# What is Named Entity Recognition? Definition & Technical Mechanics

> **Source:** [SPIDITS AI AI Glossary](https://spidits.com/ai-glossary)  
> **Category:** Natural Language Processing  
> **Canonical Citation:** [https://spidits.com/ai-glossary/named-entity-recognition](https://spidits.com/ai-glossary/named-entity-recognition)

## Definition
Named Entity Recognition (NER) is an NLP task that identifies and classifies key elements in text documents into predefined categories (such as names of people, organizations, locations, dates, or product codes).

## Architectural Mechanics & Deep Dive
Named Entity Recognition (NER) is a subtask of natural language processing that identifies and classifies key information (entities) in unstructured text into predefined categories. These categories include names of people, organizations, locations, expressions of times, quantities, and monetary values. NER is foundational for document search, information extraction, content recommendation, and question-answering systems.

## Industry Applications & Real-World Use Cases
Document data extraction, search index tagging, and customer support classification.

## Frequently Asked Questions

### How do models perform NER?
By classifying token sequences using BiLSTMs with CRFs, or prompting LLMs to return entities as structured outputs.

### What is an out-of-vocabulary entity in NER?
A brand name or location not present in the training vocabulary, which is handled using subword tokenization.

## Related Terminology
- [nlp](https://spidits.com/ai-glossary/nlp)
- [conditional-random-fields](https://spidits.com/ai-glossary/conditional-random-fields)
- [tokenizer](https://spidits.com/ai-glossary/tokenizer)

---
*From the SPIDITS AI Knowledge Base (300+ terms indexed). Explore full technical definitions: [https://spidits.com/ai-glossary](https://spidits.com/ai-glossary)*