Upload data.jsonl with huggingface_hub

data.jsonl

@@ -197,6 +197,7 @@
 {"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 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 the first name, last name, and job title of each employee, along with the job title of their manager."}, {"role": "assistant", "content": "SELECT e.first_name AS employee_first_name, e.last_name AS employee_last_name, e.job_title AS employee_job_title, m.job_title AS manager_job_title FROM government_services.employees AS e LEFT JOIN government_services.employees AS m ON e.manager_employee_id = m.employee_id;"}]}
 {"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 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) )\n", "conversations": [{"role": "user", "content": "Find pairs of active services within the same category provided by the same agency, where one service has an average processing time more than double the other's. Display the agency ID, category, the first service name and its processing time, and the second service name and its processing time."}, {"role": "assistant", "content": "SELECT s1.agency_id, s1.category, s1.service_name AS service1_name, s1.average_processing_time_days AS service1_processing_time_days, s2.service_name AS service2_name, s2.average_processing_time_days AS service2_processing_time_days FROM government_services.services AS s1 JOIN government_services.services AS s2 ON s1.agency_id = s2.agency_id AND s1.category = s2.category AND s1.service_id < s2.service_id WHERE s1.is_active = TRUE AND s2.is_active = TRUE AND s1.average_processing_time_days IS NOT NULL AND s2.average_processing_time_days IS NOT NULL AND (s1.average_processing_time_days > 2 * s2.average_processing_time_days OR s2.average_processing_time_days > 2 * s1.average_processing_time_days);"}]}
 {"system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nCREATE TABLE government_services.services (\n    service_id character varying(64) NOT NULL, -- unique identifier for the service\n    agency_id character varying(64) NOT NULL, -- FK to agencies table\n    service_name character varying(255) NOT NULL, -- name of the service (e.g., Driver's License Renewal)\n    description text,\n    category character varying(100), -- e.g., Licensing, Benefits, Taxation, Permits\n    eligibility_criteria text, -- description of who is eligible\n    standard_fee numeric(10, 2) DEFAULT 0.00, -- typical fee for the service\n    average_processing_time_days integer, -- estimated processing time\n    is_active boolean DEFAULT true, -- whether the service is currently offered\n    online_application_url character varying(255),\n    PRIMARY KEY (service_id)\n)\nCREATE TABLE government_services.service_locations (\n    location_id character varying(64) NOT NULL, -- unique identifier for the physical location\n    agency_id character varying(64) NOT NULL, -- FK to agencies table\n    location_name character varying(200), -- e.g., Downtown DMV Office\n    address text NOT NULL,\n    city character varying(100),\n    state character varying(50),\n    postal_code character varying(20),\n    latitude numeric(9, 6),\n    longitude numeric(9, 6),\n    operating_hours text, -- description of opening times\n    contact_phone character varying(32),\n    is_accessible boolean, -- accessibility information (e.g., wheelchair access)\n    PRIMARY KEY (location_id)\n)\n", "conversations": [{"role": "user", "content": "List the service name, category, and standard fee for all services offered by agencies that have at least one accessible service location in the state of 'California'."}, {"role": "assistant", "content": "SELECT DISTINCT T1.service_name, T1.category, T1.standard_fee FROM government_services.services AS T1 JOIN government_services.service_locations AS T2 ON T1.agency_id = T2.agency_id WHERE T2.is_accessible = TRUE AND T2.state = 'California';"}]}
+{"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 government_services.agencies ( agency_id character varying(64) NOT NULL, agency_name character varying(255) NOT NULL, jurisdiction_level character varying(50) NOT NULL, primary_contact_email character varying(128), main_phone_number character varying(32), website_url character varying(255), established_date date, parent_agency_id character varying(64), PRIMARY KEY (agency_id) )\nCREATE TABLE government_services.services (\n    service_id character varying(64) NOT NULL, -- unique identifier for the service\n    agency_id character varying(64) NOT NULL, -- FK to agencies table\n    service_name character varying(255) NOT NULL, -- name of the service (e.g., Driver's License Renewal)\n    description text,\n    category character varying(100), -- e.g., Licensing, Benefits, Taxation, Permits\n    eligibility_criteria text, -- description of who is eligible\n    standard_fee numeric(10, 2) DEFAULT 0.00, -- typical fee for the service\n    average_processing_time_days integer, -- estimated processing time\n    is_active boolean DEFAULT true, -- whether the service is currently offered\n    online_application_url character varying(255),\n    PRIMARY KEY (service_id)\n)\nCREATE TABLE government_services.applications (\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": "Show me all upcoming appointments in July 2024, the citizen's full name, the name of the service, and the agency responsible for the service."