participants cp2 ON cp2.conversation_id = cp.conversation_id\nWHERE c.is_group_chat = true\nGROUP BY u.username, c.group_name, cp.joined_at;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id text, username text, email text, password_hash text, full_name text, profile_picture_url text, bio text, location text, created_at timestamp, updated_at timestamp, is_verified boolean )\nCREATE TABLE social_media.posts ( post_id text, user_id text, content text, media_url text, media_type text, created_at timestamp, updated_at timestamp, visibility text, location_lat numeric, location_lon numeric )\nCREATE TABLE social_media.comments ( comment_id text, post_id text, user_id text, parent_comment_id text, content text, created_at timestamp, updated_at timestamp )\nCREATE TABLE social_media.follows ( follow_id text, follower_user_id text, following_user_id text, created_at timestamp )\nCREATE TABLE social_media.post_hashtags ( post_hashtag_id text, post_id text, hashtag_id text )\nCREATE TABLE social_media.messages ( message_id text, conversation_id text, sender_user_id text, content text, media_url text, media_type text, sent_at timestamp, read_at timestamp )\nCREATE TABLE social_media.conversation_participants ( participant_id text, conversation_id text, user_id text, joined_at timestamp, last_read_at timestamp )\nCREATE TABLE social_media.notifications ( notification_id text, recipient_user_id text, sender_user_id text, notification_type text, target_entity_id text, target_entity_type text, created_at timestamp, read_at timestamp )\nCREATE TABLE social_media.user_settings ( setting_id text, user_id text, theme text, email_notifications_enabled boolean, push_notifications_enabled boolean, private_profile boolean, updated_at timestamp )\n"} {"conversations": [{"role": "user", "content": "Retrieve the product_id, product_name, base_premium, and created_at for all active insurance products with a base_premium greater than 1000, ordered by base_premium descending."}, {"role": "assistant", "content": "SELECT\n product_id,\n product_name,\n base_premium,\n created_at\nFROM insurance.insurance_products\nWHERE is_active = true\n AND base_premium > 1000\nORDER BY base_premium DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.insurance_products (\n product_id character varying(64) NOT NULL, -- unique identifier for the insurance product\n product_name character varying(150) NOT NULL, -- name of the insurance product (e.g., 'Comprehensive Auto Insurance')\n product_type character varying(50) NOT NULL, -- category like 'Auto', 'Home', 'Life', 'Health', 'Travel'\n description text, -- detailed description of the product\n base_premium numeric(10, 2) NOT NULL, -- starting premium before adjustments\n coverage_details text, -- details about what is covered (could be JSON or structured text)\n underwriting_rules text, -- rules used for assessing risk and eligibility\n is_active boolean NOT NULL DEFAULT true, -- whether the product is currently offered\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n updated_at timestamp,\n PRIMARY KEY (product_id)\n)\n"} {"conversations": [{"role": "user", "content": "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": "Count the number of registered citizens by gender."}, {"role": "assistant", "content": "SELECT\n gender,\n COUNT(*) AS citizen_count\nFROM government_services.citizens\nGROUP BY gender;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id character varying(64) NOT NULL, national_id_number character varying(128) NOT NULL UNIQUE, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, gender character varying(20), primary_address text NOT NULL, contact_email character varying(128) UNIQUE, contact_phone character varying(32), registration_date timestamp NOT NULL, is_verified boolean DEFAULT false, PRIMARY KEY (citizen_id) )\nCREATE TABLE government_services.payments ( payment_id character varying(64) NOT NULL, application_id character varying(64), citizen_id character varying(64) NOT NULL, service_id character varying(64), amount numeric(12, 2) NOT NULL, currency character varying(3) NOT NULL DEFAULT 'USD', payment_method character varying(50), payment_provider_reference character varying(128), payment_timestamp timestamp NOT NULL, status character varying(30) NOT NULL, notes text, PRIMARY KEY (payment_id) )\nCREATE TABLE government_services.employees ( employee_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, job_title character varying(150) NOT NULL, department character varying(100), work_email character varying(128) NOT NULL UNIQUE, work_phone character varying(32), hire_date date NOT NULL, termination_date date, access_level character varying(50), manager_employee_id character varying(64), PRIMARY KEY (employee_id) )\nCREATE TABLE government_services.service_locations ( location_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, location_name character varying(200), address text NOT NULL, city character varying(100), state character varying(50), postal_code character varying(20), latitude numeric(9, 6), longitude numeric(9, 6), operating_hours text, contact_phone character varying(32), is_accessible boolean, PRIMARY KEY (location_id) )\nCREATE TABLE government_services.appointments ( appointment_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, employee_id character varying(64), location_id character varying(64), service_id character varying(64), scheduled_start_time timestamp NOT NULL, scheduled_end_time timestamp, purpose text NOT NULL, status character varying(30) NOT NULL, booking_method character varying(50), created_at timestamp NOT NULL, notes text, PRIMARY KEY (appointment_id) )\nCREATE TABLE government_services.notifications ( notification_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, application_id character varying(64), message_subject character varying(255), message_body text NOT NULL, channel character varying(30) NOT NULL, sent_at timestamp NOT NULL, status character varying(30) NOT NULL, related_entity_type character varying(50), related_entity_id character varying(64), PRIMARY KEY (notification_id) )\n"} {"conversations": [{"role": "user", "content": "Which is the token with the largest difference between its highest and lowest price in the last 24h on each chain, and what is the token's symbol and current price?"}, {"role": "assistant", "content": "SELECT chain, token_symbol, price, (highest_price_24h - lowest_price_24h) AS price_diff_24h\nFROM token_basic_info\nWHERE (chain, highest_price_24h - lowest_price_24h) IN (\n SELECT chain, MAX(highest_price_24h - lowest_price_24h) AS diff\n FROM token_basic_info\n GROUP BY chain\n)\nORDER BY price_diff_24h DESC;"}, {"role": "user", "content": "Could you also include the percentage change over 24 hours for each token in the result?"}, {"role": "assistant", "content": "SELECT chain, token_symbol, price, price_change_percentage_24h, (highest_price_24h - lowest_price_24h) AS price_diff_24h\nFROM token_basic_info\nWHERE (chain, highest_price_24h - lowest_price_24h) IN (\n SELECT chain, MAX(highest_price_24h - lowest_price_24h) AS diff\n FROM token_basic_info\n GROUP BY chain\n)\nORDER BY price_diff_24h DESC;"}, {"role": "user", "content": "I'm only interested in tokens where this price difference exceeds $5. Can you filter for that?"