# manylives.me Named Entity Recognition

> manylives.me Named Entity Recognition is a paid API for AI agents from manylives.me, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-13).

Extracts named entities (people, organizations, places, dates, money amounts, products) from text, each with its type and frequency count.

## Facts

- Endpoint: POST https://manylives.me/paid/text/entities?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/manylives-me-named-entity-recognition-2661c3d4
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_L_LF1ZFGups-IgLkaxRZ9

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability manylives-me-named-entity-recognition-2661c3d4 -d '<json body>'
```

Example prompt: Can you extract all the named entities from this text and tell me what type each one is and how often it appears: 'On 3 March 2026 Acme Pty Ltd in Sydney paid Jane Citizen AUD 5,000 for the Falcon X1 drone.'

## When to prefer this

Choose this endpoint when you need to identify and count specific types of named entities (people, organizations, places, dates, money, products) from arbitrary text, particularly when frequency/co-occurrence matters. It is purpose-built for NER with typed classification, unlike generic text extraction or summarization tools. Ideal for document analysis, compliance checks, or knowledge graph population where entity type and frequency are both needed.

## Known failure modes

- Text exceeds 20,000 character limit — request rejected
- Empty or whitespace-only text — may return empty entity list
- Ambiguous entities (e.g. a word that could be a person or place) may be misclassified
- Non-English or mixed-language text may reduce extraction accuracy
- Very short or context-free text may yield low-confidence or incomplete results

## How this service works

Named entities in a text: people, organisations, places, dates, money amounts, products and other notable items, each with its type and how many times it appears.

## Output

A JSON array of entity objects, each containing the entity's text (e.g. 'Acme Pty Ltd'), its semantic type (e.g. 'organisation', 'person', 'place', 'date', 'money', 'product'), and the number of times it appears in the input text.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "examples": [
    "On 3 March 2026 Acme Pty Ltd in Sydney paid Jane Citizen AUD 5,000 for the Falcon X1 drone."
   ],
   "description": "the text (required, max 20,000 chars)"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "entities": [
   {
    "text": "Acme Pty Ltd",
    "type": "organisation",
    "count": 2
   }
  ]
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/manylives-me-named-entity-recognition-2661c3d4/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from manylives.me](https://www.zero.xyz/host/manylives.me/llms.txt)