Triple
T17004885
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arak heavy water reactor |
E412544
|
entity |
| Predicate | designedFuelType |
P11927
|
FINISHED |
| Object | natural uranium fuel |
—
|
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: natural uranium fuel | Statement: [Arak heavy water reactor, designedFuelType, natural uranium fuel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: designedFuelType Context triple: [Arak heavy water reactor, designedFuelType, natural uranium fuel]
-
A.
fuelCharacteristic
Indicates a relationship where a fuel is associated with one of its defining properties or qualities, such as composition, performance, or behavior.
-
B.
laterFuelType
Indicates that one fuel type is used or adopted after another fuel type in time.
-
C.
fuelTypeSupported
chosen
Indicates that a system, device, or component is capable of operating with or is designed to accept a specified type of fuel.
-
D.
fuelRole
Indicates that one entity serves as the fuel or energy source used or consumed by another entity in a process or operation.
-
E.
typicalFuel
Indicates the kind of fuel that is normally or most commonly used by an entity (such as a device, vehicle, or system).
- 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.