Triple

T14130531
Position Surface form Disambiguated ID Type / Status
Subject Yang Dezhi E350151 entity
Predicate name P16 FINISHED
Object Yang Dezhi E350151 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: Yang Dezhi | Statement: [Yang Dezhi, name, Yang Dezhi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yang Dezhi
Context triple: [Yang Dezhi, name, Yang Dezhi]
  • A. Yang Dezhi chosen
    Yang Dezhi was a prominent Chinese general who held senior command roles in the People’s Liberation Army, including leadership during the Sino-Vietnamese War.
  • B. Zhao Leji
    Zhao Leji is a senior Chinese Communist Party politician and close ally of Xi Jinping who serves as one of China’s top state leaders.
  • C. Zhu Dong
    Zhu Dong was a historical Chinese scholar and educator credited with establishing the influential Yuelu Academy, one of China’s renowned ancient academies of classical learning.
  • D. Zhu Peide
    Zhu Peide was a Chinese Nationalist military general and politician who held senior command and governmental roles during the Republic of China era.
  • E. Li Zhengdao
    Li Zhengdao, also known as Tsung-Dao Lee, is a Chinese-American theoretical physicist and Nobel laureate renowned for his work on parity violation in weak interactions.
  • 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_69d827865f608190b311820428ae027b completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de610aa434819096671c5aabb9134a completed April 14, 2026, 3:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe249ebd3c81908d8b562845d9ceb1 completed May 8, 2026, 5:59 p.m.
Created at: April 9, 2026, 10:47 p.m.