Triple

T17865559
Position Surface form Disambiguated ID Type / Status
Subject The Maze E446688 entity
Predicate castMember P1668 FINISHED
Object Stanley Fraser 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: Stanley Fraser | Statement: [The Maze, castMember, Stanley Fraser]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Stanley Fraser
Context triple: [The Maze, castMember, Stanley Fraser]
  • A. Stanley Fraser chosen
    Stanley Fraser was an actor known for appearing in mid-20th-century films, including the 1953 horror movie "The Maze."
  • B. Henry Fraser
    Henry Fraser is a central character in the psychological thriller miniseries "The Undoing," around whom much of the show's mystery and family drama revolves.
  • C. Philip Mannering
    Philip Mannering is one of the main child protagonists in Enid Blyton’s "Adventure" series, known for his bravery, leadership, and love of animals.
  • D. Ronald Fraser
    Ronald Fraser was a British character actor known for his distinctive gruff charm and prolific work in film, television, and theatre from the 1950s through the 1980s.
  • E. John Rutherfurd
    John Rutherfurd was an American politician and landowner from New Jersey, notable enough in the state's history to have the borough of Rutherford named in his honor.
  • 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_69d8b9f4c22c819093c2680434472894 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e49793a2588190bb341ac606d767fe completed April 19, 2026, 8:51 a.m.
Created at: April 10, 2026, 10:17 a.m.