Triple

T19566145
Position Surface form Disambiguated ID Type / Status
Subject Where the Light Goes E489586 entity
Predicate featuresBandMember P15278 FINISHED
Object Brian Yale 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: Brian Yale | Statement: [Where the Light Goes, featuresBandMember, Brian Yale]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Brian Yale
Context triple: [Where the Light Goes, featuresBandMember, Brian Yale]
  • A. Brian Yale chosen
    Brian Yale is the bassist for the American rock band Matchbox Twenty.
  • B. Joe Yule
    Joe Yule was a Scottish-born American vaudeville and film comedian best known as the father of actor Mickey Rooney.
  • C. Doug Yule
    Doug Yule is an American musician best known as a later member of the influential rock band The Velvet Underground, contributing bass, vocals, and multi-instrumental work on several of their albums.
  • D. Michael Yates
    Michael Yates is a fictional UNIT officer from the long-running British science fiction television series Doctor Who.
  • E. Stephen Youll
    Stephen Youll is a British science fiction and fantasy artist renowned for his detailed cover illustrations for major genre novels.
  • 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_69d8e8dc5d8c8190a6d7bd8864f43ca0 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e63f777cf081909312b46ac09bce7c completed April 20, 2026, 3 p.m.
Created at: April 10, 2026, 1:42 p.m.