# How to perform Entity Extraction in Pipeline Builder

**URL:** <https://community.palantir.com/t/how-to-perform-entity-extraction-in-pipeline-builder/7286>\
**Category:** Ask the Community\
**Tags:** pipeline-builder\
**Created:** [September 28, 2026, 2:30pm UTC](https://community.palantir.com/t/how-to-perform-entity-extraction-in-pipeline-builder/7286 "2026-09-28T14:30:39Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![VincentF](https://avatars.discourse-cdn.com/v4/letter/v/8491ac/32.png) [@VincentF](https://community.palantir.com/u/VincentF)\
**Post date:** [September 28, 2026, 2:30pm UTC](https://community.palantir.com/t/how-to-perform-entity-extraction-in-pipeline-builder/7286/1 "2026-09-28T14:30:39Z")

</div>

How can I perform entity extraction in Pipeline Builder ? If I have documents, or transcripts of documents, what prompts should I use and how to structure the output to extract specific pieces of information, if present ?

---

<div class="post-metadata">

**Author:** ![VincentF](https://avatars.discourse-cdn.com/v4/letter/v/8491ac/32.png) [@VincentF](https://community.palantir.com/u/VincentF)\
**Post date:** [September 28, 2026, 2:30pm UTC](https://community.palantir.com/t/how-to-perform-entity-extraction-in-pipeline-builder/7286/2 "2026-09-28T14:30:42Z")

</div>

When using an LLM node in Pipeline Builder to perform Entity extraction, it is possible to use a prompt that asks the LLM to return key-value pairs, which allow to easily evolve entities to extract.

_Example of prompt for extracting entities in Pipeline Builder_

 ![image](https://canada1.discourse-cdn.com/palantir/original/2X/f/fde6f01f8ee2a814d556a1dd748cc2621e0dcd32.png)

A prompt like the following.

```markdown
You are a tool for <industry> extract information from <type of documents> 
You are looking for <type of information>, these are <description>

Your goal is to parse the following page text into an array of JSON structs 
where every entry contains the following fields:
- <key>: <description of what to extract, format, type>
- <key>: <description of what to extract, format, type>
- <key>: <description of what to extract, format, type>

If the text doesn't contain an a <type of information> return null
The output should be a valid JSON (without \n or or other escaping)

```

**Tip: You can as well add the document itself (for vision models) directly by adding the media reference in the prompt !**

You can then extract those key/values via the below transforms

 ![image](https://canada1.discourse-cdn.com/palantir/original/2X/8/87c2ddb83837ea2e85e270b0556199ac83b66faf.png)