}, {"role": "assistant", "content": "SELECT chain, token_symbol, price, price_change_percentage_24h, (highest_price_24h - lowest_price_24h) AS price_diff_24h\nFROM token_basic_info\nWHERE (chain, highest_price_24h - lowest_price_24h) IN (\n SELECT chain, MAX(highest_price_24h - lowest_price_24h) AS diff\n FROM token_basic_info\n GROUP BY chain\n)\nAND (highest_price_24h - lowest_price_24h) > 5\nORDER BY price_diff_24h 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\n \"CREATE TABLE token_basic_info (\",\n \"coin_id character varying(100) NOT NULL, -- the id of the token\",\n \"token_name character varying(100) NOT NULL, -- the token's name\",\n \"token_symbol character varying(100) NOT NULL, -- the token's symbol\",\n \"token_address character varying(100) NOT NULL, -- the token's address\",\n \"chain text, -- the chain that the token resides\",\n \"price double precision, -- the current price of the token\",\n \"price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour\",\n \"price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours\",\n \"price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days\",\n \"highest_price_24h double precision, -- the highest price of the token in 24 hours\",\n \"lowest_price_24h double precision, -- the lowest price of the token in 24 hours\",\n \"market_cap double precision, -- the market cap of the token\",\n \"market_cap_rank bigint, -- the rank of the token market cap in desc\",\n \"market_cap_change_percentage_24h text, -- the percentage of market cap changes in 24 hours\",\n \"total_volume text, -- the trade volum of the token both in decentralized exchange(DEX) and centralized exchange(CEX)\", \n \"narrative text, -- the category or narrative of the token\",\n \"trend_rank biging, -- the trending rank of the token, value 1 expresses the most popular token.\",\n \",PRIMARY KEY (coin_id, chain));\",\n\n"} {"conversations": [{"role": "user", "content": "I want to know, for each conversation participant, how many unread messages they have. Return participant_id, conversation_id, and unread_count."}, {"role": "assistant", "content": "SELECT cp.participant_id,\n cp.conversation_id,\n COUNT(m.message_id) AS unread_count\nFROM social_media.conversation_participants cp\nJOIN social_media.messages m\n ON m.conversation_id = cp.conversation_id\nWHERE m.sent_at > COALESCE(cp.last_read_at, '1970-01-01'::timestamp)\nGROUP BY cp.participant_id, cp.conversation_id;"}, {"role": "user", "content": "Can you filter the results to only include participants who joined the conversation before the earliest unread message was sent?"}, {"role": "assistant", "content": "SELECT cp.participant_id,\n cp.conversation_id,\n COUNT(m.message_id) AS unread_count\nFROM social_media.conversation_participants cp\nJOIN social_media.messages m\n ON m.conversation_id = cp.conversation_id\nWHERE m.sent_at > COALESCE(cp.last_read_at, '1970-01-01'::timestamp)\nGROUP BY cp.participant_id, cp.conversation_id\nHAVING cp.joined_at < MIN(m.sent_at);"}, {"role": "user", "content": "Also, include the timestamp of the most recent unread message for each participant as last_unread_at."}, {"role": "assistant", "content": "SELECT cp.participant_id,\n cp.conversation_id,\n COUNT(m.message_id) AS unread_count,\n MAX(m.sent_at) AS last_unread_at\nFROM social_media.conversation_participants cp\nJOIN social_media.messages m\n ON m.conversation_id = cp.conversation_id\nWHERE m.sent_at > COALESCE(cp.last_read_at, '1970-01-01'::timestamp)\nGROUP BY cp.participant_id, cp.conversation_id\nHAVING cp.joined_at < MIN(m.sent_at);"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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.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.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.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": "Retrieve each agent's ID, full name, and the count of 'Pending' policies they have sold with a premium_amount greater than 2000. Order the results by the policy count descending."}, {"role": "assistant", "content": "SELECT a.agent_id,\n a.first_name || ' ' || a.last_name AS agent_name,\n COUNT(p.policy_id) AS pending_policy_count\nFROM insurance.agents a\nJOIN insurance.policies p ON a.agent_id = p.agent_id\nWHERE p.status = 'Pending'\n AND p.premium_amount > 2000\nGROUP BY a.agent_id, agent_name\nORDER BY pending_policy_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.policies ( policy_id text, customer_id text, product_id text, agent_id text, policy_number text, start_date date, end_date date, premium_amount numeric, coverage_limit numeric, deductible numeric, status text, issued_at timestamp, cancellation_date date, cancellation_reason text )\nCREATE TABLE insurance.claims (\n claim_id character varying(64) NOT NULL, -- unique identifier for the claim\n policy_id character varying(64) NOT NULL, -- identifier of the policy under which the claim is made (FK to policies)\n customer_id character varying(64) NOT NULL, -- identifier of the customer making the claim (FK to customers)\n incident_date timestamp NOT NULL, -- date and time of the incident leading to the claim\n reported_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- date the claim was reported\n description text NOT NULL, -- detailed description of the incident and claim\n estimated_loss numeric(15, 2), -- initial estimated cost of the loss\n status character varying(30) NOT NULL, -- e.g., Filed, Processing, Under Review, Approved, Denied, Settled\n settlement_amount numeric(15, 2), -- final amount paid out\n settlement_date date,\n claim_handler_id character varying(64), -- identifier for the employee handling the claim (FK to employees/adjusters)\n police_report_number character varying(100),\n PRIMARY KEY (claim_id)\n)\nCREATE TABLE insurance.agents ( agent_id text, first_name text, last_name text, agency_name text, license_number text, license_state text, contact_email text, contact_phone text, hire_date date, termination_date date, status text, commission_rate numeric, manager_id text )\nCREATE TABLE insurance.policy_beneficiaries ( beneficiary_id text, policy_id text, customer_id text, first_name text, last_name text, relationship text, percentage_share numeric, contact_info text, added_at timestamp )\n"} {"conversations": [{"role": "user", "content": "How many claims were reported in the last 90 days?"}, {"role": "assistant", "content": "SELECT COUNT(*) FROM claims WHERE reported_date >= CURRENT_DATE - INTERVAL '90 days'"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.policies ( policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, product_id character varying(64) NOT NULL, agent_id character varying(64), policy_number character varying(100) NOT NULL UNIQUE, start_date date NOT NULL, end_date date NOT NULL, premium_amount numeric(12, 2) NOT NULL, coverage_limit numeric(15, 2) NOT NULL, deductible numeric(10, 2) NOT NULL, status character varying(30) NOT NULL, issued_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, cancellation_date date, cancellation_reason text, PRIMARY KEY (policy_id) )\nCREATE TABLE insurance.claims ( claim_id character varying(64) NOT NULL, policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, incident_date timestamp NOT NULL, reported_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, description text NOT NULL, estimated_loss numeric(15, 2), status character varying(30) NOT NULL, settlement_amount numeric(15, 2), settlement_date date, claim_handler_id character varying(64), police_report_number character varying(100), PRIMARY KEY (claim_id) )\nCREATE TABLE insurance.insurance_products ( product_id character varying(64) NOT NULL, product_name character varying(150) NOT NULL, product_type character varying(50) NOT NULL, description text, base_premium numeric(10, 2) NOT NULL, coverage_details