Triple
T8552537
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UltraFusion |
E202476
|
entity |
| Predicate | interconnectType |
P64333
|
FINISHED |
| Object | high-bandwidth die-to-die interconnect |
—
|
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: high-bandwidth die-to-die interconnect | Statement: [UltraFusion, interconnectType, high-bandwidth die-to-die interconnect]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: interconnectType Context triple: [UltraFusion, interconnectType, high-bandwidth die-to-die interconnect]
-
A.
interconnectionType
chosen
Indicates the specific kind or nature of relationship that links two or more entities together.
-
B.
interconnectTechnology
Indicates a relationship where different technologies are linked or integrated so they can work together or share information.
-
C.
connectorType
Indicates the specific kind or category of connection interface that links two entities.
-
D.
connectorTypeDesignation
Indicates the specific type or classification assigned to a connector within a connection or interface relationship.
-
E.
switchingFabric
Indicates a relationship where data traffic is routed or switched between multiple endpoints through an intermediate switching infrastructure.
- 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_69ca832610e08190b3b6c6cd2c250255 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe8882704819094b688d46169433a |
completed | March 31, 2026, 3:30 p.m. |
| PD | Predicate disambiguation | batch_69cbd113e05c81908f4f3fc1b5925164 |
completed | March 31, 2026, 1:50 p.m. |
Created at: March 30, 2026, 6:19 p.m.