Triple

T20898894
Position Surface form Disambiguated ID Type / Status
Subject Laurus nobilis E514615 entity
Predicate family P566 FINISHED
Object Lauraceae 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: Lauraceae | Statement: [Laurus nobilis, family, Lauraceae]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lauraceae
Context triple: [Laurus nobilis, family, Lauraceae]
  • A. Lauraceae chosen
    Lauraceae is a large family of mostly aromatic flowering trees and shrubs that includes economically important species such as laurels, cinnamon, avocado, and camphor.
  • B. Meliaceae
    Meliaceae is a family of mostly tropical flowering trees and shrubs that includes economically important timber and ornamental species such as mahogany and neem.
  • C. Sapindaceae
    Sapindaceae is a large family of flowering plants that includes many trees and shrubs such as maples, horse chestnuts, and lychees, known for their economic and ecological importance worldwide.
  • D. Laurales
    Laurales is an order of flowering plants that includes aromatic trees and shrubs such as laurels, cinnamon, and avocado.
  • E. Annonaceae
    Annonaceae is a large family of mostly tropical flowering plants that includes many trees, shrubs, and lianas such as the custard apple and ylang-ylang.
  • 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_69e0b4f7ebe48190952a85547a0f31a1 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6e8f92bd88190b59b2131ad1d9aa1 completed April 21, 2026, 3:03 a.m.
Created at: April 16, 2026, 12:47 p.m.