PatternsEntity matchingsameAs

Entity alignment

Deciding whether two records describe the same entity, with one Score per pair plus companion Nouls for the fields that disagree.

Open docs.typesafe.ai All 117 terms

Category: Patterns
Also known as: Entity matching, sameAs
Related terms: 4
Directory entries: 1
Docs: docs.typesafe.ai
Added: 2026-09-24

Definition

The cookbook scores 450 candidate beer pairs from two catalogues with a three-level Score per pair: 40 assert sameAs, 50 go to a curator, and 360 stay unlinked. Companion Nouls about name, brewery, and style localize disagreements, while ABV stays in arithmetic.

There is no fitted threshold: route() rounds the score to the nearest level, so the middle level's wording drives behavior, and the middle is explicitly a curator path rather than an automatic merge.

Tagspatternsclassificationextraction

Related terms

Definitions that connect to this one.

ScoreRate the state against 2 to 10 ordered levels; returns a probability-weighted position, per-level probabilities, and confidence.Primitives NoulThe yes/no primitive: one probability from 0 to 1, where the value is the answer and no separate confidence is returned.Primitives Human reviewThe explicit path for uncertain or high-stakes cases: route to a person instead of acting on a low-confidence answer.Patterns Composite scoringBreak a judgment into atomic Score questions, normalize each, and combine them with weights you control in code.Patterns

From the directory

Cookbook: Knowledge Graph Entity Alignment

Decide which of 450 candidate product pairs from two beer catalogues describe the same entity: one three-level Score per pair splits 40 merges, 50 curator reviews, and 360 non-matches.

Cookbooks & DemosDocs#official#cookbook#entity-matching

Official

From the community

Posts from builders shipping with Jev right now.

Follow @typesafeai

An open 151M-parameter decision engine

Hemant

@heman10x

·Follow

TypeSafe AI came out of stealth with Jev, and access is behind a waitlist. I built an open source version Verdict (Open-jev) you can run right now in a browser tab: And its a real post trained model..(link in comments) It is a post trained 151M parameters model. ModernBERT-base Show more

Diogo Almeida

@CompleteSkeptic

After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x

Watch on X

6:37 AM · Sep 18, 2026

Read 2 replies

Agent Handoff Gate: agents verify what they hand off

Matt

@zxdubx

·Follow

I built Agent Handoff Gate with typesafe Jev An experimental protocol for AI agents to verify worker evidence before handing results back to the lead. Less blind trust, fewer useless review loops. github.com/zsoXi/agent-ha…

3:16 PM · Sep 17, 2026

Read 3 replies

A local Telegram analyzer with Jev as the classifier

Dagmawi Babi

@DagmawiBabi

·Follow

I vibe-coded this simple, open-source and local Telegram content analyzer using Jev as a classifier. Jev Classifier • jevclassifier.vercel.app Export your channel data as JSON and it will analyze each post's intent, quality, sentiment, and reaction tone and if it's a DM/Group Show more

Watch on X

Diogo Almeida

@CompleteSkeptic

Watch on X

4:09 PM · Sep 17, 2026

Read 2 replies

A Krunker-inspired FPS, decided by Jev

Neel Patel

@Neel490

·Follow

Maybe I’m just washed, but Jev is beating me at my own game. Built a Krunker-inspired FPS where you 1v1 Jev. Try it out yourself: jev-arcade.vercel.app/duel

Watch on X

Diogo Almeida

@CompleteSkeptic

Watch on X

4:11 PM · Sep 17, 2026