Triple
T21225643
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | GPRS Tunnelling Protocol User Plane |
E523078
|
entity |
| Predicate | encapsulationOver |
P33248
|
FINISHED |
| Object | IP |
—
|
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: IP | Statement: [GPRS Tunnelling Protocol User Plane, encapsulationOver, IP]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: IP Context triple: [GPRS Tunnelling Protocol User Plane, encapsulationOver, IP]
-
A.
IP
chosen
IP (Internet Protocol) is the core networking protocol that defines how data is addressed and routed across interconnected computer networks such as the internet.
-
B.
IP
IP is the acronym for Infraestruturas de Portugal, the Portuguese state-owned company responsible for managing the country’s road and rail infrastructure.
-
C.
IP
IP is the stock ticker symbol for International Paper, a major global producer of paper and packaging products.
-
D.
IP
IP is the postcode area in eastern England that covers Ipswich and surrounding parts of Suffolk.
-
E.
ips
ips is an IETF working group focused on developing standards for transporting storage protocols over IP networks.
- 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_69e0b512ad94819087942b2ed925185f |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e734ab3f6c819083e277ea1c33134e |
completed | April 21, 2026, 8:26 a.m. |
Created at: April 16, 2026, 3:44 p.m.