Triple

T21482780
Position Surface form Disambiguated ID Type / Status
Subject Mpumalanga tourist routes E530036 entity
Predicate mainAttraction P5644 FINISHED
Object Lisbon Falls NE NERFINISHED

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: Lisbon Falls | Statement: [Mpumalanga tourist routes, mainAttraction, Lisbon Falls]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lisbon Falls
Context triple: [Mpumalanga tourist routes, mainAttraction, Lisbon Falls]
  • A. Lisbon Falls chosen
    Lisbon Falls is a scenic waterfall in South Africa’s Mpumalanga province, renowned for its dramatic drop and lush surroundings along the popular Panorama Route.
  • B. Lisbon Falls
    Lisbon Falls is a small town in Maine, United States, known for its historic mill heritage and scenic location along the Androscoggin River.
  • C. Slate Falls
    Slate Falls is a small rural community located within the township of Addington Highlands in eastern Ontario, Canada.
  • D. Florence Falls
    Florence Falls is a picturesque twin waterfall and popular swimming spot set amid monsoon forest in Australia’s Litchfield National Park.
  • E. Sturtevant Falls
    Sturtevant Falls is a popular waterfall in the San Gabriel Mountains of Southern California, known for its scenic hiking trail and lush canyon setting.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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.
Created at: April 16, 2026, 6:21 p.m.