Triple

T5227771
Position Surface form Disambiguated ID Type / Status
Subject The Robe E118034 entity
Predicate editor P1954 FINISHED
Object Barbara McLean E33907 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: Barbara McLean | Statement: [The Robe, editor, Barbara McLean]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Barbara McLean
Context triple: [The Robe, editor, Barbara McLean]
  • A. Barbara McLean chosen
    Barbara McLean was a highly influential American film editor of Hollywood’s studio era, renowned for her work on numerous classic films and for helping shape the art of cinematic editing.
  • B. Lois Duncan
    Lois Duncan was an American author best known for her suspenseful young adult novels that often blend mystery, psychological tension, and elements of the supernatural.
  • C. Cornelia Paterson
    Cornelia Paterson was a member of a prominent early American political family who became the wife of New York landowner and politician Stephen Van Rensselaer.
  • D. Doreen Mantle
    Doreen Mantle was a British actress best known for her long-running role as Mrs. Warboys in the BBC sitcom "One Foot in the Grave."
  • E. Margaret K. McElderry
    Margaret K. McElderry was a pioneering American children's book editor and publisher renowned for elevating the quality and literary reputation of children's literature.
  • 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_69bd4466fb8c819083b806a79414d7e4 completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd7addbdb88190baf9f47fc4cbb7fc completed March 20, 2026, 4:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69beeffea8f481909c86c932781c4e2a completed March 21, 2026, 7:22 p.m.
Created at: March 20, 2026, 1:48 p.m.