Triple
T21683184
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Argentine national nuclear program |
E535162
|
entity |
| Predicate | reactorTypeUsed |
P3675
|
FINISHED |
| Object | pressurized heavy-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: pressurized heavy-water reactor | Statement: [Argentine national nuclear program, reactorTypeUsed, pressurized heavy-water reactor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reactorTypeUsed Context triple: [Argentine national nuclear program, reactorTypeUsed, pressurized heavy-water reactor]
-
A.
reactorType
chosen
Indicates the specific kind or category of reactor associated with an entity.
-
B.
reactorTypeLicensed
Indicates that a specific type of nuclear reactor has been formally approved and licensed for use by the relevant regulatory authority.
-
C.
reactor
Indicates a relationship where an entity functions as or is associated with a nuclear or chemical reactor system.
-
D.
reactorVendor
Indicates the company or organization that supplied or manufactured a given reactor.
-
E.
reactorModel
Indicates a specific reactor design or configuration that an entity is based on, uses, or is associated with.
- 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_69e0c469b6ec8190aee4cadd1527db91 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef96c7c6a08190bbd9a89b8a3b921b |
completed | April 27, 2026, 5:03 p.m. |
| PD | Predicate disambiguation | batch_69e6968abfdc81909cf9e0bd72db9eca |
completed | April 20, 2026, 9:11 p.m. |
Created at: April 16, 2026, 6:43 p.m.