Triple
T14372827
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Moët Hennessy |
E356397
|
entity |
| Predicate | brand |
P1500
|
FINISHED |
| Object | Mercier |
E427464
|
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: Mercier | Statement: [Moët Hennessy, brand, Mercier]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mercier Context triple: [Moët Hennessy, brand, Mercier]
-
A.
Mercier
Mercier is a residential neighborhood in the east end of Montreal, Quebec, known for its family-oriented character and proximity to the St. Lawrence River.
-
B.
Mercier
chosen
Mercier is a historic Champagne producer based in Épernay, France, known for its accessible, popular sparkling wines and extensive cellars.
-
C.
Mercier
Mercier is the given first name of the influential American choreographer and dancer Merce Cunningham.
-
D.
Desmarais
Desmarais is a French surname, often associated with notable families and individuals in business, politics, and the arts.
-
E.
La Berri
La Berri is the commonly used nickname for La Berrichonne de Châteauroux, a French professional football club based in Châteauroux.
- 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_69d8279163a081908aec45c0e3f1e02f |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de8fb2082c8190b42cc5f2bab4f574 |
completed | April 14, 2026, 7:04 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd551002948190aeb93d245e1449a7 |
completed | May 8, 2026, 3:14 a.m. |
Created at: April 10, 2026, 1:15 a.m.