Triple
T17798364
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gaussian symplectic ensemble |
E444351
|
entity |
| Predicate | hasEdgeStatistics |
P3976
|
FINISHED |
| Object | Tracy–Widom distribution of type β = 4 for largest eigenvalue |
—
|
NE NERFINISHED |
How this triple was built (3 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: Tracy–Widom distribution of type β = 4 for largest eigenvalue | Statement: [Gaussian symplectic ensemble, hasEdgeStatistics, Tracy–Widom distribution of type β = 4 for largest eigenvalue]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tracy–Widom distribution of type β = 4 for largest eigenvalue Context triple: [Gaussian symplectic ensemble, hasEdgeStatistics, Tracy–Widom distribution of type β = 4 for largest eigenvalue]
-
A.
Tracy–Widom distribution
chosen
The Tracy–Widom distribution is a probability distribution that describes the fluctuations of the largest eigenvalue in many classes of large random matrices and appears widely in random matrix theory and related probabilistic limit theorems.
-
B.
Airy kernel at the soft edge
The Airy kernel at the soft edge is a universal correlation kernel describing the local eigenvalue statistics near the largest eigenvalues (soft edge) of large random matrices in ensembles such as the Gaussian orthogonal ensemble.
-
C.
Laguerre β-ensembles
Laguerre β-ensembles are families of random matrix models generalizing the classical Laguerre (Wishart) ensembles to arbitrary Dyson index β, used to study eigenvalue statistics in mathematical physics and probability theory.
-
D.
Gaussian β-ensembles
Gaussian β-ensembles are families of random matrix models in which eigenvalue statistics depend continuously on a parameter β that governs the strength of eigenvalue repulsion and interpolates between classical matrix ensembles.
-
E.
Wigner semicircle law
The Wigner semicircle law is a fundamental result in random matrix theory that describes how the eigenvalues of large random symmetric (or Hermitian) matrices are distributed according to a characteristic semicircular density.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasEdgeStatistics Context triple: [Gaussian symplectic ensemble, hasEdgeStatistics, Tracy–Widom distribution of type β = 4 for largest eigenvalue]
-
A.
hasEdgeCount
Indicates that there is a specified number of edges associated with an entity, such as a graph or geometric shape.
-
B.
hasStatistics
chosen
Indicates that an entity is associated with one or more statistical measures, records, or summaries describing its quantitative properties or performance.
-
C.
hasEdgeConnectivity
Indicates that there exists a connection or link (such as a graph edge or network link) between two entities.
-
D.
hasEdge
Indicates that there exists a direct connection or link (an edge) between two entities in a graph or network.
-
E.
hasStatisticsPage
Indicates that an entity is associated with a dedicated page or resource presenting statistical information about it.
- 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_69d8b9efe370819095cd219b143ae727 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e487fcfdc8819086f41152860dfe18 |
completed | April 19, 2026, 7:45 a.m. |
| PD | Predicate disambiguation | batch_69e3d8de28688190844b65acf6af54e6 |
completed | April 18, 2026, 7:17 p.m. |
Created at: April 10, 2026, 10:13 a.m.