Triple

T5335368
Position Surface form Disambiguated ID Type / Status
Subject Sabaki languages E123812 entity
Predicate includeLanguage P2177 FINISHED
Object Segeju
Segeju is a Bantu language of the Sabaki group spoken by the Segeju people in parts of coastal Kenya and Tanzania.
 E512927 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: Segeju | Statement: [Sabaki languages, includeLanguage, Segeju]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Segeju
Context triple: [Sabaki languages, includeLanguage, Segeju]
  • A. Buhera
    Buhera is a rural town and district center in eastern Zimbabwe known for its agricultural activities and location within Manicaland Province.
  • B. Takelsa
    Takelsa is a coastal town in northeastern Tunisia known for its agriculture and location within the Nabeul region on the Cap Bon peninsula.
  • C. Birsay
    Birsay is a coastal parish and village area on the northwest of Orkney Mainland in Scotland, known for its rich Norse history and archaeological sites.
  • D. Enkutatash
    Enkutatash is the Ethiopian New Year festival, celebrated in September with religious ceremonies, family gatherings, and the exchange of gifts and flowers.
  • E. Mandura Gumuz
    Mandura Gumuz is a Gumuz language spoken by the Gumuz people of western Ethiopia.
  • 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: Segeju
Triple: [Sabaki languages, includeLanguage, Segeju]
Generated description
Segeju is a Bantu language of the Sabaki group spoken by the Segeju people in parts of coastal Kenya and Tanzania.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Segeju
Target entity description: Segeju is a Bantu language of the Sabaki group spoken by the Segeju people in parts of coastal Kenya and Tanzania.
  • A. Buhera
    Buhera is a rural town and district center in eastern Zimbabwe known for its agricultural activities and location within Manicaland Province.
  • B. Takelsa
    Takelsa is a coastal town in northeastern Tunisia known for its agriculture and location within the Nabeul region on the Cap Bon peninsula.
  • C. Birsay
    Birsay is a coastal parish and village area on the northwest of Orkney Mainland in Scotland, known for its rich Norse history and archaeological sites.
  • D. Enkutatash
    Enkutatash is the Ethiopian New Year festival, celebrated in September with religious ceremonies, family gatherings, and the exchange of gifts and flowers.
  • E. Mandura Gumuz
    Mandura Gumuz is a Gumuz language spoken by the Gumuz people of western Ethiopia.
  • 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_69bd464b07f8819095aa76577c9829e4 completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd85af799081909ee60bfbb65149ee completed March 20, 2026, 5:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf18be4bb88190a2b83e51716e677e completed March 21, 2026, 10:16 p.m.
NEDg Description generation batch_69bf194c53a48190b0895bbe9aa2f6f1 completed March 21, 2026, 10:18 p.m.
NED2 Entity disambiguation (via description) batch_69bf1a198418819089b25102733f9191 completed March 21, 2026, 10:22 p.m.
Created at: March 20, 2026, 2 p.m.