Triple

T19390804
Position Surface form Disambiguated ID Type / Status
Subject Souss River E485061 entity
Predicate passesNear P416 FINISHED
Object Taroudant 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: Taroudant | Statement: [Souss River, passesNear, Taroudant]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Taroudant
Context triple: [Souss River, passesNear, Taroudant]
  • A. Taroudant chosen
    Taroudant is a historic walled city in southern Morocco, often called the "Grandmother of Marrakech" for its similar architecture and traditional markets.
  • B. Guelmim
    Guelmim is a city in southern Morocco known as a gateway to the Sahara and a regional center for Saharan trade and culture.
  • C. Hassi Gara
    Hassi Gara is a town and commune in northern-central Algeria, situated in the Sahara Desert within Ghardaïa Province.
  • D. Taounate
    Taounate is a prominent city in northern Morocco known as an administrative and commercial center for the surrounding rural and mountainous region.
  • E. Beni Mellal
    Beni Mellal is a major city in central Morocco known for its agricultural importance and its location at the foot of the Middle Atlas mountains.
  • 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_69d8e8d460d88190abf0591c5c9d2b0c completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e61b44b70c81908e2f0deeabe4360f completed April 20, 2026, 12:25 p.m.
Created at: April 10, 2026, 1:36 p.m.