}, {"role": "assistant", "content": "SELECT a.appointment_id, a.scheduled_start_time, c.first_name || ' ' || c.last_name AS citizen_full_name, s.service_name, ag.agency_name\nFROM government_services.appointments a\nJOIN government_services.citizens c ON a.citizen_id = c.citizen_id\nJOIN government_services.services s ON a.service_id = s.service_id\nJOIN government_services.agencies ag ON s.agency_id = ag.agency_id\nWHERE a.scheduled_start_time >= '2024-07-01' AND a.scheduled_start_time < '2024-08-01'\nORDER BY a.scheduled_start_time ASC;"}, {"role": "user", "content": "Could you also include the status of each appointment and only show those which are still 'Scheduled'?"}, {"role": "assistant", "content": "SELECT a.appointment_id, a.scheduled_start_time, c.first_name || ' ' || c.last_name AS citizen_full_name, s.service_name, ag.agency_name, a.status\nFROM government_services.appointments a\nJOIN government_services.citizens c ON a.citizen_id = c.citizen_id\nJOIN government_services.services s ON a.service_id = s.service_id\nJOIN government_services.agencies ag ON s.agency_id = ag.agency_id\nWHERE a.scheduled_start_time >= '2024-07-01' AND a.scheduled_start_time < '2024-08-01'\n  AND a.status = 'Scheduled'\nORDER BY a.scheduled_start_time ASC;"}]}
 {"system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nCREATE TABLE government_services.citizens (\n    citizen_id character varying(64) NOT NULL,  -- unique identifier for the citizen\n    national_id_number character varying(128) NOT NULL UNIQUE, -- official national identification number\n    first_name character varying(100) NOT NULL,\n    last_name character varying(100) NOT NULL,\n    date_of_birth date NOT NULL,\n    gender character varying(20),\n    primary_address text NOT NULL, -- full primary residential address\n    contact_email character varying(128) UNIQUE,\n    contact_phone character varying(32),\n    registration_date timestamp NOT NULL, -- when the citizen profile was created\n    is_verified boolean DEFAULT false, -- whether identity has been officially verified\n    PRIMARY KEY (citizen_id)\n)\nCREATE TABLE government_services.agencies ( agency_id 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.documents ( document_id text, application_id text, citizen_id text, document_type text, file_reference text, upload_timestamp timestamp, expiry_date date, verification_status text, verified_by_employee_id text, verification_timestamp timestamp )\n", "conversations": [{"role": "user", "content": "List agency_id, agency_name, and main_phone_number for agencies that do not have a main phone number specified."}, {"role": "assistant", "content": "SELECT agency_id, agency_name, main_phone_number\nFROM government_services.agencies\nWHERE main_phone_number IS NULL;"}]}
 {"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 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.routes ( route_id text, route_number text, description text, origin_location_id text, destination_location_id text, distance_km numeric, estimated_duration_minutes integer, type text )\nCREATE TABLE transportation.fuel_logs ( fuel_log_id.text, vehicle_id.text, trip_id.text, log_timestamp.timestamp, fuel_type.text, quantity.numeric, unit.text, cost_per_unit.numeric, total_cost.numeric, odometer_reading.integer, location_id.text )\nCREATE TABLE transportation.passengers ( passenger_id.text, first_name.text, last_name.text, email.text, phone_number.text, date_of_birth.date, loyalty_program_id.text, created_at.timestamp )\n", "conversations": [{"role": "user", "content": "Give me a list of all passengers with an email address on file, showing their first name, last name, and the date their record was created."}, {"role": "assistant", "content": "SELECT first_name, last_name, created_at\nFROM transportation.passengers\nWHERE email IS NOT NULL;"}, {"role": "user", "content": "Narrow the results to only include passengers who joined in 2022."}, {"role": "assistant", "content": "SELECT first_name, last_name, created_at\nFROM transportation.passengers\nWHERE email IS NOT NULL AND EXTRACT(YEAR FROM created_at) = 2022;"}]}
