Triple

T3795212
Position Surface form Disambiguated ID Type / Status
Subject Jin dynasty E89753 entity
Predicate capital P234 FINISHED
Object Zhongdu
Zhongdu was the historical capital city of the Jurchen-led Jin dynasty in northern China, located in what is now part of modern Beijing.
 E391585 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: Zhongdu | Statement: [Jin dynasty, capital, Zhongdu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Zhongdu
Context triple: [Jin dynasty, capital, Zhongdu]
  • A. Tiāntán
    Tiāntán is the Chinese pinyin name for the Temple of Heaven, a historic imperial religious complex in Beijing where Ming and Qing dynasty emperors performed annual ceremonies to pray for good harvests.
  • B. Jīlóng Shì
    Jīlóng Shì is the Mandarin Chinese pinyin name for Keelung City, a major port city in northern Taiwan.
  • C. Lingang
    Lingang is a rapidly developing industrial and high-tech district in Shanghai, China, known for hosting major manufacturing facilities such as Tesla’s Gigafactory Shanghai.
  • D. Taian
    Taian is a prefecture-level city in eastern China's Shandong province, best known as the gateway to the sacred Mount Tai.
  • E. Yuncheng
    Yuncheng is a major city in southern Shanxi Province, China, known for its historical sites and role as a regional transportation and economic hub.
  • 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: Zhongdu
Triple: [Jin dynasty, capital, Zhongdu]
Generated description
Zhongdu was the historical capital city of the Jurchen-led Jin dynasty in northern China, located in what is now part of modern Beijing.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Zhongdu
Target entity description: Zhongdu was the historical capital city of the Jurchen-led Jin dynasty in northern China, located in what is now part of modern Beijing.
  • A. Tiāntán
    Tiāntán is the Chinese pinyin name for the Temple of Heaven, a historic imperial religious complex in Beijing where Ming and Qing dynasty emperors performed annual ceremonies to pray for good harvests.
  • B. Jīlóng Shì
    Jīlóng Shì is the Mandarin Chinese pinyin name for Keelung City, a major port city in northern Taiwan.
  • C. Lingang
    Lingang is a rapidly developing industrial and high-tech district in Shanghai, China, known for hosting major manufacturing facilities such as Tesla’s Gigafactory Shanghai.
  • D. Taian
    Taian is a prefecture-level city in eastern China's Shandong province, best known as the gateway to the sacred Mount Tai.
  • E. Yuncheng
    Yuncheng is a major city in southern Shanxi Province, China, known for its historical sites and role as a regional transportation and economic hub.
  • 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_69aed9597d6881909b6ee3b9de859223 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aee79db2e88190b3aa2b8e8d885e19 completed March 9, 2026, 3:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4fb232650819089feed9d5bb8c91a completed March 14, 2026, 6:07 a.m.
NEDg Description generation batch_69b4fc7abfb481908f563e17e6e57a4e completed March 14, 2026, 6:13 a.m.
NED2 Entity disambiguation (via description) batch_69b4fce0a6a88190be19941a70caebdc completed March 14, 2026, 6:14 a.m.
Created at: March 9, 2026, 3:15 p.m.