Triple

T8043563
Position Surface form Disambiguated ID Type / Status
Subject Grebo masks E187492 entity
Predicate region P40 FINISHED
Object Upper Guinea coast E488522 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: Upper Guinea coast | Statement: [Grebo masks, region, Upper Guinea coast]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Upper Guinea coast
Context triple: [Grebo masks, region, Upper Guinea coast]
  • A. Guinea Coast chosen
    The Guinea Coast is a historical region along West Africa’s Atlantic shoreline that was a major hub for European trade, including the transatlantic slave trade, from the early modern period onward.
  • B. Upper Guinea
    Upper Guinea is a natural and historical region in eastern Guinea characterized by savanna landscapes and significant agricultural and mining activities.
  • C. Middle Guinea
    Middle Guinea is a natural and historical region of central Guinea characterized by its Fouta Djallon highlands and predominantly Fulani population.
  • D. Lower Guinea
    Lower Guinea is a coastal subregion of West Africa characterized by humid tropical forests, significant biodiversity, and important agricultural and port activities.
  • E. southeastern Guinea
    Southeastern Guinea is a region of Guinea characterized by its forested landscapes, rural villages, and proximity to the borders with Liberia and Sierra Leone.
  • 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_69ca82b00cb48190b59a300f70e97bd7 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb3f4b5e0c819092949af0f995b850 completed March 31, 2026, 3:28 a.m.
NED1 Entity disambiguation (via context triple) batch_69cc570cfad08190a8ed35ef2a47f497 completed March 31, 2026, 11:21 p.m.
Created at: March 30, 2026, 5:23 p.m.