text, underwriting_rules text, is_active boolean NOT NULL DEFAULT true, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, updated_at timestamp, PRIMARY KEY (product_id) )\nCREATE TABLE insurance.agents ( agent_id text PRIMARY KEY, first_name text, last_name text, agency_name text, license_number text, license_state text, contact_email text, contact_phone text, hire_date date, termination_date date, status text, commission_rate numeric, manager_id text )\nCREATE TABLE insurance.premium_payments ( payment_id text PRIMARY KEY, policy_id text, customer_id text, payment_date timestamp, amount_paid numeric, payment_method text, transaction_reference text, due_date date, payment_period_start date, payment_period_end date, status text )\nCREATE TABLE insurance.claim_documents ( document_id.text, claim_id.text, document_type.text, file_name.text, file_path.text, file_size_bytes.integer, mime_type.text, uploaded_by.text, uploaded_at.timestamp, description.text )\nCREATE TABLE insurance.policy_beneficiaries ( beneficiary_id.text, policy_id.text, customer_id.text, first_name.text, last_name.text, relationship.text, percentage_share.numeric, contact_info.text, added_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "List the total number of notifications sent through each channel for appointments."}, {"role": "assistant", "content": "SELECT n.channel, COUNT(*) AS notification_count\nFROM government_services.notifications n\nWHERE n.related_entity_type = 'Appointment'\nGROUP BY n.channel;"}, {"role": "user", "content": "Please only include notifications that were sent after March 1, 2024."}, {"role": "assistant", "content": "SELECT n.channel, COUNT(*) AS notification_count\nFROM government_services.notifications n\nWHERE n.related_entity_type = 'Appointment' AND n.sent_at > '2024-03-01'\nGROUP BY n.channel;"}, {"role": "user", "content": "Exclude any channels where the count is less than 5."}, {"role": "assistant", "content": "SELECT n.channel, COUNT(*) AS notification_count\nFROM government_services.notifications n\nWHERE n.related_entity_type = 'Appointment' AND n.sent_at > '2024-03-01'\nGROUP BY n.channel\nHAVING COUNT(*) >= 5;"}, {"role": "user", "content": "Can you order the results by notification_count in ascending order?"}, {"role": "assistant", "content": "SELECT n.channel, COUNT(*) AS notification_count\nFROM government_services.notifications n\nWHERE n.related_entity_type = 'Appointment' AND n.sent_at > '2024-03-01'\nGROUP BY n.channel\nHAVING COUNT(*) >= 5\nORDER BY notification_count ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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.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 (\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 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": "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": "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": "Find all addresses with a balance greater than 1000, ordered by balance in descending order."}, {"role": "assistant", "content": "SELECT address_id, public_key, balance FROM blockchain.addresses WHERE balance > 1000 ORDER BY balance DESC;"}, {"role": "user", "content": "Now, join this with another query to show the difference between each address's balance and the average balance of all addresses."}, {"role": "assistant", "content": "SELECT a.address_id, a.public_key, a.balance, (a.balance - (SELECT AVG(balance) FROM blockchain.addresses)) AS balance_difference FROM blockchain.addresses a WHERE a.balance > 1000 ORDER BY a.balance DESC;"}, {"role": "user", "content": "Can you modify this to show the percentage difference instead of absolute difference?"}, {"role": "assistant", "content": "SELECT a.address_id, a.public_key, a.balance, ((a.balance - (SELECT AVG(balance) FROM blockchain.addresses)) / (SELECT AVG(balance) FROM blockchain.addresses)) * 100 AS percentage_difference FROM blockchain.addresses a WHERE a.balance > 1000 ORDER BY a.balance DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE blockchain.addresses ( address_id text PRIMARY KEY, public_key text, balance numeric )\n"} {"conversations": [{"role": "user", "content": "Show the number of employees in each department."}, {"role": "assistant", "content": "SELECT department, COUNT(*) AS employee_count\nFROM financial_services.employees\ngroup BY department;"}, {"role": "user", "content": "Exclude departments that have less than 3 employees."}, {"role": "assistant", "content": "SELECT department, COUNT(*) AS employee_count\nFROM financial_services.employees\ngroup BY department\nHAVING COUNT(*) >= 3;"}, {"role": "user", "content": "Can you also show the average hire_date for employees in each department?"}, {"role": "assistant", "content": "SELECT department, COUNT(*) AS employee_count, AVG(hire_date) AS average_hire_date\nFROM financial_services.employees\ngroup BY department\nHAVING COUNT(*) >= 3;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.accounts ( account_id text PRIMARY KEY, customer_id text, account_number text, account_type text, balance numeric, currency text, opened_date date, status text, interest_rate numeric, last_updated_at timestamp )\nCREATE TABLE financial_services.transactions ( transaction_id text PRIMARY KEY, account_id text, related_account_id text, transaction_type text, amount numeric, currency text, transaction_date timestamp, effective_date date, description text, status text, reference_number text )\nCREATE TABLE financial_services.trades ( trade_id text PRIMARY KEY, account_id text, security_id text, order_id text, trade_type text, quantity numeric, price_per_unit numeric, total_amount numeric, commission numeric, trade_timestamp timestamp, settlement_date date, status text, execution_venue text )\nCREATE TABLE financial_services.market_data ( data_point_id bigserial PRIMARY KEY, security_id text, data_timestamp timestamp, open_price numeric, high_price numeric, low_price numeric, close_price numeric, adjusted_close_price numeric, volume bigint, source text )\nCREATE TABLE financial_services.employees ( employee_id text PRIMARY KEY, first_name text, last_name text, job_title text, department text, branch_id text, email text, phone_extension text, hire_date date, termination_date date, manager_id text, status text )\n"} {"conversations": [{"role": "user", "content": "Find documents that have the same document_name but are associated with different cases. Show the document name and the two different case IDs."}, {"role": "assistant", "content": "SELECT d1.document_name, d1.case_id AS case_id_1, d2.case_id AS case_id_2 FROM legal_services.documents AS d1 JOIN legal_services.documents AS d2 ON d1.document_name = d2.document_name WHERE d1.case_id <> d2.case_id AND d1.document_id < d2.document_id;"}, {"role": "user", "content": "Actually, only show pairs where at least one of the documents is of document_type 'Contract'."}, {"role": "assistant", "content": "SELECT d1.document_name, d1.case_id AS case_id_1, d2.case_id AS case_id_2 FROM legal_services.documents AS d1 JOIN legal_services.documents AS d2 ON d1.document_name = d2.document_name WHERE d1.case_id <> d2.case_id AND d1.document_id < d2.document_id AND (d1.document_type = 'Contract' OR d2.document_type = 'Contract');"}, {"role": "user", "content": "Also, only include pairs where both documents were uploaded in the year 2024."