Triple

T687202
Position Surface form Disambiguated ID Type / Status
Subject D. F. Malan E13309 entity
Predicate spouse P13 FINISHED
Object Helena "Lettie" Malan E85269 NE FINISHED

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: Helena "Lettie" Malan | Statement: [D. F. Malan, spouse, Helena "Lettie" Malan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Helena "Lettie" Malan
Context triple: [D. F. Malan, spouse, Helena "Lettie" Malan]
  • A. Bridgette Radebe
    Bridgette Radebe is a South African mining entrepreneur and businesswoman, recognized as one of the country’s first black female mine owners and a prominent figure in the mining industry.
  • B. Maria Louw chosen
    Maria Louw was the wife of D. F. Malan, the South African prime minister and key architect of apartheid-era policies.
  • C. Geytie Maria du Plessis
    Geytie Maria du Plessis was the wife of Paul Kruger, the influential 19th-century president of the South African Republic (Transvaal).
  • D. Yvonne Zima
    Yvonne Zima is an American actress known for her work as a child performer in films and television, including notable roles in 1990s thrillers and popular TV dramas.
  • E. Thandiwe Newton
    Thandiwe Newton is a British actress acclaimed for her nuanced performances in film and television, including prominent roles in works such as "Crash," "Westworld," and numerous other critically praised projects.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69a4933e0f98819097d22766c49b61b8 completed March 1, 2026, 7:27 p.m.
NER Named-entity recognition batch_69a4a093ac988190bb339616a3ed5adb completed March 1, 2026, 8:24 p.m.
NED1 Entity disambiguation (via context triple) batch_69a64a53c068819089e66347da55710b completed March 3, 2026, 2:41 a.m.
Created at: March 1, 2026, 7:36 p.m.