Triple
T17572991
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brossard |
E427984
|
entity |
| Predicate | borderedBy |
P224
|
FINISHED |
| Object | Carignan |
—
|
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: Carignan | Statement: [Brossard, borderedBy, Carignan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Carignan Context triple: [Brossard, borderedBy, Carignan]
-
A.
Carignan
Carignan is a red wine grape variety traditionally associated with southern France and Spain, known for producing deeply colored, tannic wines often used in blends.
-
B.
Carignan
chosen
Carignan is a small suburban city located on the South Shore of the Saint Lawrence River in Quebec, Canada.
-
C.
Aligoté
Aligoté is a white grape variety from Burgundy known for producing light, crisp, and high-acid wines often enjoyed young.
-
D.
Cinsault
Cinsault is a red wine grape variety from southern France, widely used in blends and rosé wines for its light color, soft tannins, and aromatic, fruity character.
-
E.
Counoise
Counoise is a dark-skinned French wine grape variety traditionally used in blends, especially in Châteauneuf-du-Pape, to add aromatic complexity, spice, and freshness.
- 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_69d889e0385081908a04b66f4dd4bd0d |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e459330c788190907a02fc98e0e24b |
completed | April 19, 2026, 4:25 a.m. |
Created at: April 10, 2026, 5:50 a.m.