Triple

T21137254
Position Surface form Disambiguated ID Type / Status
Subject Hou Hanshu E520844 entity
Predicate basedOnEarlierWork P7125 FINISHED
Object Dongguan Hanji
Dongguan Hanji is an earlier historical work on the Eastern Han dynasty that served as a key source for the later official history Hou Hanshu.
 E1468429 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: Dongguan Hanji | Statement: [Hou Hanshu, basedOnEarlierWork, Dongguan Hanji]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Dongguan Hanji
Context triple: [Hou Hanshu, basedOnEarlierWork, Dongguan Hanji]
  • A. Guangjia
    Guangjia was a warship of China’s late 19th-century Beiyang Fleet, one of the Qing dynasty’s principal modern naval forces.
  • B. Hangzhouhua
    Hangzhouhua is a regional Chinese dialect spoken in and around the city of Hangzhou in Zhejiang province.
  • C. Guanghua
    Guanghua is a leading business school under Peking University in China, renowned for its research and education in economics and management.
  • D. Guangqi
    Guangqi is the given name of Xu Guangqi, a prominent Ming dynasty scholar-official, scientist, and collaborator with Jesuit missionaries in introducing Western science to China.
  • E. Guangqi
    Guangqi was the era name used during part of Emperor Xizong of the Tang dynasty’s reign in late ninth-century 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: Dongguan Hanji
Triple: [Hou Hanshu, basedOnEarlierWork, Dongguan Hanji]
Generated description
Dongguan Hanji is an earlier historical work on the Eastern Han dynasty that served as a key source for the later official history Hou Hanshu.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Dongguan Hanji
Target entity description: Dongguan Hanji is an earlier historical work on the Eastern Han dynasty that served as a key source for the later official history Hou Hanshu.
  • A. Guangjia
    Guangjia was a warship of China’s late 19th-century Beiyang Fleet, one of the Qing dynasty’s principal modern naval forces.
  • B. Hangzhouhua
    Hangzhouhua is a regional Chinese dialect spoken in and around the city of Hangzhou in Zhejiang province.
  • C. Guanghua
    Guanghua is a leading business school under Peking University in China, renowned for its research and education in economics and management.
  • D. Guangqi
    Guangqi was the era name used during part of Emperor Xizong of the Tang dynasty’s reign in late ninth-century China.
  • E. Guangqi
    Guangqi is the given name of Xu Guangqi, a prominent Ming dynasty scholar-official, scientist, and collaborator with Jesuit missionaries in introducing Western science to 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_69e0b50b53048190ae34e8abbe3c5ada completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7235b89188190a6209c0a1839ee03 completed April 21, 2026, 7:12 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0965f556d881909652d21a62b10874 completed May 17, 2026, 6:53 a.m.
NEDg Description generation batch_6a0966f894d48190b6841c35a9aab417 completed May 17, 2026, 6:58 a.m.
NED2 Entity disambiguation (via description) batch_6a096adfd4248190a26c513278e7b334 completed May 17, 2026, 7:14 a.m.
Created at: April 16, 2026, 2:57 p.m.