Triple
T15575984
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yandex |
E374370
|
entity |
| Predicate | hasService |
P182
|
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, hasService, Yandex Browser]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yandex Browser Context triple: [Yandex, hasService, 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_69d85ccd575081908909b71a3f3e3a61 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04e2140388190a8df7b835eaa72ce |
completed | April 16, 2026, 2:49 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff4c4978ec8190a57de5d9a2ec6653 |
completed | May 9, 2026, 3:01 p.m. |
Created at: April 10, 2026, 4:10 a.m.