Triple

T8466151
Position Surface form Disambiguated ID Type / Status
Subject Ambiko E200165 entity
Predicate languageUsed P238 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: [Ambiko, languageUsed, Amharic]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Amharic
Context triple: [Ambiko, languageUsed, 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. 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.
  • D. Eritrean
    Eritrean refers to someone or something originating from Eritrea, a country in the Horn of Africa known for its diverse ethnic groups and Red Sea coastline.
  • E. ETHIOPIAN
    ETHIOPIAN is the radio callsign used by Ethiopian Airlines for its flight operations and air traffic communications.
  • 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_69ca83198c4c8190a337bf717d1813f5 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe4d17ec8819093becdaec750aff5 completed March 31, 2026, 3:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce39ead11c8190bf1524713a44a6fe completed April 2, 2026, 9:42 a.m.
Created at: March 30, 2026, 6:11 p.m.