Triple

T20188639
Position Surface form Disambiguated ID Type / Status
Subject Falling Down E492926 entity
Predicate starring P1507 FINISHED
Object Barbara Hershey 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: Barbara Hershey | Statement: [Falling Down, starring, Barbara Hershey]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Barbara Hershey
Context triple: [Falling Down, starring, Barbara Hershey]
  • A. Barbara Hershey chosen
    Barbara Hershey is an American actress known for her intense, emotionally complex performances in film and television, including a prominent role in the psychological thriller "Black Swan."
  • B. Sharon Reed
    Sharon Reed is a visual effects industry professional best known as one of the founders of the renowned VFX and creative studio Framestore.
  • C. Maureen Kershner
    Maureen Kershner is known as the spouse of American film director Irvin Kershner, who directed "The Empire Strikes Back."
  • D. Helen Hirsch
    Helen Hirsch is a Jewish maid in the film "Schindler's List" who endures brutal abuse under Nazi commandant Amon Göth, symbolizing the terror and dehumanization of the Holocaust.
  • E. Constance Zimmer
    Constance Zimmer is an American actress best known for her sharp, scene-stealing roles in television dramas and comedies, including prominent parts on series like Entourage, House of Cards, and Boston Legal.
  • 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_69da6268a034819081cbd9ea5a1c9475 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66ad404508190981cfb7cab18d8d3 completed April 20, 2026, 6:05 p.m.
Created at: April 11, 2026, 11:37 p.m.