Triple

T11755912
Position Surface form Disambiguated ID Type / Status
Subject Academia Sinica E279523 entity
Predicate governingBodyOf P479 FINISHED
Object Institute of Information Science, Academia Sinica
The Institute of Information Science, Academia Sinica is a leading Taiwanese research institute dedicated to advanced studies in computer science and information technologies under the national research academy Academia Sinica.
E943562 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: Institute of Information Science, Academia Sinica | Statement: [Academia Sinica, governingBodyOf, Institute of Information Science, Academia Sinica]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Institute of Information Science, Academia Sinica
Context triple: [Academia Sinica, governingBodyOf, Institute of Information Science, Academia Sinica]
  • A. Institute for Interdisciplinary Information Sciences
    The Institute for Interdisciplinary Information Sciences is a leading research center at Tsinghua University focused on cutting-edge work in computer science, quantum information, and related interdisciplinary fields.
  • B. International School of Information Science
    The International School of Information Science is an educational and research institution within the Bibliotheca Alexandrina that focuses on information science, digital libraries, and knowledge management.
  • C. Academia Sinica
    Academia Sinica is Taiwan’s national academy and leading research institution, renowned for its advanced work across the natural sciences, humanities, and social sciences.
  • D. Graduate School of Information Science and Technology
    The Graduate School of Information Science and Technology is a leading research and education institution at the University of Tokyo specializing in advanced information science, computer science, and related technologies.
  • E. Graduate School of Information Science and Technology
    The Graduate School of Information Science and Technology is a specialized graduate faculty at Osaka University focused on advanced research and education in information science, computing, and related technologies.
  • 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: Institute of Information Science, Academia Sinica
Triple: [Academia Sinica, governingBodyOf, Institute of Information Science, Academia Sinica]
Generated description
The Institute of Information Science, Academia Sinica is a leading Taiwanese research institute dedicated to advanced studies in computer science and information technologies under the national research academy Academia Sinica.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Institute of Information Science, Academia Sinica
Target entity description: The Institute of Information Science, Academia Sinica is a leading Taiwanese research institute dedicated to advanced studies in computer science and information technologies under the national research academy Academia Sinica.
  • A. Institute for Interdisciplinary Information Sciences
    The Institute for Interdisciplinary Information Sciences is a leading research center at Tsinghua University focused on cutting-edge work in computer science, quantum information, and related interdisciplinary fields.
  • B. International School of Information Science
    The International School of Information Science is an educational and research institution within the Bibliotheca Alexandrina that focuses on information science, digital libraries, and knowledge management.
  • C. Academia Sinica
    Academia Sinica is Taiwan’s national academy and leading research institution, renowned for its advanced work across the natural sciences, humanities, and social sciences.
  • D. Graduate School of Information Science and Technology
    The Graduate School of Information Science and Technology is a leading research and education institution at the University of Tokyo specializing in advanced information science, computer science, and related technologies.
  • E. Graduate School of Information Science and Technology
    The Graduate School of Information Science and Technology is a specialized graduate faculty at Osaka University focused on advanced research and education in information science, computing, and related technologies.
  • 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_69d6ab01038c819080714901502c84fc completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8a50c8d708190ad79ecb57b715d04 completed April 10, 2026, 7:21 a.m.
NED1 Entity disambiguation (via context triple) batch_69f01a2f0a848190944ba2688c6d7ad2 completed April 28, 2026, 2:23 a.m.
NEDg Description generation batch_69f0319622c48190bee6c906f08c0a8c completed April 28, 2026, 4:03 a.m.
NED2 Entity disambiguation (via description) batch_69f05af9ce808190bc6c1ec2cb9903f9 completed April 28, 2026, 7 a.m.
Created at: April 8, 2026, 9:41 p.m.