Triple

T23295677
Position Surface form Disambiguated ID Type / Status
Subject Reba E590161 entity
Predicate hasCharacter P2308 FINISHED
Object Kyra Hart 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: Kyra Hart | Statement: [Reba, hasCharacter, Kyra Hart]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kyra Hart
Context triple: [Reba, hasCharacter, Kyra Hart]
  • A. Kyra Hart chosen
    Kyra Hart is a fictional character from the American sitcom "Reba," known as Reba's witty and often sarcastic middle child.
  • B. Kyra Devore
    Kyra Devore is a pivotal ghostly character in Stephen King’s novel "Bag of Bones," whose tragic past and supernatural presence drive much of the story’s mystery and horror.
  • C. Kyra Nichols
    Kyra Nichols is an acclaimed American ballerina best known as one of the leading principal dancers of New York City Ballet during the late 20th century.
  • D. Kyra
    Kyra is a feminine given name most notably borne by American actress and producer Kyra Sedgwick.
  • E. Kyra Hollis
    Kyra Hollis is the idealistic young woman at the center of David Hare’s play "Skylight," whose complex relationship with an older former lover drives the drama’s exploration of love, class, and moral responsibility.
  • 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_69e25d1af9d88190a0b9b5e8fa608618 completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f196cec9e88190b83cfd53a6455e0f completed April 29, 2026, 5:27 a.m.
Created at: April 17, 2026, 5:03 p.m.