Triple
T8782097
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | DNS over DTLS |
E208754
|
entity |
| Predicate | preservesProperty |
P17760
|
FINISHED |
| Object | low latency |
—
|
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: low latency | Statement: [DNS over DTLS, preservesProperty, low latency]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: preservesProperty Context triple: [DNS over DTLS, preservesProperty, low latency]
-
A.
preservesFeature
chosen
Indicates that one entity maintains or keeps intact a particular feature, property, or characteristic of another entity during some process or interaction.
-
B.
preservesOwnLaw
Indicates that an entity maintains, upholds, or continues to follow its own established law or legal framework.
-
C.
preservesFragmentsOf
Indicates that one entity maintains, protects, or keeps intact partial remains or pieces of another entity.
-
D.
partiallyPreservedThrough
Indicates that something is not fully intact but has been maintained or conserved to some extent by or via another entity or medium.
-
E.
parityProperty
Indicates that a relationship or quantity has a specific parity (such as being even, odd, or matching in parity) according to the defined property.
- 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_69ca835fbee88190bf625939bac48d7f |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc5f7155b081908891e84b704f0ebf |
completed | March 31, 2026, 11:57 p.m. |
| PD | Predicate disambiguation | batch_69cc5c1aff3881908be6a9cbc9f50461 |
completed | March 31, 2026, 11:43 p.m. |
Created at: March 30, 2026, 6:42 p.m.