Triple
T28406508
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hercules Graphics Card |
E719542
|
entity |
| Predicate | videoOutputType |
P83205
|
FINISHED |
| Object | monochrome |
—
|
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: monochrome | Statement: [Hercules Graphics Card, videoOutputType, monochrome]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: videoOutputType Context triple: [Hercules Graphics Card, videoOutputType, monochrome]
-
A.
videoOutput
Indicates that one entity produces or provides video signals or content as output to another entity or medium.
-
B.
videoType
Indicates the classification or category of a video (such as format, genre, or purpose) associated with an entity.
-
C.
defaultFileFormatVideo
Indicates the default file format used for saving or exporting video content.
-
D.
videoOutputConnector
chosen
Indicates a relationship where a device or component provides a connector used to output video signals to an external display or receiver.
-
E.
videoEncoding
Indicates that one entity is used to encode, compress, or transform video data into a particular digital format or representation for another entity.
- 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_69eff6f0f37c8190b37bc6fab08a9449 |
completed | April 27, 2026, 11:53 p.m. |
| NER | Named-entity recognition | batch_69f64d700f70819080f54d75296f8890 |
completed | May 2, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_69f641e2f1708190b45b48d6a43c51d2 |
completed | May 2, 2026, 6:26 p.m. |
Created at: April 28, 2026, 1:23 a.m.