PII Entity Reference

An entity type is a named category of personal data that the detector looks for — an e-mail address, an IBAN, a person's name. Each card below carries the identifier you send to the API and a one-line description of what it matches. You pick which types to request, and a type only shows up in a result when it actually occurs in the scanned text.

Detection is a hybrid. Formatted identifiers match on an exact pattern and come back with a confidence of 1.0. Names, organisations and locations come from an NLP model and score lower, so a person still reads the findings. The API accepts up to 50,000 characters per call, so the scanner splits longer pages at word boundaries before sending them.

Why these categories exist: personal data is defined as any information relating to an identified or identifiable natural person, in Article 4(1) of Regulation (EU) 2016/679 — the GDPR, which has applied across the EU since 25 May 2018. Article 9(1) singles out special categories, such as health and biometric data, for stricter treatment. Article 83(5) puts a breach of the basic principles in the upper fine band, up to €20 million or 4% of worldwide annual turnover; Article 83(4) sets the lower band at €10 million or 2%. Where an AI system processes the same data, the EU AI Act — Regulation (EU) 2024/1689 — applies alongside the GDPR.