Triple

T11447253
Position Surface form Disambiguated ID Type / Status
Subject Pieces of a Woman E271296 entity
Predicate director P255 FINISHED
Object Kornél Mundruczó E275039 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: Kornél Mundruczó | Statement: [Pieces of a Woman, director, Kornél Mundruczó]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kornél Mundruczó
Context triple: [Pieces of a Woman, director, Kornél Mundruczó]
  • A. Kornél Mundruczó chosen
    Kornél Mundruczó is a Hungarian film and theatre director known internationally for acclaimed works such as "White God" and "Pieces of a Woman."
  • B. István Szabó
    István Szabó is a renowned Hungarian film director and screenwriter, best known for his historical and psychological dramas that often explore Central European identity and 20th-century political upheavals.
  • C. Béla Tarr
    Béla Tarr is a Hungarian film director renowned for his bleak, philosophical dramas and signature use of extremely long takes and slow, meditative pacing.
  • D. László Nemes
    László Nemes is a Hungarian film director best known internationally for his Oscar-winning Holocaust drama "Son of Saul."
  • E. Miklós Jancsó
    Miklós Jancsó was a renowned Hungarian film director celebrated for his long takes, choreographed camera movements, and politically charged explorations of power and oppression.
  • 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_69d6aadff8888190a13f253f0d460874 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d81c6d4890819082fb4a670feb2629 completed April 9, 2026, 9:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69e5d3bdafb08190aadf5d63facfedaf completed April 20, 2026, 7:20 a.m.
Created at: April 8, 2026, 9:35 p.m.