Triple
T13522299
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kavkaz |
E322927
|
entity |
| Predicate | locatedOnSideOfStrait |
P31095
|
FINISHED |
| Object | eastern side of the Kerch Strait |
—
|
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: eastern side of the Kerch Strait | Statement: [Kavkaz, locatedOnSideOfStrait, eastern side of the Kerch Strait]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locatedOnSideOfStrait Context triple: [Kavkaz, locatedOnSideOfStrait, eastern side of the Kerch Strait]
-
A.
locatedInStrait
Indicates that something is situated within or passes through a narrow body of water (a strait) that connects two larger bodies of water.
-
B.
situatedOnSideOf
chosen
Indicates that one entity is located along or beside the lateral part or edge of another entity.
-
C.
separatedByOceanFrom
Indicates that two entities are located on different landmasses with an ocean lying between them as a separating barrier.
-
D.
isNorthernmostStraitOf
Indicates that one strait is the furthest north among all straits associated with a particular geographic feature or region.
-
E.
nearbyStrait
Indicates that one entity is located close to or adjacent to a particular strait.
- 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_69d80766a21881909f21a1b7421d3b8a |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbafa535cc81908d0018fef81a2848 |
completed | April 12, 2026, 2:43 p.m. |
| PD | Predicate disambiguation | batch_69dbae0b63748190b5e207f84b2532ea |
completed | April 12, 2026, 2:36 p.m. |
Created at: April 9, 2026, 9:44 p.m.