Triple

T5514815
Position Surface form Disambiguated ID Type / Status
Subject Jezebel E144655 entity
Predicate starring P1507 FINISHED
Object Donald Crisp E66784 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: Donald Crisp | Statement: [Jezebel, starring, Donald Crisp]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Donald Crisp
Context triple: [Jezebel, starring, Donald Crisp]
  • A. Donald Crisp chosen
    Donald Crisp was a British-born American film actor and director best known for his prolific career in early Hollywood cinema, including roles in numerous silent and sound films.
  • B. Garth Algar
    Garth Algar is a shy, nerdy, and endearingly awkward best friend and co-host to Wayne Campbell in the comedy franchise "Wayne's World."
  • C. Andy Devine
    Andy Devine was an American character actor best known for his distinctive raspy voice and roles in numerous Western films and the television series "The Adventures of Wild Bill Hickok."
  • D. Eddie Albert
    Eddie Albert was an American actor best known for his roles in film and television, particularly the sitcom "Green Acres" and numerous classic Hollywood movies.
  • E. Charles Bickford
    Charles Bickford was an American character actor known for his rugged screen presence and acclaimed supporting roles in numerous classic Hollywood films.
  • 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_69c008f77ff88190b0cd50ca207295d1 completed March 22, 2026, 3:21 p.m.
NER Named-entity recognition batch_69c01f5b4e988190b590b4157cf089c1 completed March 22, 2026, 4:56 p.m.
NED1 Entity disambiguation (via context triple) batch_69c04cc0735881909b7ea6909570a750 completed March 22, 2026, 8:10 p.m.
Created at: March 22, 2026, 3:33 p.m.