Triple

T20390631
Position Surface form Disambiguated ID Type / Status
Subject Unthinkable E498073 entity
Predicate castMember P1668 FINISHED
Object Martin Donovan 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: Martin Donovan | Statement: [Unthinkable, castMember, Martin Donovan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Martin Donovan
Context triple: [Unthinkable, castMember, Martin Donovan]
  • A. Martin Donovan chosen
    Martin Donovan is an American screenwriter, director, and actor known for his work on darkly comedic and genre-blending films such as "Death Becomes Her."
  • B. Sam Donovan
    Sam Donovan is a British television director known for his work on acclaimed drama series such as "Last Tango in Halifax."
  • C. Matt Donovan
    Matt Donovan is a central human character in the supernatural drama series "The Vampire Diaries," known for his loyalty, moral compass, and resilience amid the chaos of Mystic Falls.
  • D. Jack Donnelly
    Jack Donnelly is a British actor best known for starring as Jason in the BBC fantasy-adventure series "Atlantis."
  • E. Jake O’Donnell
    Jake O’Donnell is a former American NBA referee renowned for officiating numerous high-profile games, including multiple All-Star Games and NBA Finals, during a long and distinguished career.
  • 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_69e0b4a71ebc8190b153a36c738730f4 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6790f8d9c819093038f6bb6f47a92 completed April 20, 2026, 7:05 p.m.
Created at: April 16, 2026, 11:28 a.m.