Triple

T22459126
Position Surface form Disambiguated ID Type / Status
Subject Harry Mulisch E555185 entity
Predicate name P16 FINISHED
Object Harry Mulisch 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: Harry Mulisch | Statement: [Harry Mulisch, name, Harry Mulisch]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harry Mulisch
Context triple: [Harry Mulisch, name, Harry Mulisch]
  • A. Harry Mulisch chosen
    Harry Mulisch was a prominent Dutch novelist and essayist, regarded as one of the "Great Three" of postwar Dutch literature.
  • B. Cees Nooteboom
    Cees Nooteboom is a Dutch novelist, poet, and travel writer renowned for his intellectually rich, stylistically innovative works and his significant influence on contemporary European literature.
  • C. Herman Koch
    Herman Koch is a Dutch writer and actor best known internationally for his darkly satirical novel "The Dinner."
  • D. Peter Altenberg
    Peter Altenberg was an Austrian impressionist writer and key figure of fin-de-siècle Viennese literary culture, known for his short, sketch-like prose pieces capturing everyday urban life.
  • E. Martin Walser
    Martin Walser was a prominent German novelist, playwright, and essayist known for his psychologically nuanced portrayals of postwar German society and his involvement in literary debates.
  • 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_69e11e51fdec8190adfdf9f8a6362221 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15b7e01fc8190825c3dc024484440 completed April 29, 2026, 1:14 a.m.
Created at: April 16, 2026, 8:48 p.m.