system stringlengths 315 8.06k | conversations listlengths 2 48 |
|---|---|
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.
##Table Structure
CREATE TABLE gaming_technology.player_inventory (
inventory_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for an inventory entry
player_id uuid NOT NULL, -- FK linking to the player owning the item
item_id uuid NOT NULL, -- FK linking to the item definition
quantity integer NOT NULL DEFAULT 1, -- number of items held (for stackable items)
acquired_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the item was acquired
instance_data jsonb, -- data specific to this instance (e.g., weapon mods, durability)
PRIMARY KEY (inventory_id),
-- Optional unique constraint if items are non-stackable or unique instances
-- UNIQUE (player_id, item_id) -- Use if quantity is always 1
-- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),
-- FOREIGN KEY (item_id) REFERENCES gaming_technology.in_game_items(item_id)
)
| [
{
"role": "user",
"content": "Show the latest time each player acquired any item.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT player_id, MAX(acquired_at) AS last_acquired_at FROM gaming_technology.player_inventory GROUP BY player_id;",
"sql": null
},
{
"role": "use... |
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.
##Table Structure
CREATE TABLE government_services.citizens (
citizen_id character varying(64) NOT NULL, -- unique identifier for the citizen
national_id_number character varying(128) NOT NULL UNIQUE, -- official national identification number
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, -- full primary residential address
contact_email character varying(128) UNIQUE,
contact_phone character varying(32),
registration_date timestamp NOT NULL, -- when the citizen profile was created
is_verified boolean DEFAULT false, -- whether identity has been officially verified
PRIMARY KEY (citizen_id)
)
CREATE 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) )
CREATE TABLE government_services.services (
service_id character varying(64) NOT NULL, -- unique identifier for the service
agency_id character varying(64) NOT NULL, -- FK to agencies table
service_name character varying(255) NOT NULL, -- name of the service (e.g., Driver's License Renewal)
description text,
category character varying(100), -- e.g., Licensing, Benefits, Taxation, Permits
eligibility_criteria text, -- description of who is eligible
standard_fee numeric(10, 2) DEFAULT 0.00, -- typical fee for the service
average_processing_time_days integer, -- estimated processing time
is_active boolean DEFAULT true, -- whether the service is currently offered
online_application_url character varying(255),
PRIMARY KEY (service_id)
)
CREATE TABLE government_services.applications (
application_id character varying(64) NOT NULL, -- unique identifier for the application
citizen_id character varying(64) NOT NULL, -- FK to citizens table
service_id character varying(64) NOT NULL, -- FK to services table
submitted_at timestamp NOT NULL, -- time the application was submitted
status character varying(50) NOT NULL, -- e.g., Submitted, Processing, Approved, Rejected, Pending Info
last_updated_at timestamp NOT NULL, -- time the status or details last changed
assigned_employee_id character varying(64), -- FK to employees table (optional)
decision_date date, -- date when a final decision was made
notes text, -- internal notes or citizen-provided comments
reference_number character varying(100) UNIQUE, -- publicly visible reference number
PRIMARY KEY (application_id)
)
CREATE 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 )
CREATE 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 )
CREATE TABLE government_services.employees (
employee_id character varying(64) NOT NULL, -- unique identifier for the government employee
agency_id character varying(64) NOT NULL, -- FK to agencies table
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, -- null if currently employed
access_level character varying(50), -- Role or permission level
manager_employee_id character varying(64), -- FK to self for reporting structure
PRIMARY KEY (employee_id)
)
CREATE 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) )
| [
{
"role": "user",
"content": "List the first name and last name of employees who were hired in the year 2023, along with the name of the agency they work for.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT e.first_name, e.last_name, a.agency_name FROM government_services.employee... |
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.
