Triple

T3298847
Position Surface form Disambiguated ID Type / Status
Subject Geʽez script E69281 entity
Predicate usedForLanguage P907 FINISHED
Object Tigrinya language E41857 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: Tigrinya language | Statement: [Geʽez script, usedForLanguage, Tigrinya language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tigrinya language
Context triple: [Geʽez script, usedForLanguage, Tigrinya language]
  • A. Tigrinya chosen
    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.
  • B. Amharic
    Amharic is a Semitic language widely spoken in Ethiopia and used as a major language of government, education, and media in the country.
  • C. 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.
  • D. ትግርኛ
    ትግርኛ is a Semitic language primarily spoken in Eritrea and northern Ethiopia by the Tigrinya people.
  • E. Ethiopian
    Ethiopian refers to a person from Ethiopia or of Ethiopian descent, associated with the country's distinct cultures, languages, and history in the Horn of Africa.
  • 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_69ad859e529c8190a404273f53cb487d completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb0a49b748190b6db99a85c3cb3c5 completed March 8, 2026, 5:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69b325033aa88190a6b54b767f83fa24 completed March 12, 2026, 8:41 p.m.
Created at: March 8, 2026, 3:11 p.m.