Triple

T3197218
Position Surface form Disambiguated ID Type / Status
Subject Spellbound E66961 entity
Predicate mainCharacter P1183 FINISHED
Object John Ballantyne E255052 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 Ballantyne | Statement: [Spellbound, mainCharacter, John Ballantyne]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Ballantyne
Context triple: [Spellbound, mainCharacter, John Ballantyne]
  • A. John Ballantyne chosen
    John Ballantyne is the amnesiac patient and central male protagonist in Alfred Hitchcock’s 1945 psychological thriller "Spellbound."
  • B. Walter Watt
    Walter Watt is an American local government official serving as the mayor of Muskegon Heights, Michigan.
  • C. Robert Stevenson
    Robert Stevenson was a British film director best known for his work on classic Disney live-action films, including the family drama "Old Yeller."
  • D. Robert Stevenson
    Robert Stevenson was a prominent Scottish civil engineer best known for designing and building numerous lighthouses around the Scottish coast in the late 18th and early 19th centuries.
  • E. Thomas Andrews
    Thomas Andrews was a British shipbuilder and naval architect best known as the chief designer of the RMS Titanic, who perished during its sinking in 1912.
  • 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_69ad8588ba18819086a10951c32ecb80 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada7192994819084817307065a25e2 completed March 8, 2026, 4:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69b2770201888190af6cbeded6d1ae56 completed March 12, 2026, 8:19 a.m.
Created at: March 8, 2026, 3:07 p.m.