##Table Structure
CREATE 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 )
CREATE 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 )
CREATE TABLE healthcare.medical_records ( record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, appointment_id character varying(64) UNIQUE, doctor_id character varying(64) NOT NULL, record_date timestamp with time zone NOT NULL, chief_complaint text, present_illness_history text, past_medical_history text, physical_examination_notes text, assessment text, treatment_plan text, vitals jsonb, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (record_id) )
CREATE TABLE healthcare.diagnoses ( diagnosis_id text PRIMARY KEY, record_id text, patient_id text, doctor_id text, diagnosis_code text, code_type text, description text, diagnosis_date date, status text, is_chronic boolean )
CREATE 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) )
CREATE 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) )
CREATE TABLE healthcare.patient_insurance (
patient_insurance_id character varying(64) NOT NULL, -- unique identifier for this patient-plan link
patient_id character varying(64) NOT NULL, -- FK to patients table
plan_id character varying(64) NOT NULL, -- FK to insurance_plans table
policy_number character varying(100) NOT NULL, -- patient's policy number
group_number character varying(100), -- group number, if applicable
subscriber_name character varying(200), -- name of the primary policy holder
effective_date date NOT NULL, -- date the coverage begins
expiration_date date, -- date the coverage ends (if known)
is_primary boolean NOT NULL DEFAULT true, -- indicates if this is the primary insurance
PRIMARY KEY (patient_insurance_id),
UNIQUE (patient_id, plan_id, policy_number) -- ensure a patient doesn't have the same policy twice
)
| [
{
"role": "user",
"content": "Show me all male patients who have received more than one prescription, including their full name, date of birth, and the total number of prescriptions.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT p.patient_id, p.first_name, p.last_name, p.date_of... |
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.
##Table Structure
CREATE 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 )
CREATE 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 )
CREATE 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 )
CREATE 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 )
| [
{
"role": "user",
"content": "Show me all claims with police reports that were handled by agents hired in the last 2 years, along with the agent's full name and agency.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT c.claim_id, c.policy_id, c.incident_date, c.police_report_number... |
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.
##Table Structure
CREATE 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 )
| [
{
"role": "user",
"content": "Count the total number of distinct specialties listed in the doctors table.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT count(DISTINCT specialty) FROM healthcare.doctors;",
"sql": null
},
{
"role": "user",
"content": "Show the lice... |
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.
##Table Structure
CREATE 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 )
CREATE 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 )
CREATE 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 )
CREATE 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 )
CREATE 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 )
CREATE 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 )
| [
{
"role": "user",
"content": "Show the full names and contact emails of all citizens who have made a payment for an application that is currently in 'Pending' status.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT DISTINCT c.first_name || ' ' || c.last_name AS full_name, c.contac... |
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.
##Table Structure
CREATE TABLE insurance.customers ( customer_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, ssn_hash character varying(128), address_line1 character varying(255) NOT NULL, address_line2 character varying(255), city character varying(100) NOT NULL, state character varying(50) NOT NULL, zip_code character varying(20) NOT NULL, country character varying(50) NOT NULL DEFAULT 'USA', phone_number character varying(30), email character varying(128) UNIQUE, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, updated_at timestamp, status character varying(20) NOT NULL DEFAULT 'Active', PRIMARY KEY (customer_id) )
CREATE 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) )
CREATE 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) )
CREATE 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) )
CREATE TABLE insurance.premium_payments ( payment_id character varying(64) NOT NULL, policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, payment_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, amount_paid numeric(12, 2) NOT NULL, payment_method character varying(50), transaction_reference character varying(128) UNIQUE, due_date date, payment_period_start date, payment_period_end date, status character varying(30) NOT NULL DEFAULT 'Completed', PRIMARY KEY (payment_id) )
CREATE 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) )
| [
{
"role": "user",
"content": "Count the number of premium payments that have a null payment method.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT COUNT(*) AS null_payment_method_count\nFROM insurance.premium_payments\nWHERE payment_method IS NULL;",
"sql": null
},
{
... |
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.
##Table Structure
CREATE 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 )
| [
{
"role": "user",
"content": "Show all room types that offer 'WiFi' in their amenities.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT room_type_id, property_id, type_name, amenities FROM hospitality_technology.room_types WHERE amenities LIKE '%WiFi%';",
"sql": null
},
{
... |
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.