 {"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 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": "What are the average and maximum fare amounts for each booking status?"}, {"role": "assistant", "content": "SELECT status, AVG(fare) AS avg_fare, MAX(fare) AS max_fare\nFROM transportation.bookings\nGROUP BY status;"}, {"role": "user", "content": "Only include statuses where the average fare is greater than 50."}, {"role": "assistant", "content": "SELECT status, AVG(fare) AS avg_fare, MAX(fare) AS max_fare\nFROM transportation.bookings\nGROUP BY status\nHAVING AVG(fare) > 50;"}]}
@@ -242,9 +243,8 @@
 {"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 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.routes ( route_id.text, route_number.text, description.text, origin_location_id.text, destination_location_id.text, distance_km.numeric, estimated_duration_minutes.integer, type.text )\nCREATE TABLE transportation.trips ( trip_id.text, route_id.text, vehicle_id.text, driver_id.text, scheduled_departure.timestamp, actual_departure.timestamp, scheduled_arrival.timestamp, actual_arrival.timestamp, origin_location_id.text, destination_location_id.text, status.text, passenger_count.integer, cargo_manifest_id.text )\nCREATE TABLE transportation.maintenance_logs ( log_id.text, vehicle_id.text, service_date.date, odometer_reading.integer, service_type.text, description.text, cost.numeric, mechanic_name.text, next_service_due_date.date )\nCREATE TABLE transportation.fuel_logs ( fuel_log_id.text, vehicle_id.text, trip_id.text, log_timestamp.timestamp, fuel_type.text, quantity.numeric, unit.text, cost_per_unit.numeric, total_cost.numeric, odometer_reading.integer, location_id.text )\nCREATE TABLE transportation.passengers ( passenger_id.text, first_name.text, last_name.text, email.text, phone_number.text, date_of_birth.date, loyalty_program_id.text, created_at.timestamp )\nCREATE TABLE transportation.bookings ( booking_id.text, passenger_id.text, trip_id.text, seat_number.text, booking_time.timestamp, status.text, fare.numeric, payment_transaction_id.text, special_requests.text )\n", "conversations": [{"role": "user", "content": "Show the vehicle ID and the total number of fuel logs recorded for each vehicle."}, {"role": "assistant", "content": "SELECT vehicle_id , count(*) FROM transportation.fuel_logs GROUP BY vehicle_id"}, {"role": "user", "content": "Filter this list to only show vehicles with more than 5 fuel log entries."}, {"role": "assistant", "content": "SELECT vehicle_id , count(*) FROM transportation.fuel_logs GROUP BY vehicle_id HAVING count(*) > 5"}]}
 {"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 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": "List all partners who have provided a phone number, showing their full name and email."}, {"role": "assistant", "content": "SELECT first_name, last_name, email FROM legal_services.lawyers WHERE is_partner = TRUE AND phone IS NOT NULL;"}, {"role": "user", "content": "Okay, now only include those partners hired between 2020-01-01 and 2022-12-31."}, {"role": "assistant", "content": "SELECT first_name, last_name, email FROM legal_services.lawyers WHERE is_partner = TRUE AND phone IS NOT NULL AND hire_date BETWEEN '2020-01-01' AND '2022-12-31';"}, {"role": "user", "content": "Can you also add their specialization to the output?"}, {"role": "assistant", "content": "SELECT first_name, last_name, email, specialization FROM legal_services.lawyers WHERE is_partner = TRUE AND phone IS NOT NULL AND hire_date BETWEEN '2020-01-01' AND '2022-12-31';"}, {"role": "user", "content": "Finally, order the results by specialization in ascending order, then by last name."}, {"role": "assistant", "content": "SELECT first_name, last_name, email, specialization FROM legal_services.lawyers WHERE is_partner = TRUE AND phone IS NOT NULL AND hire_date BETWEEN '2020-01-01' AND '2022-12-31' ORDER BY specialization ASC, last_name ASC;"}]}
 {"system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nCREATE TABLE hospitality_technology.staff ( staff_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, position character varying(100) NOT NULL, work_email character varying(255) UNIQUE, work_phone character varying(30), hire_date date NOT NULL, termination_date date, is_active boolean NOT NULL DEFAULT true, access_level integer NOT NULL, manager_id character varying(64), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (staff_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (manager_id) REFERENCES hospitality_technology.staff(staff_id) )\n", "conversations": [{"role": "user", "content": "Show me the email addresses and hire dates for all staff who have a manager."}, {"role": "assistant", "content": "SELECT work_email, hire_date\nFROM hospitality_technology.staff\nWHERE manager_id IS NOT NULL;"}, {"role": "user", "content": "Only include staff who were hired after January 1, 2023."}, {"role": "assistant", "content": "SELECT work_email, hire_date\nFROM hospitality_technology.staff\nWHERE manager_id IS NOT NULL AND hire_date > '2023-01-01';"}]}