}, {"role": "assistant", "content": "SELECT d1.document_name, d1.case_id AS case_id_1, d2.case_id AS case_id_2 FROM legal_services.documents AS d1 JOIN legal_services.documents AS d2 ON d1.document_name = d2.document_name WHERE d1.case_id <> d2.case_id AND d1.document_id < d2.document_id AND (d1.document_type = 'Contract' OR d2.document_type = 'Contract') AND YEAR(d1.upload_timestamp) = 2024 AND YEAR(d2.upload_timestamp) = 2024;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.documents ( document_id.text, case_id.text, document_name.text, document_type.text, storage_path.text, uploaded_by_lawyer_id.text, upload_timestamp.timestamp, version.integer, description.text )\n"} {"conversations": [{"role": "user", "content": "Count the number of users for each location where the location is not empty."}, {"role": "assistant", "content": "SELECT location, COUNT(user_id) FROM social_media.users WHERE location IS NOT NULL AND location != '' GROUP BY location;"}], "system": "You are an SQL statement expert. Given the table structure 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": "Find all patients along with the number of unique diagnoses each has received. Only include patients who have at least two diagnoses."}, {"role": "assistant", "content": "SELECT p.patient_id, p.first_name, p.last_name, COUNT(DISTINCT d.diagnosis_id) AS num_diagnoses\nFROM healthcare.patients p\nJOIN healthcare.diagnoses d ON p.patient_id = d.patient_id\nGROUP BY p.patient_id, p.first_name, p.last_name\nHAVING COUNT(DISTINCT d.diagnosis_id) >= 2;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id text, first_name text, last_name text, date_of_birth date, gender text, address text, phone_number text, email text, emergency_contact_name text, emergency_contact_phone text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.appointments ( appointment_id text, patient_id text, doctor_id text, appointment_time timestamp, duration_minutes integer, reason text, status text, location_id text, notes text, created_at timestamp )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id text, record_id text, patient_id text, doctor_id text, diagnosis_code text, code_type text, description text, diagnosis_date date, status text, is_chronic boolean )\nCREATE TABLE healthcare.medications ( medication_id text, medication_name text, generic_name text, manufacturer text, ndc_code text, description text )\n"} {"conversations": [{"role": "user", "content": "Show me the name and type for all the locations."}, {"role": "assistant", "content": "SELECT name, type FROM transportation.locations"}, {"role": "user", "content": "Now, filter this list to only include locations whose type is either 'Distribution Center' or 'Warehouse'."}, {"role": "assistant", "content": "SELECT name, type FROM transportation.locations WHERE type IN ('Distribution Center', 'Warehouse')"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.locations ( location_id.text, name.text, type.text, address_line1.text, city.text, state_province.text, postal_code.text, country.text, latitude.numeric, longitude.numeric, timezone.text )\n"} {"conversations": [{"role": "user", "content": "List all ERC20 tokens where the price is between $1 and $10, including their names, symbols, and contract addresses."}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address FROM token_metas tm JOIN token_prices_latest tpl ON tm.contract_address = tpl.address WHERE tm.is_erc20 = 1 AND tpl.price BETWEEN 1 AND 10;"}, {"role": "user", "content": "I think there's an error in your query - it should be joining with token_prices_latest on address not contract_address. Also, can you add the current price to the results?"}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address, tpl.price FROM token_metas tm JOIN token_prices_latest tpl ON tm.contract_address = tpl.address WHERE tm.is_erc20 = 1 AND tpl.price BETWEEN 1 AND 10;"}, {"role": "user", "content": "Now filter these results to only show tokens with decimals equal to 18 and sort by name alphabetically."}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address, tpl.price FROM token_metas tm JOIN token_prices_latest tpl ON tm.contract_address = tpl.address WHERE tm.is_erc20 = 1 AND tpl.price BETWEEN 1 AND 10 AND tm.decimals = 18 ORDER BY tm.name ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp timestamp, block_number bigint, transaction_hash text, transaction_index bigint, from_address text, contract_address text, symbol text, total_supply text, name text, decimals bigint, is_erc20 integer, is_erc721 integer, is_erc1155 integer, is_proxy integer, extra_info text, pk integer )\nCREATE TABLE erc1155_approval_for_all ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash text, log_index integer, contract_address text )\nCREATE TABLE erc20_balances ( block_number bigint, contract_address text, wallet_address text, amount text, pk text )\nCREATE TABLE erc20_balances_historical ( block_number bigint, contract_address text, wallet_address text, amount text, pk integer )\nCREATE TABLE nft_holders ( block_number bigint, contract_address text, wallet_address text, token_id text, contract_type text, amount text, pk text )\nCREATE TABLE nft_holder_historical ( block_number bigint, contract_address text, wallet_address text, token_id text, contract_type text, amount text, pk integer )\nCREATE TABLE sui_coins ( object_id text, status text, coin_type text, balance text, owner text )\nCREATE TABLE sui_coins_metadata ( object_id text, coin_type text, status text, decimals bigint, description text, icon_url text, symbol text, name text )\nCREATE TABLE nft_metadata ( blockchain text, contract_address text, token_id text, contract_name text, erc_type text, amount bigint, minter text, owner text, mint_block_number bigint, mint_time bigint, mint_transaction_hash text, mint_price text, token_uri text, metadata text, name text, image_uri text, traits text, updated_at bigint, status text, rarity_score real, rarity_rank integer, unique_attribute_count integer, pk integer )\nCREATE TABLE nft_collections ( blockchain text, contract_address text, name text, symbol text, deploy_block_number bigint, deploy_block_time bigint, erc_type text, owner text, traits text, description text, slug text, media_info text, image_url text, banner_image_url text, updated_at bigint, banner text, token_count bigint, floor_price text, floor_price_symbol text, floor_price_contract text, pk integer )\nCREATE TABLE token_prices ( uuid text, blockchain text, address text, decimals bigint, symbol text, price real, timestamp timestamp )\nCREATE TABLE token_prices_latest ( blockchain text, address text, decimals bigint, symbol text, price real, timestamp timestamp )\nCREATE TABLE erc20_approval ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash text, log_index integer, contract_address text, pk integer )\nCREATE TABLE token_balances ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply decimal, amount decimal )\nCREATE TABLE token_info ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text )\nCREATE TABLE token_balances_bitcoin ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply text, amount text )\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_balances_avalanche ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply decimal, amount decimal )\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id text )\n"} {"conversations": [{"role": "user", "content": "Show a list of all game developers with their name and founded year."}, {"role": "assistant", "content": "SELECT\n name,\n founded_year\nFROM gaming_technology.developers;"}, {"role": "user", "content": "Please filter the list to only include developers founded in the year 1998."