Triple

T4686423
Position Surface form Disambiguated ID Type / Status
Subject uShaka Marine World E103930 entity
Predicate regionTourismRole P52358 FINISHED
Object major Durban tourist destination 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: major Durban tourist destination | Statement: [uShaka Marine World, regionTourismRole, major Durban tourist destination]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: regionTourismRole
Context triple: [uShaka Marine World, regionTourismRole, major Durban tourist destination]
  • A. tourismRegion
    Indicates that a place or area is designated or recognized as a tourism region associated with another geographic or administrative entity.
  • B. primaryTourismHub chosen
    Indicates that a location serves as the main center or focal point for tourism activities within a given area or region.
  • C. tourismType
    Indicates the specific category or kind of tourism activity or experience associated with an entity.
  • D. tourismAssociation
    Indicates that there is an organizational or formal association related to tourism activities, services, or promotion between the involved entities.
  • E. tourismFrom
    Indicates that tourists or visitor activity originates from one place and is directed toward another location.
  • 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_69bd43debbf08190b4bc372e286ec234 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd66059bfc8190885d26d05dd38df1 completed March 20, 2026, 3:21 p.m.
PD Predicate disambiguation batch_69bd6219da948190bbbb50f08573ab4d completed March 20, 2026, 3:04 p.m.
Created at: March 20, 2026, 1:16 p.m.