Triple

T3327771
Position Surface form Disambiguated ID Type / Status
Subject Dylan Michael Douglas E69957 entity
Predicate uncle P8496 FINISHED
Object Peter Douglas E329473 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: Peter Douglas | Statement: [Dylan Michael Douglas, uncle, Peter Douglas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Peter Douglas
Context triple: [Dylan Michael Douglas, uncle, Peter Douglas]
  • A. Peter Douglas chosen
    Peter Douglas is an American film and television producer, known for projects such as "The Final Countdown" and for being the son of actor Kirk Douglas.
  • B. Georg Stanford Brown
    Georg Stanford Brown is a Cuban-born American actor and director best known for his work in 1970s and 1980s film and television, including prominent roles in series like "The Rookies."
  • C. Hugh Garner
    Hugh Garner was a Canadian author best known for his socially conscious novels and short stories depicting working-class life in Toronto.
  • D. John McArthur Jr.
    John McArthur Jr. was a 19th-century American architect best known for designing monumental public buildings in Philadelphia, most notably its iconic City Hall.
  • E. Carlo Bernard
    Carlo Bernard is an American screenwriter and producer best known for co-creating the acclaimed crime drama television series "Narcos."
  • 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_69ad85a1829881908942c14075644d0d completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb16f61248190bab10f4ac9e066f7 completed March 8, 2026, 5:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69b31a7ce34c81908df0c30a41fd925c completed March 12, 2026, 7:56 p.m.
Created at: March 8, 2026, 3:12 p.m.