Named Entity Recognition (NER) is a natural language processing technique that identifies and classifies key pieces of information in text — such as people, organisations, places, dates, and amounts.
What it means in plain English
NER pulls structured facts out of unstructured text. Given a sentence, it locates the “named entities” and labels each: this is a person, that is a company, this is a date. It effectively turns free-flowing text into organised data that software can use, which is the first step in many information-extraction tasks.
It is a foundational NLP capability used behind the scenes in search, analytics, and automation.
A simple example
Run NER on “Apple announced the iPhone in San Francisco in 2007,” and it identifies “Apple” as an organisation, “San Francisco” as a location, and “2007” as a date — extracting structured facts from an ordinary sentence.
Why it matters
NER is a workhorse of practical NLP, powering everything from resume parsing and news analysis to feeding facts into knowledge graphs. It is how AI systems find the who, what, where, and when inside large volumes of text.
Related terms
- Natural Language Processing — the field NER belongs to.
- Knowledge Graph — often built using entities from NER.
- Classification — NER classifies each entity it finds.
Frequently asked questions
What is named entity recognition?
NER is an NLP task that identifies and classifies named things in text — such as people, organisations, locations, and dates.
What is NER used for?
It powers information extraction, search, content tagging, and data organisation — anywhere you need to pull structured facts out of unstructured text.
