Triple
T22062035
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | RFC 5382 |
E545176
|
entity |
| Predicate | obsoletes |
P101
|
FINISHED |
| Object | RFC 3489 |
—
|
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: RFC 3489 | Statement: [RFC 5382, obsoletes, RFC 3489]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: RFC 3489 Context triple: [RFC 5382, obsoletes, RFC 3489]
-
A.
RFC 3489
chosen
RFC 3489 is an early IETF specification that defined the original STUN protocol for discovering a device’s public IP address and port in NAT traversal scenarios.
-
B.
RFC 3948
RFC 3948 is an IETF standard that specifies how to encapsulate IPsec ESP packets over UDP to enable IPsec traversal through NAT devices.
-
C.
RFC 3490
RFC 3490 is an Internet standard that defines Internationalized Domain Names in Applications (IDNA), enabling the use of non-ASCII characters in domain names.
-
D.
RFC 3492
RFC 3492 is the Internet standard document that defines Punycode, an encoding method used to represent Unicode characters in domain names using only ASCII characters.
-
E.
RFC 3748
RFC 3748 is the Internet Engineering Task Force (IETF) standard that specifies the Extensible Authentication Protocol (EAP) used for network access authentication.
- 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_69e11e3377c48190890c17407b9527d6 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f1285d5e508190b3124a70fe55b32e |
completed | April 28, 2026, 9:36 p.m. |
Created at: April 16, 2026, 8:27 p.m.