Triple

T11995742
Position Surface form Disambiguated ID Type / Status
Subject Annie E285524 entity
Predicate portrayedBy P1507 FINISHED
Object Aimee Brooks E291087 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: Aimee Brooks | Statement: [Annie, portrayedBy, Aimee Brooks]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Aimee Brooks
Context triple: [Annie, portrayedBy, Aimee Brooks]
  • A. Aimee Brooks chosen
    Aimee Brooks is an American actress best known for her roles in horror and cult films and television during the late 1980s and 1990s.
  • B. Aimee Graham
    Aimee Graham is an American actress and writer known for her supporting roles in independent films and for being the younger sister of actress Heather Graham.
  • C. Tara Brooks
    Tara Brooks is a character in Marvel Comics best known as the human mother of the vampire hunter Blade.
  • D. Kate Brooks
    Kate Brooks is the daughter of acclaimed British actress Jean Simmons.
  • E. Amanda Lohrey
    Amanda Lohrey is an acclaimed Australian novelist and essayist known for her psychologically rich fiction and contributions to contemporary Australian 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_69d6ab44a77c8190a652f4b27164e4ef completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d903b211688190bfe6dd15c3f96d2f completed April 10, 2026, 2:05 p.m.
NED1 Entity disambiguation (via context triple) batch_69f49d183ee881908f1c0ca4562344a9 completed May 1, 2026, 12:31 p.m.
Created at: April 8, 2026, 9:46 p.m.