Triple

T22116477
Position Surface form Disambiguated ID Type / Status
Subject Vrouemonument E546556 entity
Predicate architect P184 FINISHED
Object Frans Soff 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: Frans Soff | Statement: [Vrouemonument, architect, Frans Soff]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frans Soff
Context triple: [Vrouemonument, architect, Frans Soff]
  • A. Frans Soff chosen
    Frans Soff was an architect known for designing South Africa’s National Women’s Monument, a memorial dedicated to the women who suffered during the Anglo-Boer War.
  • B. Francis De Wolff
    Francis De Wolff was a British character actor known for his robust presence in mid-20th-century film and television, often appearing in horror, adventure, and historical productions.
  • C. René Paas
    René Paas is a Dutch politician who serves as the King's Commissioner (provincial governor) of Groningen in the Netherlands.
  • D. Frans Ludeke
    Frans Ludeke is a South African rugby union coach best known for his successful stints with Super Rugby teams and later coaching roles in Japan.
  • E. Paul Breuls
    Paul Breuls is a Belgian film producer known for financing and producing international feature films.
  • 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_69e11e38b3848190ac3a4fa97d56e65a completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f1294dc1148190b95ff00f475a6713 completed April 28, 2026, 9:40 p.m.
Created at: April 16, 2026, 8:31 p.m.