Triple

T1788928
Position Surface form Disambiguated ID Type / Status
Subject Lake Tana E39450 entity
Predicate nearCity P350 FINISHED
Object Bahir Dar E192971 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: Bahir Dar | Statement: [Lake Tana, nearCity, Bahir Dar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bahir Dar
Context triple: [Lake Tana, nearCity, Bahir Dar]
  • A. Bahir Dar chosen
    Bahir Dar is a major city in northwestern Ethiopia, known for its location on the southern shore of Lake Tana and as a gateway to the Blue Nile Falls and nearby monasteries.
  • B. Addis Ababa
    Addis Ababa is the capital and largest city of Ethiopia, serving as a major political and diplomatic hub in Africa that hosts numerous international organizations and institutions.
  • C. Lalibela
    Lalibela is a historic town in northern Ethiopia renowned for its 12th–13th century rock-hewn churches, which are among the most important pilgrimage sites of Ethiopian Christianity.
  • D. Wolaytta
    Wolaytta is a Cushitic-influenced Omotic language spoken primarily by the Wolaytta people in southern Ethiopia.
  • E. Gash‑Barka
    Gash‑Barka is a largely agricultural region in southwestern Eritrea known for its fertile land and role as one of the country’s main food-producing areas.
  • 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_69a88631854081909723959921e45c2b completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69aa65111e5481909c22abb6ad966814 completed March 6, 2026, 5:24 a.m.
NED1 Entity disambiguation (via context triple) batch_69ada9a8a69c8190885bf06a06d3869f completed March 8, 2026, 4:54 p.m.
Created at: March 4, 2026, 7:32 p.m.