Triple

T22090934
Position Surface form Disambiguated ID Type / Status
Subject Marshall E545909 entity
Predicate castMember P1668 FINISHED
Object Keesha Sharp 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: Keesha Sharp | Statement: [Marshall, castMember, Keesha Sharp]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Keesha Sharp
Context triple: [Marshall, castMember, Keesha Sharp]
  • A. Keesha Sharp chosen
    Keesha Sharp is an American actress and director best known for her roles in television series such as "Girlfriends" and "Lethal Weapon," as well as various film and stage productions.
  • B. Sharona Fleming
    Sharona Fleming is a fictional nurse and assertive personal assistant to detective Adrian Monk on the television series "Monk."
  • C. Kelli Williams
    Kelli Williams is an American actress best known for her television roles in series such as "The Practice" and "Lie to Me."
  • D. Shawna Craig
    Shawna Craig is an American actress, model, and reality television personality known for her appearances on shows like "Second Wives Club" and for her marriage to actor Lorenzo Lamas.
  • E. Keesha Franklin
    Keesha Franklin is a smart, skeptical, and often sarcastic student from the animated educational series "The Magic School Bus," known for her practical mindset and witty commentary during Ms. Frizzle’s science adventures.
  • 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_69e11e36d03c8190a83a1ba802b7231b completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f128e53dfc81909858cdad8b09c5fb completed April 28, 2026, 9:38 p.m.
Created at: April 16, 2026, 8:29 p.m.