Triple
T29867613
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Material Definition Language |
E758497
|
entity |
| Predicate | targetBackend |
P129426
|
FINISHED |
| Object | CUDA |
—
|
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: CUDA | Statement: [Material Definition Language, targetBackend, CUDA]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: targetBackend Context triple: [Material Definition Language, targetBackend, CUDA]
-
A.
backendTarget
Indicates that one entity serves as the backend system, service, or endpoint that another entity connects to or depends on for processing or functionality.
-
B.
hasBackend
chosen
Indicates that one entity functions as the backend or server-side component that supports or powers another entity.
-
C.
usesBackendTools
Indicates that one entity relies on or operates tools, systems, or services that function on the backend to perform its tasks or provide its functionality.
-
D.
implementationTarget
Indicates that one entity serves as the concrete implementation or realization of another entity’s specification, interface, or design.
-
E.
targetFeature
Indicates that one entity is the specific feature, attribute, or characteristic that another entity is directed toward, focused on, or intended to affect.
- 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_69f2245b4dec8190b85f664d918a00a5 |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69fd2839880c819099a7a89783f2270e |
completed | May 8, 2026, 12:03 a.m. |
| PD | Predicate disambiguation | batch_69fd23dc5da48190ae8ba08947d34956 |
completed | May 7, 2026, 11:44 p.m. |
Created at: April 29, 2026, 5:52 p.m.