Triple
T29996410
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Belarus–Ukraine border |
E762036
|
entity |
| Predicate | borderingUkraineOblast |
P196393
|
FINISHED |
| Object | Chernihiv Oblast |
—
|
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: Chernihiv Oblast | Statement: [Belarus–Ukraine border, borderingUkraineOblast, Chernihiv Oblast]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: borderingUkraineOblast Context triple: [Belarus–Ukraine border, borderingUkraineOblast, Chernihiv Oblast]
-
A.
borderingBelarusRegion
chosen
Indicates that one region shares a land border with a region located in Belarus.
-
B.
establishedAsOblast
Indicates that an administrative region was formally created or designated with the status of an oblast.
-
C.
bordersToTheEast
Indicates that one entity shares a boundary with another entity and is located directly to the east of it.
-
D.
borderedOnSovietSide
Indicates that one entity shared a border specifically with the Soviet-controlled side of another entity or region.
-
E.
sharesBorderWithPolishVoivodeship
Indicates that one entity has a land or water boundary directly adjoining a Polish voivodeship.
- 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_69f224695498819094a81037cad401e2 |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69fe349879848190bcd77e3cc3470458 |
completed | May 8, 2026, 7:08 p.m. |
| PD | Predicate disambiguation | batch_69fe31e3cf908190b23ebc2f7fe58722 |
completed | May 8, 2026, 6:56 p.m. |
Created at: April 29, 2026, 6:40 p.m.