Triple
T26253922
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | E8 lattice |
E656669
|
entity |
| Predicate | isPositiveDefinite |
P151074
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [E8 lattice, isPositiveDefinite, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isPositiveDefinite Context triple: [E8 lattice, isPositiveDefinite, true]
-
A.
isPositiveSemidefinite
chosen
Indicates that a matrix or operator has all non-negative eigenvalues, meaning all quadratic forms it defines are greater than or equal to zero.
-
B.
isSelfAdjoint
Indicates that an operator is equal to its own adjoint (conjugate transpose), meaning it has the same effect as its Hermitian transpose in the given inner product space.
-
C.
isHermitian
Indicates that an operator or matrix is equal to its own conjugate transpose, ensuring real eigenvalues and orthogonal eigenvectors.
-
D.
isSymmetric
Indicates that a relationship holds in both directions between two entities, so if it applies from A to B, it also applies from B to A.
-
E.
isSkewSymmetric
Indicates that a relation or matrix changes sign when its arguments or indices are swapped, i.e., R(x, y) = −R(y, x), with all diagonal/self-relations being zero.
- 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_69ee5b4d25ac819086acb51184602576 |
completed | April 26, 2026, 6:37 p.m. |
| NER | Named-entity recognition | batch_69f60dcc29cc81908880bd825cb12141 |
completed | May 2, 2026, 2:44 p.m. |
| PD | Predicate disambiguation | batch_69f602d2ec748190ae95154f34c7878f |
completed | May 2, 2026, 1:57 p.m. |
Created at: April 26, 2026, 9:08 p.m.