Triple
T7279401
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | OpenCL |
E163108
|
entity |
| Predicate | memoryHierarchy |
P9896
|
FINISHED |
| Object | global memory |
—
|
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: global memory | Statement: [OpenCL, memoryHierarchy, global memory]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: memoryHierarchy Context triple: [OpenCL, memoryHierarchy, global memory]
-
A.
memoryModel
Indicates a relationship where an entity serves as or uses a specific model or framework for representing, organizing, or managing memory.
-
B.
memoryType
chosen
Indicates the specific category or kind of memory associated with an entity or process.
-
C.
memoryCharacteristic
Indicates a relationship where a specific property or quality is attributed to a memory or memory-related entity.
-
D.
integratedMemoryController
Indicates that a memory controller is built directly into another component (such as a processor or chipset) rather than existing as a separate, external unit.
-
E.
memoryBandwidth
Indicates the rate at which data can be transferred to or from a memory system over a given period of time.
- 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_69c6885c5964819085b209701769877f |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6eb8a0b4881908ff27c5a75bd4a95 |
completed | March 27, 2026, 8:41 p.m. |
| PD | Predicate disambiguation | batch_69c6e76a84a081908d4184c55b728e48 |
completed | March 27, 2026, 8:24 p.m. |
Created at: March 27, 2026, 2:59 p.m.