Triple

T19721509
Position Surface form Disambiguated ID Type / Status
Subject Ifrane Province E473620 entity
Predicate containsCity P294 FINISHED
Object Ifrane 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: Ifrane | Statement: [Ifrane Province, containsCity, Ifrane]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ifrane
Context triple: [Ifrane Province, containsCity, Ifrane]
  • A. Ifrane chosen
    Ifrane is a Moroccan mountain town in the Middle Atlas known for its alpine-style architecture, cool climate, and reputation as one of the country’s cleanest and most picturesque cities.
  • B. Tizi Ouzou
    Tizi Ouzou is a major city in northern Algeria known as a cultural and economic center of the Kabylie region and the Kabyle Berber people.
  • C. Sidi Ghiles
    Sidi Ghiles is a coastal town and commune in northern Algeria, situated along the Mediterranean Sea in the Tipaza region.
  • D. Ghardimaou
    Ghardimaou is a town in northwestern Tunisia near the Algerian border, known as a regional transport and agricultural center.
  • E. Bou Regreg
    Bou Regreg is a river in western Morocco that flows between the cities of Rabat and Salé before emptying into the Atlantic Ocean.
  • 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_69d8e516dd048190a0b6c93ea3e71f58 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e649f483c481908c6b3114bf9c5934 completed April 20, 2026, 3:44 p.m.
Created at: April 10, 2026, 1:46 p.m.