Triple

T9365898
Position Surface form Disambiguated ID Type / Status
Subject Irifiyen E225397 entity
Predicate indigenousTo P3743 FINISHED
Object Rif region E151657 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: Rif region | Statement: [Irifiyen, indigenousTo, Rif region]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rif region
Context triple: [Irifiyen, indigenousTo, Rif region]
  • A. Rif region chosen
    The Rif region is a mountainous area in northern Morocco along the Mediterranean coast, known for its distinct Amazigh (Berber) culture and history of resistance.
  • B. Bilma region
    The Bilma region is a sparsely populated desert area in northeastern Niger, known for its historic salt caravans, oases, and role as a key stop on trans-Saharan trade routes.
  • C. Razih region
    The Razih region is a mountainous area in northwestern Yemen known for its distinct local culture and dialects, including Razihi Arabic.
  • D. Sara Province
    Sara Province is an administrative subdivision located within Bolivia's Santa Cruz Department.
  • E. Ahal Region
    Ahal Region is an administrative province in south-central Turkmenistan that surrounds the capital city, Ashgabat.
  • 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_69ca842cbddc819099d71ecec48cf9e5 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd5041261c81909edab3b7fcd1fe22 completed April 1, 2026, 5:05 p.m.
NED1 Entity disambiguation (via context triple) batch_69d100d3444c81908b14f165ec128b76 completed April 4, 2026, 12:15 p.m.
Created at: March 30, 2026, 7:43 p.m.