Triple

T8880488
Position Surface form Disambiguated ID Type / Status
Subject Lake Kivu E211397 entity
Predicate borderCity P15361 FINISHED
Object Gisenyi E573046 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: Gisenyi | Statement: [Lake Kivu, borderCity, Gisenyi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gisenyi
Context triple: [Lake Kivu, borderCity, Gisenyi]
  • A. Gisenyi chosen
    Gisenyi is a city in northwestern Rwanda on the shores of Lake Kivu, historically significant as one of the key sites affected during the 1994 Rwandan genocide.
  • B. Bukavu
    Bukavu is a major city in the eastern Democratic Republic of the Congo, located on the southwestern shore of Lake Kivu near the Rwandan border.
  • C. Butare
    Butare is a city in southern Rwanda that became a significant site of massacres and atrocities during the 1994 Rwandan genocide.
  • D. Bujumbura
    Bujumbura is the largest city and former capital of Burundi, located on the northeastern shore of Lake Tanganyika.
  • E. Nsanje
    Nsanje is a town in southern Malawi near the border with Mozambique, known as a key transport and trading center in the Lower Shire Valley.
  • 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_69ca838f9e20819096ab1f236a70381a completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc61677c9c8190aa09dc2a05d4cf95 completed April 1, 2026, 12:05 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfdb8094a88190a88e3f23f9ae17c7 completed April 3, 2026, 3:23 p.m.
Created at: March 30, 2026, 6:52 p.m.