Triple
T1870010
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Macintosh LC |
E39011
|
entity |
| Predicate | videoHardware |
P8612
|
FINISHED |
| Object | built-in frame buffer with shared system RAM |
—
|
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: built-in frame buffer with shared system RAM | Statement: [Macintosh LC, videoHardware, built-in frame buffer with shared system RAM]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: videoHardware Context triple: [Macintosh LC, videoHardware, built-in frame buffer with shared system RAM]
-
A.
videoMemorySize
Indicates the amount of video memory associated with a graphics-related component or device.
-
B.
hardwareUsedBy
Indicates that a piece of hardware is utilized or operated by a particular entity (such as a person, system, or organization).
-
C.
videoOutput
Indicates that one entity produces or provides video signals or content as output to another entity or medium.
-
D.
hasVideoBoard
Indicates that an entity is equipped with or includes a video board (graphics/display hardware component).
-
E.
graphicsAdapter
chosen
Indicates a relationship where a device or system is associated with, uses, or is equipped with a particular graphics adapter (graphics processing hardware).
- 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_69a8862f7074819096afe7fe65e179e9 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69abb0f79fbc819085c54f3189a552d9 |
completed | March 7, 2026, 5 a.m. |
| PD | Predicate disambiguation | batch_69abafe2b56c81909e13d543982e6e13 |
completed | March 7, 2026, 4:56 a.m. |
Created at: March 4, 2026, 7:34 p.m.