• PEOPLE
  • LOCATIONS
  • ORGANIZATIONS
  • HUMAN

How to extract entities from text with your AI

Connect OneAI to your agent to turn messy text into structured data. Once connected, your AI uses language pipelines to identify and isolate specific details.

Ask AI about this page

Short answer

How can I pull names and locations from my text?

Your AI uses the OneAI connector to run text through specialized language pipelines. This process isolates specific entities like people, places, and organizations from any raw input. You'll get structured lists ready for your next task.

The output categories.

Where your data lands.

The extraction process organizes your raw text into these distinct categories.

PEOPLE

Identified individuals

The AI pulls specific names of people mentioned in your text. You get a clean list of names without the surrounding fluff.

LOCATIONS

Geographic data

The pipeline finds cities, countries, and specific addresses. This turns vague descriptions into actionable location data.

ORGANIZATIONS

Company and group names

It identifies businesses, non-profits, and agencies. This helps you map out which entities are interacting in your documents.

HUMAN

Review required

The AI flags ambiguous entities that need your eyes. You decide if a specific term is a name or just a common noun.

The workflow

What your AI does when text arrives.

The AI handles the heavy lifting of scanning and categorizing your input.

  1. Text ingestion

    Your agent sends the raw, unformatted text to the connector for processing.

    run_pipeline
  2. Entity identification

    The language pipeline scans the string for patterns matching known entity types.

    run_pipeline
  3. Categorization

    The AI sorts the found entities into specific buckets like names or places.

    run_pipeline
  4. Data structuring

    The final output is formatted into a clean, readable list for your agent to use.

    run_pipeline

Try it

Copy these to start.

Use these prompts to trigger the extraction immediately.

Starting points

Swap the bracketed text for your actual content or file names.

OneAI Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_OUuZaJpMXxYZjYxd7ELA63wi1sMTV0hm1c50LuC2/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — OneAI capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "oneai-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_OUuZaJpMXxYZjYxd7ELA63wi1sMTV0hm1c50LuC2/mcp"
    }
  }
}
Copy into chat04
  • Extract all names and organizations from this email: [paste email text]

  • Run the entity extraction pipeline on the contents of [file_name.txt]

  • Find every location mentioned in this meeting transcript: [paste transcript]

  • List all the companies mentioned in this project brief: [paste brief]

  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Start here

Connect OneAI once, then ask.

Just link your account once. Your credentials stay encrypted, and you can immediately start asking your agent to process text.

Connect OneAI to your AI

FAQ

How this task behaves.

  • 01

    Can the AI extract entities from images?

    No. This connector works with raw text input provided to the pipeline.

  • 02

    Will the AI change my original text?

    No. The extraction process only reads your text to find entities; it does not modify your source files.

  • 03

    Does it work with any text file?

    Yes, as long as you can paste the text or provide the content to your agent.

  • 04

    Can the AI automatically save these names to a spreadsheet?

    No. The AI extracts the data, but you must use a different tool or manual step to move that data into a spreadsheet.

  • 05

    How accurate is the extraction?

    The pipeline is highly precise, but you should always review the 'needs human' output for ambiguous terms.

  • More questions about OneAI? The Connector page answers them. See everything the OneAI Connector can do

Connect OneAI to Claude, Cursor, ChatGPT & more