Triple

T19868218
Position Surface form Disambiguated ID Type / Status
Subject Legally Blonde E477445 entity
Predicate starring P1507 FINISHED
Object Holland Taylor 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: Holland Taylor | Statement: [Legally Blonde, starring, Holland Taylor]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Holland Taylor
Context triple: [Legally Blonde, starring, Holland Taylor]
  • A. Holland Taylor chosen
    Holland Taylor is an American actress and playwright known for her sharp-witted stage and screen performances, including acclaimed roles in television series like "Two and a Half Men" and her one-woman play "Ann."
  • B. Claudia Rose Pfeiffer
    Claudia Rose Pfeiffer is the adopted daughter of acclaimed American actress Michelle Pfeiffer.
  • C. Shirley Porter
    Shirley Porter is a singer best known as one of the original members of the American female vocal group The Three Degrees.
  • D. Elizabeth Berridge
    Elizabeth Berridge is an American actress best known for her role as Constanze Mozart in the Academy Award–winning film "Amadeus."
  • E. Rebecca Pidgeon
    Rebecca Pidgeon is a British-American actress and singer-songwriter known for her work in film, television, and theater, as well as for her collaborations with playwright and filmmaker David Mamet.
  • 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_69d8e51e7d948190aedbcd6c30361c39 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e658a168288190a2fbb735d1fd30a8 completed April 20, 2026, 4:47 p.m.
Created at: April 10, 2026, 1:51 p.m.