Triple

T262195
Position Surface form Disambiguated ID Type / Status
Subject China E5561 entity
Predicate regionalLanguage P237 FINISHED
Object Hakka
Hakka is a Sinitic language spoken primarily by the Hakka people across southern China and various overseas Chinese communities.
 E34449 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: Hakka | Statement: [China, regionalLanguage, Hakka]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Hakka
Context triple: [China, regionalLanguage, Hakka]
  • A. Paihuano
    Paihuano is a small town and commune in Chile’s Elqui Valley, known for its clear skies, pisco production, and astrotourism.
  • B. Higashi Shina Kai
    Higashi Shina Kai is the Japanese name for the East China Sea, a marginal sea located between China, Japan, Taiwan, and the Korean Peninsula.
  • C. Taihoku
    Taihoku was the Japanese colonial-era name for Taipei, which served as the administrative and political center of Taiwan under Japanese rule.
  • D. Hanyang
    Hanyang is a historic district and former city now incorporated into Wuhan in Hubei Province, China, known for its early industrial development and strategic location at the confluence of the Han and Yangtze rivers.
  • E. Tenjin
    Tenjin is the Shinto kami of scholarship and learning, widely revered by students seeking academic success.
  • 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: Hakka
Triple: [China, regionalLanguage, Hakka]
Generated description
Hakka is a Sinitic language spoken primarily by the Hakka people across southern China and various overseas Chinese communities.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Hakka
Target entity description: Hakka is a Sinitic language spoken primarily by the Hakka people across southern China and various overseas Chinese communities.
  • A. Paihuano
    Paihuano is a small town and commune in Chile’s Elqui Valley, known for its clear skies, pisco production, and astrotourism.
  • B. Higashi Shina Kai
    Higashi Shina Kai is the Japanese name for the East China Sea, a marginal sea located between China, Japan, Taiwan, and the Korean Peninsula.
  • C. Taihoku
    Taihoku was the Japanese colonial-era name for Taipei, which served as the administrative and political center of Taiwan under Japanese rule.
  • D. Hanyang
    Hanyang is a historic district and former city now incorporated into Wuhan in Hubei Province, China, known for its early industrial development and strategic location at the confluence of the Han and Yangtze rivers.
  • E. Tenjin
    Tenjin is the Shinto kami of scholarship and learning, widely revered by students seeking academic success.
  • 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_69a2580a64ac8190ad76e34bb0715b5e completed Feb. 28, 2026, 2:50 a.m.
NER Named-entity recognition batch_69a25d7428dc8190ae12b12a21fcc6cb completed Feb. 28, 2026, 3:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69a389ac93ec8190baf0c20a1e872b94 completed March 1, 2026, 12:34 a.m.
NEDg Description generation batch_69a38a1e2e7081908a132d7bd147379b completed March 1, 2026, 12:36 a.m.
NED2 Entity disambiguation (via description) batch_69a38a71c37481908cbc011e71c93c58 completed March 1, 2026, 12:38 a.m.
Created at: Feb. 28, 2026, 2:55 a.m.