Triple

T7538597
Position Surface form Disambiguated ID Type / Status
Subject Butterfield 8 E178212 entity
Predicate artDirector P7743 FINISHED
Object Hugh Hunt E230456 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: Hugh Hunt | Statement: [Butterfield 8, artDirector, Hugh Hunt]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hugh Hunt
Context triple: [Butterfield 8, artDirector, Hugh Hunt]
  • A. Hugh Hunt chosen
    Hugh Hunt was an American film art director and set decorator known for his work on numerous Hollywood productions in the mid-20th century.
  • B. Mark Curtis
    Mark Curtis is a British historian and author known for his critical works on UK foreign policy and Western interventionism.
  • C. John Bishop
    John Bishop is the son of Maurice Bishop, the revolutionary leader and former Prime Minister of Grenada.
  • D. John Bishop
    John Bishop is an English stand-up comedian, actor, and television presenter known for his energetic storytelling style and appearances on British panel shows and dramas.
  • E. Hugh Dennis
    Hugh Dennis is a British comedian, actor, and writer best known for his work on the sketch show "The Mary Whitehouse Experience" and the sitcom "Outnumbered."
  • 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_69c69f2be3888190a6667a27f8f195e9 completed March 27, 2026, 3:15 p.m.
NER Named-entity recognition batch_69c6f8710400819088e430c8c550577e completed March 27, 2026, 9:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69c84f14d20c8190ab254f991cec0d94 completed March 28, 2026, 9:58 p.m.
Created at: March 27, 2026, 3:48 p.m.