Triple
T12347151
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Crémant de Loire |
E294384
|
entity |
| Predicate | totalAgingMinimum |
P71763
|
FINISHED |
| Object | 12 months |
—
|
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: 12 months | Statement: [Crémant de Loire, totalAgingMinimum, 12 months]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: totalAgingMinimum Context triple: [Crémant de Loire, totalAgingMinimum, 12 months]
-
A.
minimumAgingTotal
chosen
Indicates that the relationship captures the smallest possible total amount of aging (or elapsed time) accumulated across the relevant entities or process.
-
B.
minimumAgingNonVintage
Indicates the minimum required aging period that a non-vintage product must undergo before it can be released or considered compliant with a standard.
-
C.
minimumAgingVintage
Indicates the earliest vintage or production year from which an item (often a wine or similar product) must date in order to meet a specified minimum aging requirement.
-
D.
oldestAge
Indicates that the associated value represents the greatest (maximum) age within a given group, set, or context.
-
E.
endAgeMa
Indicates the age (in years) at which a marriage or marital relationship ends.
- 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_69d6ab6ccbec8190b09e2d357aa80064 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d93f7ba17481908b03af7316b28d9b |
completed | April 10, 2026, 6:20 p.m. |
| PD | Predicate disambiguation | batch_69d93ecb5efc819086a3530282278bb1 |
completed | April 10, 2026, 6:17 p.m. |
Created at: April 8, 2026, 9:53 p.m.