Triple

T6302244
Position Surface form Disambiguated ID Type / Status
Subject Karbi language E141283 entity
Predicate hasDialects P4251 FINISHED
Object Amri Karbi
Amri Karbi is a dialect of the Karbi language spoken by the Karbi people in parts of Northeast India.
E584594 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: Amri Karbi | Statement: [Karbi language, hasDialects, Amri Karbi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Amri Karbi
Context triple: [Karbi language, hasDialects, Amri Karbi]
  • A. Banalata Sen
    Banalata Sen is a celebrated Bengali poem and its eponymous female figure, renowned for symbolizing beauty, solace, and timelessness in modern Bengali literature.
  • B. Basu
    Basu is an Indian surname, particularly common among Bengali communities, that is closely related to and sometimes used as a variant of the surname Bose.
  • C. Bijoy Dibos
    Bijoy Dibos is Bangladesh’s national Victory Day, commemorating the country’s triumph and independence in the Liberation War of 1971.
  • D. M.S. Banga
    M.S. Banga is an Indian business executive and corporate leader, known for his senior roles in major multinational companies and as the brother of global finance figure Ajay Banga.
  • E. Himman Dhamija
    Himman Dhamija is an Indian cinematographer known for his work on the historical film "Mangal Pandey: The Rising" and other Bollywood productions.
  • 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: Amri Karbi
Triple: [Karbi language, hasDialects, Amri Karbi]
Generated description
Amri Karbi is a dialect of the Karbi language spoken by the Karbi people in parts of Northeast India.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Amri Karbi
Target entity description: Amri Karbi is a dialect of the Karbi language spoken by the Karbi people in parts of Northeast India.
  • A. Banalata Sen
    Banalata Sen is a celebrated Bengali poem and its eponymous female figure, renowned for symbolizing beauty, solace, and timelessness in modern Bengali literature.
  • B. Basu
    Basu is an Indian surname, particularly common among Bengali communities, that is closely related to and sometimes used as a variant of the surname Bose.
  • C. Bijoy Dibos
    Bijoy Dibos is Bangladesh’s national Victory Day, commemorating the country’s triumph and independence in the Liberation War of 1971.
  • D. M.S. Banga
    M.S. Banga is an Indian business executive and corporate leader, known for his senior roles in major multinational companies and as the brother of global finance figure Ajay Banga.
  • E. Himman Dhamija
    Himman Dhamija is an Indian cinematographer known for his work on the historical film "Mangal Pandey: The Rising" and other Bollywood productions.
  • 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_69c008cf0ad4819095def81e2bd42f9f completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c0645cfca88190ace060ef5b0e00e8 completed March 22, 2026, 9:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69c5e436e7ec8190a5ea470eb83ddaea completed March 27, 2026, 1:58 a.m.
NEDg Description generation batch_69c5f3374b64819090c65e0bfdba116a completed March 27, 2026, 3:02 a.m.
NED2 Entity disambiguation (via description) batch_69c5f3d2e39c8190b579638ce8897c2d completed March 27, 2026, 3:04 a.m.
Created at: March 22, 2026, 4:27 p.m.