Triple
T1056990
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Levi-Civita connection |
E22817
|
entity |
| Predicate | instanceOf |
P0
|
FINISHED |
| Object | affine connection |
C3506
|
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: affine connection Context triple: [Levi-Civita connection, instanceOf, affine connection]
-
A.
pseudo-Riemannian manifold
A pseudo-Riemannian manifold is a smooth manifold equipped with a nondegenerate, symmetric metric tensor of arbitrary signature that allows measurement of lengths and angles, including those with indefinite sign as in spacetime geometry.
-
B.
differential geometric object
chosen
A differential geometric object is a mathematical entity, such as a manifold, tensor, or connection, defined on smooth spaces and characterized by properties that are invariant under smooth coordinate transformations.
-
C.
Lorentzian manifold
A Lorentzian manifold is a smooth manifold equipped with a metric tensor of signature \((-+\cdots+)\) (or its variants) that models spacetime in general relativity by distinguishing timelike, spacelike, and null directions.
-
D.
tensor field
A tensor field is a mathematical object that assigns a tensor (a multilinear map or multidimensional array following specific transformation rules) to every point in a space or manifold, varying smoothly from point to point.
-
E.
(0,2)-tensor
A (0,2)-tensor is a bilinear map that takes two vectors as input and returns a scalar, often representing objects like metrics or covariant tensor fields on a vector space or manifold.
- 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_69a493dada0481909c43649f9843ea91 |
completed | March 1, 2026, 7:30 p.m. |
Created at: March 1, 2026, 7:42 p.m.