Triple

T21210900
Position Surface form Disambiguated ID Type / Status
Subject Felicity Shagwell E522714 entity
Predicate portrayedBy P1507 FINISHED
Object Heather Graham 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: Heather Graham | Statement: [Felicity Shagwell, portrayedBy, Heather Graham]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Heather Graham
Context triple: [Felicity Shagwell, portrayedBy, Heather Graham]
  • A. Heather Graham chosen
    Heather Graham is an American actress known for her roles in films such as "Boogie Nights," "Austin Powers: The Spy Who Shagged Me," and "The Hangover."
  • B. Stefanie Pitt
    Stefanie Pitt is the daughter of British-Polish actress and horror icon Ingrid Pitt.
  • C. Brooke Russell
    Brooke Russell was an American socialite and philanthropist best known as the wife of financier Vincent Astor and for her prominent role in New York high society.
  • D. Melissa Hurley
    Melissa Hurley is an American dancer and choreographer best known for her work in film and television and for being married to actor Patrick Cassidy.
  • E. Sharley Hudson
    Sharley Hudson was the wife of American character actor Keenan Wynn.
  • 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_69e0b5112d8881909510b2dcdc93106d completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7346eb20c8190aeb3c0cc0a24aaf9 completed April 21, 2026, 8:25 a.m.
Created at: April 16, 2026, 3:37 p.m.