-{"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 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 )\n", "conversations": [{"role": "user", "content": "Get the total number of appointments grouped by status."}, {"role": "assistant", "content": "SELECT status,\n       COUNT(*) AS appointment_count\nFROM healthcare.appointments\nGROUP BY status;"}, {"role": "user", "content": "Now filter to include only statuses with more than 50 appointments."}, {"role": "assistant", "content": "SELECT status,\n       COUNT(*) AS appointment_count\nFROM healthcare.appointments\nGROUP BY status\nHAVING COUNT(*) > 50;"}]}
 {"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 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.post_hashtags (\n    post_hashtag_id character varying(64) NOT NULL, -- unique identifier for the post-hashtag link\n    post_id character varying(64) NOT NULL, -- identifier of the post (FK to posts.post_id)\n    hashtag_id character varying(64) NOT NULL, -- identifier of the hashtag (FK to hashtags.hashtag_id)\n    PRIMARY KEY (post_hashtag_id),\n    CONSTRAINT unique_post_hashtag UNIQUE (post_id, hashtag_id) -- prevent duplicate tags on a post\n)\nCREATE TABLE social_media.messages (\n    message_id character varying(64) NOT NULL, -- unique identifier for the message\n    conversation_id character varying(64) NOT NULL, -- identifier for the conversation thread (FK to conversations.conversation_id)\n    sender_user_id character varying(64) NOT NULL, -- identifier of the sender (FK to users.user_id)\n    content text, -- textual content of the message\n    media_url text, -- URL to attached media (image/video)\n    media_type character varying(20), -- type of media ('image', 'video', null)\n    sent_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when message was sent\n    read_at timestamp, -- timestamp when message was read by recipient(s)\n    PRIMARY KEY (message_id)\n)\nCREATE TABLE social_media.conversations (\n    conversation_id character varying(64) NOT NULL, -- unique identifier for the conversation\n    created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when conversation was initiated\n    last_message_at timestamp, -- timestamp of the last message in the conversation\n    is_group_chat boolean NOT NULL DEFAULT false, -- indicates if it's a group chat or direct message\n    group_name character varying(100), -- name of the group chat (if applicable)\n    PRIMARY KEY (conversation_id)\n)\nCREATE TABLE social_media.conversation_participants (\n    participant_id character varying(64) NOT NULL, -- unique identifier for the participant entry\n    conversation_id character varying(64) NOT NULL, -- identifier of the conversation (FK to conversations.conversation_id)\n    user_id character varying(64) NOT NULL, -- identifier of the user in the conversation (FK to users.user_id)\n    joined_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when user joined the conversation\n    last_read_at timestamp, -- timestamp indicating up to when the user has read messages\n    PRIMARY KEY (participant_id),\n    CONSTRAINT unique_user_conversation UNIQUE (conversation_id, user_id) -- prevent user being added multiple times\n)\n", "conversations": [{"role": "user", "content": "List all group chats created in 2024, showing the group_name, conversation_id, and creation time."}, {"role": "assistant", "content": "SELECT conversation_id, group_name, created_at\nFROM social_media.conversations\nWHERE is_group_chat = true AND created_at >= '2024-01-01' AND created_at < '2025-01-01';"}]}
 {"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 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 character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, specialty character varying(100) NOT NULL, license_number character varying(50) UNIQUE NOT NULL, phone_number character varying(20), email character varying(128) UNIQUE, hospital_affiliation_id character varying(64), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (doctor_id) )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id character varying(64) NOT NULL, record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, doctor_id character varying(64) NOT NULL, diagnosis_code character varying(20) NOT NULL, code_type character varying(10) NOT NULL DEFAULT 'ICD-10', description text, diagnosis_date date NOT NULL, status character varying(32) NOT NULL, is_chronic boolean DEFAULT false, PRIMARY KEY (diagnosis_id) )\nCREATE TABLE healthcare.medications ( medication_id character varying(64) NOT NULL, medication_name character varying(255) NOT NULL, generic_name character varying(255), manufacturer character varying(100), ndc_code character varying(20) UNIQUE, description text, PRIMARY KEY (medication_id) )\nCREATE TABLE healthcare.insurance_plans ( plan_id character varying(64) NOT NULL, plan_name character varying(200) NOT NULL, insurance_provider character varying(100) NOT NULL, plan_type character varying(50), contact_phone character varying(20), website character varying(255), PRIMARY KEY (plan_id) )\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, plan_id character varying(64) NOT NULL, policy_number character varying(100) NOT NULL, group_number character varying(100), subscriber_name character varying(200), effective_date date NOT NULL, expiration_date date, is_primary boolean NOT NULL DEFAULT true, PRIMARY KEY (patient_insurance_id), UNIQUE (patient_id, plan_id, policy_number) )\n", "conversations": [{"role": "user", "content": "Which patients have a primary insurance policy and are subscribed to a plan provided by 'Cigna'? List patient ID, full name, policy number, plan ID, and insurance provider."