Triple
T28506903
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | security.debian.org |
E721384
|
entity |
| Predicate | mirrorPolicy |
P165451
|
FINISHED |
| Object | mirrored to multiple servers for availability |
—
|
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: mirrored to multiple servers for availability | Statement: [security.debian.org, mirrorPolicy, mirrored to multiple servers for availability]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mirrorPolicy Context triple: [security.debian.org, mirrorPolicy, mirrored to multiple servers for availability]
-
A.
mirrorType
Indicates that one entity is a specific kind or category of mirror in relation to another entity.
-
B.
reflectsPolicy
Indicates that one entity embodies, represents, or is aligned with the rules, principles, or stance defined by a particular policy.
-
C.
mirrorTechnology
Indicates a relationship where one technology closely reflects, imitates, or duplicates the functionality or design of another.
-
D.
mirrorsRulesOf
Indicates that one entity’s rules or governing principles are modeled after, reflect, or closely replicate those of another entity.
-
E.
mirrorCount
Indicates the number of mirrors associated with or present in relation to a given entity or context.
- 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_69f01a5c072081908c7b04bcf6478da9 |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_69f659355a208190be2609ffc7a9c427 |
completed | May 2, 2026, 8:06 p.m. |
| PD | Predicate disambiguation | batch_69f6575d89788190aca478e4aea05a65 |
completed | May 2, 2026, 7:58 p.m. |
| PDg | Predicate description generation | batch_69f65875030881909007c502b7dcc998 |
completed | May 2, 2026, 8:03 p.m. |
Created at: April 28, 2026, 3:09 a.m.