Triple

T14090967
Position Surface form Disambiguated ID Type / Status
Subject National Tsing Hua University E339127 entity
Predicate hasResearchCenter P40 FINISHED
Object National Center for High-performance Computing (collaborative)
The National Center for High-performance Computing (collaborative) is a major Taiwanese research facility that provides advanced supercomputing resources and support for academic and industrial scientific computing, data analysis, and technology development.
E1080271 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: National Center for High-performance Computing (collaborative) | Statement: [National Tsing Hua University, hasResearchCenter, National Center for High-performance Computing (collaborative)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: National Center for High-performance Computing (collaborative)
Context triple: [National Tsing Hua University, hasResearchCenter, National Center for High-performance Computing (collaborative)]
  • A. High Performance Computing Collaboratory
    The High Performance Computing Collaboratory is a major research center specializing in advanced computational science and engineering, supporting large-scale simulations and high-performance computing applications across diverse scientific and industrial domains.
  • B. High‑Performance Computing Center
    The High-Performance Computing Center at Lawrence Livermore National Laboratory is a major facility housing advanced supercomputing resources used for national security, scientific research, and large-scale simulations.
  • C. National Center for Supercomputing Applications
    The National Center for Supercomputing Applications is a leading U.S. research institution known for pioneering high-performance computing technologies and software, including early web browser development.
  • D. Supercomputer Education and Research Centre
    Supercomputer Education and Research Centre is a high-performance computing and advanced research facility at the Indian Institute of Science that supports cutting-edge scientific and engineering computation.
  • E. Laboratório Nacional de Computação Científica de Alto Desempenho
    Laboratório Nacional de Computação Científica de Alto Desempenho is a Brazilian national laboratory dedicated to advanced high-performance computing research and infrastructure in support of scientific and technological development.
  • 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: National Center for High-performance Computing (collaborative)
Triple: [National Tsing Hua University, hasResearchCenter, National Center for High-performance Computing (collaborative)]
Generated description
The National Center for High-performance Computing (collaborative) is a major Taiwanese research facility that provides advanced supercomputing resources and support for academic and industrial scientific computing, data analysis, and technology development.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: National Center for High-performance Computing (collaborative)
Target entity description: The National Center for High-performance Computing (collaborative) is a major Taiwanese research facility that provides advanced supercomputing resources and support for academic and industrial scientific computing, data analysis, and technology development.
  • A. High Performance Computing Collaboratory
    The High Performance Computing Collaboratory is a major research center specializing in advanced computational science and engineering, supporting large-scale simulations and high-performance computing applications across diverse scientific and industrial domains.
  • B. High‑Performance Computing Center
    The High-Performance Computing Center at Lawrence Livermore National Laboratory is a major facility housing advanced supercomputing resources used for national security, scientific research, and large-scale simulations.
  • C. National Center for Supercomputing Applications
    The National Center for Supercomputing Applications is a leading U.S. research institution known for pioneering high-performance computing technologies and software, including early web browser development.
  • D. Supercomputer Education and Research Centre
    Supercomputer Education and Research Centre is a high-performance computing and advanced research facility at the Indian Institute of Science that supports cutting-edge scientific and engineering computation.
  • E. Laboratório Nacional de Computação Científica de Alto Desempenho
    Laboratório Nacional de Computação Científica de Alto Desempenho is a Brazilian national laboratory dedicated to advanced high-performance computing research and infrastructure in support of scientific and technological development.
  • 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_69d81c687b0c819087fd9ed4198403f8 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de5ee3213c8190af2853a2a5b302a2 completed April 14, 2026, 3:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcd0a7aab88190949cf1fd8e11b050 completed May 7, 2026, 5:49 p.m.
NEDg Description generation batch_69fcd5ad82388190a196d811734cdca2 completed May 7, 2026, 6:10 p.m.
NED2 Entity disambiguation (via description) batch_69fcd63a114881909ff7b2df937d24df completed May 7, 2026, 6:13 p.m.
Created at: April 9, 2026, 10:21 p.m.