Triple

T4530015
Position Surface form Disambiguated ID Type / Status
Subject Jeremy Ashkenas E106271 entity
Predicate softwareLibraryAuthorOf P32488 FINISHED
Object Underscore.js E449164 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Underscore.js | Statement: [Jeremy Ashkenas, softwareLibraryAuthorOf, Underscore.js]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Underscore.js
Context triple: [Jeremy Ashkenas, softwareLibraryAuthorOf, Underscore.js]
  • A. Underscore.js chosen
    Underscore.js is a popular JavaScript utility library that provides functional programming helpers for working with arrays, objects, and other data types.
  • B. Backbone.js
    Backbone.js is a lightweight JavaScript framework that provides structure to web applications by offering models, collections, views, and routers built on top of RESTful JSON and event-driven architecture.
  • C. Handlebars
    Handlebars is a popular logic-less templating engine for JavaScript that enables clean, readable templates with embedded expressions for dynamic HTML generation.
  • D. Backbone
    Backbone is an American rapper from Atlanta best known as a member of the Dungeon Family collective and for his early-2000s Southern hip hop work.
  • E. CoffeeScript
    CoffeeScript is a programming language that compiles to JavaScript, offering a more concise, Python- and Ruby-like syntax for writing web application code.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69bd43f3d6e08190a91824f833d51bbe completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd6231856c8190be9386a0ae15e7cf completed March 20, 2026, 3:05 p.m.
NED1 Entity disambiguation (via context triple) batch_69bdc55254848190940c506e75d79933 completed March 20, 2026, 10:08 p.m.
Created at: March 20, 2026, 1:03 p.m.