##Table Structure
CREATE 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 )
CREATE TABLE social_media.posts ( post_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, content text, media_url text, media_type character varying(20), created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, visibility character varying(20) NOT NULL DEFAULT 'public', location_lat numeric(9,6), location_lon numeric(9,6), PRIMARY KEY (post_id) )
CREATE TABLE social_media.follows ( follow_id text PRIMARY KEY, follower_user_id text, following_user_id text, created_at timestamp )
CREATE TABLE social_media.post_hashtags (
post_hashtag_id character varying(64) NOT NULL, -- unique identifier for the post-hashtag link
post_id character varying(64) NOT NULL, -- identifier of the post (FK to posts.post_id)
hashtag_id character varying(64) NOT NULL, -- identifier of the hashtag (FK to hashtags.hashtag_id)
PRIMARY KEY (post_hashtag_id),
CONSTRAINT unique_post_hashtag UNIQUE (post_id, hashtag_id) -- prevent duplicate tags on a post
)
CREATE TABLE social_media.conversation_participants ( participant_id text PRIMARY KEY, conversation_id text, user_id text, joined_at timestamp, last_read_at timestamp )
| [
{
"role": "user",
"content": "List the usernames and email addresses of users who have published posts with media_type 'video', along with the creation time of each post.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT u.username, u.email, p.created_at\nFROM social_media.users u\n... |
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.
##Table Structure
CREATE 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 )
CREATE 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 )
CREATE 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 )
CREATE 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 )
CREATE 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 )
CREATE 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 )
CREATE 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 )
CREATE 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 )
CREATE 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 )
| [
{
"role": "user",
"content": "Show me all service orders for spa services in the last month, including the guest name and staff who delivered the service.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT so.order_id, g.first_name, g.last_name, s.service_name, st.first_name AS staff... |
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.
##Table Structure
// Use Hashes for platform details. Key format: platform:<platform_id>
// 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
// To link platforms to stations (optional):
// SADD station:station_xyz:platforms platform:plat_123 platform:plat_456
// Use Hashes for train details. Key format: train:<train_id>
// HSET train:train_789 train_id "train_789" train_number "Acela 2151" model "Siemens Velaro" ... status "Active" ...
// To find train by train_number (optional index):
// SET train_number:"Acela 2151" train:train_789
// Use Hashes for car details. Key format: car:<car_id>
// 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"
// To link cars to trains (optional):
// SADD train:train_789:cars car:car_abc car:car_def
// Use Hashes for details. Key format: route_station:<route_station_id>
// HSET route_station:rs_ne_1 route_station_id "rs_ne_1" route_id "route_ne_corr" station_id "station_bos" sequence_order 1 ...
// To find stops for a route, use a Sorted Set (score by sequence_order):
// ZADD route:route_ne_corr:stops 1 route_station:rs_ne_1
// ZADD route:route_ne_corr:stops 2 route_station:rs_ne_2
// Use Hashes for schedule details. Key format: schedule:<schedule_id>
// 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"
// Use Hashes for details. Key format: schedule_stop:<stop_id>
// HSET schedule_stop:stop_sched1122_1 stop_id "stop_sched1122_1" schedule_id "sched_1122" station_id "station_bos" ...
// To find stops for a schedule, use a Sorted Set (score by sequence_order):
// ZADD schedule:sched_1122:stops 1 schedule_stop:stop_sched1122_1
// ZADD schedule:sched_1122:stops 2 schedule_stop:stop_sched1122_2
// Use Hashes for passenger details. Key format: passenger:<passenger_id>
// HSET passenger:pass_pqr passenger_id "pass_pqr" first_name "Alice" last_name "Smith" email "alice.smith@example.com" ...
// To find passenger by email (optional index):
// SET passenger_email:"alice.smith@example.com" passenger:pass_pqr
// Use Hashes for booking details. Key format: booking:<booking_id>
// HSET booking:book_zyx booking_id "book_zyx" passenger_id "pass_pqr" schedule_id "sched_1122" ... status "Confirmed" ...
