Triple
T24112498
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Evenkiysky District |
E597415
|
entity |
| Predicate | formerFederalSubjectPreReform |
P57407
|
FINISHED |
| Object | Evenk Autonomous Okrug |
—
|
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: Evenk Autonomous Okrug | Statement: [Evenkiysky District, formerFederalSubjectPreReform, Evenk Autonomous Okrug]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerFederalSubjectPreReform Context triple: [Evenkiysky District, formerFederalSubjectPreReform, Evenk Autonomous Okrug]
-
A.
formerSovietRepublic
Indicates that an entity is a country or region that was once part of the Soviet Union but is now independent.
-
B.
formerAutonomousRegion
chosen
Indicates that an entity was previously an autonomous region but no longer holds that status.
-
C.
partOfFormerSovietRepublic
Indicates that one entity was a territorial or administrative component of a country that was formerly a republic of the Soviet Union.
-
D.
partOfUnderRussianAdministration
Indicates that one entity is a territorial or administrative subdivision that is currently governed or controlled by Russian authorities.
-
E.
formerRegionBefore2016
Indicates that an entity was recognized as a region prior to the year 2016 but no longer holds that regional status after 2016.
- 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_69e288c60f9c8190af948d7354aedbeb |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1de1bd81c8190a44f07487d2ba176 |
completed | April 29, 2026, 10:31 a.m. |
| PD | Predicate disambiguation | batch_69f17651458c8190bbfd301883e46085 |
completed | April 29, 2026, 3:09 a.m. |
Created at: April 17, 2026, 11:03 p.m.