Triple
T26814304
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Romanée-Saint-Vivant |
E672081
|
entity |
| Predicate | servingRecommendation |
P170635
|
FINISHED |
| Object | serve at cellar temperature |
—
|
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: serve at cellar temperature | Statement: [Romanée-Saint-Vivant, servingRecommendation, serve at cellar temperature]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servingRecommendation Context triple: [Romanée-Saint-Vivant, servingRecommendation, serve at cellar temperature]
-
A.
servingSuggestionRed
Indicates that something is recommended or suggested to be served together with a red wine.
-
B.
servesType
Indicates that one entity provides, offers, or is used to deliver a particular type, category, or kind of thing or service.
-
C.
isTypicallyServedFor
Indicates that one item is most commonly or customarily served as a meal or course for the other (e.g., a dish typically served for breakfast, lunch, or dinner).
-
D.
servesProduct
Indicates that one entity provides or offers a particular product to others, typically in a commercial or service context.
-
E.
servesDish
Indicates that one entity prepares and presents a specific dish as food for another entity.
- 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_69eeb3225a3c8190aaf6746efeded2f3 |
completed | April 27, 2026, 12:51 a.m. |
| NER | Named-entity recognition | batch_69f693ffa7908190aa4c451b16df9be6 |
completed | May 3, 2026, 12:17 a.m. |
| PD | Predicate disambiguation | batch_69f690eb1e948190aab41a89969519a5 |
completed | May 3, 2026, 12:03 a.m. |
| PDg | Predicate description generation | batch_69f6938244648190a553b532387b812c |
completed | May 3, 2026, 12:14 a.m. |
Created at: April 27, 2026, 4:31 a.m.