Triple

T12301600
Position Surface form Disambiguated ID Type / Status
Subject Mayerling (1936 film) E293238 entity
Predicate screenwriter P2831 FINISHED
Object Irma von Cube E391196 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: Irma von Cube | Statement: [Mayerling (1936 film), screenwriter, Irma von Cube]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Irma von Cube
Context triple: [Mayerling (1936 film), screenwriter, Irma von Cube]
  • A. Irma von Cube chosen
    Irma von Cube was a German-American screenwriter best known for her Academy Award–nominated work on the 1948 film "Johnny Belinda."
  • B. Julie von Webenau
    Julie von Webenau was a 19th-century Austrian pianist and composer known for her salon pieces and connections with prominent Romantic-era musicians.
  • C. Gui Bonsiepe
    Gui Bonsiepe is a German designer, design theorist, and educator known for his influential work in interface and information design and his contributions to design education, particularly in Latin America.
  • D. Anne Taschenmacher
    Anne Taschenmacher is a German woman known primarily for having been married to former German Chancellor Gerhard Schröder.
  • E. Marta Linden
    Marta Linden was an American film actress active in the 1930s and 1940s, known for supporting roles in Hollywood studio productions.
  • 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_69d6ab6a2b50819082f6aedd32ed608a completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d93edb59908190bcef9d0cdc11081f completed April 10, 2026, 6:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69f61e7d757881908ac6af2b70a6dafe completed May 2, 2026, 3:55 p.m.
Created at: April 8, 2026, 9:53 p.m.