// To link bookings to passengers/schedules (optional):
// SADD passenger:pass_pqr:bookings booking:book_zyx
// SADD schedule:sched_1122:bookings booking:book_zyx
// Use Hashes for ticket details. Key format: ticket:<ticket_id>
// HSET ticket:tkt_1a2b ticket_id "tkt_1a2b" booking_id "book_zyx" car_id "car_abc" seat_number "12A" ... is_checked_in 0 ...
// To link tickets to bookings (optional):
// SADD booking:book_zyx:tickets ticket:tkt_1a2b
// Use Hashes for staff details. Key format: staff:<staff_id>
// HSET staff:staff_mno staff_id "staff_mno" first_name "Bob" ... employee_number "E12345" ... is_active 1
// To find staff by employee number (optional index):
// SET staff_employee_number:"E12345" staff:staff_mno
// Use Hashes for maintenance record details. Key format: maintenance_record:<record_id>
// HSET maintenance_record:maint_rec_001 record_id "maint_rec_001" asset_id "train_789" asset_type "Train" ... status "Completed"
// To link records to assets (optional):
// SADD train:train_789:maintenance maintenance_record:maint_rec_001
// SADD platform:plat_123:maintenance maintenance_record:maint_rec_002
| [
{
"role": "user",
"content": "Can you help me retrieve the details of all schedules for a specific train with train_id 'train_789', including the route and stops information?",
"sql": null
},
{
"role": "assistant",
"content": "HGETALL train:train_789\nSMEMBERS schedule:sched_*:train:train_78... |
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.
##Table Structure
CREATE 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 )
| [
{
"role": "user",
"content": "Can you show me all user IDs that have both email and push notifications disabled, along with whether their profile is set to private?",
"sql": null
},
{
"role": "assistant",
"content": "SELECT user_id, private_profile FROM social_media.user_settings WHERE email... |
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.
##Table Structure
CREATE 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 )
| [
{
"role": "user",
"content": "How many insurance policies does each subscriber have? Please display the subscriber name and policy count.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT subscriber_name, COUNT(*) AS policy_count FROM healthcare.patient_insurance GROUP BY subscriber... |
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.
##Table Structure
CREATE TABLE hospitality_technology.guests ( guest_id text PRIMARY KEY, first_name text, last_name text, email text, phone_number text, date_of_birth date, address_line1 text, city text, state_province text, postal_code text, country_code text, preferences text, loyalty_member_id text, communication_consent boolean, created_at timestamp, updated_at timestamp )
| [
{
"role": "user",
"content": "Retrieve the first name, last name, and email for all guests.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT first_name, last_name, email FROM hospitality_technology.guests;",
"sql": null
},
{
"role": "user",
"content": "Can you also ... |
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.
##Table Structure
CREATE TABLE smart_money_token_inflow ( token_address character varying(100) NOT NULL, -- the token's address token_symbol character varying(100), -- the tokens's symbol token_amount numeric(38,2), -- the absolute value of the amount if user bought minus the amount user sold of this token usd_value numeric(38,2), -- the absolute usd value of the bought token minus sold token avg_price numeric(38,6), -- the average cost price of user spent on this token type int, -- the direction of the trade on this token. 1 means buying, 2 means selling address_amount integer, -- the amount of the user bought this token narrative character varying(100), -- the category or narrative of the token chain character varying(100), -- the chain that the token resides ,PRIMARY KEY (token_address, chain) )
| [
{
"role": "user",
"content": "For each chain, show the total token_amount and usd_value for selling transactions (type=2).",
"sql": null
},
{
"role": "assistant",
"content": "SELECT chain, SUM(token_amount) AS total_sold_amount, SUM(usd_value) AS total_sold_usd_value\nFROM smart_money_token_... |
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.
