Triple

T13299522
Position Surface form Disambiguated ID Type / Status
Subject Central Tai E316769 entity
Predicate hasLanguage P15 FINISHED
Object Fusui Zhuang
Fusui Zhuang is a variety of the Zhuang language spoken by the Zhuang people in the Fusui region of Guangxi, southern China.
E1042373 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: Fusui Zhuang | Statement: [Central Tai, hasLanguage, Fusui Zhuang]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fusui Zhuang
Context triple: [Central Tai, hasLanguage, Fusui Zhuang]
  • A. Fangzhuang
    Fangzhuang is a residential neighborhood and commercial area in Beijing, China, known as one of the city’s earlier large-scale planned communities.
  • B. Jingxi Zhuang
    Jingxi Zhuang is a variety of the Zhuang language spoken in the Jingxi region of Guangxi, China, belonging to the Central Tai branch of the Tai–Kadai language family.
  • C. Xingyuan
    Xingyuan was the Chinese era name used during part of Emperor Dezong of Tang’s reign in the late eighth century.
  • D. Shangyuan
    Shangyuan was a Chinese imperial era name used during the reign of Emperor Suzong of the Tang dynasty.
  • E. Zhizhong
    Zhizhong is a Chinese given name shared by various individuals, including historical and contemporary figures.
  • 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: Fusui Zhuang
Triple: [Central Tai, hasLanguage, Fusui Zhuang]
Generated description
Fusui Zhuang is a variety of the Zhuang language spoken by the Zhuang people in the Fusui region of Guangxi, southern China.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Fusui Zhuang
Target entity description: Fusui Zhuang is a variety of the Zhuang language spoken by the Zhuang people in the Fusui region of Guangxi, southern China.
  • A. Fangzhuang
    Fangzhuang is a residential neighborhood and commercial area in Beijing, China, known as one of the city’s earlier large-scale planned communities.
  • B. Jingxi Zhuang
    Jingxi Zhuang is a variety of the Zhuang language spoken in the Jingxi region of Guangxi, China, belonging to the Central Tai branch of the Tai–Kadai language family.
  • C. Xingyuan
    Xingyuan was the Chinese era name used during part of Emperor Dezong of Tang’s reign in the late eighth century.
  • D. Shangyuan
    Shangyuan was a Chinese imperial era name used during the reign of Emperor Suzong of the Tang dynasty.
  • E. Zhizhong
    Zhizhong is a Chinese given name shared by various individuals, including historical and contemporary figures.
  • 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_69d806b40ab4819094adf6c374f4811a completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d990a43ed88190a8dbbbd7d6d62dc4 completed April 11, 2026, 12:07 a.m.
NED1 Entity disambiguation (via context triple) batch_69f74610b2c481909497296e999226e8 completed May 3, 2026, 12:56 p.m.
NEDg Description generation batch_69f74b744de88190b0d9dad1c91b11af completed May 3, 2026, 1:19 p.m.
NED2 Entity disambiguation (via description) batch_69f74befe7008190a059c8ec7b25f134 completed May 3, 2026, 1:21 p.m.
Created at: April 9, 2026, 9:28 p.m.