Triple

T20886725
Position Surface form Disambiguated ID Type / Status
Subject Bishoftu Air Base E514300 entity
Predicate locatedNear P294 FINISHED
Object Lake Bishoftu 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: Lake Bishoftu | Statement: [Bishoftu Air Base, locatedNear, Lake Bishoftu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lake Bishoftu
Context triple: [Bishoftu Air Base, locatedNear, Lake Bishoftu]
  • A. Lake Bishoftu chosen
    Lake Bishoftu is a small, scenic crater lake located in the town of Bishoftu in central Ethiopia, known for its volcanic origins and surrounding resort area.
  • B. Lake Afdera
    Lake Afdera is a hypersaline lake in Ethiopia’s Afar Depression, known for its extreme heat, below-sea-level elevation, and surrounding salt extraction activities.
  • C. Lake Ziway
    Lake Ziway is a freshwater lake in Ethiopia’s Rift Valley, known for its rich birdlife, fishing communities, and several historic island monasteries.
  • D. Lake Langano
    Lake Langano is a popular Rift Valley lake in Ethiopia known for its brownish waters, birdlife, and status as a major resort and recreation destination.
  • E. Lake Abaya
    Lake Abaya is a large, shallow rift valley lake in southern Ethiopia known for its reddish-brown waters and rich birdlife.
  • 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_69e0b4f733f081908a401c0b7beb0b9f completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6d058d4dc81908398f8c75e30dc77 completed April 21, 2026, 1:18 a.m.
Created at: April 16, 2026, 12:46 p.m.