Triple

T12807008
Position Surface form Disambiguated ID Type / Status
Subject Ikeji Arakeji E306170 entity
Predicate locatedIn P40 FINISHED
Object Ijesha region E1001612 NE FINISHED

How this triple was built (2 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: Ijesha region | Statement: [Ikeji Arakeji, locatedIn, Ijesha region]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ijesha region
Context triple: [Ikeji Arakeji, locatedIn, Ijesha region]
  • A. Ijesha region chosen
    The Ijesha region is a culturally rich area in southwestern Nigeria traditionally inhabited by the Ijesha subgroup of the Yoruba people.
  • B. Kapoeta region
    Kapoeta region is an area in southeastern South Sudan inhabited largely by the Toposa people and known for its pastoralist communities and semi-arid landscape.
  • C. Omusati Region
    Omusati Region is an administrative region in northwestern Namibia known for its predominantly rural communities, subsistence agriculture, and proximity to the Angolan border.
  • D. Anioma region
    The Anioma region is a culturally distinct Igbo-speaking area in Delta State, Nigeria, known for its shared linguistic heritage, customs, and historical identity.
  • E. Mamfe region
    The Mamfe region is an area in southwestern Cameroon known for its diverse indigenous communities and the distinct Mamfe languages spoken there.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d7bdf46c448190b1faa55aaacb6317 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d96e808130819080f404b3a7462c2e completed April 10, 2026, 9:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6b8c75a048190aee92e50017c214e completed May 3, 2026, 2:53 a.m.
Created at: April 9, 2026, 5:31 p.m.