##Table Structure
CREATE TABLE train_station_management.train_cars (
car_id character varying(64) NOT NULL, -- Unique identifier for the train car
train_id character varying(64) NOT NULL, -- Foreign key referencing trains
car_number character varying(10) NOT NULL, -- Identifier of the car within the train set
car_type character varying(64) NOT NULL, -- e.g., Locomotive, Passenger, Sleeper, Dining, Baggage
class character varying(32), -- e.g., First, Business, Economy (null for non-passenger cars)
capacity integer, -- Passenger capacity of this specific car (null for non-passenger cars)
features text, -- Comma-separated list of features (e.g., 'WiFi', 'Power Outlet', 'Accessible Restroom')
PRIMARY KEY (car_id),
FOREIGN KEY (train_id) REFERENCES train_station_management.trains(train_id)
)
CREATE TABLE train_station_management.routes (
route_id character varying(64) NOT NULL, -- Unique identifier for the route
route_name character varying(128) NOT NULL, -- Name of the route (e.g., 'Northeast Corridor')
description text, -- Description of the route
origin_station_id character varying(64) NOT NULL, -- Starting station
destination_station_id character varying(64) NOT NULL, -- Final station
is_active boolean NOT NULL DEFAULT true, -- Is the route currently operational?
PRIMARY KEY (route_id),
FOREIGN KEY (origin_station_id) REFERENCES train_station_management.stations(station_id),
FOREIGN KEY (destination_station_id) REFERENCES train_station_management.stations(station_id)
)
CREATE TABLE train_station_management.tickets (
ticket_id character varying(64) NOT NULL, -- Unique identifier for the ticket
booking_id character varying(64) NOT NULL, -- Foreign key referencing the booking
car_id character varying(64) NOT NULL, -- Foreign key referencing the train car
seat_number character varying(10), -- Assigned seat number (e.g., '12A')
ticket_type character varying(32) NOT NULL DEFAULT 'Adult', -- e.g., Adult, Child, Senior, Student
price numeric(10, 2) NOT NULL, -- Price of this specific ticket
is_checked_in boolean NOT NULL DEFAULT false, -- Has the passenger checked in with this ticket?
qr_code_data text, -- Data for generating a QR code for the ticket
PRIMARY KEY (ticket_id),
FOREIGN KEY (booking_id) REFERENCES train_station_management.bookings(booking_id),
FOREIGN KEY (car_id) REFERENCES train_station_management.train_cars(car_id)
)
| [
{
"role": "user",
"content": "Can you help me find the total passenger capacity for each train car on a specific route with route_id 'RT123'?",
"sql": null
},
{
"role": "assistant",
"content": "SELECT tc.train_id, tc.car_id, tc.car_number, tc.capacity\nFROM train_station_management.train_car... |
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.
##Table Structure
CREATE TABLE web3.contracts ( contract_id.text, address.text, abi.text, bytecode.text, deployer_address.text, deployed_at.timestamp, network_id.text, status.text )
CREATE TABLE web3.events (
event_id character varying(64) NOT NULL, -- unique identifier for the event
contract_id character varying(64) NOT NULL, -- identifier of the contract emitting the event
event_name character varying(128) NOT NULL, -- name of the event
data text NOT NULL, -- data payload of the event
emitted_at timestamp NOT NULL, -- time when the event was emitted
transaction_id character varying(64) NOT NULL, -- identifier of the transaction that triggered the event
log_index integer NOT NULL, -- index of the event log in the transaction
PRIMARY KEY (event_id)
)
CREATE TABLE web3.tokens ( token_id text PRIMARY KEY, contract_address text, token_name text, token_symbol text, decimals int, total_supply numeric )
CREATE TABLE web3.wallets ( wallet_id text, user_id text, address text, private_key text, created_at timestamp )
CREATE TABLE web3.users ( user_id text, username text, email text, password_hash text, created_at timestamp )
| [
{
"role": "user",
"content": "Count the number of tokens for each contract address.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT contract_address, COUNT(*) AS token_count FROM web3.tokens GROUP BY contract_address;",
"sql": null
},
{
"role": "user",
"content": "... |
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.
##Table Structure
CREATE 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 )
| [
{
"role": "user",
"content": "I want to retrieve the agent ID, first and last name, along with their manager's contact email and phone number.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT a.agent_id,\n a.first_name || ' ' || a.last_name AS agent_name,\n m.contact_em... |
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.
