Triple
T26946336
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Domaine de la Romanée-Conti |
E678653
|
entity |
| Predicate | whiteWineFrom |
P161359
|
FINISHED |
| Object | Montrachet Grand Cru |
—
|
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: Montrachet Grand Cru | Statement: [Domaine de la Romanée-Conti, whiteWineFrom, Montrachet Grand Cru]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: whiteWineFrom Context triple: [Domaine de la Romanée-Conti, whiteWineFrom, Montrachet Grand Cru]
-
A.
whiteWineShare
Indicates the proportion or share of white wine within a larger set, such as total wine consumption, production, or sales.
-
B.
wineStyle
Indicates the stylistic category or type of wine (such as its production style, sweetness, body, or other defining characteristics) associated with an entity.
-
C.
whiteWineProductionAllowed
Indicates that producing white wine is permitted under the relevant rules, regulations, or conditions.
-
D.
wineVariety
Indicates the specific type or variety of wine associated with an entity.
-
E.
wineList
Indicates that an entity is a list or collection of wines associated with another entity (such as a restaurant, event, or menu).
- F. None of above. chosen
Provenance (4 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_69eeeb4d69588190a7c912164a1c37b3 |
completed | April 27, 2026, 4:51 a.m. |
| NER | Named-entity recognition | batch_69f620858a4081909de8afda69398553 |
completed | May 2, 2026, 4:04 p.m. |
| PD | Predicate disambiguation | batch_69f611af72ac819094598dd2530d7411 |
completed | May 2, 2026, 3:01 p.m. |
| PDg | Predicate description generation | batch_69f6125e54e0819088ee33a20efcc9e6 |
completed | May 2, 2026, 3:03 p.m. |
Created at: April 27, 2026, 6:21 a.m.