Triple

T22584634
Position Surface form Disambiguated ID Type / Status
Subject Pasteur Bizimungu E564755 entity
Predicate name P16 FINISHED
Object Pasteur Bizimungu 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: Pasteur Bizimungu | Statement: [Pasteur Bizimungu, name, Pasteur Bizimungu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pasteur Bizimungu
Context triple: [Pasteur Bizimungu, name, Pasteur Bizimungu]
  • A. Pasteur Bizimungu chosen
    Pasteur Bizimungu is a Rwandan politician who served as president of Rwanda in the years following the 1994 genocide.
  • B. Émile Roux
    Émile Roux was a French physician, bacteriologist, and pioneer of immunology who played a key role in developing vaccines and antitoxins, notably for diphtheria.
  • C. Camille Pasteur
    Camille Pasteur was one of the children of the renowned French chemist and microbiologist Louis Pasteur.
  • D. Albert Calmette
    Albert Calmette was a French physician, bacteriologist, and immunologist best known as a co-developer of the BCG vaccine against tuberculosis.
  • E. Alexandre Yersin
    Alexandre Yersin was a Swiss-French physician and bacteriologist best known for identifying the plague bacillus (Yersinia pestis) and contributing significantly to infectious disease research in the late 19th century.
  • 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_69e245836014819091b91ed3074742a3 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f1615b4fa08190a8d2d66e01db429f completed April 29, 2026, 1:39 a.m.
Created at: April 17, 2026, 2:44 p.m.