Triple

T11005932
Position Surface form Disambiguated ID Type / Status
Subject John Smit E260118 entity
Predicate name P16 FINISHED
Object John Smit E260118 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: John Smit | Statement: [John Smit, name, John Smit]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Smit
Context triple: [John Smit, name, John Smit]
  • A. John Smit chosen
    John Smit is a former South African rugby union hooker who captained the Springboks to victory in the 2007 Rugby World Cup and is regarded as one of the country's most successful leaders in the sport.
  • B. Ben Viljoen
    Ben Viljoen was a prominent Boer general and political figure who played a key leadership role in the Second Boer War against the British.
  • C. Werner Louw
    Werner Louw is a person notable enough to be recognized as a bearer of the surname Louw.
  • D. Michael Louw
    Michael Louw is a person bearing the Afrikaans surname "Louw," which is of South African origin.
  • E. Roelof Botha
    Roelof Botha is a South African-born venture capitalist and former PayPal executive, known for his influential role as a partner at Sequoia Capital backing major technology companies.
  • 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_69d6aa8a6a548190a750f944ccdc8064 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d79756e6bc81908eae9d5f8ff0d43f completed April 9, 2026, 12:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69e3c8190c888190ba8d6fb2f4f3eb05 completed April 18, 2026, 6:06 p.m.
Created at: April 8, 2026, 9:25 p.m.