Triple
T33455631
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chern–Simons form |
E856766
|
entity |
| Predicate | instanceOf |
P0
|
FINISHED |
| Object | secondary characteristic class |
C58003
|
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: secondary characteristic class Context triple: [Chern–Simons form, instanceOf, secondary characteristic class]
-
A.
cohomological invariant
chosen
A cohomological invariant is a rule that assigns to each object in a given class (such as algebraic varieties, groups, or topological spaces) an element of a cohomology group in a way that is functorial and captures structural or classification information about those objects.
-
B.
cohomology theory
A cohomology theory is a functorial assignment of graded algebraic invariants to topological spaces (or other mathematical objects) that encodes global structural and obstruction information via axioms such as exactness and homotopy invariance.
-
C.
canonical classification
Canonical classification is a standardized method of organizing entities into universally recognized categories based on their essential, defining characteristics.
-
D.
homological invariant
A homological invariant is a quantity or structure derived from homology theory that remains unchanged under specified transformations, used to distinguish and classify mathematical objects up to an appropriate notion of equivalence.
-
E.
result in equivariant cohomology
A result in equivariant cohomology is a theorem or statement describing how cohomological invariants behave under a group action, typically relating equivariant cohomology groups to ordinary cohomology or geometric data of the action.
- 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_69f3497281a08190b4705de0b5f26ba7 |
completed | April 30, 2026, 12:22 p.m. |
Created at: May 1, 2026, 1:37 a.m.