# entity-extract-heuristic-bulk

> entity-extract-heuristic-bulk is a paid API for AI agents from intel.rallylive.ca, paid per call via x402, $0.1/call, status unknown (last checked 2026-09-14).

Extracts named-entity candidates from up to 20 URLs concurrently using heuristics (no LLM), returning results in input order with per-item error fields

## Facts

- Endpoint: GET https://intel.rallylive.ca/bulk/page/entities
- Price: $0.1/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-bulk-7889b6da
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_SL5Y6XpdLn1SubyC1aNoT

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-bulk-7889b6da
```

Example prompt: Can you extract all named entities — people, places, organizations — from these 15 URLs at once and group the results by URL? Use the heuristic bulk extractor so we don't burn LLM tokens.

## When to prefer this

Choose this endpoint when you already have a list of URLs (up to 20) and need entity extraction across all of them in a single roundtrip without the cost or latency of an LLM. It is ideal for bulk enrichment pipelines, dataset annotation, and monitoring workflows where heuristic-quality NER is sufficient and LLM inference cost must be avoided. Prefer the single /page/entities endpoint when you have only one URL or need to inspect a single result interactively.

## Known failure modes

- URL unreachable or returns non-200 status — per-item error field populated, counted in failure total
- Batch exceeds 20 URL limit — request rejected or truncated
- Malformed URL in input list — per-item error, processing continues for valid URLs
- Page content not parseable as HTML — empty entity list or error for that item
- Timeout fetching a slow URL — per-item error recorded
- Payment not fulfilled (x402) — entire request rejected before processing

## How this service works

Bulk entity extract heuristic: up to 20 urls in one call, processed concurrently, results returned in input order with a per-item error field and a count of failures. Same answer per item as the single /page/entities endpoint (Named-entity candidates from a page without an LLM). Batch enrichment for agents that hold a list. $0.01 per batch.

## Output

An ordered array of per-URL results matching the input URL order. Each item contains the named-entity candidates extracted heuristically from that page (people, organizations, locations, etc.) plus a per-item error field if that URL failed. A top-level failure count summarizes how many URLs could not be processed.

## 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-bulk-7889b6da/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)