Triple

T8618293
Position Surface form Disambiguated ID Type / Status
Subject Ankang E204096 entity
Predicate formerName P65 FINISHED
Object Xicheng (historical)
Xicheng (historical) was the former name of the city now known as Ankang in Shaanxi Province, China.
 E746744 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: Xicheng (historical) | Statement: [Ankang, formerName, Xicheng (historical)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Xicheng (historical)
Context triple: [Ankang, formerName, Xicheng (historical)]
  • A. Longcheng
    Longcheng was the principal royal city and political center of the Xiongnu confederation in ancient Inner Asia.
  • B. Jianxing
    Jianxing was a historical Chinese era name used during the reign of Eastern Wu ruler Sun Quan in the Three Kingdoms period.
  • C. Xinjing
    Xinjing was the capital city of the Japanese puppet state of Manchukuo in northeastern China during the 1930s and early 1940s.
  • D. Guandu
    Guandu is a district in northern Taipei, Taiwan, known for its riverside wetlands, hot springs, and the historic Guandu Temple.
  • E. Xingzhen
    Xingzhen was the personal given name of Empress Dowager Cixi, the powerful de facto ruler of the late Qing dynasty in China.
  • 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: Xicheng (historical)
Triple: [Ankang, formerName, Xicheng (historical)]
Generated description
Xicheng (historical) was the former name of the city now known as Ankang in Shaanxi Province, China.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Xicheng (historical)
Target entity description: Xicheng (historical) was the former name of the city now known as Ankang in Shaanxi Province, China.
  • A. Longcheng
    Longcheng was the principal royal city and political center of the Xiongnu confederation in ancient Inner Asia.
  • B. Jianxing
    Jianxing was a historical Chinese era name used during the reign of Eastern Wu ruler Sun Quan in the Three Kingdoms period.
  • C. Xinjing
    Xinjing was the capital city of the Japanese puppet state of Manchukuo in northeastern China during the 1930s and early 1940s.
  • D. Guandu
    Guandu is a district in northern Taipei, Taiwan, known for its riverside wetlands, hot springs, and the historic Guandu Temple.
  • E. Xingzhen
    Xingzhen was the personal given name of Empress Dowager Cixi, the powerful de facto ruler of the late Qing dynasty in China.
  • 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_69ca832ceab8819096e4a9f546695079 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cc4712e74c81908b607a0ab2f9a361 completed March 31, 2026, 10:13 p.m.
NED1 Entity disambiguation (via context triple) batch_69cebbcb910881909088da53c6e31ae3 completed April 2, 2026, 6:56 p.m.
NEDg Description generation batch_69cebcc22d208190801b4ec58614dfcb completed April 2, 2026, 7 p.m.
NED2 Entity disambiguation (via description) batch_69cebdf3f288819088d83165c741d092 completed April 2, 2026, 7:05 p.m.
Created at: March 30, 2026, 6:26 p.m.