Triple
T28137805
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ukrainian independence referendum, 1991 |
E714255
|
entity |
| Predicate | highestSupportRegion |
P31408
|
FINISHED |
| Object | western Ukraine |
—
|
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: western Ukraine | Statement: [Ukrainian independence referendum, 1991, highestSupportRegion, western Ukraine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: highestSupportRegion Context triple: [Ukrainian independence referendum, 1991, highestSupportRegion, western Ukraine]
-
A.
strongestSupportRegion
chosen
Indicates the region where an entity receives its highest level of support compared to all other regions.
-
B.
regionWithStrongBlocSupport
Indicates that a geographic region exhibits notably high or concentrated support for a particular political bloc or alliance.
-
C.
supportsRegion
Indicates that one entity provides assistance, resources, or backing to a specific geographic or administrative region.
-
D.
campaignRegion
Indicates the geographic area or territory in which a campaign is conducted or targeted.
-
E.
votingRegion
Indicates the geographic or administrative area in which an entity is eligible or authorized to vote.
- 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_69efd6af156c81908f50c2cd7db0e1ef |
completed | April 27, 2026, 9:35 p.m. |
| NER | Named-entity recognition | batch_69f6b903538481909cffcb6cc1cc0e70 |
completed | May 3, 2026, 2:54 a.m. |
| PD | Predicate disambiguation | batch_69f6b626120c819097c9ad04487570d7 |
completed | May 3, 2026, 2:42 a.m. |
Created at: April 27, 2026, 9:51 p.m.