Triple

T10737364
Position Surface form Disambiguated ID Type / Status
Subject Love, Rosie E253227 entity
Predicate director P255 FINISHED
Object Christian Ditter E882347 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: Christian Ditter | Statement: [Love, Rosie, director, Christian Ditter]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Christian Ditter
Context triple: [Love, Rosie, director, Christian Ditter]
  • A. Christian Ditter chosen
    Christian Ditter is a German film and television director, producer, and screenwriter known for works such as "How to Be Single," "Love, Rosie," and the Netflix series "Girlboss."
  • B. Christoph Dolle
    Christoph Dolle is a German local politician who serves as the mayor of the town of Blomberg.
  • C. Max Sollmann
    Max Sollmann was a Nazi official who served as a defendant in the post-World War II RuSHA Trial for his involvement in racial and resettlement policies of the SS.
  • D. Michael Stütz
    Michael Stütz is a German local politician who serves as the mayor of the municipality of Königsbronn in Baden-Württemberg.
  • E. Jochen Kuttler
    Jochen Kuttler is a German local politician who serves as the mayor of the town of Wadern in Saarland.
  • 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_69d6aa5e51e8819095f06881cecf152e completed April 8, 2026, 7:19 p.m.
NER Named-entity recognition batch_69d710410a04819090036597ac0d271c completed April 9, 2026, 2:34 a.m.
NED1 Entity disambiguation (via context triple) batch_69e343ffc428819085599f251b7553e5 completed April 18, 2026, 8:42 a.m.
Created at: April 8, 2026, 9:14 p.m.