Triple
T34918711
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Loviisa Nuclear Power Plant |
E1007076
|
entity |
| Predicate | usesSafetySystemsFrom |
P194274
|
FINISHED |
| Object | Western Europe |
—
|
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: Western Europe | Statement: [Loviisa Nuclear Power Plant, usesSafetySystemsFrom, Western Europe]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesSafetySystemsFrom Context triple: [Loviisa Nuclear Power Plant, usesSafetySystemsFrom, Western Europe]
-
A.
measuresSafetyUsing
Indicates that an entity evaluates or assesses safety by employing a specified method, tool, or standard.
-
B.
safetySystemPlanned
Indicates that a safety system has been planned or scheduled for implementation in relation to the relevant entities.
-
C.
hasEmergencySystems
Indicates that the subject is equipped with or includes systems designed to detect, respond to, or manage emergency situations.
-
D.
safetyCategory
Indicates the classification of something according to its level or type of safety.
-
E.
hasSafetyInfrastructure
Indicates that appropriate safety-related structures, systems, or measures are present for the referenced entity or environment.
- 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_69f76dc2b6b0819095a61debbd405269 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fd68abf52881909c5a390c362b7c59 |
completed | May 8, 2026, 4:38 a.m. |
| PD | Predicate disambiguation | batch_69fd6812d0c88190930d8fa2d4b92490 |
completed | May 8, 2026, 4:35 a.m. |
| PDg | Predicate description generation | batch_69fd68ab21a0819096bfc4a8c14851ad |
completed | May 8, 2026, 4:38 a.m. |
Created at: May 3, 2026, 4 p.m.