Build a knowledge graph from restaurant reviews

Used LLMs to extract structured data from Le Fooding reviews and mapped the French chef and restaurant network.

See pricing pageweeksIntermediateSource linked

Source

theophilec on Hacker News · 2025-03-03 · Project link

Written in our own words. Credit to the original author. Link checked 2026-10-14.

What they did

Used LLMs to extract structured data from Le Fooding reviews and mapped the French chef and restaurant network.

Result (as claimed)

Published with the graph and write-up.

Tools they used

Mistral Llama GPT-4o mini

Cost: Pricing depends on the tools you pick; check each official pricing page.

Set it up

Gather your sources
Collect the papers, notes, links or files you want to work from in one place.
Load them into the tool
Open Mistral, Llama, GPT-4o mini and add your sources. Keep the original files so you can check claims later.
Ask focused questions
Ask for summaries, comparisons or connections with citations to the source passages.
Verify and save
Spot check claims against the sources, then save the output as notes you can reuse.

Copy the full setup prompt

Paste into your agent and it will walk you through the setup, asking before anything that sends, posts or spends.

You are helping me set up this AI use case end to end in Claude Code.

Goal: Build a knowledge graph from restaurant reviews
What the original author did: Used LLMs to extract structured data from Le Fooding reviews and mapped the French chef and restaurant network.
Reported result (as claimed by the author): Published with the graph and write-up.
Source: https://news.ycombinator.com/item?id=43242818
Tools they used: Mistral, Llama, GPT-4o mini
Category: Research & learning

Please:
1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like).
2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure.
3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data.
4. Finish with a checklist to run it again next time.

You are helping me set up this AI use case end to end in Codex.

Goal: Build a knowledge graph from restaurant reviews
What the original author did: Used LLMs to extract structured data from Le Fooding reviews and mapped the French chef and restaurant network.
Reported result (as claimed by the author): Published with the graph and write-up.
Source: https://news.ycombinator.com/item?id=43242818
Tools they used: Mistral, Llama, GPT-4o mini
Category: Research & learning

Please:
1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like).
2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure.
3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data.
4. Finish with a checklist to run it again next time.

You are helping me set up this AI use case end to end in Grok Bot.

Goal: Build a knowledge graph from restaurant reviews
What the original author did: Used LLMs to extract structured data from Le Fooding reviews and mapped the French chef and restaurant network.
Reported result (as claimed by the author): Published with the graph and write-up.
Source: https://news.ycombinator.com/item?id=43242818
Tools they used: Mistral, Llama, GPT-4o mini
Category: Research & learning

Please:
1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like).
2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure.
3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data.
4. Finish with a checklist to run it again next time.