Triple

T4131968
Position Surface form Disambiguated ID Type / Status
Subject Meliandou E85060 entity
Predicate regionLanguage P10892 FINISHED
Object Kissi
Kissi is a West African language spoken primarily by the Kissi people in parts of Guinea, Sierra Leone, and Liberia.
 E414777 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: Kissi | Statement: [Meliandou, regionLanguage, Kissi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kissi
Context triple: [Meliandou, regionLanguage, Kissi]
  • A. Karcsi
    Karcsi is a common Hungarian diminutive form of the male given name Károly, used as an affectionate or informal nickname.
  • B. Tavuki
    Tavuki is a coastal village located on Kadavu Island in Fiji, known for its traditional Fijian community and surrounding natural beauty.
  • C. Mici
    Mici is the given name of Mária Harkányi, a person known by this shorter personal name.
  • D. Michu
    Michu is a retired Spanish attacking midfielder and forward best known for his prolific 2012–13 season with Swansea City in the English Premier League.
  • E. Sheba
    Sheba is a biblical figure traditionally associated with a people or kingdom in the ancient Near East, often linked to the famed Queen of Sheba.
  • 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: Kissi
Triple: [Meliandou, regionLanguage, Kissi]
Generated description
Kissi is a West African language spoken primarily by the Kissi people in parts of Guinea, Sierra Leone, and Liberia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kissi
Target entity description: Kissi is a West African language spoken primarily by the Kissi people in parts of Guinea, Sierra Leone, and Liberia.
  • A. Karcsi
    Karcsi is a common Hungarian diminutive form of the male given name Károly, used as an affectionate or informal nickname.
  • B. Tavuki
    Tavuki is a coastal village located on Kadavu Island in Fiji, known for its traditional Fijian community and surrounding natural beauty.
  • C. Mici
    Mici is the given name of Mária Harkányi, a person known by this shorter personal name.
  • D. Michu
    Michu is a retired Spanish attacking midfielder and forward best known for his prolific 2012–13 season with Swansea City in the English Premier League.
  • E. Sheba
    Sheba is a biblical figure traditionally associated with a people or kingdom in the ancient Near East, often linked to the famed Queen of Sheba.
  • 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_69aed935ccd881909dc61f81bcdb7a78 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69af022f55fc81909f2a1a04d0ea59e6 completed March 9, 2026, 5:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69b576c26d4c81909b8be74855cbd03f completed March 14, 2026, 2:54 p.m.
NEDg Description generation batch_69b577c2b784819096d8218dd1c1478d completed March 14, 2026, 2:59 p.m.
NED2 Entity disambiguation (via description) batch_69b5782cc448819080e306952da24ac0 completed March 14, 2026, 3:01 p.m.
Created at: March 9, 2026, 3:42 p.m.