# entity-extract-heuristic

> entity-extract-heuristic is a paid API for AI agents from intel.rallylive.ca, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-14).

Extracts named-entity candidates (people, organisations, places, years, money) from a web page using frequency-ranked heuristics, without an LLM.

## Facts

- Endpoint: GET https://intel.rallylive.ca/page/entities
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/entity-extract-heuristic-4fe545de
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_94Nc8wmmgxNdh1w2T5KNm

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 entity-extract-heuristic-4fe545de
```

Example prompt: Can you pull out all the named entities from this page — people, organisations, and places — ranked by how often they appear, without using an LLM? The URL is https://example.com/article/tech-merger.

## When to prefer this

Choose this endpoint when you need fast, low-cost named entity extraction from a web page and do not need the semantic accuracy of an LLM. It is ideal for bulk processing, cost-sensitive pipelines, or situations where deterministic, reproducible heuristic output is preferred over probabilistic AI inference. It is not suited for complex disambiguation or for pages where entity types are ambiguous without context.

## Known failure modes

- Page URL not provided or unreachable — endpoint may return an error or empty result
- Pages with little or no capitalised text yield sparse or empty entity lists
- Heavy JavaScript-rendered pages may not have text parsed correctly by the heuristic
- False positives from capitalised headings or navigation elements that are not true entities
- Monetary formats outside common patterns may be missed
- Non-English pages may produce poor heuristic results due to capitalisation differences

## How this service works

Named-entity candidates from a page without an LLM: capitalised multi-word phrases ranked by frequency, split into likely people (two or three capitalised words), organisations (with Inc, Ltd, University, Corp, Foundation...), places (after in/at/from) and other proper nouns, plus years and money mentions. $0.01 per page.

## Output

A structured response containing frequency-ranked named-entity candidates split into categories: likely people (two or three capitalised words), organisations (containing keywords like Inc, Ltd, University, Corp, Foundation), places (following prepositions like in/at/from), other proper nouns, plus year and monetary mentions — all derived via heuristics without an LLM.

## 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",
     "properties": {}
    }
   },
   "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/entity-extract-heuristic-4fe545de/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from intel.rallylive.ca](https://www.zero.xyz/host/intel.rallylive.ca/llms.txt)