Triple

T14422787
Position Surface form Disambiguated ID Type / Status
Subject Yandex Translate E357623 entity
Predicate supportsPlatform P203 FINISHED
Object Yandex Browser E72097 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: Yandex Browser | Statement: [Yandex Translate, supportsPlatform, Yandex Browser]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yandex Browser
Context triple: [Yandex Translate, supportsPlatform, Yandex Browser]
  • A. Yandex Browser chosen
    Yandex Browser is a web browser developed by the Russian company Yandex that emphasizes speed, security, and integration with Yandex’s online services.
  • B. 360 Secure Browser
    360 Secure Browser is a Chinese web browser developed by Qihoo 360, known for its built-in security features and dual-engine rendering support.
  • C. Silk Browser
    Silk Browser is Amazon's cloud-accelerated web browser designed primarily for use on Fire tablets and other Amazon devices.
  • D. Huawei Browser
    Huawei Browser is Huawei’s proprietary web browser designed for its mobile ecosystem, offering integrated services, privacy features, and optimization for Huawei devices.
  • E. 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.
  • 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_69fd648784048190a9c7e95bfeec8b23 completed May 8, 2026, 4:20 a.m.
Created at: April 10, 2026, 1:18 a.m.