Triple
T37874968
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ignalina |
E944693
|
entity |
| Predicate | formerSovietFacilityNearby |
P179784
|
FINISHED |
| Object | Ignalina Nuclear Power Plant |
—
|
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: Ignalina Nuclear Power Plant | Statement: [Ignalina, formerSovietFacilityNearby, Ignalina Nuclear Power Plant]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerSovietFacilityNearby Context triple: [Ignalina, formerSovietFacilityNearby, Ignalina Nuclear Power Plant]
-
A.
formerFacilityNearby
Indicates that an entity was previously located in a facility that was situated close to another specified entity or place.
-
B.
operatedFacilityNear
Indicates that an entity operated a facility located in close geographic proximity to another specified entity or place.
-
C.
distanceFromChernobylNPP
Indicates the spatial distance between an entity and the Chernobyl Nuclear Power Plant.
-
D.
nearbyIndustrialInstallation
chosen
Indicates that one entity is located close to an industrial facility or installation.
-
E.
locatedNearFormer
Indicates that one entity is situated close to another entity that previously occupied a nearby or the same location.
- 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_69f76eef55d481908ca6660b4b532550 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_6a0123d1162c81908182d01ba3ddd236 |
completed | May 11, 2026, 12:33 a.m. |
| PD | Predicate disambiguation | batch_6a01236713d88190b12a567c0dfb2d49 |
completed | May 11, 2026, 12:31 a.m. |
Created at: May 3, 2026, 4:19 p.m.