Triple

T14797866
Position Surface form Disambiguated ID Type / Status
Subject King Glele E347825 entity
Predicate religion P45 FINISHED
Object Vodun E171112 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: Vodun | Statement: [King Glele, religion, Vodun]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Vodun
Context triple: [King Glele, religion, Vodun]
  • A. Vodun chosen
    Vodun is a traditional West African religion centered on the worship of spirits and ancestors, particularly prominent in Benin and neighboring regions.
  • B. Vodoo
    Vodoo is the gaming alias of Alexander "Vodoo" Beutel, a professional esports player and streamer known in the competitive gaming community.
  • C. Haitian Vodou
    Haitian Vodou is a syncretic Afro-Caribbean religion from Haiti that blends West and Central African spiritual traditions with Roman Catholicism and indigenous beliefs, centered on the worship of spirits called lwa.
  • D. Orisha
    Orisha are deities or divine spirits in the Yoruba religion, each embodying specific natural forces, human traits, and aspects of daily life, and serving as intermediaries between humans and the supreme god.
  • E. Voodoo Juju
    Voodoo Juju is a notable creative work by the artist or creator known as Future User, recognized within their body of work.
  • 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_69d822ea8b7c819097dfadf3d45545e6 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69decd6131f08190885f1d27b4bfac7a completed April 14, 2026, 11:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe6b47389c8190ab0a46e3b4653a2a completed May 8, 2026, 11:01 p.m.
Created at: April 10, 2026, 1:31 a.m.