Triple
T8210230
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ROM BIOS |
E191794
|
entity |
| Predicate | providesInterface |
P12981
|
FINISHED |
| Object | software interrupt services |
—
|
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: software interrupt services | Statement: [ROM BIOS, providesInterface, software interrupt services]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: providesInterface Context triple: [ROM BIOS, providesInterface, software interrupt services]
-
A.
usesInterface
Indicates that one entity interacts with or operates another entity through a specified interface or set of interface methods.
-
B.
hasInterface
chosen
Indicates that one entity provides, exposes, or is connected through a defined interface to another entity.
-
C.
hasInterfaceCategory
Indicates that an interface is classified as belonging to a particular category or type of interface.
-
D.
usesImplement
Indicates that one entity employs or makes use of another entity as a tool, instrument, or means to perform an action or achieve a purpose.
-
E.
alsoImplements
Indicates that an entity, in addition to its primary implementation, implements another interface, protocol, or specification as well.
- 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_69ca82c8c054819087fedd9a5436b8a3 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb76dd881c8190adcbeb2f33d3295c |
completed | March 31, 2026, 7:25 a.m. |
| PD | Predicate disambiguation | batch_69cb36ad01ac81909609b15f6a6c8581 |
completed | March 31, 2026, 2:51 a.m. |
Created at: March 30, 2026, 5:44 p.m.