Triple

T14580871
Position Surface form Disambiguated ID Type / Status
Subject William I, Prince of Orange E342187 entity
Predicate alsoKnownAs P39 FINISHED
Object Willem de Zwijger E339159 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: Willem de Zwijger | Statement: [William I, Prince of Orange, alsoKnownAs, Willem de Zwijger]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Willem de Zwijger
Context triple: [William I, Prince of Orange, alsoKnownAs, Willem de Zwijger]
  • A. Willem de Zwijger chosen
    Willem de Zwijger is William the Silent, Prince of Orange, the key leader of the Dutch Revolt against Spanish rule and a founding figure of the Netherlands.
  • B. Willem
    Willem is a given name, primarily used in Dutch-speaking regions, that corresponds to the English name William.
  • C. Willem Boy
    Willem Boy was a 16th-century Flemish sculptor and architect active in Sweden, known for his work at the royal court of King John III.
  • D. Willem de Vlugt
    Willem de Vlugt was a Dutch politician who served as the mayor of Amsterdam during the late 1920s and early 1930s.
  • E. Ivan De Witte
    Ivan De Witte is a Belgian businessman and football executive best known for leading KAA Gent to major sporting and organizational growth as its long-serving chairman.
  • 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_69d822ddc0f081909cd8163c7de298cd completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb41e71748190a1deacc819dd26d3 completed April 14, 2026, 9:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd94b832b08190965b727baa700403 completed May 8, 2026, 7:46 a.m.
Created at: April 10, 2026, 1:24 a.m.