Triple

T11797173
Position Surface form Disambiguated ID Type / Status
Subject Kariocha E280529 entity
Predicate languageContext P36 FINISHED
Object Lucumí E290998 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: Lucumí | Statement: [Kariocha, languageContext, Lucumí]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lucumí
Context triple: [Kariocha, languageContext, Lucumí]
  • A. Lucumí chosen
    Lucumí is a liturgical Afro-Cuban language variety derived mainly from Yoruba, used in Santería/Regla de Ocha religious rituals.
  • B. Shango
    Shango is a major Yoruba orisha revered as the powerful god of thunder, lightning, and justice, often associated with kingship and drumming.
  • C. Babalú-Ayé
    Babalú-Ayé is a major Orisha in the Yoruba and Afro-Cuban religious traditions, revered as the powerful deity of disease, healing, and protection from epidemics.
  • D. Orixa
    Orixa is a small genus of flowering shrubs in the citrus family Rutaceae, native to East Asia and known for its aromatic foliage.
  • E. Oxóssi
    Oxóssi is an orixá in Afro-Brazilian and Yoruba religions, revered as the hunter deity associated with the forest, abundance, and knowledge.
  • 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_69d6ab258b808190b1735835c841e3a4 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d8a5a1cda0819092d66a82fd882786 completed April 10, 2026, 7:24 a.m.
NED1 Entity disambiguation (via context triple) batch_69f4715720e08190a3bc1b4fc888fe79 completed May 1, 2026, 9:24 a.m.
Created at: April 8, 2026, 9:42 p.m.