# shelf.thirdmade.net Named Entity Extraction

> shelf.thirdmade.net Named Entity Extraction is a paid API for AI agents from shelf.thirdmade.net, paid per call via x402, $0.001/call, status unknown (last checked 2026-09-14).

Extracts named entities (people, companies, and places) from arbitrary input text via a lightweight NLP probe.

## Facts

- Endpoint: GET https://shelf.thirdmade.net/probe/entity-find
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/shelf-thirdmade-net-named-entity-extraction-10ac5693
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_irr3NPAG7VQ9OpxIEqlLu

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 shelf-thirdmade-net-named-entity-extraction-10ac5693
```

Example prompt: Extract all the people, companies, and places mentioned in this text: 'Elon Musk announced that Tesla's new Gigafactory in Austin, Texas will begin production in partnership with Panasonic next quarter.'

## When to prefer this

Choose this endpoint when you need a fast, low-cost ($0.001/call) named entity extraction from arbitrary text without needing full NLP pipeline infrastructure. It is ideal for agents doing document enrichment, lead-gen prospecting, or content tagging where people, companies, and places are the primary entities of interest. Prefer this over general LLM prompting when you need structured entity output reliably and cheaply at scale.

## Known failure modes

- Empty or whitespace-only text input returns no entities
- Very short or ambiguous text may yield low-confidence or missing extractions
- Non-English text may produce degraded or empty results depending on underlying model support
- Extremely long text inputs may be truncated or cause timeout
- Misspelled or obscure proper nouns may not be recognized as entities

## How this service works

Extracts named entities (people, companies, places) from text. Wikidata resolution next iteration.

## Output

Returns a structured list of named entities found in the input text, categorized by type — persons, organizations/companies, and geographic places/locations. Each entity is identified by its surface form as it appears in the text. Wikidata resolution (canonical linking) is noted as a planned future feature.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "text"
     ],
     "properties": {
      "text": {
       "type": "string",
       "description": "Input text"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/shelf-thirdmade-net-named-entity-extraction-10ac5693/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from shelf.thirdmade.net](https://www.zero.xyz/host/shelf.thirdmade.net/llms.txt)