Triple
T11407161
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | BINAC |
E270268
|
entity |
| Predicate | primaryMemoryCapacity |
P52984
|
FINISHED |
| Object | 512 words per unit |
—
|
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: 512 words per unit | Statement: [BINAC, primaryMemoryCapacity, 512 words per unit]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryMemoryCapacity Context triple: [BINAC, primaryMemoryCapacity, 512 words per unit]
-
A.
mainMemorySize
chosen
Indicates the relationship specifying the size or capacity of an entity's main memory.
-
B.
primaryMemoryType
Indicates the main or dominant type of memory associated with or used by an entity in a given context.
-
C.
maxRAMOfficial
Indicates the officially specified maximum amount of RAM that is supported or allowed for an entity (such as a device or system).
-
D.
maxRAMUnofficial
Indicates the maximum amount of RAM that can be used or installed in an unofficial or unsupported configuration.
-
E.
videoMemorySize
Indicates the amount of video memory associated with a graphics-related component or device.
- 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_69d6aaddeaa8819088b30ef7b50598c9 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8014c820c81908538ba4a08e13230 |
completed | April 9, 2026, 7:43 p.m. |
| PD | Predicate disambiguation | batch_69d7e70ffd708190b62a78ebcbce9f78 |
completed | April 9, 2026, 5:51 p.m. |
Created at: April 8, 2026, 9:34 p.m.