Triple

T21482286
Position Surface form Disambiguated ID Type / Status
Subject GR4 long-distance footpath E530023 entity
Predicate usesWaymarking P47567 FINISHED
Object red and white blazes 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: red and white blazes | Statement: [GR4 long-distance footpath, usesWaymarking, red and white blazes]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: usesWaymarking
Context triple: [GR4 long-distance footpath, usesWaymarking, red and white blazes]
  • A. waymarkingStatus
    Indicates the current state or condition of a waymarking process, such as whether a location or route has been identified, recorded, approved, or otherwise classified in a waymarking system.
  • B. trailsMarkedBy chosen
    Indicates that a trail or path is designated or identified by specific markers, signs, or blazes placed along its route.
  • C. hasWaypoint
    Indicates that an entity follows a path or route that includes a specific intermediate location (waypoint) along its trajectory.
  • D. mapUse
    Indicates a relationship where one entity uses, applies, or employs a map (or mapping) to perform an action or achieve a purpose.
  • E. hasMarkerOrMonument
    Indicates that something possesses or is associated with a physical marker or monument commemorating it.
  • 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_69e0c45acc3881908e38d3f28964152b completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69e9ea34c4388190adc78d209d2aafb8 completed April 23, 2026, 9:45 a.m.
PD Predicate disambiguation batch_69e631ec1d048190b6da97da8222e413 completed April 20, 2026, 2:02 p.m.
Created at: April 16, 2026, 6:21 p.m.