Triple

T14908913
Position Surface form Disambiguated ID Type / Status
Subject Southwest Australia Mediterranean-climate shrublands E371207 entity
Predicate hasCharacteristicSpeciesGroup P47321 FINISHED
Object Proteaceae E107059 NE FINISHED

How this triple was built (3 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: Proteaceae | Statement: [Southwest Australia Mediterranean-climate shrublands, hasCharacteristicSpeciesGroup, Proteaceae]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Proteaceae
Context triple: [Southwest Australia Mediterranean-climate shrublands, hasCharacteristicSpeciesGroup, Proteaceae]
  • A. Proteaceae chosen
    Proteaceae is a large family of flowering plants, especially diverse in the Southern Hemisphere, that includes many shrubs and trees such as proteas, banksias, and grevilleas.
  • B. Goodeniaceae
    Goodeniaceae is a family of flowering plants within the order Asterales, comprising mostly herbs and shrubs native largely to Australia and known for their distinctive fan-shaped corollas.
  • C. Linnaeaceae
    Linnaeaceae is a small family of flowering plants within the order Dipsacales, best known for the genus Linnaea, including the twinflower.
  • D. Cistaceae
    Cistaceae is a family of flowering plants commonly known as the rockrose family, comprising mostly shrubs and subshrubs adapted to dry, Mediterranean-type climates.
  • E. Stemonuraceae
    Stemonuraceae is a small family of flowering plants, primarily tropical trees and shrubs, known for their occurrence in Southeast Asia and the Pacific regions.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasCharacteristicSpeciesGroup
Context triple: [Southwest Australia Mediterranean-climate shrublands, hasCharacteristicSpeciesGroup, Proteaceae]
  • A. characteristicTaxon
    Indicates that one taxon is characteristic or typical of another taxonomic group, such as serving as a defining or representative member.
  • B. notableSpeciesGroup chosen
    Indicates that an entity is a significant or characteristic member of a particular species group associated with another entity.
  • C. supportsSpeciesGroup
    Indicates that one entity provides suitable conditions or resources that enable the survival or persistence of a particular group of species.
  • D. taxonGroup
    Indicates a classification relationship where one taxon is grouped within or associated with a broader taxonomic group.
  • E. hasCommonSpecies
    Indicates that two entities share at least one species in common.
  • F. None of above.

Provenance (4 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_69d85cc7ea3481908228b5acb7d06f12 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded61c6b9c8190a92934d49b98fe46 completed April 15, 2026, 12:04 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe72b91cbc8190af5a3e2db460bacc completed May 8, 2026, 11:33 p.m.
PD Predicate disambiguation batch_69de9a4a14a88190951bb8f4c60bd37b completed April 14, 2026, 7:49 p.m.
Created at: April 10, 2026, 2:25 a.m.