Triple
T22989235
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kangson enrichment site (alleged) |
E572000
|
entity |
| Predicate | linkedToProgramType |
P44188
|
FINISHED |
| Object | nuclear weapons development |
—
|
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: nuclear weapons development | Statement: [Kangson enrichment site (alleged), linkedToProgramType, nuclear weapons development]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: linkedToProgramType Context triple: [Kangson enrichment site (alleged), linkedToProgramType, nuclear weapons development]
-
A.
linkedProgram
Indicates that one program is associated or connected to another program in a meaningful or dependent way.
-
B.
belongsToProgram
Indicates that an entity is a member of, or is associated with, a specific program.
-
C.
containsProgramType
Indicates that one entity includes or encompasses a specific type or category of program.
-
D.
relatesToProgram
chosen
Indicates that one entity has a relevant connection, association, or involvement with a particular program.
-
E.
hasProgramTypeRestriction
Indicates that there is a constraint limiting which types of programs are allowed or applicable in a given context.
- 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_69e245b535808190adef8a9df3c584db |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f182ea55cc8190b64b722ce8c45b53 |
completed | April 29, 2026, 4:02 a.m. |
| PD | Predicate disambiguation | batch_69ef3b974e7c8190b8be11dbb4518693 |
completed | April 27, 2026, 10:33 a.m. |
Created at: April 17, 2026, 3:49 p.m.