Triple
T4342035
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Experimental Advanced Superconducting Tokamak |
E97804
|
entity |
| Predicate | minorRadius |
P2019
|
FINISHED |
| Object | approximately 0.45 meters |
—
|
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: approximately 0.45 meters | Statement: [Experimental Advanced Superconducting Tokamak, minorRadius, approximately 0.45 meters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: minorRadius Context triple: [Experimental Advanced Superconducting Tokamak, minorRadius, approximately 0.45 meters]
-
A.
ringRadius
Indicates the size of a ring by specifying the distance from its center to its outer edge.
-
B.
hasMeanRadius
chosen
Indicates that an entity possesses a specified average radius measurement, typically representing the mean distance from its center to its surface.
-
C.
minimumRadiusOfCurves
Indicates the smallest allowable radius for any curve in a path, track, or route associated with the subject.
-
D.
minorProduction
Indicates that an entity is involved in a secondary or less significant production activity relative to a primary production process.
-
E.
minorDenomination
Indicates that one entity is a smaller or subordinate unit of currency or value in relation to 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_69b34548402c819085ab68b27c235a87 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b351878c148190b384053479d41caf |
completed | March 12, 2026, 11:51 p.m. |
| PD | Predicate disambiguation | batch_69b34f4fe1c481908d6d66e15697c04b |
completed | March 12, 2026, 11:42 p.m. |
Created at: March 12, 2026, 11:14 p.m.