Triple

T2583620
Position Surface form Disambiguated ID Type / Status
Subject Shango E57147 entity
Predicate veneratedIn P958 FINISHED
Object Haiti E4291 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: Haiti | Statement: [Shango, veneratedIn, Haiti]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Haiti
Context triple: [Shango, veneratedIn, Haiti]
  • A. Haiti chosen
    Haiti is a Caribbean nation on the island of Hispaniola known for its rich Afro-Caribbean culture, history as the first independent Black republic, and frequent vulnerability to natural disasters.
  • B. Dominican Republic
    The Dominican Republic is a Caribbean nation on the island of Hispaniola known for its beaches, mountainous interior, and vibrant blend of Spanish, African, and Taíno cultural influences.
  • C. Grenada
    Grenada is a small Caribbean island nation known for its spice production, picturesque beaches, and lush mountainous interior.
  • D. Dominica
    Dominica is a small island nation in the Caribbean known for its lush rainforests, volcanic landscapes, and rich biodiversity.
  • E. Jacmel, Haiti
    Jacmel, Haiti is a historic coastal city in southern Haiti known for its well-preserved French colonial architecture, vibrant arts scene, and annual Carnival celebrations.
  • 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_69ab4a4dca6481908c301f8e317396e7 completed March 6, 2026, 9:42 p.m.
NER Named-entity recognition batch_69abd3cb33a08190a3eae1a95e1b63bf completed March 7, 2026, 7:29 a.m.
NED1 Entity disambiguation (via context triple) batch_69af903825d881909c3f2ec2c307019d completed March 10, 2026, 3:30 a.m.
Created at: March 6, 2026, 9:49 p.m.