Triple
T23120432
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tokamak Fusion Test Reactor |
E576876
|
entity |
| Predicate | fusionFuel |
P1585
|
FINISHED |
| Object | deuterium |
—
|
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: deuterium | Statement: [Tokamak Fusion Test Reactor, fusionFuel, deuterium]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fusionFuel Context triple: [Tokamak Fusion Test Reactor, fusionFuel, deuterium]
-
A.
fueledBy
chosen
Indicates that one entity provides the energy or power source that enables the operation or functioning of another entity.
-
B.
fuelForm
Indicates the physical or chemical form in which a fuel exists or is supplied (e.g., liquid, gas, solid).
-
C.
fuelFraction
Indicates the proportion of an object's total mass or capacity that consists of fuel.
-
D.
fuelEnrichment
Indicates the degree to which a fuel has been processed to increase the concentration of its active or fissile component relative to its natural state.
-
E.
fuelSystem
Indicates a relationship where one entity serves as the fuel system (or part of it) that supplies, stores, or manages fuel for the operation 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_69e245f6c2e881909a228fdcfeb7c7d3 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18e4f9be881908307838bfb5edc0c |
completed | April 29, 2026, 4:51 a.m. |
| PD | Predicate disambiguation | batch_69ef89f020588190b43393e048e7eda3 |
completed | April 27, 2026, 4:08 p.m. |
Created at: April 17, 2026, 3:59 p.m.