Triple
T22298514
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Romny Uyezd |
E551188
|
entity |
| Predicate | presentDayCountrySubdivision |
P119114
|
FINISHED |
| Object | Sumy 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: Sumy Oblast | Statement: [Romny Uyezd, presentDayCountrySubdivision, Sumy Oblast]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: presentDayCountrySubdivision Context triple: [Romny Uyezd, presentDayCountrySubdivision, Sumy Oblast]
-
A.
identifiesCurrentSubdivision
Indicates that one entity specifies or designates the current administrative or organizational subdivision to which another entity belongs.
-
B.
administrativeDivisionToday
Indicates that one entity currently functions as an administrative subdivision or jurisdictional unit within the other.
-
C.
presentDayCityRegion
Indicates that a city is located within or associated with a particular region in the present day.
-
D.
presentDayProvince
Indicates that one entity is the present-day administrative province in which the other entity is currently located or to which it now belongs.
-
E.
presentDayAdministrativeAreasInclude
chosen
Indicates that one present-day administrative area geographically or jurisdictionally contains another administrative area.
- 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_69e11e45fb848190a1b2ae21296e3a5f |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1572200c88190b9413286136fef15 |
completed | April 29, 2026, 12:56 a.m. |
| PD | Predicate disambiguation | batch_69e72ffa438481908f80879aef2a589b |
completed | April 21, 2026, 8:06 a.m. |
Created at: April 16, 2026, 8:41 p.m.