Triple

T9186887
Position Surface form Disambiguated ID Type / Status
Subject Amarar E220481 entity
Predicate languageContext P36 FINISHED
Object Beja language E387504 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: Beja language | Statement: [Amarar, languageContext, Beja language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Beja language
Context triple: [Amarar, languageContext, Beja language]
  • A. Beja language chosen
    The Beja language is a Cushitic language spoken primarily by the Beja people across parts of Sudan, Egypt, and Eritrea.
  • B. Mirandese language
    Mirandese language is a minority Romance language spoken in northeastern Portugal, closely related to Astur-Leonese and recognized for its distinct cultural and linguistic heritage.
  • C. African Portuguese
    African Portuguese is the group of regional varieties of the Portuguese language spoken across several African countries, shaped by local languages and cultures.
  • D. Beja people
    The Beja people are a traditionally pastoralist Cushitic ethnic group inhabiting the Red Sea coastal and desert regions of Sudan, Eritrea, and Egypt, known for their distinct language, culture, and history in Northeast Africa.
  • E. Forro language
    Forro language is a Portuguese-based creole spoken primarily on São Tomé Island in São Tomé and Príncipe.
  • 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_69ca83e6d77c81909862b7afef56b1bf completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69ccc31bd6f88190b2ea644420995e41 completed April 1, 2026, 7:02 a.m.
NED1 Entity disambiguation (via context triple) batch_69d05c226bc881909609da0bfbd4748e completed April 4, 2026, 12:32 a.m.
Created at: March 30, 2026, 7:24 p.m.