Triple
T27657740
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | R7 (program counter) |
E697037
|
entity |
| Predicate | resetBehavior |
P143140
|
FINISHED |
| Object | loaded with start address on reset or boot |
—
|
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: loaded with start address on reset or boot | Statement: [R7 (program counter), resetBehavior, loaded with start address on reset or boot]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: resetBehavior Context triple: [R7 (program counter), resetBehavior, loaded with start address on reset or boot]
-
A.
resetType
Indicates the specific kind or method of reset applied to an entity, process, or system state.
-
B.
resetRule
Indicates that a rule is returned to its initial or default state, typically clearing any prior changes or accumulated effects.
-
C.
defaultBehavior
Indicates the standard or fallback way an entity acts or responds when no specific or overriding instructions or conditions are provided.
-
D.
restorationBehavior
Indicates actions or processes aimed at returning something to a previous, original, or improved state after damage, loss, or degradation.
-
E.
bootBehavior
chosen
Indicates how a system or device behaves during its startup or boot process.
- 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_69ef590b85a4819083ec7c12bd3c9c10 |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_69f631dad37c8190ab1b5918ad8a928a |
completed | May 2, 2026, 5:18 p.m. |
| PD | Predicate disambiguation | batch_69f62c1a92648190835a2c5250d8c758 |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 27, 2026, 2:35 p.m.