Triple
T23120442
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tokamak Fusion Test Reactor |
E576876
|
entity |
| Predicate | toroidalField |
P22845
|
FINISHED |
| Object | strong toroidal magnetic field for confinement |
—
|
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: strong toroidal magnetic field for confinement | Statement: [Tokamak Fusion Test Reactor, toroidalField, strong toroidal magnetic field for confinement]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: toroidalField Context triple: [Tokamak Fusion Test Reactor, toroidalField, strong toroidal magnetic field for confinement]
-
A.
toroidalFieldCoilsCount
Indicates the number of toroidal field coils associated with or used in a system or device.
-
B.
magneticField
chosen
Indicates the presence, strength, or configuration of a magnetic field associated with an entity or region.
-
C.
magneticFieldStrength
Indicates the intensity or magnitude of a magnetic field associated with an entity or at a specific location.
-
D.
hasDirectionOfFieldLines
Indicates that one entity specifies or defines the orientation or direction in which the field lines of another entity are directed.
-
E.
numberOfPlanarCoils
Indicates the quantity of planar coils associated with or contained in a given 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.