Triple
T29938253
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | cuSOLVER |
E760426
|
entity |
| Predicate | providesRoutineType |
P169058
|
FINISHED |
| Object | dense linear algebra |
—
|
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: dense linear algebra | Statement: [cuSOLVER, providesRoutineType, dense linear algebra]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: providesRoutineType Context triple: [cuSOLVER, providesRoutineType, dense linear algebra]
-
A.
includesRoutine
Indicates that one entity contains or encompasses another entity as a regular or standard part of its routine or procedure.
-
B.
runnerType
Indicates the specific category or style of running associated with an entity (e.g., sprinter, marathoner, trail runner).
-
C.
plannedServiceType
Indicates the category or kind of service that has been scheduled or planned to be provided.
-
D.
typeOfRules
Indicates that one entity specifies or categorizes the kind or category of rules that apply to or are associated with another entity.
-
E.
exposesType
chosen
Indicates that one entity reveals, makes available, or publicly presents a particular type associated with 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_69f22463f3648190a603c3ff305c660b |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69fd389cb28c819099a77e28d25f258a |
completed | May 8, 2026, 1:13 a.m. |
| PD | Predicate disambiguation | batch_69fd3826d8048190ada79a5868d1d7f3 |
completed | May 8, 2026, 1:11 a.m. |
Created at: April 29, 2026, 6:21 p.m.