Triple

T10468148
Position Surface form Disambiguated ID Type / Status
Subject Strange E246855 entity
Predicate mainCharacter P1183 FINISHED
Object John Strange E655150 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: John Strange | Statement: [Strange, mainCharacter, John Strange]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Strange
Context triple: [Strange, mainCharacter, John Strange]
  • A. John Strange chosen
    John Strange is the given name of John Strange Spencer-Churchill, a British Army officer and the younger brother of Prime Minister Winston Churchill.
  • B. Mr. Grey
    Mr. Grey is a mysterious, coldly efficient criminal mastermind who leads the subway hijacking in the thriller "The Taking of Pelham One Two Three."
  • C. Brian Moriarty
    Brian Moriarty is an American game designer best known for his influential work on classic interactive fiction titles such as "Trinity" and "Wishbringer," as well as LucasArts' "Loom."
  • D. Roderick Spencer
    Roderick Spencer is an American writer and producer known for his work in film and television and for being married to actress Alfre Woodard.
  • E. Dorian Tyrell
    Dorian Tyrell is the main villain in the 1994 film "The Mask," a ruthless mobster who becomes even more dangerous after using the magical mask’s powers.
  • 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_69d381c16c248190a2fe5b471e584e9c completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d5092ef810819093a4d1df83aeac09 completed April 7, 2026, 1:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69d89ff1cd948190a1ef331fb810bf26 completed April 10, 2026, 7 a.m.
Created at: April 6, 2026, 12:20 p.m.