Triple
T11278021
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rubis-class nuclear attack submarines |
E266985
|
entity |
| Predicate | powerPlantOrigin |
P95519
|
FINISHED |
| Object | French-designed nuclear reactor |
—
|
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: French-designed nuclear reactor | Statement: [Rubis-class nuclear attack submarines, powerPlantOrigin, French-designed nuclear reactor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: powerPlantOrigin Context triple: [Rubis-class nuclear attack submarines, powerPlantOrigin, French-designed nuclear reactor]
-
A.
powerplantOrigin
chosen
Indicates that a power plant originates from, is sourced in, or is associated with a particular geographic location or administrative region.
-
B.
powerplantType
Indicates the specific kind or category of power plant associated with an entity, based on how it generates energy.
-
C.
powerplantFor
Indicates that one entity functions as the power plant or primary energy source serving another entity.
-
D.
powerplantLocation
Indicates that a power plant is situated at or associated with a specific geographic location.
-
E.
powerPlantName
Indicates the specific name assigned to a power plant.
- 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_69d6aac8c2f48190ad0596f1f89f0470 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e967ebb4819080b09ed3cec44e77 |
completed | April 9, 2026, 6:01 p.m. |
| PD | Predicate disambiguation | batch_69d787a240588190aa097298f951c915 |
completed | April 9, 2026, 11:04 a.m. |
Created at: April 8, 2026, 9:31 p.m.