Triple

T507944
Position Surface form Disambiguated ID Type / Status
Subject Ethiopian Rite E10542 entity
Predicate primaryLiturgicalLanguage P3115 FINISHED
Object Ge'ez E44574 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: Ge'ez | Statement: [Ethiopian Rite, primaryLiturgicalLanguage, Ge'ez]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ge'ez
Context triple: [Ethiopian Rite, primaryLiturgicalLanguage, Ge'ez]
  • A. Ge'ez chosen
    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.
  • 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. Amharic
    Amharic is a Semitic language widely spoken in Ethiopia and used as a major language of government, education, and media in the country.
  • D. Gumuz languages
    Gumuz languages are a small group of closely related, under-documented languages spoken primarily by the Gumuz people in parts of Ethiopia and Sudan.
  • E. Oromo
    Oromo is a Cushitic language widely spoken by the Oromo people, primarily in Ethiopia and parts of neighboring East African countries.
  • 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_69a2e848adf881908e5e04f7af030093 completed Feb. 28, 2026, 1:06 p.m.
NER Named-entity recognition batch_69a2f14dcd688190ad47a3b31b95b6d4 completed Feb. 28, 2026, 1:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69a498506418819090190a35e8763982 completed March 1, 2026, 7:49 p.m.
Created at: Feb. 28, 2026, 1:12 p.m.