Triple

T21993937
Position Surface form Disambiguated ID Type / Status
Subject Tracey Ullman E543155 entity
Predicate familyName P18 FINISHED
Object Ullman 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: Ullman | Statement: [Tracey Ullman, familyName, Ullman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ullman
Context triple: [Tracey Ullman, familyName, Ullman]
  • A. Ullman chosen
    Ullman is a surname most prominently associated with British-American actress, comedian, and singer Tracey Ullman.
  • B. Ullmann
    Ullmann is a Norwegian actress and film director renowned for her intense performances in Ingmar Bergman’s films and her influential contributions to European cinema.
  • C. Tanenbaum
    Tanenbaum is the surname of Andrew S. Tanenbaum, a prominent computer scientist known for his influential work on operating systems and computer networks.
  • D. Galvin
    Galvin is a surname of Irish origin borne by various notable individuals in fields such as sports, business, and the arts.
  • E. Abelson
    Abelson is a surname most notably associated with Hal Abelson, an American computer scientist and educator known for his work on the Scheme programming language and the textbook "Structure and Interpretation of Computer Programs."
  • 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_69e11e2c814c8190837d072789000486 completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f127639bf48190800b3fa3c1527983 completed April 28, 2026, 9:32 p.m.
Created at: April 16, 2026, 8:17 p.m.