Triple

T10073371
Position Surface form Disambiguated ID Type / Status
Subject Beiyang Government E213683 entity
Predicate headOfState P112 FINISHED
Object Cao Kun E212948 NE 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: Cao Kun | Statement: [Beiyang Government, headOfState, Cao Kun]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cao Kun
Context triple: [Beiyang Government, headOfState, Cao Kun]
  • A. Cao Kun chosen
    Cao Kun was a prominent Chinese warlord and politician of the early Republic era who became president of the Beiyang government after consolidating power within the Beiyang Army.
  • B. Guo Songling
    Guo Songling was a Chinese warlord-era general best known for his role in the Fengtian clique and his attempted rebellion against Zhang Zuolin in the 1920s.
  • C. Li Yuanhong
    Li Yuanhong was a Chinese military leader and politician who became a key figure in the 1911 Revolution and later served as president of the Republic of China.
  • D. Yuan Guiren
    Yuan Guiren is a Chinese politician and educator who served as China’s Minister of Education.
  • E. Chen Yi
    Chen Yi was a prominent Chinese Communist military commander and later a senior political leader who served as Foreign Minister of the People’s Republic of China.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ca839add308190b57d53b4ec21f2d0 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cdd015ad488190aee3a2bfb58fb855 completed April 2, 2026, 2:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69d98811fd3881909369e0f00f2a8267 completed April 10, 2026, 11:30 p.m.
Created at: March 30, 2026, 8:59 p.m.