Triple

T507945
Position Surface form Disambiguated ID Type / Status
Subject Ethiopian Rite E10542 entity
Predicate liturgicalLanguages P3115 FINISHED
Object Ge'ez E44574 NE FINISHED

How this triple was built (3 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, liturgicalLanguages, Ge'ez]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ge'ez
Context triple: [Ethiopian Rite, liturgicalLanguages, 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.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: liturgicalLanguages
Context triple: [Ethiopian Rite, liturgicalLanguages, Ge'ez]
  • A. liturgicalText
    Indicates that one entity is a liturgical or ritual text used in the religious or ceremonial practices associated with another entity.
  • B. liturgicalSetting
    Indicates the specific religious or worship context in which a liturgical text, action, or element is intended to be used.
  • C. languageOfWorship chosen
    Indicates the language in which religious worship, rituals, or liturgical practices are conducted.
  • D. liturgicalUsage
    Indicates how something is used, practiced, or functions within a specific liturgical or worship context.
  • E. liturgicalServices
    Indicates that one entity conducts, provides, or is associated with formal acts of public worship or religious rites for another entity or context.
  • F. None of above.

Provenance (4 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_69a49ebaf5c48190b24614b2a1ab9466 completed March 1, 2026, 8:16 p.m.
PD Predicate disambiguation batch_69a2edfce7a08190a408bc019de60d5d completed Feb. 28, 2026, 1:30 p.m.
Created at: Feb. 28, 2026, 1:12 p.m.