Triple

T18205035
Position Surface form Disambiguated ID Type / Status
Subject LayoutLM E435880 entity
Predicate hasAuthor P4244 FINISHED
Object Lei Cui
Lei Cui is a computer scientist and AI researcher known for his work on document understanding and the development of models such as LayoutLM.
E1329379 NE FINISHED

How this triple was built (4 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: Lei Cui | Statement: [LayoutLM, hasAuthor, Lei Cui]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lei Cui
Context triple: [LayoutLM, hasAuthor, Lei Cui]
  • A. Xing Li
    Xing Li is the creator and original developer of FanFiction.net, one of the largest and earliest online archives for user-written fan fiction.
  • B. Xing Li
    Xing Li is a computer networking expert known for co-authoring IETF standards, including RFC 6145 on IPv4/IPv6 translation mechanisms.
  • C. Liwen Shao
    Liwen Shao is a brilliant and ambitious Chinese businesswoman and technologist in the Pacific Rim universe, known for her pivotal role in developing advanced Jaeger drone technology.
  • D. Langche Zeng
    Langche Zeng is a political scientist and quantitative methodologist known for his collaborative work with Gary King on statistical methods in social science research.
  • E. Wei Li
    Wei Li is a computer scientist known for co-authoring and introducing the T5 (Text-to-Text Transfer Transformer) language model in natural language processing research.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Lei Cui
Triple: [LayoutLM, hasAuthor, Lei Cui]
Generated description
Lei Cui is a computer scientist and AI researcher known for his work on document understanding and the development of models such as LayoutLM.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Lei Cui
Target entity description: Lei Cui is a computer scientist and AI researcher known for his work on document understanding and the development of models such as LayoutLM.
  • A. Xing Li
    Xing Li is the creator and original developer of FanFiction.net, one of the largest and earliest online archives for user-written fan fiction.
  • B. Xing Li
    Xing Li is a computer networking expert known for co-authoring IETF standards, including RFC 6145 on IPv4/IPv6 translation mechanisms.
  • C. Liwen Shao
    Liwen Shao is a brilliant and ambitious Chinese businesswoman and technologist in the Pacific Rim universe, known for her pivotal role in developing advanced Jaeger drone technology.
  • D. Langche Zeng
    Langche Zeng is a political scientist and quantitative methodologist known for his collaborative work with Gary King on statistical methods in social science research.
  • E. Wei Li
    Wei Li is a computer scientist known for co-authoring and introducing the T5 (Text-to-Text Transfer Transformer) language model in natural language processing research.
  • F. None of above. chosen

Provenance (5 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.
NED1 Entity disambiguation (via context triple) batch_6a049159cbe081908872d559d3fa57a7 completed May 13, 2026, 2:57 p.m.
NEDg Description generation batch_6a049275f2c08190b9be34f87b05841a completed May 13, 2026, 3:02 p.m.
NED2 Entity disambiguation (via description) batch_6a0492fb82348190a3639ca54ac6f014 completed May 13, 2026, 3:04 p.m.
Created at: April 10, 2026, 10:32 a.m.