Triple

T19872152
Position Surface form Disambiguated ID Type / Status
Subject Such Good Friends E477544 entity
Predicate starred P5563 FINISHED
Object Louise Lasser 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: Louise Lasser | Statement: [Such Good Friends, starred, Louise Lasser]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Louise Lasser
Context triple: [Such Good Friends, starred, Louise Lasser]
  • A. Louise Lasser chosen
    Louise Lasser is an American actress best known for her neurotic, deadpan comedic style and her iconic 1970s television work, including her lead role in the satirical soap opera "Mary Hartman, Mary Hartman."
  • B. Lucille Norchet
    Lucille Norchet was the wife of legendary Montreal Canadiens hockey player Maurice "Rocket" Richard.
  • C. Lucille Sheardown
    Lucille Sheardown was one of the later wives of American inventor Lee de Forest, associated with his personal life rather than his pioneering work in radio and electronics.
  • D. Louise Dreyfus
    Louise Dreyfus was the wife of pioneering French sociologist Émile Durkheim and the mother of French statesman Marcel Mauss.
  • E. Lucille Grosvenor
    Lucille Grosvenor is a notable member of the prominent Fairbanks family, recognized for her connection to this influential lineage.
  • 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_69d8e51e7d948190aedbcd6c30361c39 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e658d826f88190be04188997952d1b completed April 20, 2026, 4:48 p.m.
Created at: April 10, 2026, 1:51 p.m.