Triple

T2105338
Position Surface form Disambiguated ID Type / Status
Subject Zhou dynasty E37180 entity
Predicate capital P234 FINISHED
Object Haojing
Haojing was the primary western capital city of the early Zhou dynasty in ancient China, located near present-day Xi’an.
 E233751 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: Haojing | Statement: [Zhou dynasty, capital, Haojing]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Haojing
Context triple: [Zhou dynasty, capital, Haojing]
  • A. Xinjing
    Xinjing was the capital city of the Japanese puppet state of Manchukuo in northeastern China during the 1930s and early 1940s.
  • B. Jianye
    Jianye is an ancient name for the city now known as Nanjing, a historically significant capital in several Chinese dynasties.
  • C. Zhizhong
    Zhizhong is a Chinese given name shared by various individuals, including historical and contemporary figures.
  • D. Shëngjin
    Shëngjin is a coastal town and port in northwestern Albania on the Adriatic Sea, historically significant for its strategic maritime position.
  • E. 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.
  • 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: Haojing
Triple: [Zhou dynasty, capital, Haojing]
Generated description
Haojing was the primary western capital city of the early Zhou dynasty in ancient China, located near present-day Xi’an.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Haojing
Target entity description: Haojing was the primary western capital city of the early Zhou dynasty in ancient China, located near present-day Xi’an.
  • A. Xinjing
    Xinjing was the capital city of the Japanese puppet state of Manchukuo in northeastern China during the 1930s and early 1940s.
  • B. Jianye
    Jianye is an ancient name for the city now known as Nanjing, a historically significant capital in several Chinese dynasties.
  • C. Zhizhong
    Zhizhong is a Chinese given name shared by various individuals, including historical and contemporary figures.
  • D. Shëngjin
    Shëngjin is a coastal town and port in northwestern Albania on the Adriatic Sea, historically significant for its strategic maritime position.
  • E. 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.
  • 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_69a8861828948190924aa30c08806b3a completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69abbadcd4a081909d60b9b241950335 completed March 7, 2026, 5:42 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae306bee8881908c62306fb1f6aea1 completed March 9, 2026, 2:29 a.m.
NEDg Description generation batch_69ae30e1c7488190acd6d29c5ad10c33 completed March 9, 2026, 2:30 a.m.
NED2 Entity disambiguation (via description) batch_69ae316398488190b9dd38145d5488b4 completed March 9, 2026, 2:33 a.m.
Created at: March 4, 2026, 7:43 p.m.