Triple
T36512871
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Borchali region |
E899956
|
entity |
| Predicate | hasHistoricalTensionsBetween |
P55763
|
FINISHED |
| Object | Georgia |
—
|
NE NERFINISHED |
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: Georgia | Statement: [Borchali region, hasHistoricalTensionsBetween, Georgia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHistoricalTensionsBetween Context triple: [Borchali region, hasHistoricalTensionsBetween, Georgia]
-
A.
historicalRelationsWith
Indicates a relationship where one entity has documented or recognized connections, interactions, or associations with another entity in the past.
-
B.
hasHistoricalPeriodOfConflict
Indicates that there exists a specific historical period during which the related entities were engaged in conflict or hostilities.
-
C.
hasEthnicTensionHistory
chosen
Indicates that there has been a history of conflict, strain, or hostility between ethnic groups within the referenced context.
-
D.
opponentInHistoricalConflict
Indicates that two entities stood on opposing sides in a specific historical conflict or war.
-
E.
doesNotHaveFormalPeaceTreatyWith
Indicates that no official, legally binding peace treaty exists between the two entities.
- 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_69f76e5dada881909da2d34bc7a9202a |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69ff65987ff88190b09be64f7c0e1da9 |
completed | May 9, 2026, 4:49 p.m. |
| PD | Predicate disambiguation | batch_69ff6525b0548190bef7a9f009e00bb8 |
completed | May 9, 2026, 4:47 p.m. |
Created at: May 3, 2026, 4:10 p.m.