Triple
T213521
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Corsicans |
E4767
|
entity |
| Predicate | traditionalProduct |
P3553
|
FINISHED |
| Object | Corsican wine |
—
|
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: Corsican wine | Statement: [Corsicans, traditionalProduct, Corsican wine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: traditionalProduct Context triple: [Corsicans, traditionalProduct, Corsican wine]
-
A.
primaryProduct
Indicates that one entity is the main or most important product associated with, produced by, or offered by another entity.
-
B.
traditionalCraft
Indicates that an entity is associated with or practices a craft or skill that is rooted in long-established, culturally transmitted traditions.
-
C.
traditionalOrder
Indicates that entities are arranged or occur according to a customary, historically established sequence or hierarchy.
-
D.
typicalProductionType
Indicates the usual or characteristic type of production activity associated with an entity.
-
E.
commodity
chosen
Indicates that one entity is a tradable good or resource that is bought, sold, or exchanged in relation to another entity.
- 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_69a2575cb1dc8190a01ad332426dc339 |
completed | Feb. 28, 2026, 2:47 a.m. |
| NER | Named-entity recognition | batch_69a25c32ae208190a03d504ef43ea659 |
completed | Feb. 28, 2026, 3:08 a.m. |
| PD | Predicate disambiguation | batch_69a25b509400819093a6c1a1bac861e3 |
completed | Feb. 28, 2026, 3:04 a.m. |
Created at: Feb. 28, 2026, 2:52 a.m.