Triple

T2694444
Position Surface form Disambiguated ID Type / Status
Subject Alchemilla E58478 entity
Predicate order P568 FINISHED
Object Rosales E2077 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: Rosales | Statement: [Alchemilla, order, Rosales]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rosales
Context triple: [Alchemilla, order, Rosales]
  • A. Rosales chosen
    Rosales is an order of flowering plants that includes many familiar trees, shrubs, and herbs such as elms, roses, and nettles.
  • B. Icacinales
    Icacinales is an order of flowering plants within the asterid clade, comprising several families of mostly tropical trees, shrubs, and lianas.
  • C. Lardizabalaceae
    Lardizabalaceae is a small family of mostly woody, often climbing flowering plants known for their ornamental foliage and sometimes edible fruits, native primarily to East Asia and the Andes.
  • D. Laurales
    Laurales is an order of flowering plants that includes aromatic trees and shrubs such as laurels, cinnamon, and avocado.
  • E. Sapindales
    Sapindales is an order of flowering plants that includes economically and ecologically important trees and shrubs such as mangoes, citrus, maples, and cashews.
  • 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_69ab4ac269e481909cb317d79e68b75b completed March 6, 2026, 9:44 p.m.
NER Named-entity recognition batch_69abda10a9bc81908473d02ab9116cef completed March 7, 2026, 7:56 a.m.
NED1 Entity disambiguation (via context triple) batch_69afbbba22348190a3f70439a6b21e1c completed March 10, 2026, 6:35 a.m.
Created at: March 6, 2026, 9:55 p.m.