Triple

T12970894
Position Surface form Disambiguated ID Type / Status
Subject Marcia Wallace E321391 entity
Predicate role P268 FINISHED
Object Carol Kester E294362 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: Carol Kester | Statement: [Marcia Wallace, role, Carol Kester]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Carol Kester
Context triple: [Marcia Wallace, role, Carol Kester]
  • A. Carol Kester chosen
    Carol Kester is the witty, fast-talking receptionist on the classic American sitcom "The Bob Newhart Show."
  • B. Marilyn Vance
    Marilyn Vance is an American costume designer known for her influential work on numerous popular films, including iconic 1980s and 1990s movies.
  • C. Patti Deutsch
    Patti Deutsch was an American comedic actress and voice artist known for her distinctive nasal voice and appearances on game shows and in animated films and television series.
  • D. Sol Lesser
    Sol Lesser was an American film producer best known for his extensive work on the Tarzan movie series during the mid-20th century.
  • E. Betty Parker
    Betty Parker is the daughter of Trey Parker, the American animator, writer, and co-creator of the television series "South Park."
  • 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_69d80763bd6c819094437da5b20b01d2 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69d97e418d548190be1c73db76cb3aa8 completed April 10, 2026, 10:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6b8ea91f08190b1daf6d05621acf9 completed May 3, 2026, 2:54 a.m.
Created at: April 9, 2026, 8:35 p.m.