Triple

T18204461
Position Surface form Disambiguated ID Type / Status
Subject BART E435868 entity
Predicate paperAuthors P2002 FINISHED
Object Yinhan Liu 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: Yinhan Liu | Statement: [BART, paperAuthors, Yinhan Liu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yinhan Liu
Context triple: [BART, paperAuthors, Yinhan Liu]
  • A. Yinhan Liu chosen
    Yinhan Liu is a natural language processing researcher best known for co-developing the RoBERTa language model and related advances in large-scale pretraining.
  • B. Huan Liu
    Huan Liu is a prominent computer scientist known for his influential research in data mining and machine learning, particularly in feature selection and social media analytics.
  • C. Tingye Li
    Tingye Li was a pioneering Chinese-American optical engineer and physicist renowned for his foundational contributions to laser and fiber-optic communications.
  • D. Zhilin Yang
    Zhilin Yang is a computer scientist and AI researcher known for his work on large-scale language models and as a lead author of the XLNet architecture.
  • E. Yuhuai Wu
    Yuhuai Wu is an AI researcher and entrepreneur known for his work on large language models and as a member of Elon Musk’s xAI team.
  • 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_69d8b90dba6481908e119eb9aa4ca0cb completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4e222831081908f7d5500424e3acb completed April 19, 2026, 2:09 p.m.
Created at: April 10, 2026, 10:32 a.m.