Named-entity recognition
Named-entity recognition is a natural language processing task that extracts names of entities from text and classifies them into categories. These entities are usually people, organizations, locations, dates, quantities, monetary values, percentages, and more.
On this page
Source content checked . English translation published 2026-10-27.
In business automation
Named-entity recognition extracts names, organizations, dates, and amounts from free text. In automation, it turns an email or inquiry into fields that can be written to a CRM, provided there is a review step when confidence is low.
Examples
These examples illustrate a possible workflow. Adapt the connections and rules to your own systems.
Extract a name and amount from a quote email
A customer's email arrives as free text. The model extracts a company name, date, and amount. If a field is missing or confidence is low, the inquiry is routed to a representative instead of being recorded as a closed deal in the system.
Relevant tools
- Hugging Face
- Pretrained models for named-entity recognition are available. Test them on your own Hebrew emails instead of assuming they will match the accuracy shown in a general example.
What to check
- An entity that looks like an amount is not necessarily the amount due. Without a rejection rule, the wrong number may be recorded.