JevMade

Sign in
← Back to guides

JevMade field notes / Written guide

Using Jev to Sort Decisions in a Knowledge Graph

Partha Sarkar proposes using Jev for routine choices in a map of connected facts, leaving explanation and reasoning to a language model.

Original by Partha SarkarRetrieval
Leave a noteWhat would you try with this? : Using Jev to Sort Decisions in a Knowledge Graph

Only you can see your notes.

Listen to this guide

JevMade’s plain-English explanation

0:00 /

Our summary

People, products and places can be linked by relationships in a knowledge graph: a map of connected facts. Partha Sarkar proposes using Jev for the repeated small decisions involved in building and searching it. A language model would handle the larger work of explaining and combining what that map reveals.

Seven patterns appear in the article. They include deciding whether two names refer to the same thing, combining duplicate relationships and choosing useful facts for a search. Jev can select options, answer yes/no or give scores; the application stores those scores with the facts and connections.

Before merging facts or pruning a search, Sarkar recommends testing score cutoffs on labeled examples. The suggested numbers and large search-context reduction are illustrative, not verified scaling results. No public implementation or benchmark exists, so readers would still need to test the design on their own graphs.

Key takeaways

  1. Let the decision model handle repeated linking and filtering, leaving the larger reasoning task elsewhere.
  2. Check cutoffs against known matches before merging facts or removing search candidates.
  3. Keep scores alongside graph data so later searches can use them.

This is an architecture proposal with illustrative code, not a demonstrated large-scale system. The author labels the article’s images as AI-generated; its score cutoffs are examples, not universal defaults.

towardsdatascience.com · Original published

Read the original guide Opens the author’s site in a new tab.

Your note

Only you can see this. Clear the text and save to remove it.

Keep what you save

Sign in to keep bookmarks and private notes on every device. We email you a link; there is no password, and the same link creates your account.