Triple

T2390523
Position Surface form Disambiguated ID Type / Status
Subject Marc Andreessen E48930 entity
Predicate notableWork P4 FINISHED
Object Mosaic web browser E44728 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: Mosaic web browser | Statement: [Marc Andreessen, notableWork, Mosaic web browser]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mosaic web browser
Context triple: [Marc Andreessen, notableWork, Mosaic web browser]
  • A. Mosaic (web browser) chosen
    Mosaic was one of the first widely used graphical web browsers, instrumental in popularizing the World Wide Web in the early 1990s.
  • B. Colibri Browser
    Colibri Browser is a minimalist web browser focused on speed and simplicity, built on the Blink rendering engine.
  • C. Netscape Navigator
    Netscape Navigator was a pioneering mid-1990s web browser that played a central role in popularizing the World Wide Web and ignited the first major “browser war.”
  • D. Brave web browser
    Brave web browser is a privacy-focused, open-source web browser known for its built-in ad and tracker blocking and optional cryptocurrency-based rewards system for users and publishers.
  • 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_69a88aa5f63081908d07fd302029fcbd completed March 4, 2026, 7:40 p.m.
NER Named-entity recognition batch_69abc87457388190822d5506327db8f2 completed March 7, 2026, 6:40 a.m.
NED1 Entity disambiguation (via context triple) batch_69aeb3d4f0608190bcc77a67fa85b963 completed March 9, 2026, 11:49 a.m.
Created at: March 4, 2026, 7:57 p.m.