Triple

T12640574
Position Surface form Disambiguated ID Type / Status
Subject Gentianales E301885 entity
Predicate secondLargestFamily P35038 FINISHED
Object Apocynaceae E289838 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: Apocynaceae | Statement: [Gentianales, secondLargestFamily, Apocynaceae]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Apocynaceae
Context triple: [Gentianales, secondLargestFamily, Apocynaceae]
  • A. Apocynaceae chosen
    Apocynaceae is a large family of flowering plants, commonly known as the dogbane family, that includes many tropical trees, shrubs, and vines often noted for their milky sap and toxic or medicinal properties.
  • B. Euphorbiaceae
    Euphorbiaceae is a large and diverse family of flowering plants, commonly known as the spurge family, that includes herbs, shrubs, and trees often characterized by milky latex and unique inflorescences.
  • C. Phytolaccaceae
    Phytolaccaceae is a family of flowering plants, commonly known as the pokeweed family, that includes mostly herbaceous species and shrubs found in tropical and subtropical regions.
  • D. Datiscaceae
    Datiscaceae is a small family of flowering plants known for its herbaceous species, such as Datisca, that often exhibit unusual reproductive traits like dioecy and are native to regions in Eurasia and North America.
  • E. Anacardiaceae
    Anacardiaceae is a family of flowering plants that includes economically important species such as mango, cashew, and pistachio.
  • 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: secondLargestFamily
Context triple: [Gentianales, secondLargestFamily, Apocynaceae]
  • A. secondHolderFamilyName
    Indicates that the relationship specifies the family name (surname) of a second holder or secondary person associated with an entity.
  • B. largestFamily
    Indicates that the subject entity has the largest family (in size or number of members) compared to a specified group of entities.
  • C. isSecondLargest chosen
    Indicates that one entity has a value or size that is greater than all others except for a single larger entity, making it the second largest in the compared set.
  • D. secondLargestStructureIn
    Indicates that one structure is the second largest (by size, height, volume, or another defined measure) among all structures within a specified location or context.
  • E. majorFamily
    Indicates that one entity belongs to or is a primary member of the same family group or lineage as another entity.
  • 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_69d7bdec9f9c8190b4bac675b7588211 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d961ae493481908f82e0d05dce20bd completed April 10, 2026, 8:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6719a45d881908dd895836a225781 completed May 2, 2026, 9:50 p.m.
PD Predicate disambiguation batch_69d960b47130819097e1162ed4fc993a completed April 10, 2026, 8:42 p.m.
Created at: April 9, 2026, 5:16 p.m.