Triple

T4340149
Position Surface form Disambiguated ID Type / Status
Subject Uncle Paul E97559 entity
Predicate notableBearer P458 FINISHED
Object Paul Kruger E3410 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: Paul Kruger | Statement: [Uncle Paul, notableBearer, Paul Kruger]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Paul Kruger
Context triple: [Uncle Paul, notableBearer, Paul Kruger]
  • A. Paul Kruger chosen
    Paul Kruger was a prominent Boer political and military leader who served as President of the South African Republic and became a central figure in resistance against British rule during the late 19th century.
  • B. Otto Kruger
    Otto Kruger was an American stage and film actor known for his suave, often villainous roles in Hollywood films of the 1930s and 1940s.
  • C. Paul Kruger Church
    Paul Kruger Church is a historic Christian church in Pretoria, South Africa, associated with the legacy of former Boer leader and president Paul Kruger.
  • D. A.B. Xuma
    A.B. Xuma was a prominent South African medical doctor and anti-apartheid leader who served as president of the African National Congress in the 1940s.
  • E. Lon Kruger
    Lon Kruger is an American college basketball coach known for leading multiple programs to the NCAA Tournament, including Final Four appearances with Florida and Oklahoma.
  • 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_69b3454662a481908fbcd0bbfaa3a0a4 completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b3516f92588190bdf004d8020c1203 completed March 12, 2026, 11:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5f5ca65948190b435ecc30190a0e4 completed March 14, 2026, 11:56 p.m.
Created at: March 12, 2026, 11:14 p.m.