Triple

T9034901
Position Surface form Disambiguated ID Type / Status
Subject Mathare E216465 entity
Predicate languageUsed P238 FINISHED
Object Sheng
Sheng is an urban Kenyan slang language that blends Swahili, English, and various local languages, widely spoken in Nairobi’s informal settlements and youth culture.
 E773371 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: Sheng | Statement: [Mathare, languageUsed, Sheng]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sheng
Context triple: [Mathare, languageUsed, Sheng]
  • A. Sheng
    Sheng is the primary male role type in traditional Chinese Peking opera, typically portraying dignified scholars, officials, and heroic figures.
  • B. Shengzhi
    Shengzhi is the given name of Tang Shengzhi, a prominent Chinese Nationalist general active during the early 20th century.
  • C. Shuheng
    Shuheng is the given name of He Shuheng, an early Chinese Communist revolutionary and political figure.
  • D. Yangsheng
    Yangsheng is a traditional Chinese practice focused on nurturing life and cultivating health and longevity through balanced living, diet, exercise, and spiritual refinement.
  • E. Shengzu
    Shengzu is the temple name of the Kangxi Emperor, one of the longest-reigning and most influential rulers of China’s Qing dynasty.
  • 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: Sheng
Triple: [Mathare, languageUsed, Sheng]
Generated description
Sheng is an urban Kenyan slang language that blends Swahili, English, and various local languages, widely spoken in Nairobi’s informal settlements and youth culture.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sheng
Target entity description: Sheng is an urban Kenyan slang language that blends Swahili, English, and various local languages, widely spoken in Nairobi’s informal settlements and youth culture.
  • A. Sheng
    Sheng is the primary male role type in traditional Chinese Peking opera, typically portraying dignified scholars, officials, and heroic figures.
  • B. Shengzhi
    Shengzhi is the given name of Tang Shengzhi, a prominent Chinese Nationalist general active during the early 20th century.
  • C. Shuheng
    Shuheng is the given name of He Shuheng, an early Chinese Communist revolutionary and political figure.
  • D. Yangsheng
    Yangsheng is a traditional Chinese practice focused on nurturing life and cultivating health and longevity through balanced living, diet, exercise, and spiritual refinement.
  • E. Shengzu
    Shengzu is the temple name of the Kangxi Emperor, one of the longest-reigning and most influential rulers of China’s Qing dynasty.
  • 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_69ca83d10b608190b2b2f8e0a7faaf14 completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cc6abf4af481908d21245332329d99 completed April 1, 2026, 12:45 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfdbce352c8190b5862d0cc103bfdb completed April 3, 2026, 3:25 p.m.
NEDg Description generation batch_69cfdcdb9d0c81908f89d2085c80016c completed April 3, 2026, 3:29 p.m.
NED2 Entity disambiguation (via description) batch_69cfdda4bf048190bc054fe9b1dcc98d completed April 3, 2026, 3:32 p.m.
Created at: March 30, 2026, 7:08 p.m.