Triple

T22233367
Position Surface form Disambiguated ID Type / Status
Subject Marais Viljoen E549524 entity
Predicate familyName P18 FINISHED
Object Viljoen 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: Viljoen | Statement: [Marais Viljoen, familyName, Viljoen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Viljoen
Context triple: [Marais Viljoen, familyName, Viljoen]
  • A. Viljoen chosen
    Viljoen is an Afrikaans-origin surname commonly found in South Africa and Namibia, associated with several notable figures in politics, sports, and the military.
  • B. Voskuijl
    Voskuijl is a Dutch surname most notably associated with Bep Voskuijl, one of the helpers of Anne Frank and her family during their time in hiding.
  • C. Saasveld
    Saasveld is a small village in the Dutch province of Overijssel, known for its rural character and historic church.
  • D. Zwanenburg
    Zwanenburg is a village in North Holland, Netherlands, situated near Amsterdam and known as a suburban residential community within the Haarlemmermeer municipality.
  • E. Veulen
    Veulen is a small village in the Belgian province of Limburg, forming part of the municipality of Heers.
  • 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_69e11e4102b881909cf47d3768e25c19 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f12bf4e0348190b755a9ac0bc96cdd completed April 28, 2026, 9:51 p.m.
Created at: April 16, 2026, 8:38 p.m.