Triple

T1328918
Position Surface form Disambiguated ID Type / Status
Subject Tamazight (generic) E28395 entity
Predicate coversVariety P13946 FINISHED
Object Siwi E29648 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: Siwi | Statement: [Tamazight (generic), coversVariety, Siwi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Siwi
Context triple: [Tamazight (generic), coversVariety, Siwi]
  • A. Siwi chosen
    Siwi is a Berber language spoken primarily in Egypt’s Siwa Oasis, known for its unique features and relative isolation from other Berber varieties.
  • B. Seraiki
    Seraiki is an Indo-Aryan language spoken primarily in central and southern Pakistan, especially in the southern Punjab region.
  • C. Micali
    Micali is an Italian surname most notably associated with Silvio Micali, a Turing Award–winning computer scientist and cryptographer.
  • D. Wawa
    Wawa is a small town in northern Ontario, Canada, known for its iconic giant Canada goose statue and its history as a mining and forestry community.
  • E. Evessa
    Evessa is a professional basketball team based in Osaka, Japan, competing in the B.League.
  • 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_69a498540a2481909e807a762280d3ba completed March 1, 2026, 7:49 p.m.
NER Named-entity recognition batch_69a4c48d25608190b069fb4d0d460aa6 completed March 1, 2026, 10:58 p.m.
NED1 Entity disambiguation (via context triple) batch_69acbf32b488819095dc63d338a30b9b completed March 8, 2026, 12:13 a.m.
Created at: March 1, 2026, 7:55 p.m.