Triple
T18323546
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ITU-T Recommendation G.993.2 |
E438943
|
entity |
| Predicate | supportsApplication |
P15794
|
FINISHED |
| Object | VoIP |
—
|
NE NERFINISHED |
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: VoIP | Statement: [ITU-T Recommendation G.993.2, supportsApplication, VoIP]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: VoIP Context triple: [ITU-T Recommendation G.993.2, supportsApplication, VoIP]
-
A.
VoIP
chosen
VoIP (Voice over Internet Protocol) is a technology that enables voice communications and multimedia sessions to be delivered over Internet Protocol (IP) networks instead of traditional telephone lines.
-
B.
SIP
SIP is the IATA airport code for Simferopol International Airport, the main air gateway to the Crimean Peninsula.
-
C.
SIP
SIP is a Unicode supplementary plane that contains additional CJK ideographs beyond those in the Basic Multilingual Plane.
-
D.
SIP
SIP is a macOS security technology that restricts system-level modifications to protect the operating system from malware and accidental damage.
-
E.
SIP
SIP is the National Rail station code for Shipton railway station in Oxfordshire, England.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b916a2d081909e249e4902f6aad9 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e50aa886508190902ffc26b30731ae |
completed | April 19, 2026, 5:02 p.m. |
Created at: April 10, 2026, 10:36 a.m.