Triple

T23368408
Position Surface form Disambiguated ID Type / Status
Subject Ekondo-Titi E593389 entity
Predicate partOf P40 FINISHED
Object Ndian Division communes NE NERFINISHED

How this triple was built (3 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: Ndian Division communes | Statement: [Ekondo-Titi, partOf, Ndian Division communes]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ndian Division communes
Context triple: [Ekondo-Titi, partOf, Ndian Division communes]
  • A. Ndé Division
    Ndé Division is an administrative division in Cameroon’s West Region, known for its predominantly Bamileke population and economic activities centered around agriculture and trade.
  • B. Kumba Division
    Kumba Division is an administrative division in the Southwest Region of Cameroon, centered around the city of Kumba and known for its role as a regional commercial hub.
  • C. Ndé Department
    Ndé Department is an administrative division in western Cameroon known for its predominantly rural communities and agricultural activities.
  • D. Dantu District
    Dantu District is an administrative district of the city of Zhenjiang in Jiangsu Province, eastern China, known for its mix of urban development and industrial areas along the Yangtze River.
  • E. Diffa Department
    Diffa Department is an administrative subdivision in southeastern Niger that encompasses the city of Diffa and surrounding areas near the border with Nigeria and Chad.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ndian Division communes
Target entity description: Ndian Division communes are local government areas within Cameroon’s Ndian Division, encompassing towns and rural communities such as Ekondo-Titi.
  • A. Ndé Division
    Ndé Division is an administrative division in Cameroon’s West Region, known for its predominantly Bamileke population and economic activities centered around agriculture and trade.
  • B. Kumba Division
    Kumba Division is an administrative division in the Southwest Region of Cameroon, centered around the city of Kumba and known for its role as a regional commercial hub.
  • C. Ndé Department
    Ndé Department is an administrative division in western Cameroon known for its predominantly rural communities and agricultural activities.
  • D. Dantu District
    Dantu District is an administrative district of the city of Zhenjiang in Jiangsu Province, eastern China, known for its mix of urban development and industrial areas along the Yangtze River.
  • E. Diffa Department
    Diffa Department is an administrative subdivision in southeastern Niger that encompasses the city of Diffa and surrounding areas near the border with Nigeria and Chad.
  • F. None of above. chosen

Provenance (2 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_69e25d2593c88190bcdf4a716a94ccb2 completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f1a0aed374819097d38f51894bee44 completed April 29, 2026, 6:09 a.m.
Created at: April 17, 2026, 5:32 p.m.