Triple

T18794338
Position Surface form Disambiguated ID Type / Status
Subject Tencent Holdings Limited E459593 entity
Predicate hasSubsidiary P254 FINISHED
Object Tencent Cloud NE NERFINISHED

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: Tencent Cloud | Statement: [Tencent Holdings Limited, hasSubsidiary, Tencent Cloud]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tencent Cloud
Context triple: [Tencent Holdings Limited, hasSubsidiary, Tencent Cloud]
  • A. Alibaba Cloud
    Alibaba Cloud is a leading global cloud computing and infrastructure services provider originating from China, offering a wide range of scalable computing, storage, and data solutions.
  • B. Tencent chosen
    Tencent is a Chinese multinational technology and entertainment conglomerate known for its dominant social media, gaming, and digital services platforms such as WeChat and QQ.
  • C. Yandex Cloud
    Yandex Cloud is a public cloud computing platform by Yandex that provides scalable infrastructure, storage, and managed services for building and running applications.
  • D. Baidu AI Cloud
    Baidu AI Cloud is Baidu’s cloud computing and artificial intelligence platform offering infrastructure, AI services, and industry-specific solutions.
  • E. Naver Cloud
    Naver Cloud is a South Korean cloud computing and IT infrastructure service provider offering a wide range of cloud-based solutions for businesses and developers.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8d396f54c8190ba49db31e8743842 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e5a01cc0c0819098ef4326e82ff524 completed April 20, 2026, 3:40 a.m.
Created at: April 10, 2026, 11:53 a.m.