Triple

T21897083
Position Surface form Disambiguated ID Type / Status
Subject Ouezzane E540706 entity
Predicate hasFeature P182 FINISHED
Object old medina NE NERFINISHED

How this triple was built (3 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: old medina | Statement: [Ouezzane, hasFeature, old medina]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: old medina
Context triple: [Ouezzane, hasFeature, old medina]
  • A. old medina
    The old medina is the historic walled quarter of al-Mahdiyya, characterized by narrow streets, traditional architecture, and a dense urban fabric dating back to its early Islamic and medieval periods.
  • B. old medina
    Old Medina is the historic quarter of Medenine, Tunisia, known for its traditional architecture, narrow streets, and cultural heritage that attract visitors.
  • C. old medina
    The old medina of Tiznit is a historic walled quarter known for its traditional architecture, narrow streets, and vibrant local markets in southern Morocco.
  • D. old medina
    The old medina of Larache is a historic walled quarter characterized by narrow streets, traditional Moroccan architecture, and vibrant local markets that reflect the city’s cultural heritage.
  • E. medina
    A medina is the historic, typically walled old quarter of a North African city, characterized by narrow streets, traditional markets, and dense urban fabric dating back to the Islamic medieval period.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: old medina
Target entity description: The old medina is the historic walled quarter of Ouezzane, characterized by narrow streets, traditional architecture, and a preserved Moroccan urban fabric.
  • A. old medina
    The old medina is the historic walled quarter of al-Mahdiyya, characterized by narrow streets, traditional architecture, and a dense urban fabric dating back to its early Islamic and medieval periods.
  • B. old medina
    The old medina of Larache is a historic walled quarter characterized by narrow streets, traditional Moroccan architecture, and vibrant local markets that reflect the city’s cultural heritage.
  • C. old medina
    Old Medina is the historic quarter of Medenine, Tunisia, known for its traditional architecture, narrow streets, and cultural heritage that attract visitors.
  • D. old medina
    The old medina of Tiznit is a historic walled quarter known for its traditional architecture, narrow streets, and vibrant local markets in southern Morocco.
  • E. medina
    A medina is the historic, typically walled old quarter of a North African city, characterized by narrow streets, traditional markets, and dense urban fabric dating back to the Islamic medieval period.
  • F. None of above. chosen

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_69e0c47a95908190ae3e19b716accb3d completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f11fc7c70c81908b9bb4de68616e41 completed April 28, 2026, 8:59 p.m.
Created at: April 16, 2026, 7:07 p.m.