Triple
T22815131
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | DCCP |
E565076
|
entity |
| Predicate | comparedToTCP |
P23099
|
FINISHED |
| Object | lower latency for loss-tolerant traffic |
—
|
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: lower latency for loss-tolerant traffic | Statement: [DCCP, comparedToTCP, lower latency for loss-tolerant traffic]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: comparedToTCP Context triple: [DCCP, comparedToTCP, lower latency for loss-tolerant traffic]
-
A.
overheadComparedToTCP
Indicates the additional protocol or processing cost incurred by something relative to using TCP as the baseline.
-
B.
reliabilityComparedToTCP
Indicates how the reliability of one protocol or mechanism compares relative to that of TCP.
-
C.
differenceFromTCP
chosen
Indicates a relationship where one protocol, configuration, or behavior is characterized specifically by how it differs from TCP.
-
D.
differenceFromUDP
Indicates a relationship where something is characterized or measured in terms of how it differs from UDP (User Datagram Protocol) in behavior, properties, or implementation.
-
E.
hasHigherThroughputThan
Indicates that one entity can process or transmit a greater volume of work, data, or operations per unit time than another entity.
- 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_69e2458426188190b58b8ab4844fe420 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17dcb872881909a031d8560635fce |
completed | April 29, 2026, 3:40 a.m. |
| PD | Predicate disambiguation | batch_69eed2cb30f481909566369f515f6eff |
completed | April 27, 2026, 3:06 a.m. |
Created at: April 17, 2026, 3:33 p.m.