Triple
T19341767
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ribolla Gialla |
E483771
|
entity |
| Predicate | knownAs |
P39
|
FINISHED |
| Object | Rebula |
—
|
NE NERFINISHED |
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: Rebula | Statement: [Ribolla Gialla, knownAs, Rebula]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rebula Context triple: [Ribolla Gialla, knownAs, Rebula]
-
A.
Rebula
chosen
Rebula is a white wine grape variety traditionally grown in the Vipava Valley and surrounding regions, known for producing fresh, mineral-driven wines.
-
B.
Rebati
Rebati is a pioneering Odia short story by Fakir Mohan Senapati, often regarded as one of the earliest and most influential works in modern Odia literature.
-
C.
Rechila
Rechila was a 5th-century king of the Suebi in Gallaecia, known for expanding and consolidating their kingdom in the Iberian Peninsula.
-
D.
Beldibi
Beldibi is a coastal resort village in Turkey’s Antalya Province, known for its beaches, forested mountain backdrop, and proximity to ancient ruins and natural attractions.
-
E.
Rebola
Rebola is a town on the island of Bioko in Equatorial Guinea, located near the capital Malabo.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e8d244f8819080eb1f3491300db2 |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e6185795bc8190a63061ca794c0d67 |
completed | April 20, 2026, 12:13 p.m. |
Created at: April 10, 2026, 1:33 p.m.