Triple

T3672848
Position Surface form Disambiguated ID Type / Status
Subject Stripes E77918 entity
Predicate starring P1507 FINISHED
Object John Larroquette E98907 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: John Larroquette | Statement: [Stripes, starring, John Larroquette]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Larroquette
Context triple: [Stripes, starring, John Larroquette]
  • A. John Larroquette chosen
    John Larroquette is an American actor and comedian best known for his Emmy-winning role on "Night Court" and prominent performances in both television and film.
  • B. Paul Benedict
    Paul Benedict was an American character actor best known for his comedic roles on television and in film, including his portrayal of the eccentric English neighbor Harry Bentley on the sitcom "The Jeffersons."
  • C. George Wendt
    George Wendt is an American actor best known for playing the lovable bar regular Norm Peterson on the classic sitcom "Cheers."
  • D. Bill Prady
    Bill Prady is an American television writer and producer best known for co-creating the hit sitcom "The Big Bang Theory."
  • E. Ted Baxter
    Ted Baxter is a vain, bumbling, and egotistical TV news anchor who serves as a major comic figure on the classic sitcom "The Mary Tyler Moore Show."
  • 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_69ad85e083008190b2e1b7085fe500bd completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc42f82548190b4d5f0fe7250decb completed March 8, 2026, 6:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69b488526214819092abb95f7cf119d5 completed March 13, 2026, 9:57 p.m.
Created at: March 8, 2026, 3:25 p.m.