Triple

T21467353
Position Surface form Disambiguated ID Type / Status
Subject The Joke E529625 entity
Predicate character P662 FINISHED
Object Kostka 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: Kostka | Statement: [The Joke, character, Kostka]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kostka
Context triple: [The Joke, character, Kostka]
  • A. Kostka chosen
    Kostka is a Polish surname most famously borne by Saint Stanislaus Kostka, a 16th-century Jesuit novice venerated in the Catholic Church.
  • B. Kubek
    Kubek is the surname of Tony Kubek, a former Major League Baseball shortstop and longtime television sportscaster best known for his years with the New York Yankees.
  • C. De Kova
    De Kova is a surname most notably associated with American character actor Frank De Kova, known for his roles in mid-20th-century film and television.
  • D. Klötze
    Klötze is a small town in the Altmark region of Saxony-Anhalt in central Germany.
  • E. Krychaw
    Krychaw is a town in eastern Belarus known as an industrial and transport center within the Mogilev Region.
  • 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_69e0c459acb481909bb6ee452a0045c7 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69e9e9f415d48190a2b0993a4f3c018f completed April 23, 2026, 9:44 a.m.
Created at: April 16, 2026, 6:14 p.m.