Triple

T19521902
Position Surface form Disambiguated ID Type / Status
Subject Rif tribes E488421 entity
Predicate language P15 FINISHED
Object Tarifit 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: Tarifit | Statement: [Rif tribes, language, Tarifit]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tarifit
Context triple: [Rif tribes, language, Tarifit]
  • A. Tarifit chosen
    Tarifit is a Northern Berber language spoken primarily by the Riffian people in the Rif region of northern Morocco.
  • B. Tijarafe
    Tijarafe is a small rural municipality on the northwest coast of the Canary Island of La Palma, known for its dramatic cliffs, traditional agriculture, and scenic Atlantic views.
  • C. Tazirbu
    Tazirbu is a remote oasis settlement in southeastern Libya, known for its desert environment and traditional reliance on groundwater resources.
  • D. Pazarlar
    Pazarlar is a small town and district in western Turkey known for its rural character and location within Kütahya Province.
  • E. Tagaste
    Tagaste was an ancient North African town in the Roman province of Numidia, best known as the birthplace of Saint Augustine and his mother Saint Monica.
  • 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_69d8e8da8bec819081f400199491ccc3 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e635a0b37c8190b70b7427c2e85f59 completed April 20, 2026, 2:18 p.m.
Created at: April 10, 2026, 1:40 p.m.