Triple

T22800888
Position Surface form Disambiguated ID Type / Status
Subject Alan Johnston E564386 entity
Predicate knownFor P22 FINISHED
Object ZRTP 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: ZRTP | Statement: [Alan Johnston, knownFor, ZRTP]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ZRTP
Context triple: [Alan Johnston, knownFor, ZRTP]
  • A. ZRTP chosen
    ZRTP is a cryptographic key-agreement protocol designed to enable end-to-end encryption for real-time voice and video communications over RTP-based systems.
  • B. Linphone
    Linphone is an open-source Voice over IP (VoIP) softphone application that supports audio and video calls, messaging, and encryption across multiple platforms.
  • C. Jitsi
    Jitsi is an open-source, cross-platform suite of real-time voice, video, and chat communication tools focused on secure, encrypted conferencing.
  • D. DTLS-SRTP
    DTLS-SRTP is a security protocol framework that uses Datagram Transport Layer Security to negotiate keys and provide encryption and authentication for Secure Real-time Transport Protocol media streams, commonly used in VoIP and WebRTC.
  • E. STUN
    STUN (Session Traversal Utilities for NAT) is a network protocol that helps devices discover their public IP address and port as seen by external servers, enabling communication across NAT and firewalls.
  • 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_69e2458185f88190b0045227ee420411 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17cdc72908190827c9e36a498dc97 completed April 29, 2026, 3:37 a.m.
Created at: April 17, 2026, 3:31 p.m.