Triple

T12390516
Position Surface form Disambiguated ID Type / Status
Subject Nkisi E295979 entity
Predicate hasVariant P455 FINISHED
Object nkondi E975025 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: nkondi | Statement: [Nkisi, hasVariant, nkondi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: nkondi
Context triple: [Nkisi, hasVariant, nkondi]
  • A. nkisi nkondi chosen
    Nkisi nkondi are power figures from Kongo spiritual and artistic traditions, wooden sculptures embedded with nails or blades and used to harness spiritual forces for protection, justice, and healing.
  • B. NKo
    NKo is a Unicode block that encodes the characters of the N’Ko script used for writing several West African Mande languages.
  • C. Noukounkan
    Noukounkan is a town in Guinea known in part for its international twinning partnership with the French commune of Aubervilliers.
  • D. Chkondidi
    Chkondidi is a historic locality in western Georgia known primarily for its medieval ecclesiastical significance and association with the Chkondidi Cathedral.
  • E. Konjo
    Konjo is an Austronesian language spoken by the Konjo people of South Sulawesi, Indonesia.
  • 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.