Triple
T25236743
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mâcon-Solutré-Pouilly AOC |
E632357
|
entity |
| Predicate | mainMarketCategory |
P64612
|
FINISHED |
| Object | still dry white Burgundy |
—
|
LITERAL 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: still dry white Burgundy | Statement: [Mâcon-Solutré-Pouilly AOC, mainMarketCategory, still dry white Burgundy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainMarketCategory Context triple: [Mâcon-Solutré-Pouilly AOC, mainMarketCategory, still dry white Burgundy]
-
A.
coreMarket
Indicates that an entity serves as the primary or most important market for another entity’s products, services, or activities.
-
B.
marketsThrough
Indicates that one entity promotes, sells, or distributes its products or services by using another entity as a marketing or sales channel.
-
C.
parentMarket
Indicates that one market serves as the higher-level or containing market in which another market is nested or from which it is derived.
-
D.
coreCategory
chosen
Indicates that one entity is the primary or fundamental category to which another entity belongs or is classified under.
-
E.
cornerCategory
Indicates that something is classified as belonging to a specific type or category of corner.
- F. None of above.
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_69e75a8ec5f88190b9eba06ae42b413a |
completed | April 21, 2026, 11:07 a.m. |
| NER | Named-entity recognition | batch_69f47dfb2c9c8190b34148512dd535c8 |
completed | May 1, 2026, 10:18 a.m. |
| PD | Predicate disambiguation | batch_69f44d849e7c81909945438f40e35362 |
completed | May 1, 2026, 6:51 a.m. |
Created at: April 21, 2026, 1:07 p.m.