Triple
T7979102
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Silvaner wine |
E185519
|
entity |
| Predicate | canBeProducedAs |
P74478
|
FINISHED |
| Object | dry 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: dry wine | Statement: [Silvaner wine, canBeProducedAs, dry wine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canBeProducedAs Context triple: [Silvaner wine, canBeProducedAs, dry wine]
-
A.
producesFor
Indicates that one entity creates, manufactures, or generates something specifically intended for another entity’s use, benefit, or distribution.
-
B.
producedAs
chosen
Indicates that one entity is created, generated, or brought into existence as a result or output of another entity or process.
-
C.
hasProduction
Indicates that an entity is associated with, or responsible for, the creation or manufacture of another entity or product.
-
D.
canBeConstructedWith
Indicates that one entity can be formed, built, or assembled using another entity as material, components, or means.
-
E.
eligibleProductionType
Indicates that a given entity qualifies for or is allowed to participate in a specified type or category of production.
- 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_69ca829851908190b4e03829353ee7c3 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3c261904819086910898071f3629 |
completed | March 31, 2026, 3:14 a.m. |
| PD | Predicate disambiguation | batch_69cb048009a08190b4c577208a9f8f76 |
completed | March 30, 2026, 11:17 p.m. |
Created at: March 30, 2026, 5:14 p.m.