Triple

T22101827
Position Surface form Disambiguated ID Type / Status
Subject Sapphire E546189 entity
Predicate stars P1956 FINISHED
Object Michael Craig 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: Michael Craig | Statement: [Sapphire, stars, Michael Craig]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michael Craig
Context triple: [Sapphire, stars, Michael Craig]
  • A. Michael Craig chosen
    Michael Craig is a British actor and screenwriter known for his work in mid-20th-century film and television, including roles in dramas and thrillers.
  • B. Michael Pennington
    Michael Pennington is a distinguished English actor and director, particularly renowned for his work in classical theatre and Shakespearean performance.
  • C. John Gibbon
    John Gibbon was a 19th-century United States Army officer and Civil War general who later played a key role in the Indian Wars, including campaigns against the Nez Perce.
  • D. Michael Pate
    Michael Pate was an Australian actor and writer known for his prolific character roles in film and television from the 1940s through the 1980s.
  • E. David Leahy
    David Leahy is a notable individual recognized for achievements significant enough to be associated with the surname Leahy.
  • 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_69e11e378dc08190896d6a51597afd5a completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f129163b908190b63ace06016f4db8 completed April 28, 2026, 9:39 p.m.
Created at: April 16, 2026, 8:30 p.m.