Triple
T28034013
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Spätburgunder |
E708351
|
entity |
| Predicate | hasTypicalAcidity |
P2070
|
FINISHED |
| Object | medium acidity |
—
|
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: medium acidity | Statement: [Spätburgunder, hasTypicalAcidity, medium acidity]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTypicalAcidity Context triple: [Spätburgunder, hasTypicalAcidity, medium acidity]
-
A.
acidityLevel
chosen
Indicates the degree or intensity of acidity associated with an entity, typically measured by pH or a comparable scale.
-
B.
wineAcidityType
Indicates the type or category of acidity associated with a given wine.
-
C.
isMoreAcidicThan
Indicates that one substance has a lower pH (greater concentration of hydrogen ions) and thus a stronger acidic character than another substance.
-
D.
hasBitternessLevel
Indicates that an entity is associated with a specific degree or intensity of bitterness.
-
E.
typicalSweetnessLevel
Indicates the usual or characteristic degree of sweetness associated with something.
- 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_69ef9b6bdd9c8190bb3a574a03774ad1 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69fcd867f36081908c88c55a6a1404c1 |
completed | May 7, 2026, 6:22 p.m. |
| PD | Predicate disambiguation | batch_69fcd1f47b188190b4cf4b4c748d9d03 |
completed | May 7, 2026, 5:55 p.m. |
Created at: April 27, 2026, 8:19 p.m.