Triple
T30091725
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Super Tuscan wines |
E764751
|
entity |
| Predicate | typicalOakType |
P87418
|
FINISHED |
| Object | French oak barriques |
—
|
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: French oak barriques | Statement: [Super Tuscan wines, typicalOakType, French oak barriques]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalOakType Context triple: [Super Tuscan wines, typicalOakType, French oak barriques]
-
A.
oakTypeUsed
Indicates that a particular type of oak is used in relation to another entity, such as in construction, manufacturing, or production.
-
B.
typicalOakAroma
Indicates that something has the characteristic smell commonly associated with oak wood or oak aging.
-
C.
oakAgingTypical
chosen
Indicates that it is typical or customary for something (such as a product, especially a beverage) to undergo aging in oak.
-
D.
commonTreeType
Indicates that two or more entities share the same type or classification of tree.
-
E.
oakRegimen
Indicates a prescribed or customary course of actions, treatments, or behaviors associated with the entity referred to as "oak."
- 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_69f22473c0fc8190a926a8051b3b378b |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_6a036054129081909e66c5d62015e6c1 |
completed | May 12, 2026, 5:16 p.m. |
| PD | Predicate disambiguation | batch_6a035f17cbf88190acd6bdbfc9789ffb |
completed | May 12, 2026, 5:10 p.m. |
Created at: April 29, 2026, 7:06 p.m.