Triple

T18001997
Position Surface form Disambiguated ID Type / Status
Subject Isoberlinia E430650 entity
Predicate genusOf P9413 FINISHED
Object Isoberlinia doka NE NERFINISHED

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: Isoberlinia doka | Statement: [Isoberlinia, genusOf, Isoberlinia doka]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Isoberlinia doka
Context triple: [Isoberlinia, genusOf, Isoberlinia doka]
  • A. Isoberlinia chosen
    Isoberlinia is a genus of African trees in the legume family, best known for forming extensive dry woodlands and savanna ecosystems.
  • B. Hagenia abyssinica
    Hagenia abyssinica is a large, medicinally important tree native to East African highland regions, commonly found in Afromontane forests.
  • C. Khaya
    Khaya is a genus of tropical African trees in the mahogany family, valued for their high-quality timber.
  • D. Mastixia
    Mastixia is a genus of flowering trees and shrubs native mainly to tropical Asia, known for their glossy leaves and small, often clustered fruits.
  • E. Afrocarpus
    Afrocarpus is a small genus of evergreen coniferous trees native to Africa, belonging to the yellowwood family and valued for their timber and ornamental use.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8b904530081908bf341d842464856 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4b3e9498c8190bdfa7a53b0c0d8db completed April 19, 2026, 10:52 a.m.
Created at: April 10, 2026, 10:23 a.m.