}, {"role": "assistant", "content": "SELECT\n name,\n founded_year\nFROM gaming_technology.developers\nWHERE\n founded_year = 1998;"}, {"role": "user", "content": "Can you also include the number of games each of these developers has released?"}, {"role": "assistant", "content": "SELECT\n T1.name,\n T1.founded_year,\n COUNT(T2.game_id) AS game_count\nFROM gaming_technology.developers AS T1\nLEFT JOIN gaming_technology.games AS T2\n ON T1.developer_id = T2.developer_id\nWHERE\n T1.founded_year = 1998\nGROUP BY\n T1.developer_id,\n T1.name,\n T1.founded_year;"}, {"role": "user", "content": "Now, only show the developers who have released exactly 2 games."}, {"role": "assistant", "content": "SELECT\n T1.name,\n T1.founded_year,\n COUNT(T2.game_id) AS game_count\nFROM gaming_technology.developers AS T1\nJOIN gaming_technology.games AS T2\n ON T1.developer_id = T2.developer_id\nWHERE\n T1.founded_year = 1998\nGROUP BY\n T1.developer_id,\n T1.name,\n T1.founded_year\nHAVING\n COUNT(T2.game_id) = 2;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.players (\n player_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the player\n username character varying(100) NOT NULL UNIQUE, -- player's chosen display name\n email character varying(255) NOT NULL UNIQUE, -- player's email address for login/recovery\n password_hash text NOT NULL, -- securely hashed password\n registration_date timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the player account was created\n last_login timestamp with time zone, -- timestamp of the last successful login\n country_code character(2), -- player's country (ISO 3166-1 alpha-2)\n status character varying(20) NOT NULL DEFAULT 'active', -- account status (e.g., active, banned, suspended)\n profile_data jsonb, -- flexible field for avatar url, bio, preferences etc.\n PRIMARY KEY (player_id)\n)\nCREATE TABLE gaming_technology.games (\n game_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game\n title character varying(200) NOT NULL, -- official title of the game\n developer_id uuid NOT NULL, -- FK linking to the developers table\n publisher_id uuid, -- FK linking to a potential publishers table (optional)\n genre character varying(100), -- primary genre (e.g., RPG, FPS, Strategy)\n release_date date, -- official release date\n description text, -- short description or synopsis of the game\n platform character varying(50) NOT NULL, -- primary platform (e.g., PC, PlayStation 5, Xbox Series X, Mobile)\n engine character varying(100), -- game engine used (e.g., Unreal Engine 5, Unity)\n website character varying(255), -- official website URL\n PRIMARY KEY (game_id)\n -- FOREIGN KEY (developer_id) REFERENCES gaming_technology.developers(developer_id) -- Example FK constraint\n)\nCREATE TABLE gaming_technology.developers (\n developer_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the developer studio\n name character varying(150) NOT NULL UNIQUE, -- name of the development studio\n country character varying(100), -- country where the studio is based\n founded_year integer, -- year the studio was founded\n website character varying(255), -- developer's official website\n created_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP,\n PRIMARY KEY (developer_id)\n)\nCREATE TABLE gaming_technology.game_sessions (\n session_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game session\n player_id uuid NOT NULL, -- FK linking to the players table\n game_id uuid NOT NULL, -- FK linking to the games table\n server_id uuid, -- FK linking to the servers table (nullable for single-player)\n start_time timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the session began\n end_time timestamp with time zone, -- when the session ended (null if ongoing)\n duration_seconds integer, -- calculated duration of the session in seconds\n score integer, -- player's score for the session, if applicable\n session_data jsonb, -- flexible field for session-specific info (e.g., map played, character used)\n PRIMARY KEY (session_id)\n -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id),\n -- FOREIGN KEY (server_id) REFERENCES gaming_technology.servers(server_id)\n)\nCREATE TABLE gaming_technology.servers (\n server_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game server instance\n game_id uuid NOT NULL, -- FK linking to the game this server hosts\n server_name character varying(150), -- display name for the server\n region character varying(50) NOT NULL, -- geographical region (e.g., us-east-1, eu-west-2)\n ip_address character varying(45), -- IP address (IPv4 or IPv6)\n port integer, -- network port number\n current_players integer NOT NULL DEFAULT 0, -- number of players currently connected\n max_players integer NOT NULL, -- maximum player capacity\n status character varying(30) NOT NULL DEFAULT 'offline', -- server status (e.g., online, offline, maintenance)\n last_heartbeat timestamp with time zone, -- last time the server reported its status\n PRIMARY KEY (server_id)\n -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id)\n)\nCREATE TABLE gaming_technology.achievements (\n achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for an achievement definition\n game_id uuid NOT NULL, -- FK linking to the game the achievement belongs to\n name character varying(150) NOT NULL, -- name of the achievement\n description text NOT NULL, -- how to unlock the achievement\n icon_url character varying(255), -- URL for the achievement's icon\n points integer DEFAULT 0, -- points awarded for unlocking (optional)\n hidden boolean DEFAULT false, -- whether the achievement details are hidden until unlocked\n PRIMARY KEY (achievement_id)\n -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id)\n)\nCREATE TABLE gaming_technology.player_achievements (\n player_achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for this unlock instance\n player_id uuid NOT NULL, -- FK linking to the player who unlocked it\n achievement_id uuid NOT NULL, -- FK linking to the achievement definition\n unlocked_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the achievement was unlocked\n PRIMARY KEY (player_achievement_id),\n UNIQUE (player_id, achievement_id) -- Ensure a player can only unlock an achievement once\n -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n -- FOREIGN KEY (achievement_id) REFERENCES gaming_technology.achievements(achievement_id)\n)\n"} {"conversations": [{"role": "user", "content": "What are the personal contact details of the staff member associated with staff_id 'STAFF789' who worked on a specific maintenance record?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide personal contact details of staff members as this information is not stored in the maintenance_records table and is outside the scope of the available data."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.maintenance_records ( record_id text, asset_id text, asset_type text, maintenance_type text, staff_id text, start_datetime timestamp, end_datetime timestamp, description text, cost numeric, status text )\n"} {"conversations": [{"role": "user", "content": "I want to find all claim IDs that have both an 'Accident Report' and a 'Police Report' document."}, {"role": "assistant", "content": "SELECT DISTINCT a.claim_id\nFROM insurance.claim_documents a\nJOIN insurance.claim_documents b\n ON a.claim_id = b.claim_id\nWHERE a.document_type = 'Accident Report'\n AND b.document_type = 'Police Report';"}, {"role": "user", "content": "Now, only include those pairs if both documents were uploaded after '2024-06-01'."