Triple

T19196644
Position Surface form Disambiguated ID Type / Status
Subject William Bent E469987 entity
Predicate familyName P18 FINISHED
Object Bent 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: Bent | Statement: [William Bent, familyName, Bent]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bent
Context triple: [William Bent, familyName, Bent]
  • A. Bent
    Bent is an English electronic music duo known for their downtempo, chillout, and sample-heavy productions that gained prominence in the early 2000s.
  • B. Bent
    "Bent" is a hit rock ballad by Matchbox Twenty that became one of the band's most commercially successful and recognizable songs.
  • C. Bent chosen
    Bent is a surname of English origin borne by various notable individuals across sports, arts, and public life.
  • D. Bent (TV series)
    Bent is a short-lived American romantic comedy television series that aired on NBC in 2012, following the relationship between a recently divorced lawyer and her charming contractor.
  • E. Never Bend
    Never Bend was a prominent American Thoroughbred racehorse and influential sire known for his speed and for founding a successful bloodline in modern racing.
  • 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_69d8dd0ad9088190a173b32657ae2e7a completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5f8a5dabc81908fffad811f177b03 completed April 20, 2026, 9:57 a.m.
Created at: April 10, 2026, 12:07 p.m.