Triple

T12214152
Position Surface form Disambiguated ID Type / Status
Subject Helena Zengel E291039 entity
Predicate characterPlayed P1507 FINISHED
Object Johanna Leonberger E295547 NE FINISHED

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: Johanna Leonberger | Statement: [Helena Zengel, characterPlayed, Johanna Leonberger]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Johanna Leonberger
Context triple: [Helena Zengel, characterPlayed, Johanna Leonberger]
  • A. Johanna Leonberger chosen
    Johanna Leonberger is a young orphaned girl of German heritage who becomes the emotionally pivotal companion to Captain Jefferson Kyle Kidd in the Western drama film "News of the World."
  • B. Johanna Hiedler
    Johanna Hiedler was an Austrian woman of the 19th century known primarily as the maternal grandmother of Adolf Hitler.
  • C. Katharina Gsell
    Katharina Gsell was the wife of the eminent Swiss mathematician Leonhard Euler and the daughter of Swiss painter Georg Gsell.
  • D. Johanna Wokalek
    Johanna Wokalek is a German actress known for her work in film, television, and theater, including prominent roles in critically acclaimed German-language productions.
  • E. Johanna Fiedler
    Johanna Fiedler was an American arts publicist and author, best known for her work with the Metropolitan Opera and her books on classical music figures and institutions.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d6ab65923081909acfc61b7a612233 completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d91c931cec819083ca19be06a33e1c completed April 10, 2026, 3:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69f684cc45b48190a388b38ef301c2f8 completed May 2, 2026, 11:12 p.m.
Created at: April 8, 2026, 9:51 p.m.