Triple

T8883891
Position Surface form Disambiguated ID Type / Status
Subject Roger Howells E211477 entity
Predicate name P16 FINISHED
Object Roger Howells E211477 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: Roger Howells | Statement: [Roger Howells, name, Roger Howells]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Roger Howells
Context triple: [Roger Howells, name, Roger Howells]
  • A. Roger Howells chosen
    Roger Howells is a relatively obscure individual whose name is notably recorded as a bearer of the surname Howells.
  • B. Phil Woolpert
    Phil Woolpert was a prominent American college basketball coach best known for leading the University of San Francisco to multiple national championships in the 1950s.
  • C. Michael Howells
    Michael Howells was the son of English composer Herbert Howells, to whose memory the choral work "Hymnus Paradisi" is dedicated.
  • D. Danny Howells
    Danny Howells is a British DJ and electronic music producer known for his eclectic, progressive house and tech-house sets and long-standing presence in the global club scene.
  • E. David Howells
    David Howells is a former Welsh professional footballer best known for his long midfield career with Tottenham Hotspur in the English top flight.
  • 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_69ca838f9e20819096ab1f236a70381a completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc616b2d988190b923ef1e33aab787 completed April 1, 2026, 12:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfabd254148190b5ea3d308fe96851 completed April 3, 2026, noon
Created at: March 30, 2026, 6:53 p.m.