Triple
T30124540
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UKHH |
E765655
|
entity |
| Predicate | locationOblast |
P202672
|
FINISHED |
| Object | Kharkiv 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: Kharkiv Oblast | Statement: [UKHH, locationOblast, Kharkiv Oblast]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locationOblast Context triple: [UKHH, locationOblast, Kharkiv Oblast]
-
A.
establishedAsOblast
Indicates that an administrative region was formally created or designated with the status of an oblast.
-
B.
administrativeOkrug
Indicates that one entity functions as an administrative district or okrug governing or encompassing another entity within an administrative hierarchy.
-
C.
associatedVoivodeship
Indicates that one entity is administratively or geographically linked to a specific voivodeship (province-level region).
-
D.
modernBelarusianAdministrativeRegion
Indicates that an entity is an administrative region within the contemporary state structure of Belarus.
-
E.
cityOrDistrict
Indicates that the subject is classified as either a city or a district in relation to the object.
- F. None of above. chosen
Provenance (4 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_69f2247716748190ae4f16998f49ddf1 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_6a00ab25c5b48190ad07ff508392ef56 |
completed | May 10, 2026, 3:58 p.m. |
| PD | Predicate disambiguation | batch_6a00a8a5cfc48190bbe97fb2bbd1b947 |
completed | May 10, 2026, 3:47 p.m. |
| PDg | Predicate description generation | batch_6a00ab24c4b0819088a8bba78f20b3d3 |
completed | May 10, 2026, 3:58 p.m. |
Created at: April 29, 2026, 7:14 p.m.