Triple

T23380511
Position Surface form Disambiguated ID Type / Status
Subject Spaak E593731 entity
Predicate notableBearer P458 FINISHED
Object Charles 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: Charles Spaak | Statement: [Spaak, notableBearer, Charles Spaak]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Charles Spaak
Context triple: [Spaak, notableBearer, Charles Spaak]
  • A. Charles Spaak chosen
    Charles Spaak was a prominent Belgian-born screenwriter known for his influential work on classic French cinema from the 1930s to the 1950s.
  • B. Robert Swink
    Robert Swink was an American film editor known for his work on numerous classic Hollywood films, including "Roman Holiday."
  • C. Lou Dorfsman
    Lou Dorfsman was an influential American graphic designer and longtime creative director at CBS, renowned for shaping the network’s visual identity and for his pioneering work in modern corporate design and typography.
  • D. Jan van der Does
    Jan van der Does was a Dutch nobleman, poet, and military leader best known for organizing and leading the defense of Leiden during the Eighty Years' War.
  • E. Jef Alberts
    Jef Alberts is a fictional character from the long-running Dutch soap opera "Goede tijden, slechte tijden," known as one of its early and central figures.
  • 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.