Triple
T3011693
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | მტკვარი |
E82235
|
entity |
| Predicate | აუზის_ფართობი |
P13670
|
FINISHED |
| Object | დაახლოებით 188000 კვადრატული კილომეტრი |
—
|
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: დაახლოებით 188000 კვადრატული კილომეტრი | Statement: [მტკვარი, აუზის_ფართობი, დაახლოებით 188000 კვადრატული კილომეტრი]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: აუზის_ფართობი Context triple: [მტკვარი, აუზის_ფართობი, დაახლოებით 188000 კვადრატული კილომეტრი]
-
A.
area
Indicates that one entity has a measured two-dimensional extent or surface size quantified by another entity.
-
B.
lengthInKm
Indicates that one entity specifies the length or distance of another entity measured in kilometers.
-
C.
areaApprox
Indicates that one entity’s area is approximately equal to the area of another entity.
-
D.
areaApproxKm2
chosen
Indicates that one entity has an approximate area, measured in square kilometers, given by the other entity.
-
E.
widthKilometres
Indicates the measurement of how wide something is, expressed in kilometres.
- 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.