Triple
T9932100
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ed25519 |
E192669
|
entity |
| Predicate | usedIn |
P98
|
FINISHED |
| Object | WireGuard |
E233811
|
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: WireGuard | Statement: [Ed25519, usedIn, WireGuard]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: WireGuard Context triple: [Ed25519, usedIn, WireGuard]
-
A.
WireGuard VPN protocol
chosen
WireGuard VPN protocol is a modern, lightweight, and high-performance virtual private network protocol focused on simplicity and strong cryptographic security.
-
B.
OpenVPN
OpenVPN is an open-source virtual private network (VPN) solution that enables secure, encrypted connections over the internet for remote access and site-to-site networking.
-
C.
Teredo
Teredo is a tunneling protocol that enables IPv6 connectivity for devices on IPv4 networks, particularly those behind NAT.
-
D.
TUN
TUN is the three-letter ISO 3166-1 alpha-3 country code assigned to Tunisia.
-
E.
Avast SecureLine VPN
Avast SecureLine VPN is a virtual private network service by Avast that encrypts internet traffic and masks users’ IP addresses to enhance online privacy and security.
- 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_69ca82dd978c8190947124ab0d3315ac |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdb5b54f348190b8e70e7beff6098a |
completed | April 2, 2026, 12:17 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d228d1620c8190ac7125b268dd6832 |
completed | April 5, 2026, 9:18 a.m. |
Created at: March 30, 2026, 8:43 p.m.