Triple

T17904923
Position Surface form Disambiguated ID Type / Status
Subject Michael Pitt E447675 entity
Predicate hasWorkedWithDirector P19638 FINISHED
Object Michael Haneke 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: Michael Haneke | Statement: [Michael Pitt, hasWorkedWithDirector, Michael Haneke]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michael Haneke
Context triple: [Michael Pitt, hasWorkedWithDirector, Michael Haneke]
  • A. Michael Haneke chosen
    Michael Haneke is an acclaimed Austrian film director and screenwriter known for his austere, unsettling dramas that critically examine modern society and human psychology.
  • B. Susanne Haneke
    Susanne Haneke is the wife of acclaimed Austrian filmmaker Michael Haneke.
  • C. Ulrich Seidl
    Ulrich Seidl is an Austrian film director and screenwriter known for his stark, provocative dramas and documentaries that explore human vulnerability and social taboos with a distinctive, often unsettling visual style.
  • D. Oliver Hirschbiegel
    Oliver Hirschbiegel is a German film and television director best known internationally for his acclaimed World War II drama "Downfall."
  • E. Stefan Ruzowitzky
    Stefan Ruzowitzky is an Austrian film director and screenwriter best known for his Academy Award–winning Holocaust drama "The Counterfeiters."
  • 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_69d8b9f6d394819082a6d69fd1e23d2f completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e49e9b643c8190a01e9ec4caa88183 completed April 19, 2026, 9:21 a.m.
Created at: April 10, 2026, 10:19 a.m.