Triple

T402870
Position Surface form Disambiguated ID Type / Status
Subject Ethiopian Jews E9322 entity
Predicate language P15 FINISHED
Object Amharic E41109 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: Amharic | Statement: [Ethiopian Jews, language, Amharic]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Amharic
Context triple: [Ethiopian Jews, language, Amharic]
  • A. Amharic chosen
    Amharic is a Semitic language widely spoken in Ethiopia and used as a major language of government, education, and media in the country.
  • B. Tigrinya
    Tigrinya is a Semitic language spoken primarily in Eritrea and northern Ethiopia, serving as a major language of communication, education, and media in the region.
  • C. Oromo
    Oromo is a Cushitic language widely spoken by the Oromo people, primarily in Ethiopia and parts of neighboring East African countries.
  • D. Ge'ez
    Ge'ez is an ancient Semitic language of Ethiopia and Eritrea, best known today as the classical and liturgical language of the Ethiopian and Eritrean Orthodox Tewahedo Churches.
  • E. Somali
    Somali is a Cushitic language spoken primarily in Somalia and neighboring regions of the Horn of Africa, serving as a major lingua franca and national language for the Somali people.
  • 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_69a2e8004cb88190b92ed1add6abf41a completed Feb. 28, 2026, 1:05 p.m.
NER Named-entity recognition batch_69a2eca0e2048190a7bf360257965e56 completed Feb. 28, 2026, 1:24 p.m.
NED1 Entity disambiguation (via context triple) batch_69a41042136c819096dde34d5608feec completed March 1, 2026, 10:09 a.m.
Created at: Feb. 28, 2026, 1:08 p.m.