##Table Structure
CREATE TABLE healthcare.medical_records (
record_id character varying(64) NOT NULL, -- unique identifier for the medical record entry
patient_id character varying(64) NOT NULL, -- FK to patients table
appointment_id character varying(64) UNIQUE, -- FK to appointments table (can be null if record not tied to specific appt)
doctor_id character varying(64) NOT NULL, -- FK to doctors table (doctor creating the record)
record_date timestamp with time zone NOT NULL, -- date the record/observation was made
chief_complaint text, -- patient's primary reason for visit
present_illness_history text, -- detailed history of the current issue
past_medical_history text, -- relevant past conditions/surgeries
physical_examination_notes text, -- findings from the physical exam
assessment text, -- doctor's assessment/diagnosis summary
treatment_plan text, -- planned course of action
vitals jsonb, -- store vitals like BP, HR, Temp as structured JSON
created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,
PRIMARY KEY (record_id)
)
| [
{
"role": "user",
"content": "List each patient's first and last medical record entries, showing patient_id, earliest_record_id, earliest_record_date, latest_record_id, and latest_record_date.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT\n fl.patient_id,\n fr.record_id AS... |
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.
##Table Structure
CREATE 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) )
CREATE 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) )
CREATE TABLE government_services.services ( service_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, service_name character varying(255) NOT NULL, description text, category character varying(100), eligibility_criteria text, standard_fee numeric(10, 2) DEFAULT 0.00, average_processing_time_days integer, is_active boolean DEFAULT true, online_application_url character varying(255), PRIMARY KEY (service_id) )
CREATE TABLE government_services.applications ( application_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, service_id character varying(64) NOT NULL, submitted_at timestamp NOT NULL, status character varying(50) NOT NULL, last_updated_at timestamp NOT NULL, assigned_employee_id character varying(64), decision_date date, notes text, reference_number character varying(100) UNIQUE, PRIMARY KEY (application_id) )
CREATE 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) )
CREATE 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) )
CREATE 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) )
CREATE 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) )
CREATE 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) )
| [
{
"role": "user",
"content": "List the first and last names of citizens along with the reference numbers of the applications they have submitted.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT T1.first_name , T1.last_name , T2.reference_number FROM government_services.citizens ... |
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.
##Table Structure
CREATE TABLE web3.tokens (
token_id character varying(64) NOT NULL, -- unique identifier for the token
contract_address character varying(128) NOT NULL, -- address of the token contract
token_name character varying(128) NOT NULL, -- name of the token
token_symbol character varying(32) NOT NULL, -- symbol of the token
decimals integer NOT NULL, -- number of decimals for the token
total_supply numeric(38,14) NOT NULL, -- total supply of the token
PRIMARY KEY (token_id)
)
| [
{
"role": "user",
"content": "Count how many tokens exist for each contract_address.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT contract_address,\n COUNT(*) AS token_count\nFROM web3.tokens\nGROUP BY contract_address;",
"sql": null
},
{
"role": "user",
"... |
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.
##Table Structure
CREATE 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 )
CREATE 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 )
CREATE 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 )
CREATE TABLE social_media.likes ( like_id text, user_id text, post_id text, comment_id text, created_at timestamp )
CREATE TABLE social_media.follows ( follow_id text, follower_user_id text, following_user_id text, created_at timestamp )
CREATE TABLE social_media.hashtags ( hashtag_id text, tag_name text, created_at timestamp )
CREATE 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 )
CREATE TABLE social_media.conversations ( conversation_id text, created_at timestamp, last_message_at timestamp, is_group_chat boolean, group_name text )
CREATE TABLE social_media.conversation_participants ( participant_id text, conversation_id text, user_id text, joined_at timestamp, last_read_at timestamp )
CREATE 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 )
| [
{
"role": "user",
"content": "Find the latest three posts with their content and posting users' full names.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT p.content, u.full_name, p.created_at\nFROM social_media.posts p\nJOIN social_media.users u ON p.user_id = u.user_id\nORDER BY... |
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.
