Triple

T21391418
Position Surface form Disambiguated ID Type / Status
Subject All Quiet on the Western Front (2022 film) E527658 entity
Predicate castMember P1668 FINISHED
Object Moritz Klaus 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: Moritz Klaus | Statement: [All Quiet on the Western Front (2022 film), castMember, Moritz Klaus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Moritz Klaus
Context triple: [All Quiet on the Western Front (2022 film), castMember, Moritz Klaus]
  • A. Moritz Klaus chosen
    Moritz Klaus is a German actor best known internationally for his role in the 2022 anti-war film "All Quiet on the Western Front."
  • B. Moritz Kerz
    Moritz Kerz is a mathematician known for his work in arithmetic geometry and algebraic K-theory.
  • C. Moritz Suter
    Moritz Suter is a Swiss entrepreneur and aviation executive best known for building Crossair into a major European regional airline.
  • D. Moritz von Fries
    Moritz von Fries was an influential Austrian banker and aristocratic patron of the arts in early 19th-century Vienna, known for supporting leading composers of his time.
  • E. Moritz Leuenberger
    Moritz Leuenberger is a Swiss politician and former member of the Federal Council who served as head of the Federal Department of Environment, Transport, Energy and Communications.
  • 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_69e0b51ff3748190935c0a513c62a12b completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e8b113690c81909c0a378fddba5d3a completed April 22, 2026, 11:29 a.m.
Created at: April 16, 2026, 5:13 p.m.