Triple

T21482671
Position Surface form Disambiguated ID Type / Status
Subject Berlin Falls E530033 entity
Predicate near P350 FINISHED
Object Mac-Mac 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: Mac-Mac Falls | Statement: [Berlin Falls, near, Mac-Mac Falls]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mac-Mac Falls
Context triple: [Berlin Falls, near, Mac-Mac Falls]
  • A. Mac-Mac Falls chosen
    Mac-Mac Falls is a scenic twin waterfall in South Africa’s Mpumalanga province, renowned for its dramatic drop, surrounding forested gorge, and popularity as a stop along the Panorama Route.
  • B. Mackay Falls
    Mackay Falls is a picturesque waterfall in Fiordland National Park, New Zealand, renowned as a scenic highlight along the Milford Track hiking route.
  • C. Cascades Falls
    Cascades Falls is a scenic waterfall that serves as the main natural attraction within Cascades Falls Park.
  • D. Dry Falls
    Dry Falls is a massive, now-dry Ice Age waterfall in central Washington State, renowned as one of the world’s largest known former waterfalls and a key feature of the Channeled Scablands.
  • E. Dry Falls
    Dry Falls is a scenic waterfall in the Nantahala National Forest of western North Carolina, known for the walkway that allows visitors to pass behind the cascading water.
  • 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.