Triple

T19750514
Position Surface form Disambiguated ID Type / Status
Subject Victor Koo E474359 entity
Predicate coFounded P104 FINISHED
Object Youku 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: Youku | Statement: [Victor Koo, coFounded, Youku]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Youku
Context triple: [Victor Koo, coFounded, Youku]
  • A. Youku Tudou chosen
    Youku Tudou is a major Chinese online video hosting and streaming platform formed from the merger of Youku and Tudou, often likened to China’s YouTube.
  • B. iQIYI
    iQIYI is a major Chinese online video and streaming platform offering a wide range of films, TV series, and original content.
  • C. Xigua Video
    Xigua Video is a Chinese online video-sharing and streaming platform owned by ByteDance, offering a mix of user-generated and professionally produced content.
  • D. Tencent Video
    Tencent Video is a major Chinese online video streaming platform offering a wide range of TV dramas, films, variety shows, and original content.
  • E. Pinduoduo
    Pinduoduo is a major Chinese e-commerce platform known for its group-buying model and deep discounts that target price-sensitive consumers, especially in lower-tier cities.
  • 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_69d8e51940a0819087bd2996f98da668 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6529875688190952af476aa5be492 completed April 20, 2026, 4:21 p.m.
Created at: April 10, 2026, 1:47 p.m.