Triple

T23243813
Position Surface form Disambiguated ID Type / Status
Subject Yuan Shikai E581528 entity
Predicate child P120 FINISHED
Object Yuan Kewen NE NERFINISHED

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: Yuan Kewen | Statement: [Yuan Shikai, child, Yuan Kewen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yuan Kewen
Context triple: [Yuan Shikai, child, Yuan Kewen]
  • A. Yuan Kewen chosen
    Yuan Kewen was a Chinese scholar, calligrapher, and eccentric intellectual of the early 20th century, best known as the second son of warlord and short-lived emperor Yuan Shikai.
  • B. Yuan Wenkang
    Yuan Wenkang is a Chinese actor known for his roles in film and television dramas.
  • C. Zhou Xiaowen
    Zhou Xiaowen is a Chinese film director known for his contributions to contemporary Chinese cinema.
  • D. Zhou Kaiya
    Zhou Kaiya is a Chinese zoologist and cetacean specialist known for his extensive research on the baiji (Lipotes vexillifer), the now functionally extinct Yangtze River dolphin.
  • E. Chen Weiya
    Chen Weiya is a Chinese film and stage director best known for co-directing and choreographing large-scale productions, including the acclaimed ceremonies of the 2008 Beijing Olympics.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e24606b17c81908aba1a4911c8a8ba completed April 17, 2026, 2:39 p.m.
NER Named-entity recognition batch_69f192efd44c8190b179b4d1cb71efa5 completed April 29, 2026, 5:11 a.m.
Created at: April 17, 2026, 4:10 p.m.