Triple
T17676325
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | LAPACK |
E440650
|
entity |
| Predicate | predecessor |
P97
|
FINISHED |
| Object | EISPACK |
—
|
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: EISPACK | Statement: [LAPACK, predecessor, EISPACK]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: EISPACK Context triple: [LAPACK, predecessor, EISPACK]
-
A.
EISPACK
chosen
EISPACK is a numerical software library written in Fortran for computing eigenvalues and eigenvectors of matrices, widely used before being superseded by LAPACK.
-
B.
LINPACK
LINPACK is a widely used benchmark and software library for performing numerical linear algebra computations, particularly solving systems of linear equations.
-
C.
arpack
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.
-
D.
ELL (ELLPACK)
ELL (ELLPACK) is a sparse matrix storage format that stores each row with a fixed number of nonzero elements, enabling efficient and regular memory access patterns on parallel architectures like GPUs.
-
E.
Jacobi eigenvalue algorithm
The Jacobi eigenvalue algorithm is an iterative numerical method for computing all eigenvalues and eigenvectors of a real symmetric matrix by applying a sequence of orthogonal similarity transformations.
- 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_69d8b9e940b081908b862bb0e6e89b0d |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e46f6d9ab88190ab0e25eac8b0101c |
completed | April 19, 2026, 6 a.m. |
Created at: April 10, 2026, 10:01 a.m.