Triple
T35412311
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ghemme DOCG |
E1023544
|
entity |
| Predicate | upgradeFromDOCToDOCG |
P23059
|
FINISHED |
| Object | 20th century |
—
|
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: 20th century | Statement: [Ghemme DOCG, upgradeFromDOCToDOCG, 20th century]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: upgradeFromDOCToDOCG Context triple: [Ghemme DOCG, upgradeFromDOCToDOCG, 20th century]
-
A.
containsDOCG
Indicates that one entity includes or encompasses a DOCG (Denominazione di Origine Controllata e Garantita) designation or item within it.
-
B.
upgradeFor
Indicates that one entity serves as an improved or enhanced replacement for another entity.
-
C.
upgradeGoal
Indicates that an entity has a target or intended improvement to a higher level, version, or state relative to its current condition.
-
D.
upgradesFrom
Indicates that one entity is a newer or improved version that replaces or enhances another entity.
-
E.
upgradeDate
chosen
Indicates the date on which an entity was upgraded to a newer or improved version.
- 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_69f76df54bac8190bd0d3b0eb35cda5f |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f79da9f80c8190b0afd8509f28747b |
completed | May 3, 2026, 7:10 p.m. |
| PD | Predicate disambiguation | batch_69f79617d40481909ba372f94209c08b |
completed | May 3, 2026, 6:38 p.m. |
Created at: May 3, 2026, 4:03 p.m.