Triple

T18330567
Position Surface form Disambiguated ID Type / Status
Subject Mistresses E439126 entity
Predicate executiveProducer P7225 FINISHED
Object Douglas Rae 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: Douglas Rae | Statement: [Mistresses, executiveProducer, Douglas Rae]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Douglas Rae
Context triple: [Mistresses, executiveProducer, Douglas Rae]
  • A. Douglas Rae chosen
    Douglas Rae is a British film and television producer known for founding Ecosse Films and producing acclaimed dramas and feature films.
  • B. Ian McDougall
    Ian McDougall is an Australian architect best known as a founding director of the influential firm Ashton Raggatt McDougall (ARM), recognized for its bold and unconventional public architecture.
  • C. Paul Duguid
    Paul Duguid is a scholar of information studies and co-author of the influential book "The Social Life of Information" with John Seely Brown.
  • D. Philip Mackie
    Philip Mackie was a British screenwriter and producer best known for his work in television drama and literary adaptations.
  • E. David Geddes
    David Geddes is a cinematographer known for his work on the horror-comedy film "Tucker & Dale vs. Evil."
  • 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_69d8b916a2d081909e249e4902f6aad9 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e50ec900808190bc4468270e0957c1 completed April 19, 2026, 5:20 p.m.
Created at: April 10, 2026, 10:36 a.m.