Triple
T33173421
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Amiga 500 Plus |
E849096
|
entity |
| Predicate | floppyFormat |
P32610
|
FINISHED |
| Object | 880 KB double-density (standard Amiga format) |
—
|
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: 880 KB double-density (standard Amiga format) | Statement: [Amiga 500 Plus, floppyFormat, 880 KB double-density (standard Amiga format)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: floppyFormat Context triple: [Amiga 500 Plus, floppyFormat, 880 KB double-density (standard Amiga format)]
-
A.
floppyDiskFormat
chosen
Indicates the specific data storage format or standard used on a floppy disk.
-
B.
standardFloppyDriveSize
Indicates that one entity specifies or is associated with the standard physical size or form factor of a floppy disk drive used by another entity.
-
C.
floppyDriveCapacity
Indicates the storage capacity associated with a floppy drive.
-
D.
floppyDriveModel
Indicates that one entity is a specific model or type designation of a floppy disk drive associated with the other entity.
-
E.
compatibleFloppyDrive
Indicates that one entity can properly use, read from, or write to floppy disks designed for the other 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_69f3495be8808190bbf427733df08aad |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6dd3cc0648190a275812d6711275a |
completed | May 3, 2026, 5:29 a.m. |
| PD | Predicate disambiguation | batch_69f6d82eaee081908f06a71546315aea |
completed | May 3, 2026, 5:07 a.m. |
Created at: May 1, 2026, 1:29 a.m.