Triple
T310934
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | H Reactor |
E7604
|
entity |
| Predicate | associatedProgram |
P2830
|
FINISHED |
| Object | U.S. nuclear deterrent |
—
|
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: U.S. nuclear deterrent | Statement: [H Reactor, associatedProgram, U.S. nuclear deterrent]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedProgram Context triple: [H Reactor, associatedProgram, U.S. nuclear deterrent]
-
A.
organizationAssociatedWith
Indicates that there is a formal or recognized connection or affiliation between an organization and another entity.
-
B.
grantProgram
Indicates that an entity administers or is associated with a structured grant-based funding program.
-
C.
isAssociatedWith
chosen
Indicates that there exists a connection, relationship, or involvement between two entities without specifying its exact nature.
-
D.
relatedPoliticalProgram
Indicates that one political program is associated with, connected to, or contextually linked with another political program.
-
E.
associatedState
Indicates that one entity is linked or connected to a particular state, condition, or status of another entity.
- 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_69a2e7e7af7881908890039d6be4e9b8 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2ea49636c8190a69cbd951fc0a4db |
completed | Feb. 28, 2026, 1:14 p.m. |
| PD | Predicate disambiguation | batch_69a2e940b9e8819092b821ff17ed026b |
completed | Feb. 28, 2026, 1:10 p.m. |
Created at: Feb. 28, 2026, 1:07 p.m.