Triple

T899743
Position Surface form Disambiguated ID Type / Status
Subject Benue River E19419 entity
Predicate flowsThrough P225 FINISHED
Object Makurdi E106865 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: Makurdi | Statement: [Benue River, flowsThrough, Makurdi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Makurdi
Context triple: [Benue River, flowsThrough, Makurdi]
  • A. Makurdi chosen
    Makurdi is the capital city of Benue State in central Nigeria, serving as an important administrative and commercial hub in the region.
  • B. Bauchi
    Bauchi is a prominent city in northeastern Nigeria that serves as the capital of Bauchi State and a key commercial and administrative center in the region.
  • C. Enugu
    Enugu is a major city in southeastern Nigeria known historically for its coal mining industry and role as a regional administrative and economic center.
  • D. Owerri
    Owerri is the capital and largest city of Imo State in southeastern Nigeria, known as a regional cultural and commercial center.
  • E. Onitsha
    Onitsha is a major commercial and river port city on the eastern bank of the Niger River in southeastern Nigeria, known for its large open-air market and vibrant trade.
  • 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_69a4939e889c8190ac148b3ac1a7f90b completed March 1, 2026, 7:29 p.m.
NER Named-entity recognition batch_69a4ad4162848190aa2787b2fa3e6575 completed March 1, 2026, 9:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69a7cf5a4118819086035d6e250a53cc completed March 4, 2026, 6:21 a.m.
Created at: March 1, 2026, 7:39 p.m.