Triple

T18052413
Position Surface form Disambiguated ID Type / Status
Subject Theobroma E431952 entity
Predicate includesTaxon P1393 FINISHED
Object Theobroma speciosum 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: Theobroma speciosum | Statement: [Theobroma, includesTaxon, Theobroma speciosum]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Theobroma speciosum
Context triple: [Theobroma, includesTaxon, Theobroma speciosum]
  • A. Eugenia uniflora
    Eugenia uniflora is a tropical fruit-bearing shrub or small tree, commonly known as Surinam cherry, valued for its bright ribbed berries and use in ornamental planting and traditional medicine.
  • B. Theobroma chosen
    Theobroma is a genus of tropical American trees best known for including Theobroma cacao, the source of cocoa and chocolate.
  • C. Brosimum
    Brosimum is a genus of tropical American trees in the mulberry family (Moraceae), known for species such as breadnut that provide edible seeds and valuable timber.
  • D. Anacardium occidentale
    Anacardium occidentale is the cashew tree, a tropical evergreen species cultivated worldwide for its edible nuts and accessory fruit.
  • E. Paubrasilia echinata
    Paubrasilia echinata is a Brazilian hardwood tree historically prized for its dense, red-colored timber and as the original source of brazilwood dye, giving Brazil its name.
  • 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_69d8b906482481908183315b9ecf9994 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4c0ff580c8190bc3ca04025476255 completed April 19, 2026, 11:48 a.m.
Created at: April 10, 2026, 10:25 a.m.