Triple
T28064858
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Шилка |
E709217
|
entity |
| Predicate | находится в административной единице |
P96712
|
FINISHED |
| Object | Забайкальский край |
—
|
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: Забайкальский край | Statement: [Шилка, находится в административной единице, Забайкальский край]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: находится в административной единице Context triple: [Шилка, находится в административной единице, Забайкальский край]
-
A.
находитсяК
chosen
Indicates that one entity is located at, in, or near another entity.
-
B.
устьеНаходитсяВ
Indicates that the mouth of a river or stream is located within or at a specified body of water or geographic area.
-
C.
находитсяВСтране
Indicates that something is located within the territory or borders of a specific country.
-
D.
establishedInAdministrativeUnit
Indicates that something (such as an organization, facility, or institution) was founded or formally created within a specific administrative unit or jurisdiction.
-
E.
meetsInAdministrativeTerritorialEntity
Indicates that two or more entities come together or hold a meeting within a specified administrative territorial unit (such as a city, district, or region).
- 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_69ef9b6eb6d88190a3fea236eb0f7bed |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69f6401a0a048190acce63aa4eceffac |
completed | May 2, 2026, 6:19 p.m. |
| PD | Predicate disambiguation | batch_69f637120c008190b2b5adf46f022e48 |
completed | May 2, 2026, 5:40 p.m. |
Created at: April 27, 2026, 8:42 p.m.