Triple

T4101378
Position Surface form Disambiguated ID Type / Status
Subject Djerba E87947 entity
Predicate hasEthnicGroup P1898 FINISHED
Object Berbers E6842 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: Berbers | Statement: [Djerba, hasEthnicGroup, Berbers]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Berbers
Context triple: [Djerba, hasEthnicGroup, Berbers]
  • A. Berbers chosen
    The Berbers, or Amazigh, are an indigenous ethnic group of North Africa with their own distinct languages and cultural traditions, predating Arab and Islamic influences in the region.
  • B. Mozabite Berber
    Mozabite Berber is a Zenati Berber language spoken primarily by the Ibadi Mozabite community in Algeria’s M’zab region.
  • C. Amazigh
    Amazigh are the Indigenous Berber peoples of North Africa, known for their distinct languages, culture, and historical presence across the Maghreb and Sahara regions.
  • D. Siwa Berber
    Siwa Berber is a Berber (Amazigh) language spoken primarily in Egypt’s Siwa Oasis, known for its unique features within the Berber language family and its relative isolation from other Amazigh-speaking communities.
  • E. Moors
    Moors is a surname of English origin that appears as the middle name of American businessman and philanthropist John Moors Cabot.
  • 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_69aed94564cc8190a9c1457daedb6e7f completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aefd0ed168819093c83ba079d6725c completed March 9, 2026, 5:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69b576a3e75c8190ab08954220b4b89a completed March 14, 2026, 2:54 p.m.
Created at: March 9, 2026, 3:40 p.m.