Triple
T34546368
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hitchin connection |
E886934
|
entity |
| Predicate | instanceOf |
P0
|
FINISHED |
| Object | projectively flat connection |
C45572
|
CONCEPT FINISHED |
How this triple was built (1 step)
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.
CD
Concept disambiguation
gpt-5-mini-2025-08-07
Target class: projectively flat connection Context triple: [Hitchin connection, instanceOf, projectively flat connection]
-
A.
Finsler metric
A Finsler metric is a function on the tangent bundle of a manifold that assigns to each tangent vector a length in a smooth, positively homogeneous, and strongly convex way, generalizing the notion of a Riemannian metric.
-
B.
tensorial connection coefficient
A tensorial connection coefficient is a geometric object that encodes how tensor components change under parallel transport or differentiation on a manifold in a way that transforms as a true tensor.
-
C.
curvature tensor
A curvature tensor is a multilinear mathematical object in differential geometry that measures how much a space (or manifold) deviates from being flat by quantifying the failure of vectors to return to their original direction after parallel transport around infinitesimal loops.
-
D.
configuration in projective geometry
A configuration in projective geometry is a structured arrangement of points, lines, and sometimes higher-dimensional subspaces, together with specified incidence relations among them.
-
E.
connection on a fiber bundle
chosen
A connection on a fiber bundle is a geometric structure that specifies how to consistently differentiate or "transport" fibers along paths in the base space, thereby splitting motions into horizontal and vertical components.
- F. None of above.
Provenance (1 batch)
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_69f349cff89081908f91e0b064f4833e |
completed | April 30, 2026, 12:23 p.m. |
Created at: May 1, 2026, 2:02 a.m.