Triple

T12390355
Position Surface form Disambiguated ID Type / Status
Subject Palo Mayombe E295976 entity
Predicate usesObject P4791 FINISHED
Object nganga E295980 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: nganga | Statement: [Palo Mayombe, usesObject, nganga]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: nganga
Context triple: [Palo Mayombe, usesObject, nganga]
  • A. tata nganga chosen
    Tata nganga is a high-ranking priest and ritual specialist in the Afro-Cuban Palo Monte religion, responsible for leading ceremonies, divination, and work with spiritual forces.
  • B. inyanga
    An inyanga is a traditional Zulu healer and herbalist who uses medicinal plants and spiritual knowledge to diagnose and treat illnesses.
  • C. ngi
    ngi is the ISO 639-3 language code for Ngizim, a West Chadic language spoken primarily in northeastern Nigeria.
  • D. Angangueo
    Angangueo is a historic mining town in central Mexico best known as a gateway to the Monarch Butterfly Biosphere Reserve.
  • E. Ngankarrparni
    Ngankarrparni is a musical track featured on the album "Long Walk Home."
  • 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_69d6ad9e653c8190b1473c860ee53dae completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d93fd0bcc48190bb1a59a3aaa6bfdf completed April 10, 2026, 6:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69f63479df38819085c5ca791c460d5e completed May 2, 2026, 5:29 p.m.
Created at: April 8, 2026, 9:54 p.m.