Triple
T19895918
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sherbrooke |
E478151
|
entity |
| Predicate | hasMayor |
P185
|
FINISHED |
| Object | Évelyne Beaudin |
—
|
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: Évelyne Beaudin | Statement: [Sherbrooke, hasMayor, Évelyne Beaudin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Évelyne Beaudin Context triple: [Sherbrooke, hasMayor, Évelyne Beaudin]
-
A.
Évelyne Beaudin
chosen
Évelyne Beaudin is a Canadian municipal politician who serves as the mayor of Sherbrooke, Quebec.
-
B.
Nathalie Perron
Nathalie Perron is a person notable enough to be specifically cited as a bearer of the surname Perron, though detailed public information about her is limited.
-
C.
Suzanne Brière
Suzanne Brière was the French-born wife of Indian industrialist Ratanji Dadabhoy Tata and the mother of aviation pioneer and business leader J. R. D. Tata.
-
D.
Marie-France Boisselle
Marie-France Boisselle is known as the wife of American actor Fred Ward.
-
E.
Suzanne Desrocher
Suzanne Desrocher is the widow of influential horror filmmaker George A. Romero, known for being his longtime partner and collaborator later in his life.
- 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_69d8e520682081909892916424699bd5 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6593cb45881909cc34a9c601db001 |
completed | April 20, 2026, 4:50 p.m. |
Created at: April 10, 2026, 1:52 p.m.