Triple

T2254071
Position Surface form Disambiguated ID Type / Status
Subject Southern Nilotic languages E49679 entity
Predicate includesLanguage P2177 FINISHED
Object Marakwet
Marakwet is a Southern Nilotic language spoken primarily by the Marakwet people of Kenya’s Rift Valley region.
 E247223 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: Marakwet | Statement: [Southern Nilotic languages, includesLanguage, Marakwet]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Marakwet
Context triple: [Southern Nilotic languages, includesLanguage, Marakwet]
  • A. Mwotlap
    Mwotlap is an Oceanic Austronesian language spoken on Mota Lava and nearby islands in northern Vanuatu.
  • B. Negombo
    Negombo is a coastal city in western Sri Lanka known historically as a strategic colonial port and today for its fishing industry and beach tourism.
  • C. Sanglechi
    Sanglechi is a lesser-known Eastern Iranian language spoken in parts of northeastern Afghanistan and adjacent regions.
  • D. Karanga
    Karanga is a major dialect of the Shona language spoken primarily in southern Zimbabwe, known for its distinct phonological and lexical features.
  • E. Apswa
    Apswa is the endonym used by the Abkhaz people to refer to themselves and their language.
  • 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: Marakwet
Triple: [Southern Nilotic languages, includesLanguage, Marakwet]
Generated description
Marakwet is a Southern Nilotic language spoken primarily by the Marakwet people of Kenya’s Rift Valley region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Marakwet
Target entity description: Marakwet is a Southern Nilotic language spoken primarily by the Marakwet people of Kenya’s Rift Valley region.
  • A. Mwotlap
    Mwotlap is an Oceanic Austronesian language spoken on Mota Lava and nearby islands in northern Vanuatu.
  • B. Negombo
    Negombo is a coastal city in western Sri Lanka known historically as a strategic colonial port and today for its fishing industry and beach tourism.
  • C. Sanglechi
    Sanglechi is a lesser-known Eastern Iranian language spoken in parts of northeastern Afghanistan and adjacent regions.
  • D. Karanga
    Karanga is a major dialect of the Shona language spoken primarily in southern Zimbabwe, known for its distinct phonological and lexical features.
  • E. Apswa
    Apswa is the endonym used by the Abkhaz people to refer to themselves and their language.
  • 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_69a88aaa9250819095e127d0d77e8a32 completed March 4, 2026, 7:40 p.m.
NER Named-entity recognition batch_69abc12029548190af9f2cdd7a4de2d6 completed March 7, 2026, 6:09 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae6b1dd6fc8190bd762fb3a17258b0 completed March 9, 2026, 6:39 a.m.
NEDg Description generation batch_69ae6bbdef14819084b96389435ca080 completed March 9, 2026, 6:42 a.m.
NED2 Entity disambiguation (via description) batch_69ae6c2cfac48190b0425088e79cd122 completed March 9, 2026, 6:43 a.m.
Created at: March 4, 2026, 7:47 p.m.