Triple

T19251026
Position Surface form Disambiguated ID Type / Status
Subject Stephanus Schoeman E481391 entity
Predicate familyName P18 FINISHED
Object Schoeman 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: Schoeman | Statement: [Stephanus Schoeman, familyName, Schoeman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Schoeman
Context triple: [Stephanus Schoeman, familyName, Schoeman]
  • A. Swanepoel
    Swanepoel is a South African surname most prominently associated with supermodel Candice Swanepoel.
  • B. Hendrik Schoeman
    Hendrik Schoeman was a prominent South African politician and Boer leader who served as a government minister in the South African Republic during the late 19th century.
  • C. Vorster
    Vorster is a South African surname most prominently associated with B. J. Vorster, who served as prime minister during the apartheid era.
  • D. Stephanus Schoeman chosen
    Stephanus Schoeman was a 19th-century Boer military and political leader who briefly headed the South African Republic during its early, turbulent years.
  • E. Greeff
    Greeff is a surname of likely Afrikaans or Dutch origin borne by individuals such as Jacoba Elizabeth Greeff.
  • 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_69d8e8cd9d1081908a181d02b88b59b8 completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e5fb30bf6c819094c44aceb544a023 completed April 20, 2026, 10:08 a.m.
Created at: April 10, 2026, 1:27 p.m.