Extract named entities from text as JSON

Document intelligenceKINDA1 method

KINDA — AI can help, with a person in the loop.

1 method on the page: 1 prompt.

Use cases

Methods

Paste into a general LLM and extract people, organizations, locations, and other named entities with supporting cont…

prompt

LLMPrompt

Prompt
Copied 0
Extract named entities from the document. Return ONLY valid JSON:

{
  "entities": [
    {
      "name": "string",
      "type": "PERSON|ORGANIZATION|LOCATION|OTHER",
      "context": "short quote or sentence where it appears"
    }
  ]
}

Rules:
- Prefer types PERSON, ORGANIZATION, LOCATION; use OTHER only when needed.
- Do not invent entities not present in the text.
- Deduplicate exact same name+type pairs.

<document>
<<<paste text>>>
</document>