Triple

T14586446
Position Surface form Disambiguated ID Type / Status
Subject Djenné E342327 entity
Predicate locatedOnRiver P165 FINISHED
Object Bani River NE NERFINISHED

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: Bani River | Statement: [Djenné, locatedOnRiver, Bani River]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bani River
Context triple: [Djenné, locatedOnRiver, Bani River]
  • A. Bani River chosen
    The Bani River is a significant West African waterway that joins the Niger River in Mali, contributing substantially to its flow and regional agriculture.
  • B. Bihad River
    The Bihad River is a regional river flowing through the Baghelkhand area of central India, contributing to the region’s drainage and local agriculture.
  • C. Tala River
    The Tala River is a watercourse in the Zaqatala region of northwestern Azerbaijan, contributing to the area's local hydrology and landscape.
  • D. Awali River
    The Awali River is a significant watercourse in Lebanon that flows through the region of Sidon before emptying into the Mediterranean Sea.
  • E. Baga River
    Baga River is a small coastal river in North Goa, India, known for flowing through the popular beach and tourist area of Baga before emptying into the Arabian Sea.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69d822ddc0f081909cd8163c7de298cd completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb421bb308190a457425429ef6aa5 completed April 14, 2026, 9:39 p.m.
Created at: April 10, 2026, 1:24 a.m.