Triple
T20277095
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lugana |
E503044
|
entity |
| Predicate | primaryGrapeVariety |
P975
|
FINISHED |
| Object | Turbiana |
—
|
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: Turbiana | Statement: [Lugana, primaryGrapeVariety, Turbiana]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Turbiana Context triple: [Lugana, primaryGrapeVariety, Turbiana]
-
A.
Turbiana
chosen
Turbiana is a white grape variety from northern Italy, closely associated with the Lugana wine region and known for producing fresh, mineral-driven wines with good aging potential.
-
B.
Lodoletta
Lodoletta is an opera in three acts by Italian composer Pietro Mascagni, known for its verismo style and tragic love story.
-
C.
Lamba Doria
Lamba Doria was a prominent 13th-century Genoese admiral renowned for his decisive naval victory over Venice at the Battle of Curzola in 1298.
-
D.
Fontanarrosa
Fontanarrosa is the surname of Roberto Fontanarrosa, a renowned Argentine cartoonist, writer, and humorist.
-
E.
Vincenza
Vincenza is an Italian feminine given name, commonly used as the female counterpart of Vincenzo.
- 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_69e0b4b0e79c8190bd61f22ef1329fa8 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e675e4cdfc81908c7cb4519a7d744b |
completed | April 20, 2026, 6:52 p.m. |
Created at: April 16, 2026, 10:35 a.m.