Triple

T19956997
Position Surface form Disambiguated ID Type / Status
Subject Kate’s Cottage E479709 entity
Predicate onRacingSection P55669 FINISHED
Object mountain section of Snaefell Mountain Course LITERAL 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: mountain section of Snaefell Mountain Course | Statement: [Kate’s Cottage, onRacingSection, mountain section of Snaefell Mountain Course]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: onRacingSection
Context triple: [Kate’s Cottage, onRacingSection, mountain section of Snaefell Mountain Course]
  • A. raceTrack
    Indicates that one entity serves as a race track or racing course used by another entity for racing activities.
  • B. racecourseFeature chosen
    Indicates that one entity is a physical or functional feature or component of a racecourse associated with the other entity.
  • C. racingDivision
    Indicates that one entity is classified into, or associated with, a particular racing division within a competitive racing context.
  • D. racingSeries
    Indicates that one entity is a racing series in which the other entity (such as a race, team, or driver) participates or to which it belongs.
  • E. racesOn
    Indicates that one entity participates in a race or competitive running event that takes place on or along another entity (such as a track, course, or surface).
  • F. None of above.

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_69d8e523c19881909f9197037200dde6 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65af08e008190a3a1b807b638a99e completed April 20, 2026, 4:57 p.m.
PD Predicate disambiguation batch_69e537f7e4848190b431a69ec3f1b609 completed April 19, 2026, 8:15 p.m.
Created at: April 10, 2026, 1:54 p.m.