##Table Structure
CREATE TABLE social_media.comments (
comment_id character varying(64) NOT NULL, -- unique identifier for the comment
post_id character varying(64) NOT NULL, -- identifier of the post being commented on (FK to posts.post_id)
user_id character varying(64) NOT NULL, -- identifier of the user who made the comment (FK to users.user_id)
parent_comment_id character varying(64), -- identifier of the parent comment if it's a reply (FK to comments.comment_id)
content text NOT NULL, -- textual content of the comment
created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of comment creation
updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last comment edit
PRIMARY KEY (comment_id)
)
CREATE TABLE social_media.conversation_participants ( participant_id text, conversation_id text, user_id text, joined_at timestamp, last_read_at timestamp )
CREATE 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 )
| [
{
"role": "user",
"content": "List the content and comment ID for all comments made by users with private profiles.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT c.comment_id, c.content FROM social_media.comments AS c JOIN social_media.user_settings AS us ON c.user_id = us.user_... |
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.
##Table Structure
CREATE 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 )
CREATE TABLE social_media.likes ( like_id.text, user_id.text, post_id.text, comment_id.text, created_at.timestamp )
CREATE TABLE social_media.hashtags ( hashtag_id text, tag_name text, created_at timestamp )
CREATE TABLE social_media.post_hashtags ( post_hashtag_id text, post_id text, hashtag_id text )
CREATE TABLE social_media.conversation_participants ( participant_id character varying(64) NOT NULL, conversation_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, joined_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, last_read_at timestamp, PRIMARY KEY (participant_id), CONSTRAINT unique_user_conversation UNIQUE (conversation_id, user_id) )
CREATE TABLE social_media.notifications (
notification_id character varying(64) NOT NULL, -- unique identifier for the notification
recipient_user_id character varying(64) NOT NULL, -- user receiving the notification (FK to users.user_id)
sender_user_id character varying(64), -- user triggering the notification (FK to users.user_id, can be null for system notifications)
notification_type character varying(30) NOT NULL, -- type of notification ('like', 'comment', 'follow', 'mention', 'message')
target_entity_id character varying(64), -- ID of the related entity (post_id, comment_id, user_id, conversation_id)
target_entity_type character varying(20), -- type of the related entity ('post', 'comment', 'user', 'conversation')
created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp notification was created
read_at timestamp, -- timestamp notification was marked as read
PRIMARY KEY (notification_id)
)
| [
{
"role": "user",
"content": "List all post IDs and the corresponding hashtag names where posts were created near latitude 40.0 and longitude -74.0.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT p.post_id, h.tag_name\nFROM social_media.posts p\nJOIN social_media.post_hashtags ph... |
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.
##Table Structure
CREATE 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 )
| [
{
"role": "user",
"content": "List the latitude and longitude coordinates for all service locations located in a city named 'Seattle'.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT latitude , longitude FROM government_services.service_locations WHERE city = 'Seattle'",
"sql... |
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.
##Table Structure
CREATE 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 )
CREATE 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 )
| [
{
"role": "user",
"content": "Retrieve the policy_number, start_date, end_date, premium_amount, and corresponding product_name for policies with a coverage_limit greater than 500000.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT p.policy_number, p.start_date, p.end_date, p.premi... |
You are an expert in writing database language and you can refuse the user's question if the question is not related to the table structure. 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.
##Table Structure
CREATE TABLE manufacturing.employees ( employee_id text PRIMARY KEY, first_name text, last_name text, job_title text, skill_certifications text, hire_date date, assigned_line_id text, employment_status text, supervisor_employee_id text )
| [
{
"role": "user",
"content": "What is the total number of vacation days taken by employee with ID 'EMP101' in the past year?",
"sql": null
},
{
"role": "assistant",
"content": "I'm sorry, but I can't provide information on the vacation days taken by an employee as this data is not stored in ... |
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.
##Table Structure
CREATE 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 )
| [
{
"role": "user",
"content": "List pairs of documents uploaded by the same user for the same claim. Return uploaded_by, claim_id, document_id AS doc1_id, and the paired document_id AS doc2_id.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT cd1.uploaded_by,\n cd1.claim_id,\n... |
End of preview. Expand
in Data Studio
No dataset card yet
- Downloads last month
- 4