Triple

T22716517
Position Surface form Disambiguated ID Type / Status
Subject Liz Sherman E561745 entity
Predicate voiceActedBy P39669 FINISHED
Object Peri Gilpin 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: Peri Gilpin | Statement: [Liz Sherman, voiceActedBy, Peri Gilpin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Peri Gilpin
Context triple: [Liz Sherman, voiceActedBy, Peri Gilpin]
  • A. Peri Gilpin chosen
    Peri Gilpin is an American actress best known for playing radio producer Roz Doyle on the long-running sitcom "Frasier."
  • B. Glenne Headly
    Glenne Headly was an American actress known for her versatile film, television, and stage performances, including prominent roles in comedies and dramas from the 1980s onward.
  • C. Elisabeth McGowan
    Elisabeth McGowan was an American theater pioneer best known as one of the founders of the Cleveland Play House, one of the nation’s oldest professional regional theaters.
  • D. Betty Gilpin
    Betty Gilpin is an American actress best known for her Emmy-nominated role in the Netflix series "GLOW" and performances in films such as "The Hunt" and "The Tomorrow War."
  • E. 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."
  • 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_69e2454fc984819088213b58ee87a002 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f1790e14c88190af6acb27910ae9c1 completed April 29, 2026, 3:20 a.m.
Created at: April 17, 2026, 3:19 p.m.