Triple
T16859111
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Treaty of Kars |
E409861
|
entity |
| Predicate | territoryGranted |
P22232
|
FINISHED |
| Object | Kars region |
—
|
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: Kars region | Statement: [Treaty of Kars, territoryGranted, Kars region]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: territoryGranted Context triple: [Treaty of Kars, territoryGranted, Kars region]
-
A.
landGrantedBy
Indicates that one party has given or transferred legal rights to a piece of land to another party.
-
B.
territoryPolicy
Indicates the rules, restrictions, or strategies that govern how a territory is managed, controlled, or used in relation to other entities.
-
C.
receivedTerritory
chosen
Indicates that one entity was granted or took possession of a territory from another entity.
-
D.
claimsTerritory
Indicates that one entity asserts ownership, control, or sovereign rights over a specific geographic area or region.
-
E.
territoryType
Indicates the specific kind or classification of a territory associated with an entity (e.g., country, region, zone, or jurisdiction type).
- 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_69d88395e6c88190b22730f335107c14 |
completed | April 10, 2026, 4:59 a.m. |
| NER | Named-entity recognition | batch_69e3b501f72881909f7600311705fb33 |
completed | April 18, 2026, 4:44 p.m. |
| PD | Predicate disambiguation | batch_69e32b8cbb048190878a259cc5be960e |
completed | April 18, 2026, 6:58 a.m. |
Created at: April 10, 2026, 5:24 a.m.