}, {"role": "assistant", "content": "SELECT DISTINCT a.claim_id\nFROM insurance.claim_documents a\nJOIN insurance.claim_documents b\n ON a.claim_id = b.claim_id\nWHERE a.document_type = 'Accident Report'\n AND b.document_type = 'Police Report'\n AND a.uploaded_at > '2024-06-01'\n AND b.uploaded_at > '2024-06-01';"}, {"role": "user", "content": "Additionally, ensure that both files are larger than 500 KB."}, {"role": "assistant", "content": "SELECT DISTINCT a.claim_id\nFROM insurance.claim_documents a\nJOIN insurance.claim_documents b\n ON a.claim_id = b.claim_id\nWHERE a.document_type = 'Accident Report'\n AND b.document_type = 'Police Report'\n AND a.uploaded_at > '2024-06-01'\n AND b.uploaded_at > '2024-06-01'\n AND a.file_size_bytes > 512000\n AND b.file_size_bytes > 512000;"}, {"role": "user", "content": "Finally, show me the file_name and uploaded_by for both document types in the results."}, {"role": "assistant", "content": "SELECT\n a.claim_id,\n a.file_name AS accident_file_name,\n a.uploaded_by AS accident_uploaded_by,\n b.file_name AS police_file_name,\n b.uploaded_by AS police_uploaded_by\nFROM insurance.claim_documents a\nJOIN insurance.claim_documents b\n ON a.claim_id = b.claim_id\nWHERE a.document_type = 'Accident Report'\n AND b.document_type = 'Police Report'\n AND a.uploaded_at > '2024-06-01'\n AND b.uploaded_at > '2024-06-01'\n AND a.file_size_bytes > 512000\n AND b.file_size_bytes > 512000;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.claim_documents ( document_id text, claim_id text, document_type text, file_name text, file_path text, file_size_bytes integer, mime_type text, uploaded_by text, uploaded_at timestamp, description text )\n"} {"conversations": [{"role": "user", "content": "Show me all claim documents that are PDFs and were uploaded in the last 30 days, along with their claim IDs and file sizes."}, {"role": "assistant", "content": "SELECT cd.document_id, cd.claim_id, cd.file_size_bytes, c.policy_id FROM insurance.claim_documents cd JOIN insurance.claims c ON cd.claim_id = c.claim_id WHERE cd.mime_type = 'application/pdf' AND cd.uploaded_at >= DATE_SUB(CURRENT_DATE, INTERVAL 30 DAY);"}, {"role": "user", "content": "I also want to see the policy details for these claims, including the coverage limit and premium amount."}, {"role": "assistant", "content": "SELECT cd.document_id, cd.claim_id, cd.file_size_bytes, c.policy_id, p.coverage_limit, p.premium_amount FROM insurance.claim_documents cd JOIN insurance.claims c ON cd.claim_id = c.claim_id JOIN insurance.policies p ON c.policy_id = p.policy_id WHERE cd.mime_type = 'application/pdf' AND cd.uploaded_at >= DATE_SUB(CURRENT_DATE, INTERVAL 30 DAY);"}, {"role": "user", "content": "Now filter to only show documents larger than 1MB and include the upload date."}, {"role": "assistant", "content": "SELECT cd.document_id, cd.claim_id, cd.file_size_bytes, cd.uploaded_at, c.policy_id, p.coverage_limit, p.premium_amount FROM insurance.claim_documents cd JOIN insurance.claims c ON cd.claim_id = c.claim_id JOIN insurance.policies p ON c.policy_id = p.policy_id WHERE cd.mime_type = 'application/pdf' AND cd.uploaded_at >= DATE_SUB(CURRENT_DATE, INTERVAL 30 DAY) AND cd.file_size_bytes > 1000000;"}, {"role": "user", "content": "Finally, show me the count of such PDF documents per policy, ordered by count descending."}, {"role": "assistant", "content": "SELECT c.policy_id, COUNT(cd.document_id) AS pdf_count FROM insurance.claim_documents cd JOIN insurance.claims c ON cd.claim_id = c.claim_id WHERE cd.mime_type = 'application/pdf' AND cd.uploaded_at >= DATE_SUB(CURRENT_DATE, INTERVAL 30 DAY) AND cd.file_size_bytes > 1000000 GROUP BY c.policy_id ORDER BY pdf_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.policies ( policy_id text 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 )\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.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": "Show me all invoices where the amount paid is exactly equal to the total amount."}, {"role": "assistant", "content": "SELECT * FROM legal_services.invoices WHERE amount_paid = total_amount;"}, {"role": "user", "content": "Instead, show only the invoice_number, client_id, and payment_date for these invoices, and sort by payment_date descending."}, {"role": "assistant", "content": "SELECT invoice_number, client_id, payment_date FROM legal_services.invoices WHERE amount_paid = total_amount ORDER BY payment_date DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.invoices (\n invoice_id character varying(64) NOT NULL, -- unique identifier for the invoice\n invoice_number character varying(100) UNIQUE NOT NULL, -- user-facing invoice number\n client_id character varying(64) NOT NULL, -- FK to clients table\n case_id character varying(64), -- FK to cases table (optional, could be general retainer)\n issue_date date NOT NULL, -- date the invoice was generated\n due_date date NOT NULL, -- date the payment is due\n total_amount numeric(12, 2) NOT NULL, -- total amount due on the invoice\n amount_paid numeric(12, 2) DEFAULT 0.00, -- amount already paid\n status character varying(50) NOT NULL, -- e.g., Draft, Sent, Paid, Partially Paid, Overdue, Void\n payment_date timestamp, -- date the invoice was fully paid (nullable)\n notes text, -- additional notes or terms on the invoice\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n PRIMARY KEY (invoice_id)\n)\n"} {"conversations": [{"role": "user", "content": "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": "Show me all bookings with a status of 'confirmed' that were made in the last 7 days, including passenger_id and fare."}, {"role": "assistant", "content": "SELECT booking_id, passenger_id, fare FROM transportation.bookings WHERE status = 'confirmed' AND booking_time >= CURRENT_DATE - INTERVAL '7 days';"}, {"role": "user", "content": "Now include only bookings where the fare is greater than $50 and order them by booking_time in descending order."}, {"role": "assistant", "content": "SELECT booking_id, passenger_id, fare FROM transportation.bookings WHERE status = 'confirmed' AND booking_time >= CURRENT_DATE - INTERVAL '7 days' AND fare > 50 ORDER BY booking_time DESC;"}, {"role": "user", "content": "Can you also include the trip_id and filter to only show bookings for trip_id 'TRIP789'?"}, {"role": "assistant", "content": "SELECT booking_id, passenger_id, fare, trip_id FROM transportation.bookings WHERE status = 'confirmed' AND booking_time >= CURRENT_DATE - INTERVAL '7 days' AND fare > 50 AND trip_id = 'TRIP789' ORDER BY booking_time DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.bookings ( booking_id text PRIMARY KEY, passenger_id text, trip_id text, seat_number text, booking_time timestamp, status text, fare numeric, payment_transaction_id text, special_requests text )\n"} {"conversations": [{"role": "user", "content": "List all players and the number of distinct games they have grabbed in-game items from, as well as the name of each game."}, {"role": "assistant", "content": "SELECT p.player_id, p.username, g.game_id, g.title, COUNT(DISTINCT pi.item_id) AS distinct_items_acquired\nFROM gaming_technology.players p\nJOIN gaming_technology.player_inventory pi ON p.player_id = pi.player_id\nJOIN gaming_technology.in_game_items i ON pi.item_id = i.item_id\nJOIN gaming_technology.games g ON i.game_id = g.game_id\nGROUP BY p.player_id, p.username, g.game_id, g.title;"}, {"role": "user", "content": "Could you only show players who have grabbed items from more than one game?"