Triple

T10110058
Position Surface form Disambiguated ID Type / Status
Subject Old Xiang E218215 entity
Predicate hasDialects P4251 FINISHED
Object Shaoyang Old Xiang
Shaoyang Old Xiang is a regional variety of the Old Xiang branch of Chinese spoken in and around Shaoyang in Hunan Province.
 E846965 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: Shaoyang Old Xiang | Statement: [Old Xiang, hasDialects, Shaoyang Old Xiang]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Shaoyang Old Xiang
Context triple: [Old Xiang, hasDialects, Shaoyang Old Xiang]
  • A. Liling Xiang
    Liling Xiang is a regional Chinese dialect spoken in and around Liling in Hunan Province.
  • B. Anhua Xiang
    Anhua Xiang is a regional variety of the Xiang Chinese language spoken primarily in Anhua County, Hunan Province, China.
  • C. Shuangfeng Old Xiang
    Shuangfeng Old Xiang is a traditional variety of the Old Xiang Chinese language spoken primarily in Shuangfeng County, Hunan Province.
  • D. Fenghuang Xiang
    Fenghuang Xiang is a regional variety of the Xiang Chinese language spoken in and around Fenghuang County in Hunan Province, China.
  • E. Pingxiang
    Pingxiang is a prefecture-level industrial city in western Jiangxi Province, China, known historically for its coal mining and ceramics production.
  • 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: Shaoyang Old Xiang
Triple: [Old Xiang, hasDialects, Shaoyang Old Xiang]
Generated description
Shaoyang Old Xiang is a regional variety of the Old Xiang branch of Chinese spoken in and around Shaoyang in Hunan Province.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Shaoyang Old Xiang
Target entity description: Shaoyang Old Xiang is a regional variety of the Old Xiang branch of Chinese spoken in and around Shaoyang in Hunan Province.
  • A. Liling Xiang
    Liling Xiang is a regional Chinese dialect spoken in and around Liling in Hunan Province.
  • B. Anhua Xiang
    Anhua Xiang is a regional variety of the Xiang Chinese language spoken primarily in Anhua County, Hunan Province, China.
  • C. Shuangfeng Old Xiang
    Shuangfeng Old Xiang is a traditional variety of the Old Xiang Chinese language spoken primarily in Shuangfeng County, Hunan Province.
  • D. Fenghuang Xiang
    Fenghuang Xiang is a regional variety of the Xiang Chinese language spoken in and around Fenghuang County in Hunan Province, China.
  • E. Pingxiang
    Pingxiang is a prefecture-level industrial city in western Jiangxi Province, China, known historically for its coal mining and ceramics production.
  • 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_69ca83da93fc8190b54e44bc2b34857c completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cdd0cdb3c88190a74f75bf865664f3 completed April 2, 2026, 2:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69d3174bc46081909d78cdb524625ec3 completed April 6, 2026, 2:15 a.m.
NEDg Description generation batch_69d3183a8410819094e81fe9f43717b2 completed April 6, 2026, 2:19 a.m.
NED2 Entity disambiguation (via description) batch_69d318adfcb081909a3567f5327765ab completed April 6, 2026, 2:21 a.m.
Created at: March 30, 2026, 9:03 p.m.