Triple

T10954617
Position Surface form Disambiguated ID Type / Status
Subject Oh, Boy! E258811 entity
Predicate bookWriter P24104 FINISHED
Object Guy Bolton E138801 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: Guy Bolton | Statement: [Oh, Boy!, bookWriter, Guy Bolton]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Guy Bolton
Context triple: [Oh, Boy!, bookWriter, Guy Bolton]
  • A. Guy Bolton chosen
    Guy Bolton was a British-American playwright and librettist best known for his influential musical comedies and collaborations with figures like P. G. Wodehouse and Jerome Kern.
  • B. Guy Bensley
    Guy Bensley is a film editor best known for his work on the comedy spy film "Johnny English Reborn."
  • C. Henry Gayden
    Henry Gayden is an American screenwriter best known for writing the superhero film "Shazam!" and its sequel in the DC Extended Universe.
  • D. Lewis Morley
    Lewis Morley was a British photographer best known for his iconic 1963 portrait of model Christine Keeler, which became emblematic of the Profumo affair era.
  • E. Michael Balson
    Michael Balson is a film editor best known for his work on the post-apocalyptic action movie "Mad Max Beyond Thunderdome."
  • 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_69d6aa88500c819097d7032ca578e74f completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d770ff718c81909d4baebea3b56b83 completed April 9, 2026, 9:27 a.m.
NED1 Entity disambiguation (via context triple) batch_69e2d7439204819092fcd061a161fd7b completed April 18, 2026, 12:58 a.m.
Created at: April 8, 2026, 9:23 p.m.