Triple

T1948195
Position Surface form Disambiguated ID Type / Status
Subject Xiang Chinese E42101 entity
Predicate hasDialects P4251 FINISHED
Object New Xiang
New Xiang is a modern branch of the Xiang group of Chinese dialects, spoken primarily in parts of Hunan province and influenced by neighboring Mandarin varieties.
E218214 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: New Xiang | Statement: [Xiang Chinese, hasDialects, New Xiang]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: New Xiang
Context triple: [Xiang Chinese, hasDialects, New Xiang]
  • A. Ximending
    Ximending is a bustling shopping and entertainment district in Taipei known for its youth culture, street performances, and vibrant nightlife.
  • B. Xiang
    Xiang is the standard abbreviation and common short name used to refer to China’s Hunan Province.
  • C. Ban Shu Legend
    Ban Shu Legend is a Chinese historical romance television drama series centered on the life and adventures of a spirited young woman in the Han dynasty.
  • D. Vista Chinesa
    Vista Chinesa is a famous hilltop lookout in Rio de Janeiro offering panoramic views of the city, beaches, and surrounding rainforest.
  • E. Xing
    Xing is a German-based professional networking platform focused on career development and business connections, particularly in German-speaking countries.
  • 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: New Xiang
Triple: [Xiang Chinese, hasDialects, New Xiang]
Generated description
New Xiang is a modern branch of the Xiang group of Chinese dialects, spoken primarily in parts of Hunan province and influenced by neighboring Mandarin varieties.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: New Xiang
Target entity description: New Xiang is a modern branch of the Xiang group of Chinese dialects, spoken primarily in parts of Hunan province and influenced by neighboring Mandarin varieties.
  • A. Ximending
    Ximending is a bustling shopping and entertainment district in Taipei known for its youth culture, street performances, and vibrant nightlife.
  • B. Xiang
    Xiang is the standard abbreviation and common short name used to refer to China’s Hunan Province.
  • C. Ban Shu Legend
    Ban Shu Legend is a Chinese historical romance television drama series centered on the life and adventures of a spirited young woman in the Han dynasty.
  • D. Vista Chinesa
    Vista Chinesa is a famous hilltop lookout in Rio de Janeiro offering panoramic views of the city, beaches, and surrounding rainforest.
  • E. Xing
    Xing is a German-based professional networking platform focused on career development and business connections, particularly in German-speaking countries.
  • 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_69a8870e08fc8190a319cbf2600db15f completed March 4, 2026, 7:25 p.m.
NER Named-entity recognition batch_69abb33040c881908f42e80cbe1b1aca completed March 7, 2026, 5:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69adfbbf724081909b24680d483edbd1 completed March 8, 2026, 10:44 p.m.
NEDg Description generation batch_69adfc6aa96c81909ae3cff6c7ab7f79 completed March 8, 2026, 10:47 p.m.
NED2 Entity disambiguation (via description) batch_69adfcebbc808190a74f9082636bce11 completed March 8, 2026, 10:49 p.m.
Created at: March 4, 2026, 7:36 p.m.