}, {"role": "assistant", "content": "SELECT p.patient_id, p.first_name, p.last_name, pi.policy_number, pi.plan_id, ip.insurance_provider\nFROM healthcare.patient_insurance pi\nJOIN healthcare.patients p ON pi.patient_id = p.patient_id\nJOIN healthcare.insurance_plans ip ON pi.plan_id = ip.plan_id\nWHERE pi.is_primary = true AND ip.insurance_provider = 'Cigna';"}, {"role": "user", "content": "Additionally, only show results where the policy has not expired yet."}, {"role": "assistant", "content": "SELECT p.patient_id, p.first_name, p.last_name, pi.policy_number, pi.plan_id, ip.insurance_provider\nFROM healthcare.patient_insurance pi\nJOIN healthcare.patients p ON pi.patient_id = p.patient_id\nJOIN healthcare.insurance_plans ip ON pi.plan_id = ip.plan_id\nWHERE pi.is_primary = true AND ip.insurance_provider = 'Cigna' AND (pi.expiration_date IS NULL OR pi.expiration_date >= CURRENT_DATE);"}]}
 {"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 legal_services.clients ( client_id text, first_name text, last_name text, company_name text, email text, phone text, address text, date_registered timestamp, status text )\nCREATE TABLE legal_services.lawyers ( lawyer_id text, first_name text, last_name text, bar_number text, firm_id text, email text, phone text, specialization text, hire_date timestamp, is_partner boolean )\nCREATE TABLE legal_services.law_firms ( firm_id text, firm_name text, address text, phone text, website text, founded_date date, managing_partner_id text )\nCREATE TABLE legal_services.documents ( document_id text, case_id text, document_name text, document_type text, storage_path text, uploaded_by_lawyer_id text, upload_timestamp timestamp, version integer, description text )\nCREATE TABLE legal_services.time_entries ( entry_id text, case_id text, lawyer_id text, date_worked date, hours_spent numeric, billing_rate numeric, description text, is_billable boolean, is_billed boolean, invoice_id text, created_at timestamp )\nCREATE TABLE legal_services.appointments ( appointment_id text, client_id text, lawyer_id text, case_id text, start_time timestamp, end_time timestamp, location text, subject text, notes text, status text, created_at timestamp )\n", "conversations": [{"role": "user", "content": "I need a list showing the name of each law firm and the full name of every lawyer employed by that firm."}, {"role": "assistant", "content": "SELECT T1.firm_name, T2.first_name, T2.last_name FROM law_firms AS T1 JOIN lawyers AS T2 ON T1.firm_id = T2.firm_id;"}]}
 {"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 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": "Show me all customers (customer_id, first_name, last_name, email) who were born after 1985 (date_of_birth > '1985-12-31') and have an email address ending with '@yahoo.com', along with their city and state information."}, {"role": "assistant", "content": "SELECT customer_id, first_name, last_name, email, city, state FROM financial_services.customers WHERE date_of_birth > '1985-12-31' AND email LIKE '%@yahoo.com';"}]}
-{"system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nCREATE TABLE web3.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": "List the total value and count of transactions for each status, ordered by total value descending."}, {"role": "assistant", "content": "SELECT status, COUNT(*) AS transaction_count, SUM(value) AS total_value\nFROM web3.transactions\nGROUP BY status\nORDER BY total_value DESC;"}, {"role": "user", "content": "Actually, can you also include the average value per transaction for each status?"}, {"role": "assistant", "content": "SELECT status, COUNT(*) AS transaction_count, SUM(value) AS total_value, AVG(value) AS avg_value\nFROM web3.transactions\nGROUP BY status\nORDER BY total_value DESC;"}]}
+{"system": "You are an 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 insurance.policy_beneficiaries ( beneficiary_id text, policy_id text, customer_id text, first_name text, last_name text, relationship text, percentage_share numeric, contact_info text, added_at timestamp )\n", "conversations": [{"role": "user", "content": "List all 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 = ''"}]}