Triple
T20337105
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ცხინვალი |
E495642
|
entity |
| Predicate | კონფლიქტის ზონა |
P34508
|
FINISHED |
| Object | ქართულ-ოსური კონფლიქტი |
—
|
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: ქართულ-ოსური კონფლიქტი | Statement: [ცხინვალი, კონფლიქტის ზონა, ქართულ-ოსური კონფლიქტი]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: კონფლიქტის ზონა Context triple: [ცხინვალი, კონფლიქტის ზონა, ქართულ-ოსური კონფლიქტი]
-
A.
regionOfConflict
chosen
Indicates that a specified region is the location where a particular conflict or dispute takes place.
-
B.
locatedOnSideOfConflict
Indicates that an entity is positioned or aligned on a particular side or faction within a conflict.
-
C.
conflictRegion
Indicates that the entities are located in or associated with a geographic area characterized by active or recent conflict, tension, or hostilities.
-
D.
conflictGround
Indicates that one entity is the cause, basis, or subject matter of a conflict involving another entity.
-
E.
locationDuringConflict
Indicates that an entity is situated in a specific place for some or all of the duration of a particular conflict or hostilities.
- 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_69e0b4a1a09881908d97270d6971a25a |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e677ed75e081909bfc534033ac1c59 |
completed | April 20, 2026, 7:01 p.m. |
| PD | Predicate disambiguation | batch_69e5762655ac8190a8cc48a29fa2c0c4 |
completed | April 20, 2026, 12:41 a.m. |
Created at: April 16, 2026, 11:23 a.m.