Triple
T8507773
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | DRAM |
E201374
|
entity |
| Predicate | dataBusConnection |
P59538
|
FINISHED |
| Object | connected to system memory bus |
—
|
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: connected to system memory bus | Statement: [DRAM, dataBusConnection, connected to system memory bus]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dataBusConnection Context triple: [DRAM, dataBusConnection, connected to system memory bus]
-
A.
dataBusType
Indicates the type or category of data bus used to transfer data between components or systems.
-
B.
dataInterface
Indicates that one entity serves as a data interface through which another entity can access, exchange, or manipulate data.
-
C.
systemBus
chosen
Indicates a relationship where a component is connected to or communicates over a shared system-wide communication bus.
-
D.
connectorType
Indicates the specific kind or category of connection interface that links two entities.
-
E.
connectsViaCanal
Indicates that one entity is linked or joined to another by means of a canal.
- 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_69ca8320e5748190ac2c585a0bba8193 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe5de18448190a695eec609b34e1a |
completed | March 31, 2026, 3:18 p.m. |
| PD | Predicate disambiguation | batch_69cbd10cfd208190a519049fad32c508 |
completed | March 31, 2026, 1:50 p.m. |
Created at: March 30, 2026, 6:14 p.m.