Triple

T7574790
Position Surface form Disambiguated ID Type / Status
Subject Kalemie E179333 entity
Predicate river P165 FINISHED
Object Lukuga River E232618 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: Lukuga River | Statement: [Kalemie, river, Lukuga River]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lukuga River
Context triple: [Kalemie, river, Lukuga River]
  • A. Lukuga River chosen
    The Lukuga River is a major river in central Africa that drains Lake Tanganyika westward toward the Congo River basin.
  • B. Ruvubu River
    The Ruvubu River is a major East African river that flows through Burundi and Tanzania, forming part of the upper Nile basin.
  • C. Ulanga River
    The Ulanga River is a fictional East African waterway famously depicted as the treacherous river route navigated in C.S. Forester’s novel and the classic film "The African Queen."
  • D. Msunduzi River
    The Msunduzi River is a river in South Africa’s KwaZulu-Natal province that forms part of the drainage system feeding into the Lake St Lucia estuarine complex.
  • E. Mfolozi River
    The Mfolozi River is a major river in KwaZulu-Natal, South Africa, known for flowing through the Hluhluwe–iMfolozi Park and draining into the Indian Ocean near the iSimangaliso Wetland Park.
  • 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_69c69f316e50819081a271c85c06f918 completed March 27, 2026, 3:16 p.m.
NER Named-entity recognition batch_69c6f94a25148190b5b76e000e0336c4 completed March 27, 2026, 9:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69c922a94b3881908a3482ca45891df7 completed March 29, 2026, 1:01 p.m.
Created at: March 27, 2026, 3:51 p.m.