Triple
T17520853
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ARPACK |
E426675
|
entity |
| Predicate | fullName |
P16
|
FINISHED |
| Object | ARnoldi PACKage |
—
|
NE NERFINISHED |
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: ARnoldi PACKage | Statement: [ARPACK, fullName, ARnoldi PACKage]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: ARnoldi PACKage Context triple: [ARPACK, fullName, ARnoldi PACKage]
-
A.
arpack
chosen
arpack is a numerical software library for efficiently computing a few eigenvalues and eigenvectors of large sparse matrices, commonly used in scientific computing and machine learning.
-
B.
EISPACK
EISPACK is a numerical software library written in Fortran for computing eigenvalues and eigenvectors of matrices, widely used before being superseded by LAPACK.
-
C.
ScaLAPACK
ScaLAPACK is a high-performance library for solving large-scale linear algebra problems on distributed-memory parallel computers.
-
D.
LINPACK
LINPACK is a widely used benchmark and software library for performing numerical linear algebra computations, particularly solving systems of linear equations.
-
E.
LAPACK
LAPACK is a widely used software library that provides highly optimized routines for numerical linear algebra operations such as solving systems of equations, eigenvalue problems, and singular value decompositions.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d889de677081909b22d2657b1f0292 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e452d23cf08190925510344fa36f57 |
completed | April 19, 2026, 3:58 a.m. |
Created at: April 10, 2026, 5:49 a.m.