Triple

T18056902
Position Surface form Disambiguated ID Type / Status
Subject St Columb's College E432061 entity
Predicate notableAlumnus P304 FINISHED
Object Phil Coulter 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: Phil Coulter | Statement: [St Columb's College, notableAlumnus, Phil Coulter]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Phil Coulter
Context triple: [St Columb's College, notableAlumnus, Phil Coulter]
  • A. Phil Coulter chosen
    Phil Coulter is an Irish musician, songwriter, and record producer renowned for his hit compositions and contributions to Celtic and popular music.
  • B. Jim Hughson
    Jim Hughson is a Canadian sportscaster best known as one of the premier play-by-play voices in NHL broadcasting.
  • C. Dave McNair
    Dave McNair is a Grammy-winning American mastering engineer and producer known for his work across rock, pop, and indie music.
  • D. Guy Edwards
    Guy Edwards is a British former racing driver best known for his Formula One career in the 1970s and for helping rescue Niki Lauda from his fiery crash at the 1976 German Grand Prix.
  • E. Gene Keady
    Gene Keady is a highly respected American college basketball coach best known for his long, successful tenure leading the Purdue Boilermakers.
  • 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_69d8b906482481908183315b9ecf9994 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4c103cedc819086a905269b118795 completed April 19, 2026, 11:48 a.m.
Created at: April 10, 2026, 10:26 a.m.