}, {"role": "assistant", "content": "SELECT p.player_id, p.username, COUNT(DISTINCT g.game_id) AS games_with_items\nFROM gaming_technology.players p\nJOIN gaming_technology.player_inventory pi ON p.player_id = pi.player_id\nJOIN gaming_technology.in_game_items i ON pi.item_id = i.item_id\nJOIN gaming_technology.games g ON i.game_id = g.game_id\nGROUP BY p.player_id, p.username\nHAVING COUNT(DISTINCT g.game_id) > 1;"}, {"role": "user", "content": "Can you also include the total quantity of all items these players have from each game?"}, {"role": "assistant", "content": "SELECT p.player_id, p.username, g.game_id, g.title, SUM(pi.quantity) AS total_quantity\nFROM gaming_technology.players p\nJOIN gaming_technology.player_inventory pi ON p.player_id = pi.player_id\nJOIN gaming_technology.in_game_items i ON pi.item_id = i.item_id\nJOIN gaming_technology.games g ON i.game_id = g.game_id\nGROUP BY p.player_id, p.username, g.game_id, g.title\nHAVING COUNT(DISTINCT g.game_id) > 1;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.players ( player_id uuid PRIMARY KEY, username text, email text, password_hash text, registration_date timestamptz, last_login timestamptz, country_code text, status text, profile_data jsonb )\nCREATE TABLE gaming_technology.games ( game_id uuid PRIMARY KEY, title text, developer_id uuid, publisher_id uuid, genre text, release_date date, description text, platform text, engine text, website text )\nCREATE TABLE gaming_technology.game_sessions ( session_id uuid PRIMARY KEY, player_id uuid, game_id uuid, server_id uuid, start_time timestamptz, end_time timestamptz, duration_seconds int, score int, session_data jsonb )\nCREATE TABLE gaming_technology.servers (\n server_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game server instance\n game_id uuid NOT NULL, -- FK linking to the game this server hosts\n server_name character varying(150), -- display name for the server\n region character varying(50) NOT NULL, -- geographical region (e.g., us-east-1, eu-west-2)\n ip_address character varying(45), -- IP address (IPv4 or IPv6)\n port integer, -- network port number\n current_players integer NOT NULL DEFAULT 0, -- number of players currently connected\n max_players integer NOT NULL, -- maximum player capacity\n status character varying(30) NOT NULL DEFAULT 'offline', -- server status (e.g., online, offline, maintenance)\n last_heartbeat timestamp with time zone, -- last time the server reported its status\n PRIMARY KEY (server_id)\n -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id)\n)\nCREATE TABLE gaming_technology.achievements ( achievement_id.uuid, game_id.uuid, name.text, description.text, icon_url.text, points.integer, hidden.boolean )\nCREATE TABLE gaming_technology.player_achievements ( player_achievement_id.uuid, player_id.uuid, achievement_id.uuid, unlocked_at.timestamptz )\nCREATE TABLE gaming_technology.in_game_items ( item_id uuid NOT NULL DEFAULT gen_random_uuid(), game_id uuid NOT NULL, item_name character varying(150) NOT NULL, item_type character varying(50) NOT NULL, description text, rarity character varying(30), cost_currency character varying(10), cost_amount numeric(12, 2), attributes jsonb, PRIMARY KEY (item_id) )\nCREATE TABLE gaming_technology.player_inventory ( inventory_id uuid NOT NULL DEFAULT gen_random_uuid(), player_id uuid NOT NULL, item_id uuid NOT NULL, quantity integer NOT NULL DEFAULT 1, acquired_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, instance_data jsonb, PRIMARY KEY (inventory_id) )\n"} {"conversations": [{"role": "user", "content": "Show the usernames and registration dates for all players whose status is 'inactive'."}, {"role": "assistant", "content": "SELECT username, registration_date FROM players WHERE status = 'inactive';"}, {"role": "user", "content": "Refine the list to only include players registered after '2023-01-01'."}, {"role": "assistant", "content": "SELECT username, registration_date FROM players WHERE status = 'inactive' AND registration_date >= '2023-01-01';"}, {"role": "user", "content": "Instead, find the number of unique players who registered before '2020-01-01' and have never logged in (last_login is NULL)."}, {"role": "assistant", "content": "SELECT count(player_id) FROM players WHERE registration_date < '2020-01-01' AND last_login IS NULL;"}, {"role": "user", "content": "List the usernames and registration dates for those specific players instead of just the count."}, {"role": "assistant", "content": "SELECT username, registration_date FROM players WHERE registration_date < '2020-01-01' AND last_login 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 gaming_technology.players (\n player_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the player\n username character varying(100) NOT NULL UNIQUE, -- player's chosen display name\n email character varying(255) NOT NULL UNIQUE, -- player's email address for login/recovery\n password_hash text NOT NULL, -- securely hashed password\n registration_date timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the player account was created\n last_login timestamp with time zone, -- timestamp of the last successful login\n country_code character(2), -- player's country (ISO 3166-1 alpha-2)\n status character varying(20) NOT NULL DEFAULT 'active', -- account status (e.g., active, banned, suspended)\n profile_data jsonb, -- flexible field for avatar url, bio, preferences etc.\n PRIMARY KEY (player_id)\n)\nCREATE TABLE gaming_technology.games (\n game_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game\n title character varying(200) NOT NULL, -- official title of the game\n developer_id uuid NOT NULL, -- FK linking to the developers table\n publisher_id uuid, -- FK linking to a potential publishers table (optional)\n genre character varying(100), -- primary genre (e.g., RPG, FPS, Strategy)\n release_date date, -- official release date\n description text, -- short description or synopsis of the game\n platform character varying(50) NOT NULL, -- primary platform (e.g., PC, PlayStation 5, Xbox Series X, Mobile)\n engine character varying(100), -- game engine used (e.g., Unreal Engine 5, Unity)\n website character varying(255), -- official website URL\n PRIMARY KEY (game_id)\n -- FOREIGN KEY (developer_id) REFERENCES gaming_technology.developers(developer_id) -- Example FK constraint\n)\nCREATE TABLE gaming_technology.game_sessions (\n session_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game session\n player_id uuid NOT NULL, -- FK linking to the players table\n game_id uuid NOT NULL, -- FK linking to the games table\n server_id uuid, -- FK linking to the servers table (nullable for single-player)\n start_time timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the session began\n end_time timestamp with time zone, -- when the session ended (null if ongoing)\n duration_seconds integer, -- calculated duration of the session in seconds\n score integer, -- player's score for the session, if applicable\n session_data jsonb, -- flexible field for session-specific info (e.g., map played, character used)\n PRIMARY KEY (session_id)\n -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id),\n -- FOREIGN KEY (server_id) REFERENCES gaming_technology.servers(server_id)\n)\nCREATE TABLE gaming_technology.servers (\n server_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game server instance\n game_id uuid NOT NULL, -- FK linking to the game this server hosts\n server_name character varying(150), -- display name for the server\n region character varying(50) NOT NULL, -- geographical region (e.g., us-east-1, eu-west-2)\n ip_address