Triple
T26123872
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Uzlyany, Belarus |
E659046
|
entity |
| Predicate | historicalEntityOf |
P147192
|
FINISHED |
| Object | Russian Empire |
—
|
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: Russian Empire | Statement: [Uzlyany, Belarus, historicalEntityOf, Russian Empire]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: historicalEntityOf Context triple: [Uzlyany, Belarus, historicalEntityOf, Russian Empire]
-
A.
historicalEntityWithin
chosen
Indicates that one historical entity is geographically, administratively, or contextually contained within another historical entity.
-
B.
historicalEntityType
Indicates that an entity belongs to a specific historical category or classification, such as a type, role, or function recognized in a historical context.
-
C.
historicalEntityAssociated
Indicates that one entity has a documented historical connection, relevance, or involvement with another entity.
-
D.
roleHistoricallyAssociatedWith
Indicates that one role, position, or function has been historically linked or commonly associated with another entity, role, or context over time.
-
E.
eraOfHistoricalAssociation
Indicates the historical time period during which the association or relationship between the entities took place.
- 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_69ee5bc2b2948190b458ad3f580af779 |
completed | April 26, 2026, 6:38 p.m. |
| NER | Named-entity recognition | batch_69f7626667f48190ad90867eb67ec582 |
completed | May 3, 2026, 2:57 p.m. |
| PD | Predicate disambiguation | batch_69f76175d6608190b60b268e20f49ed9 |
completed | May 3, 2026, 2:53 p.m. |
Created at: April 26, 2026, 8:10 p.m.