Triple

T6166918
Position Surface form Disambiguated ID Type / Status
Subject Enemy E137588 entity
Predicate starring P1507 FINISHED
Object Sarah Gadon E467333 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: Sarah Gadon | Statement: [Enemy, starring, Sarah Gadon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sarah Gadon
Context triple: [Enemy, starring, Sarah Gadon]
  • A. Sarah Gadon chosen
    Sarah Gadon is a Canadian actress known for her work in film and television, including prominent roles in period dramas and genre movies.
  • B. Isabelle Nélisse
    Isabelle Nélisse is a Canadian actress known for her roles in psychologically intense films and television series, often portraying complex and troubled young characters.
  • C. Radha Mitchell
    Radha Mitchell is an Australian actress known for her versatile performances in independent films and Hollywood productions, including notable roles in dramas, thrillers, and horror films.
  • D. Maria Riva
    Maria Riva is a German-American actress and author best known as the daughter and biographer of film legend Marlene Dietrich.
  • E. Madeleine Lesser
    Madeleine Lesser is the wife of British actor Anton Lesser, known for his work in television, film, and theatre.
  • 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_69c008a68c508190a8d78245c865960e completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c05d6366948190b35ef44dd9d6fcd6 completed March 22, 2026, 9:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69c16ee26ed8819084a5cfd84ba9564e completed March 23, 2026, 4:48 p.m.
Created at: March 22, 2026, 4:17 p.m.