Triple
T34689092
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cava DO |
E890834
|
entity |
| Predicate | minimumAgingOnLeesParajeCalificado |
P71763
|
FINISHED |
| Object | 36 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: 36 months | Statement: [Cava DO, minimumAgingOnLeesParajeCalificado, 36 months]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: minimumAgingOnLeesParajeCalificado Context triple: [Cava DO, minimumAgingOnLeesParajeCalificado, 36 months]
-
A.
minimumAgingOnLeesGranReserva
Indicates the minimum required time that a Gran Reserva wine must spend aging on its lees before it can be designated as such.
-
B.
minimumAgingTotal
chosen
Indicates that the relationship captures the smallest possible total amount of aging (or elapsed time) accumulated across the relevant entities or process.
-
C.
minimumAgeMa
Indicates that there is a specified minimum age requirement associated with an entity, below which the related action, status, or relationship is not permitted.
-
D.
minimumAgeInYears
Indicates the smallest number of years an entity must have lived or existed to meet a specified age requirement.
-
E.
maximumAgeMa
Indicates that there is a specified maximum age limit applicable to an entity or relationship.
- 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_69f349db7ab8819086808e833f472871 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f731cc6d1881908f80386ef4d70a09 |
completed | May 3, 2026, 11:30 a.m. |
| PD | Predicate disambiguation | batch_69f7317779e08190bf85777578221a6b |
completed | May 3, 2026, 11:28 a.m. |
Created at: May 1, 2026, 2:05 a.m.