Triple

T6418560
Position Surface form Disambiguated ID Type / Status
Subject Charles Robberts Swart E127887 entity
Predicate succeededBy P78 FINISHED
Object Jim Fouché E549523 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: Jim Fouché | Statement: [Charles Robberts Swart, succeededBy, Jim Fouché]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jim Fouché
Context triple: [Charles Robberts Swart, succeededBy, Jim Fouché]
  • A. Jim Fouché chosen
    Jim Fouché was a South African National Party politician who served as the country’s ceremonial State President from 1968 to 1975.
  • B. Bob Gaillard
    Bob Gaillard was a prominent American college basketball coach best known for leading the University of San Francisco Dons during the 1970s.
  • C. Raymond Bonner
    Raymond Bonner is an American investigative journalist and author known for his groundbreaking reporting on human rights abuses and U.S. foreign policy, particularly in Central America.
  • D. Roy Furman
    Roy Furman is an American theater producer and financier known for backing numerous successful Broadway productions.
  • E. William Blinn
    William Blinn was an American television writer and producer best known for his work on landmark series and miniseries such as "Roots" and "Brian's Song."
  • 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_69c0083815208190a9b299b8e0640218 completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c068eb6c988190b54de6182d0f490d completed March 22, 2026, 10:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6637d35888190bbe9802229e55df1 completed March 27, 2026, 11:01 a.m.
Created at: March 22, 2026, 4:42 p.m.