Triple
T27107191
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Westinghouse 3-loop PWR |
E686612
|
entity |
| Predicate | neutronReflector |
P54127
|
FINISHED |
| Object | water and structural materials |
—
|
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: water and structural materials | Statement: [Westinghouse 3-loop PWR, neutronReflector, water and structural materials]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: neutronReflector Context triple: [Westinghouse 3-loop PWR, neutronReflector, water and structural materials]
-
A.
usesNeutronReflector
chosen
Indicates that an entity employs a neutron reflector to bounce escaping neutrons back into a region, typically to enhance or sustain a nuclear reaction.
-
B.
reflector
Indicates that one entity functions as a surface or device that reflects light, sound, or other waves originating from another entity.
-
C.
usesNeutronModerator
Indicates that one entity employs another entity as a neutron moderator to slow down neutrons in a nuclear process or system.
-
D.
neutronSourceType
Indicates the type or classification of the source from which neutrons are produced or emitted.
-
E.
neutronSpectrum
Indicates the energy distribution or range of neutrons present in a given system, interaction, or environment.
- 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_69ef148accd48190b6ed6e13a15f2a4f |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69f623fef610819086a38b74d8c934b3 |
completed | May 2, 2026, 4:19 p.m. |
| PD | Predicate disambiguation | batch_69f61b40f02081909bd9c3ea73249163 |
completed | May 2, 2026, 3:41 p.m. |
Created at: April 27, 2026, 8:51 a.m.