Triple
T8918499
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | DNSSEC KSK |
E212351
|
entity |
| Predicate | rotationProcess |
P86397
|
FINISHED |
| Object | KSK rollover |
—
|
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: KSK rollover | Statement: [DNSSEC KSK, rotationProcess, KSK rollover]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rotationProcess Context triple: [DNSSEC KSK, rotationProcess, KSK rollover]
-
A.
rotationType
Indicates the specific kind or mode of rotational movement or orientation applied in a given context.
-
B.
rotationPractice
Indicates that an entity engages in or is involved with practicing rotational movements or rotation-related skills.
-
C.
rotationEffect
Indicates that one entity is rotated around a specified point or axis by a given angle, affecting its orientation relative to other entities.
-
D.
rotatesAmong
Indicates that an entity takes turns occupying or performing a role, position, or function in sequence with other entities.
-
E.
rotationSense
Indicates the direction or orientation in which an object or system rotates relative to a defined reference frame.
- F. None of above. chosen
Provenance (4 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_69ca8393b1808190bd4336787ffa2c40 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc6613639881909090d060f388a865 |
completed | April 1, 2026, 12:25 a.m. |
| PD | Predicate disambiguation | batch_69cc5ed0ef3c81908cc69eac852ee12a |
completed | March 31, 2026, 11:54 p.m. |
| PDg | Predicate description generation | batch_69cc600a59708190ae426044bbcd7929 |
completed | April 1, 2026, midnight |
Created at: March 30, 2026, 6:56 p.m.