Triple

T12851538
Position Surface form Disambiguated ID Type / Status
Subject Lower Congo region E307333 entity
Predicate locatedOnRiver P165 FINISHED
Object Congo River E29137 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: Congo River | Statement: [Lower Congo region, locatedOnRiver, Congo River]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Congo River
Context triple: [Lower Congo region, locatedOnRiver, Congo River]
  • A. Congo River chosen
    The Congo River is Africa’s second-longest river and the world’s deepest, flowing through central Africa to the Atlantic Ocean and serving as a major waterway for transport, ecology, and regional economies.
  • B. Congo
    Congo is a Central African country whose economy is heavily reliant on oil production and exports.
  • C. Nam River
    The Nam River is a river in South Korea that flows through the city of Jinju and is known for its scenic views and historical significance in the region.
  • D. Kongō
    Kongō was a Japanese Kongō-class fast battleship that served prominently in the Imperial Japanese Navy during World War II.
  • E. Niger River
    The Niger River is a major West African river that flows in a great arc through countries including Guinea, Mali, Niger, and Nigeria before emptying into the Atlantic Ocean.
  • 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_69d7bdf5e7cc8190be357278bc5ba3bb completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d97020eacc81909357b3398d17dc49 completed April 10, 2026, 9:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6c0e393fc8190812380a3e41778bf completed May 3, 2026, 3:28 a.m.
Created at: April 9, 2026, 5:36 p.m.