Triple

T16165094
Position Surface form Disambiguated ID Type / Status
Subject Shangjing E392282 entity
Predicate successorCapital P30709 FINISHED
Object Yanjing
Yanjing was a historic Chinese capital city, best known as the former name of modern-day Beijing.
 E1197391 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: Yanjing | Statement: [Shangjing, successorCapital, Yanjing]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Yanjing
Context triple: [Shangjing, successorCapital, Yanjing]
  • A. Xinjing
    Xinjing was the capital city of the Japanese puppet state of Manchukuo in northeastern China during the 1930s and early 1940s.
  • B. Yiheyuan
    Yiheyuan, known in English as the Summer Palace, is a vast imperial garden and former royal retreat in Beijing famed for its lakes, palaces, and classical Chinese landscape design.
  • C. Dajing
    Dajing is a Chinese given name notably borne by Olympic short track speed skating champion Wu Dajing.
  • D. Jūyōngguān
    Jūyōngguān is a historically significant mountain pass and fortified section of the Great Wall of China located northwest of Beijing.
  • E. Xianqing
    Xianqing was a regnal era of the Tang dynasty under Emperor Gaozong, marking a specific period of his reign used for dating official documents and events.
  • 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: Yanjing
Triple: [Shangjing, successorCapital, Yanjing]
Generated description
Yanjing was a historic Chinese capital city, best known as the former name of modern-day Beijing.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Yanjing
Target entity description: Yanjing was a historic Chinese capital city, best known as the former name of modern-day Beijing.
  • A. Xinjing
    Xinjing was the capital city of the Japanese puppet state of Manchukuo in northeastern China during the 1930s and early 1940s.
  • B. Yiheyuan
    Yiheyuan, known in English as the Summer Palace, is a vast imperial garden and former royal retreat in Beijing famed for its lakes, palaces, and classical Chinese landscape design.
  • C. Dajing
    Dajing is a Chinese given name notably borne by Olympic short track speed skating champion Wu Dajing.
  • D. Jūyōngguān
    Jūyōngguān is a historically significant mountain pass and fortified section of the Great Wall of China located northwest of Beijing.
  • E. Xianqing
    Xianqing was a regnal era of the Tang dynasty under Emperor Gaozong, marking a specific period of his reign used for dating official documents and events.
  • 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_69d87f1d32208190942e4e499a80c18c completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e21e622ae481909f3cf25b38886d3a completed April 17, 2026, 11:49 a.m.
NED1 Entity disambiguation (via context triple) batch_69fff7b96bf08190b23bd3b705a34c61 completed May 10, 2026, 3:12 a.m.
NEDg Description generation batch_69fff87caefc8190836d690dfb2523f9 completed May 10, 2026, 3:16 a.m.
NED2 Entity disambiguation (via description) batch_69fff98b3d7c8190bb284321d17f58e2 completed May 10, 2026, 3:20 a.m.
Created at: April 10, 2026, 5:02 a.m.