Triple

T12653766
Position Surface form Disambiguated ID Type / Status
Subject Vai language E302228 entity
Predicate hasDialects P4251 FINISHED
Object Sierra Leonean Vai
Sierra Leonean Vai is a regional variety of the Vai language spoken primarily in Sierra Leone, distinguished by its own phonological and lexical features.
 E998832 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: Sierra Leonean Vai | Statement: [Vai language, hasDialects, Sierra Leonean Vai]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sierra Leonean Vai
Context triple: [Vai language, hasDialects, Sierra Leonean Vai]
  • A. Liberian Vai
    Liberian Vai is a primary dialect of the Vai language spoken in Liberia, known for its use of the indigenous Vai syllabary.
  • B. Mòoré
    Mòoré is a major Gur language spoken primarily by the Mossi people in Burkina Faso and surrounding West African countries.
  • C. Guere-Krahn
    Guere-Krahn is an exonym referring collectively to related Krahn and Guere ethnic groups of West Africa, primarily found in Liberia and Côte d’Ivoire.
  • D. Mandji
    Mandji is a town located within Ngounié Province in southwestern Gabon.
  • E. Vuré
    Vuré is an alternative name for the Lakon language, an Oceanic language spoken on the island of Gaua in Vanuatu.
  • 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: Sierra Leonean Vai
Triple: [Vai language, hasDialects, Sierra Leonean Vai]
Generated description
Sierra Leonean Vai is a regional variety of the Vai language spoken primarily in Sierra Leone, distinguished by its own phonological and lexical features.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sierra Leonean Vai
Target entity description: Sierra Leonean Vai is a regional variety of the Vai language spoken primarily in Sierra Leone, distinguished by its own phonological and lexical features.
  • A. Liberian Vai
    Liberian Vai is a primary dialect of the Vai language spoken in Liberia, known for its use of the indigenous Vai syllabary.
  • B. Mòoré
    Mòoré is a major Gur language spoken primarily by the Mossi people in Burkina Faso and surrounding West African countries.
  • C. Guere-Krahn
    Guere-Krahn is an exonym referring collectively to related Krahn and Guere ethnic groups of West Africa, primarily found in Liberia and Côte d’Ivoire.
  • D. Mandji
    Mandji is a town located within Ngounié Province in southwestern Gabon.
  • E. Vuré
    Vuré is an alternative name for the Lakon language, an Oceanic language spoken on the island of Gaua in Vanuatu.
  • 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_69d7bded71a88190bb76e2413af9ea66 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d96160730c81909e1aa3efb51bf159 completed April 10, 2026, 8:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6719c18508190a9c28b2526e6b336 completed May 2, 2026, 9:50 p.m.
NEDg Description generation batch_69f6749c2ddc8190945270e6e5b210dd completed May 2, 2026, 10:03 p.m.
NED2 Entity disambiguation (via description) batch_69f675c42fec8190b60751c0db88f3b6 completed May 2, 2026, 10:08 p.m.
Created at: April 9, 2026, 5:18 p.m.