Triple

T14422508
Position Surface form Disambiguated ID Type / Status
Subject WebKitGTK E357617 entity
Predicate usedBy P260 FINISHED
Object Epiphany web browser E357611 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: Epiphany web browser | Statement: [WebKitGTK, usedBy, Epiphany web browser]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Epiphany web browser
Context triple: [WebKitGTK, usedBy, Epiphany web browser]
  • A. Epiphany web browser chosen
    Epiphany web browser, also known as GNOME Web, is the lightweight, default web browser for the GNOME desktop environment, focused on simplicity and tight integration with GNOME technologies.
  • B. GNOME Web
    GNOME Web is the official web browser for the GNOME desktop environment, designed to be simple, integrated, and lightweight while using the WebKit rendering engine.
  • C. Odyssey Web Browser
    Odyssey Web Browser is a lightweight, WebKit-based browser primarily known for bringing modern web standards support to MorphOS and other niche or legacy computing platforms.
  • D. Colibri Browser
    Colibri Browser is a minimalist web browser focused on speed and simplicity, built on the Blink rendering engine.
  • E. Torch Browser
    Torch Browser is a Chromium-based web browser known for its built-in media downloading, torrent management, and social media integration features.
  • 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_69d82793421c8190861eb0e673b085de completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de91102c3c81908f571a1fff3bdd47 completed April 14, 2026, 7:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd5bcb131c8190935d9bacb1afc995 completed May 8, 2026, 3:43 a.m.
Created at: April 10, 2026, 1:18 a.m.