Triple
T31723416
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Troisième Cru Classé |
E809644
|
entity |
| Predicate | appliesToWineType |
P91796
|
FINISHED |
| Object | red Bordeaux wine |
—
|
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: red Bordeaux wine | Statement: [Troisième Cru Classé, appliesToWineType, red Bordeaux wine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: appliesToWineType Context triple: [Troisième Cru Classé, appliesToWineType, red Bordeaux wine]
-
A.
sweetWineSuitability
Indicates the degree to which something is appropriate or recommended for pairing with or serving as a sweet wine.
-
B.
usesWineType
Indicates that one entity makes use of, incorporates, or is associated with a particular type or category of wine.
-
C.
wineVariety
chosen
Indicates the specific type or variety of wine associated with an entity.
-
D.
regulatesWineType
Indicates that one entity has authority or influence over the rules, standards, or conditions governing a particular type of wine.
-
E.
wineTypeAllowed
Indicates that a particular type of wine is permitted or acceptable in a given context or for a given purpose.
- 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_69f348e009c8819095d77df52c645b9c |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69fe779248c081909f0ed1a2a0df23db |
completed | May 8, 2026, 11:53 p.m. |
| PD | Predicate disambiguation | batch_69fe76eaf6d48190998bc7168749cc42 |
completed | May 8, 2026, 11:51 p.m. |
Created at: April 30, 2026, 11:19 p.m.