Triple

T1625300
Position Surface form Disambiguated ID Type / Status
Subject Project 985 E35126 entity
Predicate initialMembers P446 FINISHED
Object Peking University E50963 NE FINISHED

How this triple was built (3 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: Peking University | Statement: [Project 985, initialMembers, Peking University]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Peking University
Context triple: [Project 985, initialMembers, Peking University]
  • A. Peking University chosen
    Peking University is a leading Chinese research university in Beijing, renowned for its academic excellence, historical significance, and global influence.
  • B. Tsinghua University
    Tsinghua University is a leading research-intensive university in Beijing, China, renowned for its strong engineering, science, and technology programs and its significant influence in Chinese higher education and innovation.
  • C. Nanjing University
    Nanjing University is one of China’s oldest and most prestigious research universities, renowned for its strong academic programs and historical significance.
  • D. Fudan University
    Fudan University is a prestigious and comprehensive research university in Shanghai, China, renowned for its strong academic programs and leading role in Chinese higher education.
  • E. East China Normal University
    East China Normal University is a leading comprehensive research university in Shanghai, China, renowned for its strengths in teacher education, the humanities, and the social sciences.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: initialMembers
Context triple: [Project 985, initialMembers, Peking University]
  • A. originalNumberOfMembers
    Indicates the initial total count of members in a group or organization before any changes such as additions or removals.
  • B. primaryMembers
    Indicates that the related entities are the main or most important members within a larger group or organization.
  • C. foundingMember chosen
    Indicates that an entity is one of the original creators or initial participants involved in establishing another entity, such as an organization, group, or project.
  • D. originalSixMember
    Indicates that an entity was one of the six original members of a specific group, organization, or set.
  • E. typicalMembers
    Indicates that the related entities are representative or characteristic members of a larger group, category, or class.
  • F. None of above.

Provenance (4 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_69a886023194819080a3fccd6e325d0e completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a9431af5ac8190893133f1ae490142 completed March 5, 2026, 8:47 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad8aba8d4c819098be250f8487df45 completed March 8, 2026, 2:42 p.m.
PD Predicate disambiguation batch_69a907c91c888190b6ed295c1a2e0977 completed March 5, 2026, 4:34 a.m.
Created at: March 4, 2026, 7:28 p.m.