Place of birth
PLACE_OF_BIRTHA place explicitly linked to a person as their birthplace.
- Status
- Core
- Kind
- Entity
- Found by
- Specialised text models and contextual verification
- Token
- [PLACE_OF_BIRTH_81af3c]
- Example
- Ankara
- Default
- Replace and restore
One catalogue. Every class is listed with how it is found, how it is validated, and what its token looks like. Coverage is measured per class on your own data before go-live.
Text detection runs on CPU. With the same input, pinned release, runtime, policy and settings, core detection is repeatable without generative sampling. OCR and the optional Semantic Layer use GPU acceleration and are scoped separately.
Deterministic. A number has to pass its own validation before it counts; a labelled value that fails, for example after OCR damage, is still masked at reduced confidence.
Compact models selected, trained or adapted for specific tasks: names, organisations, addresses and places. Language and document coverage are validated for your deployment.
A purpose-trained document reader combines visual recognition with language modelling. Reads scans in Turkish, English and other languages using GPU acceleration inside your environment. Images are never forwarded; only protected text continues.
A separate model re-checks supported candidates in local context, including rows and headers, to remove false hits.
Resolves the class when layers disagree, then applies the tenant policy: replace and restore, stop, or leave readable.
Who the text is about. Core names and supported identity formats.
A place explicitly linked to a person as their birthplace.
Nationality or citizenship attributed to a person in the document.
A natural person named in the text. Adjacent titles follow the agreed span policy.
The same sensitive value reuses its token within a retained Context.
Companies and institutions named in the text.
Measured as its own slice. Tenants decide whether public institutions are masked.
Turkish Republic identity number.
A labelled number that fails its checksum, for example after OCR damage, is still masked at reduced confidence.
Turkish and foreign passport formats when a passport label is nearby.
Birth dates only. Other dates stay readable so the model can reason with them.
Turkish registration plates.
How to reach or find them.
Mobile and landline numbers, including subscriber numbers in traffic records.
Any address, including Turkish characters in the local part.
A deliverable address: street, number, district, with or without the city.
A place named on its own: a city, district, country or administrative chain. Never a postal address.
Tenants that want cities readable switch this class off.
Latitude and longitude pairs in decimal or degree notation.
Only links that identify a person, such as a profile page. Other links stay readable.
IPv4 and IPv6 addresses.
Checksums where defined; labels and context for other formats.
Central registration identifiers in supported business-document contexts.
Electronic notification addresses in supported labelled and document contexts.
Supported social-security registration identifiers, distinguished by document context.
International bank account numbers, Turkish and foreign, with or without separators, in any case.
Debit and credit card numbers.
Cards can be blocked or tokenised according to the agreed deployment policy.
Turkish tax identification numbers of companies and sole traders.
Domestic account numbers when an account label is nearby.
Customer and subscriber number formats supplied by the customer, configured and validated per deployment.
Subscriber and handset identities as they appear in traffic records.
Subscriber identity on the SIM.
SIM card serial number.
Device identity of a handset.
International and sector formats delivered for your jurisdictions. Credential rules are configured per deployment; validate the agreed scope on your documents.
Selected international identity, tax and social-security formats for the jurisdictions your organisation works in. Delivery scope and validators are agreed per deployment.
Turkish and foreign licence numbers in identity-document workflows.
Hardware addresses in telecom and network logs.
API keys, access tokens and private keys, built on established secret-detection rules. Covers the coding and chat relay.
Routing numbers, sort codes and similar domestic formats.
Patient and insurance numbers.
Wallet and exchange addresses across the major chains.
Images are never forwarded. With the agreed OCR workflow, extracted text is protected before it continues; the source image stays inside your environment.
A signature on a scanned page, photo or image attachment.
Passports, national ID cards, driving licences and other identity documents, scanned or photographed.
A recognisable face in a photo or on a scanned page.
Your own identifiers, as a first-class class.
Customer, employee, case, contract and policy formats agreed and delivered as first-class classes for the deployment.
Optional and complementary. Masks a stated disclosure about an identifiable person; generic statements pass unchanged. It only adds protection; it never removes or re-types what the core found.
The semantic layer. Finance and telecom presets are available on request. The purpose-trained semantic model judges customer-attributed values against an agreed policy; Salus places the resulting protection in the original text. It only adds protection and never unmasks or re-types a core finding. Further sector or organisation-specific policies can be added on request. Each enabled policy is validated on your documents before activation.
Customer-attributed amounts, fees, balances, limits, income, debt, payment purpose and statement rows. Public tariffs and the institution's own figures pass unchanged.
Available on request. GPU-accelerated, with scope and acceptance criteria agreed before activation. No public accuracy figure is claimed.
Subscriber-attributed data, minutes, messages, packages, own-bill amounts and usage rows. Published tariffs, catalogues and network-wide aggregates pass unchanged.
Available on request. Further sector or organisation-specific policies can be added on request and validated on your documents.
All examples are synthetic.