Triple

T18406796
Position Surface form Disambiguated ID Type / Status
Subject Jiangxi Soviet E441644 entity
Predicate leader P981 FINISHED
Object Xiang Ying 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: Xiang Ying | Statement: [Jiangxi Soviet, leader, Xiang Ying]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Xiang Ying
Context triple: [Jiangxi Soviet, leader, Xiang Ying]
  • A. Xiang Ying chosen
    Xiang Ying was a prominent Chinese Communist military and political leader who played a key role in organizing and directing guerrilla resistance against Japanese forces during the Second Sino-Japanese War.
  • B. Xiang Jingyu
    Xiang Jingyu was an early female leader of the Chinese Communist movement and a pioneering advocate for women's emancipation in modern China.
  • C. Dazexiang
    Dazexiang is a village in China historically known as the starting point of the Dazexiang Uprising against the Qin dynasty.
  • D. Zhu Biao
    Zhu Biao was the Crown Prince of the Ming dynasty and eldest son of the Hongwu Emperor, whose early death altered the imperial succession and paved the way for the Yongle Emperor’s rise.
  • E. Duan Xingzhi
    Duan Xingzhi was the final monarch of the Dali Kingdom, marking the end of this medieval Bai state in what is now Yunnan, China.
  • 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_69d8b9eb8a508190a942fd75ebd8b1dc completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e519591fdc8190a92f9587ec88478d completed April 19, 2026, 6:05 p.m.
Created at: April 10, 2026, 10:46 a.m.