Triple
T15575994
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yandex |
E374370
|
entity |
| Predicate | hasService |
P182
|
FINISHED |
| Object | Yandex Zen |
E357624
|
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 Zen | Statement: [Yandex, hasService, Yandex Zen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yandex Zen Context triple: [Yandex, hasService, Yandex Zen]
-
A.
Yandex Zen
chosen
Yandex Zen is a personalized content recommendation and news feed platform that delivers articles, videos, and other media based on users’ interests and browsing behavior.
-
B.
Yandex
Yandex is a major Russian multinational technology company best known for its internet search engine and wide range of online 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.
Yandex (R&D center)
Yandex (R&D center) is a research and development facility of the Russian technology company Yandex, focused on advancing its internet, AI, and data-driven products and services.
-
E.
Yandex 360 for Business
Yandex 360 for Business is a cloud-based productivity and collaboration suite by Yandex that provides integrated email, storage, communication, and office tools for organizations.
- 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.