Triple

T17964366
Position Surface form Disambiguated ID Type / Status
Subject Backbone.js E449163 entity
Predicate creator P184 FINISHED
Object Jeremy Ashkenas NE NERFINISHED

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: Jeremy Ashkenas | Statement: [Backbone.js, creator, Jeremy Ashkenas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jeremy Ashkenas
Context triple: [Backbone.js, creator, Jeremy Ashkenas]
  • A. Jeremy Ashkenas chosen
    Jeremy Ashkenas is an American programmer and open-source developer best known for creating the CoffeeScript language and contributing to projects like Backbone.js and Underscore.js.
  • B. Asher Goldstein
    Asher Goldstein is a film producer known for socially conscious dramas, including the acclaimed legal drama "Just Mercy."
  • C. Lee Aronsohn
    Lee Aronsohn is an American television writer and producer best known for co-creating the hit sitcom "Two and a Half Men."
  • D. Marc Roskin
    Marc Roskin is a television producer and director best known for his work on genre and adventure series such as "The Librarians."
  • E. Benjy Eisen
    Benjy Eisen is a music journalist and author best known for co-writing memoirs with Grateful Dead drummer Bill Kreutzmann.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8b9f9927c8190a006110c8b996e61 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e4b135cd2c8190a6190cf6611dbe08 completed April 19, 2026, 10:40 a.m.
Created at: April 10, 2026, 10:22 a.m.