Triple

T29387772
Position Surface form Disambiguated ID Type / Status
Subject Twenty-One Demands E745296 entity
Predicate group5Subject P170164 FINISHED
Object Japanese advisers and control over Chinese politics, police, and economy LITERAL FINISHED

How this triple was built (2 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: Japanese advisers and control over Chinese politics, police, and economy | Statement: [Twenty-One Demands, group5Subject, Japanese advisers and control over Chinese politics, police, and economy]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: group5Subject
Context triple: [Twenty-One Demands, group5Subject, Japanese advisers and control over Chinese politics, police, and economy]
  • A. group3Subject
    Indicates that an entity serves as the subject (main actor or topic) within the third group in a grouped or partitioned structure.
  • B. subjectGroup
    Indicates that an entity functions as a group or collection that the subject belongs to or is categorized under.
  • C. book5Subject
    Indicates that an entity serves as the subject (main topic or focus) of the fifth book in a series or collection.
  • D. schoolSubject
    Indicates that an entity is an academic subject taught, studied, or associated with a school or educational program.
  • E. subjectType
    Indicates the classification or category that defines what kind of entity the subject is.
  • F. None of above. chosen

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_69f0a79cfd5481909b4dde750cb8d2c6 completed April 28, 2026, 12:27 p.m.
NER Named-entity recognition batch_69f68b121eac81909e90416207bc1157 completed May 2, 2026, 11:38 p.m.
PD Predicate disambiguation batch_69f6860def1c81909d79e1f088c4b5e5 completed May 2, 2026, 11:17 p.m.
PDg Predicate description generation batch_69f68a160374819084d720985f800dfc completed May 2, 2026, 11:34 p.m.
Created at: April 28, 2026, 2:40 p.m.