Triple

T14486729
Position Surface form Disambiguated ID Type / Status
Subject Empress Ma E359246 entity
Predicate spousePersonalName P109531 FINISHED
Object Zhu Yuanzhang E78573 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: Zhu Yuanzhang | Statement: [Empress Ma, spousePersonalName, Zhu Yuanzhang]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Zhu Yuanzhang
Context triple: [Empress Ma, spousePersonalName, Zhu Yuanzhang]
  • A. Hongwu Emperor chosen
    The Hongwu Emperor was the founding ruler of China’s Ming dynasty, known for overthrowing the Mongol-led Yuan dynasty and establishing a centralized, autocratic government.
  • B. Taizu
    Taizu is the temple name of the Hongwu Emperor, the founding ruler of China’s Ming dynasty.
  • C. Taizu
    Taizu is the temple name given to Tang of Shang, the founding king of China’s Shang dynasty.
  • D. Yongle Emperor
    The Yongle Emperor was the third ruler of China’s Ming dynasty, known for moving the capital to Beijing, commissioning the Forbidden City, and sponsoring the voyages of Zheng He.
  • E. Ming Huidi
    Ming Huidi, born Zhu Yunwen, was the second emperor of China’s Ming dynasty, known for his short and turbulent reign that ended when he was overthrown by his uncle, the Yongle Emperor.
  • 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_69d8279740308190af9df93a3af8592e completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de924ee0f08190baf68318b41fa64d completed April 14, 2026, 7:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69ff0b3017808190a44087056ba6a472 completed May 9, 2026, 10:23 a.m.
Created at: April 10, 2026, 1:20 a.m.