Triple

T8458279
Position Surface form Disambiguated ID Type / Status
Subject SG̱ang Gwaay E199974 entity
Predicate visitorManagement P82756 FINISHED
Object guided visits by Haida Watchmen 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: guided visits by Haida Watchmen | Statement: [SG̱ang Gwaay, visitorManagement, guided visits by Haida Watchmen]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: visitorManagement
Context triple: [SG̱ang Gwaay, visitorManagement, guided visits by Haida Watchmen]
  • A. visitorAccessPoint
    Indicates a location or interface through which visitors are allowed to enter, connect, or gain access to a place, system, or resource.
  • B. visitorCenter
    Indicates that a location serves as a visitor center for a place, providing information or services to visitors of that place.
  • C. visitorStatus
    Indicates the current state or condition of an entity in its role as a visitor (e.g., whether they are active, pending, past, or otherwise classified in their visit).
  • D. visitorInformation
    Indicates that information or details are provided for or about visitors in relation to a particular place, service, or event.
  • E. visitorUse
    Indicates that an entity is being used, accessed, or engaged with by a visitor or temporary user.
  • F. None of above. chosen

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_69ca83198c4c8190a337bf717d1813f5 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe49064f881909391d565b97e9886 completed March 31, 2026, 3:13 p.m.
PD Predicate disambiguation batch_69cbd0fc634481909842c0a30077bfde completed March 31, 2026, 1:49 p.m.
PDg Predicate description generation batch_69cbe12dd0b88190a38ec4d15dcc870b completed March 31, 2026, 2:58 p.m.
Created at: March 30, 2026, 6:10 p.m.