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.