Triple
T15999503
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | PowerVR2 |
E388058
|
entity |
| Predicate | memoryInterface |
P120709
|
FINISHED |
| Object | connected to 8 MB of video RAM in Dreamcast |
—
|
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: connected to 8 MB of video RAM in Dreamcast | Statement: [PowerVR2, memoryInterface, connected to 8 MB of video RAM in Dreamcast]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: memoryInterface Context triple: [PowerVR2, memoryInterface, connected to 8 MB of video RAM in Dreamcast]
-
A.
memoryController
Indicates a relationship where one entity manages, coordinates, or regulates access to memory resources for another entity or system.
-
B.
memoryType
Indicates the specific category or kind of memory associated with an entity or process.
-
C.
memoryModel
Indicates a relationship where an entity serves as or uses a specific model or framework for representing, organizing, or managing memory.
-
D.
memoryCharacteristic
Indicates a relationship where a specific property or quality is attributed to a memory or memory-related entity.
-
E.
memoryRegion
Indicates a relationship where one entity represents or refers to a specific region or segment within a larger memory space.
- F. None of above. chosen
Provenance (4 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_69d86daa562c81908aacc179c0fe8fb5 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e173b3bf6c81909230170e833d7ce7 |
completed | April 16, 2026, 11:41 p.m. |
| PD | Predicate disambiguation | batch_69e142dc081c819082527e3fa8773460 |
completed | April 16, 2026, 8:13 p.m. |
| PDg | Predicate description generation | batch_69e173af801c8190bfc0f602831bb594 |
completed | April 16, 2026, 11:41 p.m. |
Created at: April 10, 2026, 4:55 a.m.