Skip to main content

DOCUMENT ONTOLOGY

529 document types. Zero templates.

Talonic classifies every document using a 529-type ontology that spans invoices, contracts, medical records, shipping documents, financial statements, and more. Each type is recognized out of the box — no training data, no template configuration, no manual rules.

Financial & Tax53 typesSchedule K-1, Form 1099-MISC, Form W-8BEN, Form 1040, and 49 moreProcurement & Invoicing53 typesPurchase Order, Commercial Invoice, Pro Forma Invoice, Goods Receipt Note, and 49 moreTrade & Logistics53 typesBill of Lading (Ocean), Bill of Lading (Inland), Air Waybill (AWB), House Air Waybill (HAWB), and 49 moreLegal & Contracts53 typesNotarial Deed, Master Service Agreement, Statement of Work, Non-Disclosure Agreement, and 49 moreCorporate & Governance53 typesCommercial Register Extract, Certificate of Good Standing, Certificate of Incorporation, Annual Return, and 49 moreHealthcare & Life Sciences53 typesPatient Intake Form, Medical History Questionnaire, Informed Consent Form, Discharge Summary, and 49 moreManufacturing & Quality53 typesQC Inspection Form, Certificate of Analysis (CoA), Certificate of Conformance, First Article Inspection Report, and 49 moreInsurance & Claims53 typesInsurance Application, Policy Declaration Page, Insurance Policy Wording, Endorsement / Rider, and 49 moreReal Estate & Construction53 typesProperty Deed, Title Report, Land Registry Extract, Survey Plan, and 49 moreHR & Employee Records52 typesEmployment Application, Offer Letter, Employment Contract, Background Check Report, and 48 more

529 document types across 10 categories — no templates, no training, no configuration.

What is a document ontology

Talonic's ontology is a hierarchical classification of 529 enterprise document types organized across 10 categories. Each document type maps to a defined set of expected fields in the Field Registry — the structured schema that governs what data gets extracted. When a document is uploaded, Talonic classifies it against the ontology before extraction begins, ensuring the correct fields and validation rules are applied automatically.

No templates, no training

Traditional document extraction platforms require per-type templates or training data before they can process a new document format. Talonic's ontology-driven approach means every document type is recognized from day one. The Field Registry maps each type to its expected fields, confidence thresholds, and validation rules — no configuration, no manual setup, no waiting for a model to learn your documents.