Supported Entities
While Gretel Transform will attempt to classify any arbitrary entity type, we have specifically fine-tuned GLiNER on the list of entities specified here.
We have fine-tuned GLiNER on the entity types shown in the table below, although Gretel Transform will attempt to classify any arbitrary entity type specified.
account_number
Account Number
An account number is a unique identifier for a financial account, such as a bank account or credit card.
GDPR, HIPAA, CPRA
address
Address
A physical address, including street, city, state, and / or country.
GDPR, HIPAA
api_key
API Key
An API key is a unique identifier that authenticates a user, developer, or program to an application programming interface (API).
GDPR, CPRA
bank_routing_number
Bank Routing Number
An American bank association routing number
GDPR, HIPAA, CPRA
biometric_identifier
Biometric Identifier
A biometric identifier is a unique physical characteristic of an individual used to identify them.
GDPR, HIPAA, CPRA
certificate_license_number
Certificate License Number
A unique, traceable number assigned to a certificate or license.
GDPR, HIPAA, CPRA
city
City
A city in the world.
GDPR, HIPAA, CPRA
company_name
Company Name
A company name.
coordinate
GPS Coordinate
A combination of latitude and longitude into a single tuple.
GDPR, HIPAA
country
Country
A country in the world.
credit_card_number
Credit Card Number
A credit card number is 12 to 19 digits long. It is used for payment transactions globally.
GDPR, HIPAA, CPRA
customer_id
Customer ID
A customer ID, or customer identifier, is a unique code or number that identifies a customer or entity.
cvv
Credit Card Verification Value
A CVV is a unique three or four digit number on a payment card that helps prevent fraud.
GDPR, HIPAA, CPRA
date
Date
A date. This includes most date formats, as well as the names of common world holidays.
HIPAA
date_of_birth
Date of Birth
A date of birth.
GDPR, HIPAA, CPRA
date_time
Date Time
A date and timestamp. This includes most date/time formats.
HIPAA
device_identifier
Device Identifier
A device identifier is a unique string of numbers and letters that identifies a device, such as a mobile phone or computer.
GDPR, HIPAA, CPRA
An email address identifies the mailbox that emails are sent to or from. The maximum length of the domain name is 255 characters, and the maximum length of the local-part is 64 characters.
GDPR, HIPAA, CPRA
employee_id
Employee ID
An ID number associated with an employee to identify them within their system.
first_name
First Name
A first name for a person.
GDPR, HIPAA, CPRA
health_plan_beneficiary_number
Health Plan Beneficiary Number
A health plan beneficiary number is a unique number assigned to an individual by their health insurance provider to identify them within their system.
HIPAA
ipv4
IP Address (version 4)
An Internet Protocol (IP) address for IPv4.
GDPR, HIPAA, CPRA
ipv6
IP Address (version 6)
An Internet Protocol (IP) address for IPv6.
GDPR, HIPAA, CPRA
last_name
Last Name
A last name for a person.
GDPR, HIPAA, CPRA
license_plate
License Plate Number
A license plate number used to identify a vehicle.
GDPR
medical_record_number
Medical Record Number
A medical record number is a unique identifier for a patient's medical records in a healthcare system.
HIPAA
name
Name
A full person name, which can include first names, middle names or initials, and last names.
GDPR, HIPAA, CPRA
national_id
National ID
A national identity number is a unique identifier issued by a government to track its citizens and residents.
GDPR, HIPAA, CPRA
password
Password
A password used to login to a computer network.
CPRA
phone_number
Phone Number
A telephone number.
GDPR, HIPAA, CPRA
pin
Personal Identification Number
A personal identification number (PIN) is a numerical code issued with a payment card that is required to be entered to complete various financial transactions.
GDPR
postcode
Postal Code
Postal code used by the United States Postal Service.
GDPR, HIPAA
ssn
US Social Security Number
A United States Social Security number (SSN) is a 9-digit number issued to US citizens, permanent residents, and temporary residents. The Social Security number has effectively become the United States national identification number.
GDPR, HIPAA, CPRA
state
USA State
A state in the United States of America.
GDPR
street_address
Street Address
A physical street address.
GDPR, HIPAA, CPRA
swift_bic
Business Identifier Code
A SWIFT code is the same as a Bank Identifier Code (BIC). It's a unique identification code for a particular bank. These codes are used when transferring money between banks, particularly for international wire transfers. Banks also use the codes for exchanging other messages.
GDPR, HIPAA, CPRA
tax_id
Tax ID
A Taxpayer Identification Number (TIN) is an identification number used by the Internal Revenue Service (IRS) in the administration of tax laws.
GDPR, HIPAA, CPRA
time
Time
A timestamp of a specific time of day.
unique_identifier
Unique ID
A Universally Unique Identifier (UUID).
url
URL
A Uniform Resource Locator (URL).
GDPR, HIPAA, CPRA
user_name
User Name
A username used to uniquely identify a user on a computer network.
CPRA
vehicle_identifier
Vehicle Identification Number
A VIN is composed of 17 characters (digits and capital letters) and acts as a unique identifier for a vehicle.
GDPR, CPRA
Transform supports the following transformation types for entities:
Fake: Replaces the value with synthetic data
Note that to
fakevalues, only entities supported by Faker will work
Hash: Anonymizes by converting data to a unique alphanumeric value
Normalize: Ensures data consistency by removing spaces and punctuation marks
Expression: Allows custom transformations
Null: No transformation applied
Last updated