Triple

T14084788
Position Surface form Disambiguated ID Type / Status
Subject Governor-General of Liangguang E338962 entity
Predicate officeHeldBy P537 FINISHED
Object Xiliang
Xiliang was a late Qing dynasty official who served as a prominent provincial governor-general and played a key role in the empire’s final reform and defense efforts.
E1084798 NE FINISHED

How this triple was built (4 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: Xiliang | Statement: [Governor-General of Liangguang, officeHeldBy, Xiliang]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Xiliang
Context triple: [Governor-General of Liangguang, officeHeldBy, Xiliang]
  • A. Linxiang
    Linxiang is a county-level city administered by Yueyang in Hunan Province, China, known for its location near the Yangtze River and its regional agricultural and industrial activities.
  • B. Yuxiang
    Yuxiang is a Chinese given name notably borne by the early 20th-century warlord and military leader Feng Yuxiang.
  • C. Yuanxing
    Yuanxing was the era name used by Eastern Wu emperor Sun Hao during part of his tumultuous late Three Kingdoms–period reign in China.
  • D. Xiluoyuan
    Xiluoyuan is a residential neighborhood and subdistrict located in Beijing’s Fengtai District.
  • E. Xingyuan
    Xingyuan was the Chinese era name used during part of Emperor Dezong of Tang’s reign in the late eighth century.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Xiliang
Triple: [Governor-General of Liangguang, officeHeldBy, Xiliang]
Generated description
Xiliang was a late Qing dynasty official who served as a prominent provincial governor-general and played a key role in the empire’s final reform and defense efforts.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Xiliang
Target entity description: Xiliang was a late Qing dynasty official who served as a prominent provincial governor-general and played a key role in the empire’s final reform and defense efforts.
  • A. Linxiang
    Linxiang is a county-level city administered by Yueyang in Hunan Province, China, known for its location near the Yangtze River and its regional agricultural and industrial activities.
  • B. Yuxiang
    Yuxiang is a Chinese given name notably borne by the early 20th-century warlord and military leader Feng Yuxiang.
  • C. Yuanxing
    Yuanxing was the era name used by Eastern Wu emperor Sun Hao during part of his tumultuous late Three Kingdoms–period reign in China.
  • D. Xiluoyuan
    Xiluoyuan is a residential neighborhood and subdistrict located in Beijing’s Fengtai District.
  • E. Xingyuan
    Xingyuan was the Chinese era name used during part of Emperor Dezong of Tang’s reign in the late eighth century.
  • F. None of above. chosen

Provenance (5 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_69d81c687b0c819087fd9ed4198403f8 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de5ede40048190b465e909565730c1 completed April 14, 2026, 3:35 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd1930da6481908d17adc6f7bbedd4 completed May 7, 2026, 10:58 p.m.
NEDg Description generation batch_69fd19e4d374819084f01e17052428a2 completed May 7, 2026, 11:01 p.m.
NED2 Entity disambiguation (via description) batch_69fd1ab75e8c819091ebc3b4bc16f2cb completed May 7, 2026, 11:05 p.m.
Created at: April 9, 2026, 10:21 p.m.