Triple

T23278654
Position Surface form Disambiguated ID Type / Status
Subject Simarouba E588793 entity
Predicate hasSpecies P965 FINISHED
Object Simarouba tulae 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: Simarouba tulae | Statement: [Simarouba, hasSpecies, Simarouba tulae]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Simarouba tulae
Context triple: [Simarouba, hasSpecies, Simarouba tulae]
  • A. Simarouba chosen
    Simarouba is a genus of tropical trees and shrubs known for species like the paradise-tree, some of which are used for timber, traditional medicine, and oil-rich seeds.
  • B. Toona
    Toona is a small genus of deciduous trees in the mahogany family, known for their valuable timber and use in traditional medicine.
  • C. Ocotea
    Ocotea is a large genus of mostly evergreen trees and shrubs native to tropical and subtropical regions, many of which are valued for their aromatic wood and essential oils.
  • D. Ceiba
    Ceiba is a coastal municipality in eastern Puerto Rico known for its former naval base and proximity to the islands of Vieques and Culebra.
  • E. Ceiba
    Ceiba is a genus of large tropical trees, including the iconic kapok tree, known for their towering trunks, buttress roots, and ecological and cultural importance in tropical America and West Africa.
  • 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_69e25d16e2c08190a291de254703129e completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f1957991108190ac82fa6dd355f722 completed April 29, 2026, 5:22 a.m.
Created at: April 17, 2026, 4:49 p.m.