Triple

T16567868
Position Surface form Disambiguated ID Type / Status
Subject Mandara language E402508 entity
Predicate languageSubbranch P1967 FINISHED
Object Biu–Mandara
Biu–Mandara is a major branch of the Chadic language family spoken primarily in parts of Nigeria, Cameroon, and Chad.
E1222793 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: Biu–Mandara | Statement: [Mandara language, languageSubbranch, Biu–Mandara]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Biu–Mandara
Context triple: [Mandara language, languageSubbranch, Biu–Mandara]
  • A. Mandara
    Mandara is a Chadic language spoken primarily in parts of Cameroon and Nigeria, associated with the Mandara (Wandala) ethnic group.
  • B. Dutsin-Ma
    Dutsin-Ma is a town in northern Nigeria known for hosting the Federal University Dutsin-Ma and serving as an important local commercial and educational center.
  • C. Rumuokoro
    Rumuokoro is a bustling urban town and major commercial transport hub in Obio-Akpor, within the Port Harcourt metropolitan area of Rivers State, Nigeria.
  • D. Mbini
    Mbini is a town in mainland Equatorial Guinea situated along the Benito River, known historically as a small river port and local administrative center.
  • E. Tontemboan
    Tontemboan is an Austronesian language spoken by the Tontemboan people in North Sulawesi, Indonesia.
  • 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: Biu–Mandara
Triple: [Mandara language, languageSubbranch, Biu–Mandara]
Generated description
Biu–Mandara is a major branch of the Chadic language family spoken primarily in parts of Nigeria, Cameroon, and Chad.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Biu–Mandara
Target entity description: Biu–Mandara is a major branch of the Chadic language family spoken primarily in parts of Nigeria, Cameroon, and Chad.
  • A. Mandara
    Mandara is a Chadic language spoken primarily in parts of Cameroon and Nigeria, associated with the Mandara (Wandala) ethnic group.
  • B. Dutsin-Ma
    Dutsin-Ma is a town in northern Nigeria known for hosting the Federal University Dutsin-Ma and serving as an important local commercial and educational center.
  • C. Rumuokoro
    Rumuokoro is a bustling urban town and major commercial transport hub in Obio-Akpor, within the Port Harcourt metropolitan area of Rivers State, Nigeria.
  • D. Mbini
    Mbini is a town in mainland Equatorial Guinea situated along the Benito River, known historically as a small river port and local administrative center.
  • E. Tontemboan
    Tontemboan is an Austronesian language spoken by the Tontemboan people in North Sulawesi, Indonesia.
  • 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_69d8838648088190acf97ef11fc3f61b completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e35772f6608190a125c7d3c199c3e2 completed April 18, 2026, 10:05 a.m.
NED1 Entity disambiguation (via context triple) batch_6a00759424348190889dacbbc7435238 completed May 10, 2026, 12:09 p.m.
NEDg Description generation batch_6a00783334a08190ae76fd7e114a9dd6 completed May 10, 2026, 12:21 p.m.
NED2 Entity disambiguation (via description) batch_6a0078562e788190b80a4ee27788ff69 completed May 10, 2026, 12:21 p.m.
Created at: April 10, 2026, 5:16 a.m.