Triple
T9756933
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NPF-57 |
E236576
|
entity |
| Predicate | reactorTypeLicensed |
P90832
|
FINISHED |
| Object | boiling water 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: boiling water reactor | Statement: [NPF-57, reactorTypeLicensed, boiling water reactor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reactorTypeLicensed Context triple: [NPF-57, reactorTypeLicensed, boiling water reactor]
-
A.
reactorType
Indicates the specific kind or category of reactor associated with an entity.
-
B.
dualLicensed
Indicates that an entity is simultaneously licensed under two distinct licenses or licensing regimes.
-
C.
typeOfLicense
Indicates the specific kind or category of license associated with an entity.
-
D.
operatedUnderLicenseFrom
Indicates that one entity conducts its activities or uses certain rights with formal permission granted by another entity that holds the original authority or ownership.
-
E.
hasLicensing
Indicates that one entity holds or is granted licensing rights, permissions, or authorization in relation to another entity or resource.
- 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_69ca84d64f6c8190a4ed4e9f5936eda5 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cd9fb2889481908fba4a449d5007fe |
completed | April 1, 2026, 10:44 p.m. |
| PD | Predicate disambiguation | batch_69cd03d0772c8190bd1750cf1cfba309 |
completed | April 1, 2026, 11:38 a.m. |
| PDg | Predicate description generation | batch_69cd081a9c5c819093439be7e802ff85 |
completed | April 1, 2026, 11:57 a.m. |
Created at: March 30, 2026, 8:24 p.m.