Triple
T192234
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Super Proton Synchrotron |
E3744
|
entity |
| Predicate | magnetType |
P3957
|
FINISHED |
| Object | conventional electromagnets |
—
|
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: conventional electromagnets | Statement: [Super Proton Synchrotron, magnetType, conventional electromagnets]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: magnetType Context triple: [Super Proton Synchrotron, magnetType, conventional electromagnets]
-
A.
usesMagnetType
chosen
Indicates that one entity employs or operates with a specific type of magnet in its function or configuration.
-
B.
hasMagnetosphere
Indicates that an astronomical body possesses a magnetic field strong enough to create a surrounding magnetosphere.
-
C.
hasMaterialType
Indicates that something is composed of, made from, or characterized by a specific type of material.
-
D.
driveType
Indicates the type or configuration of the drive mechanism used to power or propel an entity.
-
E.
hasElectricCharge
Indicates that an entity possesses a nonzero electric charge as a physical property.
- 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_69a2548debd48190ae3a06d6e65b53c6 |
completed | Feb. 28, 2026, 2:35 a.m. |
| NER | Named-entity recognition | batch_69a259669ba08190a5be1d2e10e70b27 |
completed | Feb. 28, 2026, 2:56 a.m. |
| PD | Predicate disambiguation | batch_69a2567567508190b3a41329a15c7156 |
completed | Feb. 28, 2026, 2:44 a.m. |
Created at: Feb. 28, 2026, 2:41 a.m.