Triple

T8609024
Position Surface form Disambiguated ID Type / Status
Subject GNOME Core Applications E203873 entity
Predicate includesApplication P14571 FINISHED
Object GNOME Web 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: GNOME Web | Statement: [GNOME Core Applications, includesApplication, GNOME Web]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: GNOME Web
Context triple: [GNOME Core Applications, includesApplication, GNOME Web]
  • A. 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.
  • B. Waterfox
    Waterfox is a privacy-focused web browser derived from Mozilla Firefox, optimized for speed and compatibility with legacy extensions.
  • C. 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.
  • 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_69ca832c23e4819095a9f3eea4a21828 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cc46ed77588190a872d22d9d1f7429 completed March 31, 2026, 10:13 p.m.
NED1 Entity disambiguation (via context triple) batch_69cea90dd93081908140ac0ce23be820 completed April 2, 2026, 5:36 p.m.
Created at: March 30, 2026, 6:25 p.m.