Triple

T19155010
Position Surface form Disambiguated ID Type / Status
Subject Somali Latin alphabet E468907 entity
Predicate replaced P101 FINISHED
Object Borama alphabet NE NERFINISHED

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: Borama alphabet | Statement: [Somali Latin alphabet, replaced, Borama alphabet]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Borama alphabet
Context triple: [Somali Latin alphabet, replaced, Borama alphabet]
  • A. Borama script chosen
    The Borama script is an indigenous writing system historically used by some Somali communities to represent the Somali language before the adoption of more widespread scripts.
  • B. Boko alphabet
    The Boko alphabet is a Latin-based writing system used primarily for transcribing the Hausa language in West Africa.
  • C. Soyombo script
    The Soyombo script is an artificial writing system created in the 17th century by Mongolian monk and scholar Zanabazar for writing Mongolian, Tibetan, and Sanskrit.
  • D. Hawar alphabet
    The Hawar alphabet is a Latin-based writing system developed in the 20th century that serves as the primary standardized script for the Kurmanji dialect of Kurdish.
  • E. Alfabeto Unificado
    Alfabeto Unificado is a standardized writing system proposed for the Mapudungun language to promote consistent spelling and literacy among its speakers.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8dd084ff48190ac0f8c46ee722629 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5eeb914248190a92dc5f30cbc8fcc completed April 20, 2026, 9:15 a.m.
Created at: April 10, 2026, 12:06 p.m.