Triple

T2662948
Position Surface form Disambiguated ID Type / Status
Subject Lingala E54766 entity
Predicate hasDialects P4251 FINISHED
Object Bangala
Bangala is a regional variety of the Bantu language Lingala, spoken primarily in parts of the Democratic Republic of the Congo and neighboring areas.
 E286636 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: Bangala | Statement: [Lingala, hasDialects, Bangala]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Bangala
Context triple: [Lingala, hasDialects, Bangala]
  • A. Bangalee
    Bangalee is the popular stage nickname of Nigerian singer, songwriter, and harmonica-playing entertainer D'banj, known for his energetic Afrobeats hits.
  • B. Banga
    Banga is an Indian-origin surname most prominently associated with Ajay Banga, the business executive and current President of the World Bank.
  • C. Kalanga
    Kalanga is a Southern Bantu language spoken primarily in southwestern Zimbabwe and northeastern Botswana by the Kalanga people.
  • D. Odishi
    Odishi is the historical name for a region in western Georgia, corresponding largely to present-day Samegrelo and known for its distinct Mingrelian culture and history.
  • E. Beng
    Beng is the ISO 15924 four-letter code that designates the Bengali script used for writing the Bengali language and several other languages of the Indian subcontinent.
  • 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: Bangala
Triple: [Lingala, hasDialects, Bangala]
Generated description
Bangala is a regional variety of the Bantu language Lingala, spoken primarily in parts of the Democratic Republic of the Congo and neighboring areas.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Bangala
Target entity description: Bangala is a regional variety of the Bantu language Lingala, spoken primarily in parts of the Democratic Republic of the Congo and neighboring areas.
  • A. Bangalee
    Bangalee is the popular stage nickname of Nigerian singer, songwriter, and harmonica-playing entertainer D'banj, known for his energetic Afrobeats hits.
  • B. Banga
    Banga is an Indian-origin surname most prominently associated with Ajay Banga, the business executive and current President of the World Bank.
  • C. Kalanga
    Kalanga is a Southern Bantu language spoken primarily in southwestern Zimbabwe and northeastern Botswana by the Kalanga people.
  • D. Odishi
    Odishi is the historical name for a region in western Georgia, corresponding largely to present-day Samegrelo and known for its distinct Mingrelian culture and history.
  • E. Beng
    Beng is the ISO 15924 four-letter code that designates the Bengali script used for writing the Bengali language and several other languages of the Indian subcontinent.
  • 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_69ab49e028948190b97e01d73548b1d9 completed March 6, 2026, 9:40 p.m.
NER Named-entity recognition batch_69abd96b9f1c8190a8a9460ca88a9aaf completed March 7, 2026, 7:53 a.m.
NED1 Entity disambiguation (via context triple) batch_69af98dc36d8819086fc739c324f0761 completed March 10, 2026, 4:06 a.m.
NEDg Description generation batch_69af9a14cda48190bd903495ce48a4f0 completed March 10, 2026, 4:12 a.m.
NED2 Entity disambiguation (via description) batch_69af9a7b27608190ba76048c4c8a4bae completed March 10, 2026, 4:13 a.m.
Created at: March 6, 2026, 9:53 p.m.