Triple
T22462157
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ricard |
E555255
|
entity |
| Predicate | similarTo |
P4460
|
FINISHED |
| Object | Pernod |
—
|
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: Pernod | Statement: [Ricard, similarTo, Pernod]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pernod Context triple: [Ricard, similarTo, Pernod]
-
A.
Pernod
chosen
Pernod is a French company best known for producing anise-flavored spirits and other alcoholic beverages, and for its historical sponsorship of major cycling competitions.
-
B.
Cointreau
Cointreau is a French orange-flavored triple sec liqueur known for its clear, crisp citrus profile and frequent use in classic cocktails.
-
C.
D’Ussé cognac
D’Ussé cognac is a modern French cognac brand, co-owned by Bacardi and Jay-Z, known for its bold, smooth flavor profile and distinctive cross-emblazoned bottle.
-
D.
Grand Marnier
Grand Marnier is a French orange-flavored liqueur made from a blend of cognac and distilled essence of bitter orange, commonly used in cocktails and desserts.
-
E.
Cognac
Cognac is a renowned French town in the Charente department, famous worldwide as the center of production for the eponymous brandy.
- 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_69e11e51fdec8190adfdf9f8a6362221 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15b80983081908084947b2e31c9d4 |
completed | April 29, 2026, 1:14 a.m. |
Created at: April 16, 2026, 8:48 p.m.