Triple

T17599704
Position Surface form Disambiguated ID Type / Status
Subject Skyline Rotorua E428660 entity
Predicate activityCategory P8834 FINISHED
Object adventure tourism 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: adventure tourism | Statement: [Skyline Rotorua, activityCategory, adventure tourism]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: activityCategory
Context triple: [Skyline Rotorua, activityCategory, adventure tourism]
  • A. activityType chosen
    Indicates the specific kind or category of action or event that an entity is engaged in or associated with.
  • B. typicalActivity
    Indicates that an entity is commonly or characteristically engaged in a particular activity.
  • C. activityCorrelatesWith
    Indicates that the level or occurrence of one activity is statistically associated with the level or occurrence of another activity, without implying direct causation.
  • D. activityDomain
    Indicates the general field, sector, or area of activity within which an entity operates or performs its main actions.
  • E. activity
    Indicates that an entity is engaged in or performing a particular action, behavior, or process.
  • 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_69d889e1c6148190ba76241e74688f8b completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e46c4812d48190bf8e899fa8f7fbe4 completed April 19, 2026, 5:46 a.m.
PD Predicate disambiguation batch_69e3b4fff0348190b899a32da537eaca completed April 18, 2026, 4:44 p.m.
Created at: April 10, 2026, 5:51 a.m.