Triple
T1621447
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Windows 98 |
E35038
|
entity |
| Predicate | maxPhysicalMemory |
P3700
|
FINISHED |
| Object | approximately 1 GB (practically ~512 MB stable) |
—
|
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: approximately 1 GB (practically ~512 MB stable) | Statement: [Windows 98, maxPhysicalMemory, approximately 1 GB (practically ~512 MB stable)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: maxPhysicalMemory Context triple: [Windows 98, maxPhysicalMemory, approximately 1 GB (practically ~512 MB stable)]
-
A.
maximumVolumeSize
Indicates the largest allowable size or capacity that a volume can have within a given system or context.
-
B.
minRAM
Indicates that an entity requires at least a specified minimum amount of RAM to function or be considered valid.
-
C.
addressSpaceSize
chosen
Indicates the total amount of addressable memory or identifier range allocated or available within a given address space.
-
D.
maximumCapacity
Indicates the greatest allowable or designed amount of something that an entity can hold, contain, or handle.
-
E.
maxUnifiedMemory
Indicates the maximum amount of unified (shared CPU/GPU) memory that can be allocated or used in a given context.
- 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_69a886023194819080a3fccd6e325d0e |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69aaf4a0ef748190ae52b9656474c0ef |
completed | March 6, 2026, 3:37 p.m. |
| PD | Predicate disambiguation | batch_69a907c731808190a1d998155041b3c1 |
completed | March 5, 2026, 4:34 a.m. |
Created at: March 4, 2026, 7:28 p.m.