Skip to content

Glossary

What is named entity recognition (NER)?

Named entity recognition finds and labels mentions in text, such as people, organisations, locations and dates, so they can be counted or linked to records.

Updated 21 Aug 2026

01

Where this one gets misread

Entity extraction looks convincing and depends entirely on the entity types it was built for and the domain it saw in training. The names, organisations and references in your material may be nothing like its expectations.

02

Questions to ask

Ask for a worked example on your own material, and the evidence needed to reproduce it.

  • Which entity types, and can you add your own?
  • How does it handle two people with the same name?
  • What is the accuracy on your document types?
  • How are corrections fed back?
03

How Marella uses the term

We use “Named entity recognition (NER)” only where a product mechanism or an evaluation method backs it up, and we say when the behaviour depends on how a deployment is configured.

  • Backed by a product mechanism or an evaluation method
  • Deployment differences flagged

What this page does not prove

  1. B1A definition is not a claim about how the product performs.
  2. B2Vendor implementations vary.
  3. B3Test the term against a representative workflow.

Test the claim on your documents

Pick a real piece of work, agree what a good answer looks like, then go through the results together.