Triple

T20980430
Position Surface form Disambiguated ID Type / Status
Subject Sky Masterson E516743 entity
Predicate associatedWith P37 FINISHED
Object Nathan Detroit 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: Nathan Detroit | Statement: [Sky Masterson, associatedWith, Nathan Detroit]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nathan Detroit
Context triple: [Sky Masterson, associatedWith, Nathan Detroit]
  • A. Nathan Detroit chosen
    Nathan Detroit is a lovable, perpetually scheming New York gambler best known as the organizer of an illegal floating crap game in the musical "Guys and Dolls."
  • B. Nathan
    Nathan is a prophet in the Hebrew Bible known for advising King David and courageously confronting him over his sin with Bathsheba.
  • C. Nathan
    Nathan is the central character of Gotthold Ephraim Lessing’s play "Nathan the Wise," portrayed as a wise and compassionate Jewish merchant who advocates religious tolerance and humanism.
  • D. Nathan
    Nathan is a common given name used in various cultures, often derived from Hebrew meaning "he gave" or "gift."
  • E. Nathan
    Nathan is the given first name of the American writer and poet Jean Toomer, known for his modernist work "Cane."
  • 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_69e0b4ffac148190bbade9f0eceb660b completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6fbdd89f48190b58c67cc1f7968c0 completed April 21, 2026, 4:23 a.m.
Created at: April 16, 2026, 1:47 p.m.