Triple

T10811462
Position Surface form Disambiguated ID Type / Status
Subject The Wolf Man E255109 entity
Predicate character P662 FINISHED
Object Larry Talbot E410051 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: Larry Talbot | Statement: [The Wolf Man, character, Larry Talbot]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Larry Talbot
Context triple: [The Wolf Man, character, Larry Talbot]
  • A. Lawrence Talbot chosen
    Lawrence Talbot is the tormented nobleman who becomes a cursed werewolf at the center of the 2010 horror film "The Wolfman."
  • B. Lyle Talbot
    Lyle Talbot was an American actor known for his prolific work in film and television from the 1930s through the 1980s, including roles in both major studio productions and low-budget cult classics.
  • C. Julian Rathbone
    Julian Rathbone was a British novelist known for his eclectic, genre-blending fiction and politically charged historical and crime novels.
  • D. Jean Byron
    Jean Byron was an American actress best known for her role as the mother, Natalie Lane, on the 1960s television sitcom "The Patty Duke Show."
  • E. Arthur Worthington
    Arthur Worthington was a 19th-century religious impostor and founder of the New Zealand-based cult known as the Temple of Truth.
  • 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_69d6aa61c15c8190a1839550c56e75e1 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d733b7bfac8190b6ae34144376d6ad completed April 9, 2026, 5:05 a.m.
NED1 Entity disambiguation (via context triple) batch_69deb0ea2b6481909dfd94fe0c3c4499 completed April 14, 2026, 9:26 p.m.
Created at: April 8, 2026, 9:18 p.m.