Entity Types

The following entity types are detected by the PII and NER models.

PII Entities

Name	Description	Example
PERSON_NAME	People's names (first, last, full)	John Doe, Sarah J. Parker
NATIONAL_ID	National IDs: SSN, driver's license, passport numbers	123-45-6789
EMAIL_ADDRESS	Email addresses	john@example.com
PHONE_NUMBER	Phone numbers (landline, mobile, international)	+1-555-1234
ADDRESS	Street addresses, cities, states, ZIP codes	123 Main St, New York, NY 10001
DATE	Dates (absolute and relative)	2024-01-15
CREDIT_CARD	Credit/debit card numbers (PAN)	4111-1111-1111-1111
IBAN	International Bank Account Numbers	GB82 WEST 1234 5698 7654 32
VAT_NUMBER	Tax registration IDs (VAT, GST, EIN, ITIN)	GB123456789
USERNAME	Usernames and account identifiers	johndoe
ZIP_CODE	US ZIP codes (5 or 9 digit)	10001
LICENSE_KEY	Software license keys	XXXXX-XXXXX-XXXXX-XXXXX
API_KEY	API keys for SaaS services	sk-abc..., qa_live_xxx

NER Entities

Name	Description	Example
ORGANIZATION	Companies, agencies, institutions	Acme Corp, Stanford University
LOCATION	Geographic locations, landmarks	Eiffel Tower, Grand Canyon
GPE	Geo-political entities (countries, cities, states)	France, California, London

How Detection Works

The PII recognizer and the NER recognizer run in parallel. Results are merged, deduplicated, and sorted by position in the original text.

Specifying Entities

By default, all entity types are detected. Use the entities parameter with a comma-separated string of entity names to filter:

{
  "text": "My name is John Doe and my SSN is 123-45-6789.",
  "entities": "PERSON_NAME,NATIONAL_ID"
}

List available entities at runtime:

curl https://demo.questa-ai.online/anonymize/entities

---

Next: Custom Entities