Triple

T23380520
Position Surface form Disambiguated ID Type / Status
Subject Paul-Henri Spaak E593731 entity
Predicate familyName P18 FINISHED
Object Spaak 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: Spaak | Statement: [Paul-Henri Spaak, familyName, Spaak]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Spaak
Context triple: [Paul-Henri Spaak, familyName, Spaak]
  • A. Spaak chosen
    Spaak is a Belgian surname most notably associated with Paul-Henri Spaak, a key statesman and founding figure of European integration.
  • B. Halsema
    Halsema is a Dutch surname most prominently associated with Femke Halsema, a politician who became the first female mayor of Amsterdam.
  • C. De Gucht
    De Gucht is a Belgian political family name most prominently associated with liberal politician and former EU Trade Commissioner Karel De Gucht.
  • D. Paul Spaak
    Paul Spaak was a Belgian lawyer and playwright, and the father of prominent statesman Paul-Henri Spaak.
  • E. De Wever
    De Wever is a Flemish surname most prominently associated with Belgian politician Bart De Wever, a leading figure in contemporary Flemish nationalism.
  • 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_69e25d268a50819095f2fd479da8ef3f completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f1a3b6ddfc8190a23d291286f3fe42 completed April 29, 2026, 6:22 a.m.
Created at: April 17, 2026, 5:34 p.m.