Triple

T575780
Position Surface form Disambiguated ID Type / Status
Subject Blink E13758 entity
Predicate usedIn P98 FINISHED
Object Microsoft Edge E24811 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: Microsoft Edge | Statement: [Blink, usedIn, Microsoft Edge]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Microsoft Edge
Context triple: [Blink, usedIn, Microsoft Edge]
  • A. Microsoft Edge chosen
    Microsoft Edge is a web browser developed by Microsoft that serves as the default browser for Windows and supports modern web standards and technologies.
  • B. Google Chrome
    Google Chrome is a widely used cross-platform web browser developed by Google, known for its speed, simplicity, and integration with Google services.
  • C. Yandex Browser
    Yandex Browser is a web browser developed by the Russian company Yandex that emphasizes speed, security, and integration with Yandex’s online services.
  • D. Internet Explorer
    Internet Explorer is a discontinued web browser that was once the dominant way to access the web on Windows computers.
  • E. Windows 10
    Windows 10 is a major version of Microsoft's Windows operating system that introduced a unified platform across PCs, tablets, and other devices, featuring the return of the Start menu and continuous feature updates.
  • 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_69a4933fa4d88190a7949cc83c08c5c1 completed March 1, 2026, 7:27 p.m.
NER Named-entity recognition batch_69a49b67395c8190a8046ff7debe9d1f completed March 1, 2026, 8:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69a501bfb6408190bf7e1f462f39723d completed March 2, 2026, 3:19 a.m.
Created at: March 1, 2026, 7:33 p.m.