Triple
T3011700
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | მტკვარი |
E82235
|
entity |
| Predicate | გამოყენება |
P98
|
FINISHED |
| Object | სარწყავი წყლის წყარო |
—
|
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: სარწყავი წყლის წყარო | Statement: [მტკვარი, გამოყენება, სარწყავი წყლის წყარო]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: გამოყენება Context triple: [მტკვარი, გამოყენება, სარწყავი წყლის წყარო]
-
A.
usedFor
chosen
Indicates that one entity serves a purpose, function, or role in accomplishing, enabling, or supporting another entity or activity.
-
B.
usageType
Indicates the specific manner, purpose, or context in which something is used or intended to be used.
-
C.
actualUse
Indicates that an entity is currently being used or utilized in practice, as opposed to being merely available, planned, or potential.
-
D.
partOfUse
Indicates that something functions as a component or constituent within the use or application of something else.
-
E.
usedOn
Indicates that one entity is applied to, operated on, or otherwise utilized 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_69ad8b1eb53481908c39bbcd1ec104b2 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad9a66c334819082d1d320c48eca1b |
completed | March 8, 2026, 3:48 p.m. |
| PD | Predicate disambiguation | batch_69ad961a97188190809dc73430a8eda8 |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 3 p.m.