Triple
T18923981
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Albert Calmette |
E462930
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Calmette |
—
|
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: Calmette | Statement: [Albert Calmette, familyName, Calmette]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Calmette Context triple: [Albert Calmette, familyName, Calmette]
-
A.
Albert Calmette
chosen
Albert Calmette was a French physician, bacteriologist, and immunologist best known as a co-developer of the BCG vaccine against tuberculosis.
-
B.
Yersin
Yersin is a French surname most notably borne by Alexandre Yersin, the bacteriologist who co-discovered the plague-causing bacterium Yersinia pestis.
-
C.
Guerin
Guerin is a surname of French origin borne by various notable individuals across fields such as arts, sports, and public life.
-
D.
Pasteur Bizimungu
Pasteur Bizimungu is a Rwandan politician who served as president of Rwanda in the years following the 1994 genocide.
-
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_69d8dcfdbbb881909964fa5a75bd0b48 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c9b549448190850d7eed4de7872b |
completed | April 20, 2026, 6:37 a.m. |
Created at: April 10, 2026, 11:59 a.m.