Triple

T23243475
Position Surface form Disambiguated ID Type / Status
Subject Khaya E581521 entity
Predicate containsSpecies P7733 FINISHED
Object Khaya senegalensis 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: Khaya senegalensis | Statement: [Khaya, containsSpecies, Khaya senegalensis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Khaya senegalensis
Context triple: [Khaya, containsSpecies, Khaya senegalensis]
  • A. Khaya chosen
    Khaya is a genus of tropical African trees in the mahogany family, valued for their high-quality timber.
  • B. Hyphaene thebaica
    Hyphaene thebaica is a species of African palm tree, commonly known as the doum palm, noted for its branching trunk and edible, fibrous fruits.
  • C. Parkia
    Parkia is a genus of tropical leguminous trees, commonly known as nitta or African locust beans, valued for their edible seeds and ecological importance in tropical forests.
  • D. Acacia tortilis
    Acacia tortilis, commonly known as the umbrella thorn acacia, is a hardy African tree species characteristic of savanna landscapes and well adapted to hot, arid environments.
  • E. Hagenia abyssinica
    Hagenia abyssinica is a large, medicinally important tree native to East African highland regions, commonly found in Afromontane forests.
  • 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_69e24606b17c81908aba1a4911c8a8ba completed April 17, 2026, 2:39 p.m.
NER Named-entity recognition batch_69f192efd44c8190b179b4d1cb71efa5 completed April 29, 2026, 5:11 a.m.
Created at: April 17, 2026, 4:10 p.m.