character varying(45), -- IP address (IPv4 or IPv6)\n port integer, -- network port number\n current_players integer NOT NULL DEFAULT 0, -- number of players currently connected\n max_players integer NOT NULL, -- maximum player capacity\n status character varying(30) NOT NULL DEFAULT 'offline', -- server status (e.g., online, offline, maintenance)\n last_heartbeat timestamp with time zone, -- last time the server reported its status\n PRIMARY KEY (server_id)\n -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id)\n)\nCREATE TABLE gaming_technology.achievements (\n achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for an achievement definition\n game_id uuid NOT NULL, -- FK linking to the game the achievement belongs to\n name character varying(150) NOT NULL, -- name of the achievement\n description text NOT NULL, -- how to unlock the achievement\n icon_url character varying(255), -- URL for the achievement's icon\n points integer DEFAULT 0, -- points awarded for unlocking (optional)\n hidden boolean DEFAULT false, -- whether the achievement details are hidden until unlocked\n PRIMARY KEY (achievement_id)\n -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id)\n)\nCREATE TABLE gaming_technology.player_achievements (\n player_achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for this unlock instance\n player_id uuid NOT NULL, -- FK linking to the player who unlocked it\n achievement_id uuid NOT NULL, -- FK linking to the achievement definition\n unlocked_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the achievement was unlocked\n PRIMARY KEY (player_achievement_id),\n UNIQUE (player_id, achievement_id) -- Ensure a player can only unlock an achievement once\n -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n -- FOREIGN KEY (achievement_id) REFERENCES gaming_technology.achievements(achievement_id)\n)\nCREATE TABLE gaming_technology.in_game_items (\n item_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the item definition\n game_id uuid NOT NULL, -- FK linking to the game this item belongs to\n item_name character varying(150) NOT NULL, -- name of the item\n item_type character varying(50) NOT NULL, -- type (e.g., Cosmetic, Consumable, Weapon, Armor)\n description text, -- description of the item\n rarity character varying(30), -- item rarity (e.g., Common, Rare, Epic, Legendary)\n cost_currency character varying(10), -- currency code if purchasable (e.g., USD, EUR, GOLD)\n cost_amount numeric(12, 2), -- price if purchasable\n attributes jsonb, -- flexible field for item stats or properties\n PRIMARY KEY (item_id)\n -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id)\n)\nCREATE TABLE gaming_technology.player_inventory (\n inventory_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for an inventory entry\n player_id uuid NOT NULL, -- FK linking to the player owning the item\n item_id uuid NOT NULL, -- FK linking to the item definition\n quantity integer NOT NULL DEFAULT 1, -- number of items held (for stackable items)\n acquired_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the item was acquired\n instance_data jsonb, -- data specific to this instance (e.g., weapon mods, durability)\n PRIMARY KEY (inventory_id),\n -- Optional unique constraint if items are non-stackable or unique instances\n -- UNIQUE (player_id, item_id) -- Use if quantity is always 1\n -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n -- FOREIGN KEY (item_id) REFERENCES gaming_technology.in_game_items(item_id)\n)\n"} {"conversations": [{"role": "user", "content": "I need to get the most recent message each verified user has sent in any group chat, showing username, group_name, message_id, and sent_at."}, {"role": "assistant", "content": "WITH user_recent AS (\n SELECT m.sender_user_id, m.message_id, m.conversation_id, m.sent_at,\n ROW_NUMBER() OVER (PARTITION BY m.sender_user_id ORDER BY m.sent_at DESC) AS rn\n FROM social_media.messages m\n JOIN social_media.conversations c ON m.conversation_id = c.conversation_id\n WHERE c.is_group_chat = true\n)\nSELECT u.username, c.group_name, ur.message_id, ur.sent_at\nFROM user_recent ur\nJOIN social_media.users u ON ur.sender_user_id = u.user_id\nJOIN social_media.conversations c ON ur.conversation_id = c.conversation_id\nWHERE ur.rn = 1\n AND u.is_verified = true;"}, {"role": "user", "content": "Actually, I only want messages sent in the past 30 days."}, {"role": "assistant", "content": "WITH user_recent AS (\n SELECT m.sender_user_id, m.message_id, m.conversation_id, m.sent_at,\n ROW_NUMBER() OVER (PARTITION BY m.sender_user_id ORDER BY m.sent_at DESC) AS rn\n FROM social_media.messages m\n JOIN social_media.conversations c ON m.conversation_id = c.conversation_id\n WHERE c.is_group_chat = true\n AND m.sent_at >= NOW() - INTERVAL '30 days'\n)\nSELECT u.username, c.group_name, ur.message_id, ur.sent_at\nFROM user_recent ur\nJOIN social_media.users u ON ur.sender_user_id = u.user_id\nJOIN social_media.conversations c ON ur.conversation_id = c.conversation_id\nWHERE ur.rn = 1\n AND u.is_verified = true;"}, {"role": "user", "content": "Also, exclude any users who have disabled push notifications."}, {"role": "assistant", "content": "WITH user_recent AS (\n SELECT m.sender_user_id, m.message_id, m.conversation_id, m.sent_at,\n ROW_NUMBER() OVER (PARTITION BY m.sender_user_id ORDER BY m.sent_at DESC) AS rn\n FROM social_media.messages m\n JOIN social_media.conversations c ON m.conversation_id = c.conversation_id\n WHERE c.is_group_chat = true\n AND m.sent_at >= NOW() - INTERVAL '30 days'\n)\nSELECT u.username, c.group_name, ur.message_id, ur.sent_at\nFROM user_recent ur\nJOIN social_media.users u ON ur.sender_user_id = u.user_id\nJOIN social_media.conversations c ON ur.conversation_id = c.conversation_id\nJOIN social_media.user_settings s ON s.user_id = u.user_id\nWHERE ur.rn = 1\n AND u.is_verified = true\n AND s.push_notifications_enabled = true;"}, {"role": "user", "content": "And order the results by sent_at descending."}, {"role": "assistant", "content": "WITH user_recent AS (\n SELECT m.sender_user_id, m.message_id, m.conversation_id, m.sent_at,\n ROW_NUMBER() OVER (PARTITION BY m.sender_user_id ORDER BY m.sent_at DESC) AS rn\n FROM social_media.messages m\n JOIN social_media.conversations c ON m.conversation_id = c.conversation_id\n WHERE c.is_group_chat = true\n AND m.sent_at >= NOW() - INTERVAL '30 days'\n)\nSELECT u.username, c.group_name, ur.message_id, ur.sent_at\nFROM user_recent ur\nJOIN social_media.users u ON ur.sender_user_id = u.user_id\nJOIN social_media.conversations c ON ur.conversation_id = c.conversation_id\nJOIN social_media.user_settings s ON s.user_id = u.user_id\nWHERE ur.rn = 1\n AND u.is_verified = true\n AND s.push_notifications_enabled = true\nORDER BY ur.sent_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.hashtags ( hashtag_id character varying(64) NOT NULL, tag_name character varying(100) NOT NULL UNIQUE, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (hashtag_id) )\nCREATE TABLE social_media.post_hashtags ( post_hashtag_id character varying(64) NOT NULL, post_id character varying(64) NOT NULL, hashtag_id character varying(64) NOT NULL, PRIMARY KEY (post_hashtag_id), CONSTRAINT unique_post_hashtag UNIQUE (post_id, hashtag_id) )\nCREATE TABLE social_media.messages ( 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.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, user_id text, theme text, email_notifications_enabled boolean, push_notifications_enabled boolean, private_profile boolean, updated_at timestamp )\n"}