Triple

T8949590
Position Surface form Disambiguated ID Type / Status
Subject Xia dynasty E213310 entity
Predicate capital P234 FINISHED
Object Yangcheng
Yangcheng was an ancient Chinese city traditionally regarded as one of the earliest capitals of the Xia dynasty.
 E768317 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: Yangcheng | Statement: [Xia dynasty, capital, Yangcheng]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Yangcheng
Context triple: [Xia dynasty, capital, Yangcheng]
  • A. Yangsan
    Yangsan is a city in South Gyeongsang Province, South Korea, known as a growing residential and educational hub near Busan.
  • B. Yangsansi
    Yangsansi is a city in South Korea located within Gyeonggi Province, forming part of the greater Seoul metropolitan area.
  • C. Bo'an
    Bo'an is the courtesy name of Wang Yangming, the influential Ming dynasty philosopher, statesman, and Neo-Confucian thinker.
  • D. Thamien
    Thamien is an alternate name for the Tamyen, a Native American people and language historically associated with the San Francisco Bay Area in California.
  • E. Songshan
    Songshan is one of China's Five Great Mountains, renowned as a sacred Taoist and Buddhist site and home to the historic Shaolin Monastery.
  • 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: Yangcheng
Triple: [Xia dynasty, capital, Yangcheng]
Generated description
Yangcheng was an ancient Chinese city traditionally regarded as one of the earliest capitals of the Xia dynasty.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Yangcheng
Target entity description: Yangcheng was an ancient Chinese city traditionally regarded as one of the earliest capitals of the Xia dynasty.
  • A. Yangsan
    Yangsan is a city in South Gyeongsang Province, South Korea, known as a growing residential and educational hub near Busan.
  • B. Yangsansi
    Yangsansi is a city in South Korea located within Gyeonggi Province, forming part of the greater Seoul metropolitan area.
  • C. Bo'an
    Bo'an is the courtesy name of Wang Yangming, the influential Ming dynasty philosopher, statesman, and Neo-Confucian thinker.
  • D. Thamien
    Thamien is an alternate name for the Tamyen, a Native American people and language historically associated with the San Francisco Bay Area in California.
  • E. Songshan
    Songshan is one of China's Five Great Mountains, renowned as a sacred Taoist and Buddhist site and home to the historic Shaolin Monastery.
  • 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_69ca839843408190a39069a029a89f15 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc670b5f50819080f1c73992fe5281 completed April 1, 2026, 12:30 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfc206550c8190abf016f25b14fa64 completed April 3, 2026, 1:35 p.m.
NEDg Description generation batch_69cfc3f170a08190a2cab07eb280ee3b completed April 3, 2026, 1:43 p.m.
NED2 Entity disambiguation (via description) batch_69cfc476204481909f0baaf400483f33 completed April 3, 2026, 1:45 p.m.
Created at: March 30, 2026, 6:59 p.m.