Triple

T9248433
Position Surface form Disambiguated ID Type / Status
Subject Niklas Frank E222256 entity
Predicate name P16 FINISHED
Object Niklas Frank E222256 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: Niklas Frank | Statement: [Niklas Frank, name, Niklas Frank]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Niklas Frank
Context triple: [Niklas Frank, name, Niklas Frank]
  • A. Niklas Frank chosen
    Niklas Frank is a German journalist and author known for his critical writings about his father, Nazi governor-general Hans Frank, and the legacy of the Third Reich.
  • B. Andreas Stahl
    Andreas Stahl is a Swedish mixed martial artist who has competed in the UFC’s welterweight division.
  • C. Jan Niklas
    Jan Niklas is a German actor known for his work in European cinema and television, particularly in historical and dramatic roles.
  • D. Matthias Kleinheisterkamp
    Matthias Kleinheisterkamp was a high-ranking Waffen-SS officer and division commander during World War II who served in several key SS formations on the Eastern and Western Fronts.
  • E. Hannes Messemer
    Hannes Messemer was a German actor best known for his roles in postwar European cinema, particularly in war and drama films.
  • 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_69ca841d2b18819089f9faf5b2c2aec0 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd05f6d62c8190a1e33f1854767b47 completed April 1, 2026, 11:48 a.m.
NED1 Entity disambiguation (via context triple) batch_69d09bd3fb4c8190a7fa9a60c7f286a0 completed April 4, 2026, 5:04 a.m.
Created at: March 30, 2026, 7:31 p.m.