Triple
T18714448
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | თერგი |
E457598
|
entity |
| Predicate | წყლის აუზი |
P1778
|
FINISHED |
| Object | კასპიის ზღვის აუზი |
—
|
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: კასპიის ზღვის აუზი | Statement: [თერგი, წყლის აუზი, კასპიის ზღვის აუზი]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: წყლის აუზი Context triple: [თერგი, წყლის აუზი, კასპიის ზღვის აუზი]
-
A.
reservoir
Indicates that one entity serves as a storage or containment source (often for a resource) that can supply or affect another entity.
-
B.
watercourseHasDam
Indicates that a watercourse (such as a river or stream) has a dam constructed on or across it.
-
C.
bodyOfWater
chosen
Indicates that one entity is a body of water that is geographically or physically associated with another entity.
-
D.
isWatercourseOf
Indicates that a watercourse (such as a river or stream) flows through, belongs to, or is geographically associated with a particular area or feature.
-
E.
riverImpounded
Indicates that a river’s natural flow is obstructed or controlled, typically by a dam or similar structure, creating an impoundment such as a reservoir.
- 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_69d8d392aad081909fe31aa03e6e97d1 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e56ab4ee6881908f19558937cbb078 |
completed | April 19, 2026, 11:52 p.m. |
| PD | Predicate disambiguation | batch_69e478e0889c8190a118d67b200ce8ef |
completed | April 19, 2026, 6:40 a.m. |
Created at: April 10, 2026, 11:50 a.m.