Triple

T623386
Position Surface form Disambiguated ID Type / Status
Subject Saraiki E14560 entity
Predicate hasDialects P4251 FINISHED
Object Jatki
Jatki is a regional dialect of the Saraiki language spoken primarily in parts of Pakistan.
 E77871 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: Jatki | Statement: [Saraiki, hasDialects, Jatki]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Jatki
Context triple: [Saraiki, hasDialects, Jatki]
  • A. Juhurim
    Juhurim are a Jewish ethnic group from the eastern and northern Caucasus, particularly Dagestan and Azerbaijan, with their own distinct language (Juhuri) and cultural traditions.
  • B. Jagaban
    Jagaban is the popular political nickname of Nigerian politician and current president Bola Ahmed Tinubu, often used to signify his influential “godfather” status in Nigerian politics.
  • C. Raka
    Raka is a renowned Afrikaans narrative poem by N. P. van Wyk Louw that explores themes of civilization, barbarism, and moral conflict through an allegorical tale.
  • D. Jaakko
    Jaakko is a Finnish given name, equivalent to the English name James.
  • E. Juché
    Juché is an alternative spelling of Juche, the North Korean state ideology centered on self-reliance and the absolute leadership of the Kim 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: Jatki
Triple: [Saraiki, hasDialects, Jatki]
Generated description
Jatki is a regional dialect of the Saraiki language spoken primarily in parts of Pakistan.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Jatki
Target entity description: Jatki is a regional dialect of the Saraiki language spoken primarily in parts of Pakistan.
  • A. Juhurim
    Juhurim are a Jewish ethnic group from the eastern and northern Caucasus, particularly Dagestan and Azerbaijan, with their own distinct language (Juhuri) and cultural traditions.
  • B. Jagaban
    Jagaban is the popular political nickname of Nigerian politician and current president Bola Ahmed Tinubu, often used to signify his influential “godfather” status in Nigerian politics.
  • C. Raka
    Raka is a renowned Afrikaans narrative poem by N. P. van Wyk Louw that explores themes of civilization, barbarism, and moral conflict through an allegorical tale.
  • D. Jaakko
    Jaakko is a Finnish given name, equivalent to the English name James.
  • E. Juché
    Juché is an alternative spelling of Juche, the North Korean state ideology centered on self-reliance and the absolute leadership of the Kim 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_69a4934b17c881909ace8270e8ddd202 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a49e41753881909f0faed720cc31bc completed March 1, 2026, 8:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69a563cc368c8190920e0d84d65a236e completed March 2, 2026, 10:17 a.m.
NEDg Description generation batch_69a5644ac23c8190b4df2a9f96385fe0 completed March 2, 2026, 10:19 a.m.
NED2 Entity disambiguation (via description) batch_69a564c7011c81908560b563a4cad560 completed March 2, 2026, 10:21 a.m.
Created at: March 1, 2026, 7:35 p.m.