Triple
T6640676
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kindzmarauli |
E150577
|
entity |
| Predicate | typicalExportProduct |
P53553
|
FINISHED |
| Object | Georgian wine export |
—
|
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: Georgian wine export | Statement: [Kindzmarauli, typicalExportProduct, Georgian wine export]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalExportProduct Context triple: [Kindzmarauli, typicalExportProduct, Georgian wine export]
-
A.
exportedGood
Indicates that a good has been sent out from one country or region to another as part of international trade.
-
B.
typicalGoodsSold
chosen
Indicates the kinds of goods or products that an entity most commonly or characteristically sells.
-
C.
typicalProductionType
Indicates the usual or characteristic type of production activity associated with an entity.
-
D.
isTypicallySoldAs
Indicates that one entity is commonly offered for sale in the form, packaging, or configuration represented by another entity.
-
E.
exportedTo
Indicates that goods, services, or resources are sent out from one entity or region to another for trade or sale.
- 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_69c687f1a3048190828b7342f7125d5c |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6c308a08881908501c862b3029321 |
completed | March 27, 2026, 5:48 p.m. |
| PD | Predicate disambiguation | batch_69c6ad024860819084b9b535b136ede6 |
completed | March 27, 2026, 4:14 p.m. |
Created at: March 27, 2026, 2 p.m.