Triple
T13636467
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | RFC 1071 |
E325860
|
entity |
| Predicate | appliesToProtocol |
P1129
|
FINISHED |
| Object | UDP |
E1266
|
NE 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: UDP | Statement: [RFC 1071, appliesToProtocol, UDP]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: UDP Context triple: [RFC 1071, appliesToProtocol, UDP]
-
A.
UDP
chosen
UDP (User Datagram Protocol) is a lightweight, connectionless transport-layer protocol used on the Internet for fast, low-overhead data transmission without guaranteed delivery or ordering.
-
B.
UDT
UDT (Timorese Democratic Union) is a political party in East Timor that played a key role in the country’s independence struggle and later became part of the National Council of Timorese Resistance.
-
C.
Datagram Delivery Protocol
Datagram Delivery Protocol is the connectionless network-layer protocol of the AppleTalk suite, responsible for routing and delivering datagram packets between AppleTalk nodes.
-
D.
Packet
Packet is the nickname of the Fairchild C-82, an American twin-engine military transport aircraft used primarily in the 1940s and 1950s.
-
E.
DCCP
DCCP (Datagram Congestion Control Protocol) is a transport-layer protocol designed to provide congestion-controlled, unreliable datagram delivery for real-time and multimedia applications.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d8076beddc8190a53156f5bea77f5e |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbc5a616dc81908b8c1213e1d4beed |
completed | April 12, 2026, 4:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f78af297008190b12256c936714213 |
completed | May 3, 2026, 5:50 p.m. |
Created at: April 9, 2026, 9:51 p.m.