Triple

T10110035
Position Surface form Disambiguated ID Type / Status
Subject Old Xiang E218215 entity
Predicate hasAlternativeName P39 FINISHED
Object Old Hsiang
Old Hsiang is an early historical form of the Xiang Chinese language, spoken in parts of Hunan province before later modern dialect developments.
 E842124 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: Old Hsiang | Statement: [Old Xiang, hasAlternativeName, Old Hsiang]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Old Hsiang
Context triple: [Old Xiang, hasAlternativeName, Old Hsiang]
  • A. Longcheng
    Longcheng was the principal royal city and political center of the Xiongnu confederation in ancient Inner Asia.
  • B. Guandu
    Guandu is a district in northern Taipei, Taiwan, known for its riverside wetlands, hot springs, and the historic Guandu Temple.
  • C. Haojing
    Haojing was the primary western capital city of the early Zhou dynasty in ancient China, located near present-day Xi’an.
  • D. Shangyuan
    Shangyuan was a Chinese imperial era name used during the reign of Emperor Suzong of the Tang dynasty.
  • E. Xingyuan
    Xingyuan was the Chinese era name used during part of Emperor Dezong of Tang’s reign in the late eighth century.
  • 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: Old Hsiang
Triple: [Old Xiang, hasAlternativeName, Old Hsiang]
Generated description
Old Hsiang is an early historical form of the Xiang Chinese language, spoken in parts of Hunan province before later modern dialect developments.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Old Hsiang
Target entity description: Old Hsiang is an early historical form of the Xiang Chinese language, spoken in parts of Hunan province before later modern dialect developments.
  • A. Longcheng
    Longcheng was the principal royal city and political center of the Xiongnu confederation in ancient Inner Asia.
  • B. Guandu
    Guandu is a district in northern Taipei, Taiwan, known for its riverside wetlands, hot springs, and the historic Guandu Temple.
  • C. Haojing
    Haojing was the primary western capital city of the early Zhou dynasty in ancient China, located near present-day Xi’an.
  • D. Shangyuan
    Shangyuan was a Chinese imperial era name used during the reign of Emperor Suzong of the Tang dynasty.
  • E. Xingyuan
    Xingyuan was the Chinese era name used during part of Emperor Dezong of Tang’s reign in the late eighth century.
  • 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_69d2cc1805d08190bc39aadf1e84a569 completed April 5, 2026, 8:54 p.m.
NEDg Description generation batch_69d2cd8f0a688190a437b7e2d158c70c completed April 5, 2026, 9:01 p.m.
NED2 Entity disambiguation (via description) batch_69d2ce422e4c8190b54b94cdfa0c4c98 completed April 5, 2026, 9:04 p.m.
Created at: March 30, 2026, 9:03 p.m.