Triple
T22857779
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kobeliaky Uyezd |
E566830
|
entity |
| Predicate | historicalEntityType |
P149997
|
FINISHED |
| Object | former administrative division |
—
|
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: former administrative division | Statement: [Kobeliaky Uyezd, historicalEntityType, former administrative division]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: historicalEntityType Context triple: [Kobeliaky Uyezd, historicalEntityType, former administrative division]
-
A.
historicalEntityWithin
Indicates that one historical entity is geographically, administratively, or contextually contained within another historical entity.
-
B.
historicalEntityAssociated
Indicates that one entity has a documented historical connection, relevance, or involvement with another entity.
-
C.
historicalFigure
Indicates that an entity is recognized as a notable person from the past who played a significant role in history.
-
D.
historicalPeople
Indicates that the related entities are people who lived in or are associated with a past historical period or context.
-
E.
notableHistoricalEntity
Indicates that an entity holds recognized historical significance or prominence within a historical context.
- 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_69e24589083081908d5694c4fdc80086 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17ebe3f9c8190a864f4e84dc7795d |
completed | April 29, 2026, 3:45 a.m. |
| PD | Predicate disambiguation | batch_69eed2d507c08190895ed971af0fc755 |
completed | April 27, 2026, 3:07 a.m. |
| PDg | Predicate description generation | batch_69eeeb577e2081909f4a4e9c296535c0 |
completed | April 27, 2026, 4:51 a.m. |
Created at: April 17, 2026, 3:37 p.m.