Triple

T7060801
Position Surface form Disambiguated ID Type / Status
Subject Béjaïa Province E164209 entity
Predicate majorCity P316 FINISHED
Object Akbou E635081 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: Akbou | Statement: [Béjaïa Province, majorCity, Akbou]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Akbou
Context triple: [Béjaïa Province, majorCity, Akbou]
  • A. Akbou chosen
    Akbou is a significant urban center in the Kabylie region of northern Algeria, known for its role as a local economic and cultural hub.
  • B. El Hadaba
    El Hadaba is the famous nickname of Egyptian singer Amr Diab, one of the Arab world's most successful and influential pop music stars.
  • C. Aoulouz
    Aoulouz is a small town located in the Souss-Massa region of southern Morocco, known for its agricultural surroundings and position along regional travel routes.
  • D. Kharbouch
    Kharbouch is the family surname of Moroccan-American rapper and entrepreneur French Montana.
  • E. Aourir
    Aourir is a small coastal town in southwestern Morocco, known for its banana plantations and proximity to the surf beaches near Agadir.
  • 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_69c688796c148190adb2f1596f595f22 completed March 27, 2026, 1:39 p.m.
NER Named-entity recognition batch_69c6e459de348190912cd5326fb8bee0 completed March 27, 2026, 8:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69c81ea4f7f081909c94b7062c0d4dde completed March 28, 2026, 6:32 p.m.
Created at: March 27, 2026, 2:38 p.m.