Triple

T8479474
Position Surface form Disambiguated ID Type / Status
Subject Lisa Simpson E200479 entity
Predicate voiceActor P1507 FINISHED
Object Yeardley Smith E738237 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: Yeardley Smith | Statement: [Lisa Simpson, voiceActor, Yeardley Smith]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yeardley Smith
Context triple: [Lisa Simpson, voiceActor, Yeardley Smith]
  • A. Yeardley Smith chosen
    Yeardley Smith is an American actress and voice actress best known for voicing Lisa Simpson on the long-running animated television series "The Simpsons."
  • B. Laura Innes
    Laura Innes is an American actress and television director best known for her long-running role as Dr. Kerry Weaver on the medical drama series "ER."
  • C. Tiffani Thiessen
    Tiffani Thiessen is an American actress best known for her roles on the television series "Saved by the Bell" and "Beverly Hills, 90210."
  • D. Shannon Elizabeth
    Shannon Elizabeth is an American actress and former fashion model best known for her breakout role in the comedy film "American Pie."
  • E. Danielle Panabaker
    Danielle Panabaker is an American actress best known for her role as Caitlin Snow/Killer Frost in the Arrowverse television series "The Flash."
  • 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_69ca831b17988190a1f3f3413d57b820 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe5232d008190ae55b982f5fc9e8b completed March 31, 2026, 3:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69cf27e1bda481909062b9259a168eb0 completed April 3, 2026, 2:37 a.m.
Created at: March 30, 2026, 6:12 p.m.