Triple

T21041646
Position Surface form Disambiguated ID Type / Status
Subject Kit Kat Klub E518339 entity
Predicate featuresCharacter P626 FINISHED
Object Sally Bowles 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: Sally Bowles | Statement: [Kit Kat Klub, featuresCharacter, Sally Bowles]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sally Bowles
Context triple: [Kit Kat Klub, featuresCharacter, Sally Bowles]
  • A. Sally Bowles chosen
    Sally Bowles is a hedonistic, free-spirited nightclub singer in 1930s Berlin, best known as the central character of the musical and film "Cabaret."
  • B. cabaret singer Maude Maggart
    Maude Maggart is an American cabaret singer known for her intimate, nostalgic interpretations of early 20th-century popular songs and standards.
  • C. Nelly Kröger
    Nelly Kröger was the second wife of German novelist Heinrich Mann, known primarily through her connection to his life and literary circle.
  • D. Hildy Beyeler
    Hildy Beyeler is a Swiss art patron known for co-founding the renowned Beyeler Foundation Museum, which houses one of Europe’s leading collections of modern and contemporary art.
  • E. Cecelia Halpert
    Cecelia Halpert is the daughter of Jim and Pam Halpert on the U.S. television series "The Office."
  • 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_69e0b50438e08190917e2538bb8bc034 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e6fcefe4688190ad1bed1ef2d7a3e5 completed April 21, 2026, 4:28 a.m.
Created at: April 16, 2026, 2:15 p.m.