Triple
T17004879
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arak heavy water reactor |
E412544
|
entity |
| Predicate | potentialCapability |
P17736
|
FINISHED |
| Object | plutonium production |
—
|
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: plutonium production | Statement: [Arak heavy water reactor, potentialCapability, plutonium production]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: potentialCapability Context triple: [Arak heavy water reactor, potentialCapability, plutonium production]
-
A.
capabilityType
Indicates the type or category of capability that an entity possesses or is associated with.
-
B.
demonstratedCapability
Indicates that an entity has shown, through evidence or performance, the ability to carry out a specific action or function.
-
C.
consideredCapability
chosen
Indicates that something is regarded or evaluated as a potential capability of an entity.
-
D.
isCapableOf
Indicates that an entity has the ability or capacity to perform a particular action or function.
-
E.
payloadCapability
Indicates the capacity or suitability of an entity to carry, support, or transport a specified payload.
- 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_69d886cb581c8190ab05f4b429c9cd85 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d382400c819092ec0ca0de815888 |
completed | April 18, 2026, 6:54 p.m. |
| PD | Predicate disambiguation | batch_69e35d552bc08190af17ef7659e094ef |
completed | April 18, 2026, 10:30 a.m. |
Created at: April 10, 2026, 5:32 a.m.