Triple

T15361414
Position Surface form Disambiguated ID Type / Status
Subject ResNeXt E367297 entity
Predicate paperAuthors P2002 FINISHED
Object Saining Xie
Saining Xie is a computer vision researcher known for his influential work on deep convolutional neural network architectures, including the ResNeXt model.
E1159757 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: Saining Xie | Statement: [ResNeXt, paperAuthors, Saining Xie]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Saining Xie
Context triple: [ResNeXt, paperAuthors, Saining Xie]
  • A. Xing Li
    Xing Li is a computer networking expert known for co-authoring IETF standards, including RFC 6145 on IPv4/IPv6 translation mechanisms.
  • B. 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.
  • C. Yiping Gan
    Yiping Gan is a regional variety of Gan Chinese, a Sinitic language spoken primarily in Jiangxi province and surrounding areas.
  • D. Xiaodong Chen
    Xiaodong Chen is a prominent materials scientist and nanotechnology researcher who serves as editor-in-chief of the journal ACS Nano.
  • E. Xindong Wu
    Xindong Wu is a prominent computer scientist known for his influential contributions to data mining and knowledge discovery 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: Saining Xie
Triple: [ResNeXt, paperAuthors, Saining Xie]
Generated description
Saining Xie is a computer vision researcher known for his influential work on deep convolutional neural network architectures, including the ResNeXt model.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Saining Xie
Target entity description: Saining Xie is a computer vision researcher known for his influential work on deep convolutional neural network architectures, including the ResNeXt model.
  • 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. Yiping Gan
    Yiping Gan is a regional variety of Gan Chinese, a Sinitic language spoken primarily in Jiangxi province and surrounding areas.
  • D. Xiaodong Chen
    Xiaodong Chen is a prominent materials scientist and nanotechnology researcher who serves as editor-in-chief of the journal ACS Nano.
  • E. Xindong Wu
    Xindong Wu is a prominent computer scientist known for his influential contributions to data mining and knowledge discovery 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_69d85a1483788190ad93c2748e8af34b completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03e4607408190ab281a7f7a8012d3 completed April 16, 2026, 1:41 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff2cec4f2481908fae5209bfd48dcf completed May 9, 2026, 12:47 p.m.
NEDg Description generation batch_69ff2e7bf8c881909fecb6cf86bc32f2 completed May 9, 2026, 12:54 p.m.
NED2 Entity disambiguation (via description) batch_69ff331c267c8190bbc26ddd47273be7 completed May 9, 2026, 1:14 p.m.
Created at: April 10, 2026, 3:18 a.m.