Triple

T23556041
Position Surface form Disambiguated ID Type / Status
Subject Fortunella E578188 entity
Predicate subtribe P29097 FINISHED
Object Citrinae 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: Citrinae | Statement: [Fortunella, subtribe, Citrinae]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Citrinae
Context triple: [Fortunella, subtribe, Citrinae]
  • A. Citrinae chosen
    Citrinae is a subtribe within the citrus family Rutaceae that includes true citrus fruits and closely related genera such as Microcitrus.
  • B. Coerebinae
    Coerebinae is a subfamily of tanagers that includes the Darwin’s finches and other closely related Neotropical songbirds.
  • C. Leithiinae
    Leithiinae is a subfamily of dormice comprising several small, nocturnal rodent species found across parts of Europe, Asia, and North Africa.
  • D. Pimplinae
    Pimplinae is a subfamily of ichneumon wasps known for its parasitoid lifestyle, primarily attacking the pupae and cocoons of other insects and spiders.
  • E. Cerylinae
    Cerylinae is a subfamily of kingfishers known for their fish-eating habits and often crested appearance, including species such as the belted kingfisher.
  • 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_69e245fa93448190919cb04534560542 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f1aed37f248190992f040f4d22f0bf completed April 29, 2026, 7:10 a.m.
Created at: April 17, 2026, 6:12 p.m.