Triple

T433678
Position Surface form Disambiguated ID Type / Status
Subject Bulawayo E9766 entity
Predicate hasMajorRailLinksTo P13914 FINISHED
Object Victoria Falls E8989 NE 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: Victoria Falls | Statement: [Bulawayo, hasMajorRailLinksTo, Victoria Falls]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Victoria Falls
Context triple: [Bulawayo, hasMajorRailLinksTo, Victoria Falls]
  • A. Victoria Falls chosen
    Victoria Falls is one of the world’s largest and most famous waterfalls, spanning the Zambezi River between Zambia and Zimbabwe and renowned for its dramatic curtain of falling water and mist.
  • B. Iguazu Falls
    Iguazu Falls is a vast and spectacular system of waterfalls on the Iguazu River at the border of Argentina and Brazil, renowned as one of the world’s most impressive natural wonders.
  • C. Churchill Falls
    Churchill Falls is a remote company town in western Labrador, Canada, best known for its massive hydroelectric generating station on the Churchill River.
  • D. Angel Falls
    Angel Falls is the world’s highest uninterrupted waterfall, plunging from the Auyán-tepui plateau in Venezuela.
  • E. Niagara Falls
    Niagara Falls is a famous group of massive waterfalls on the border between the United States and Canada, renowned for their impressive volume and natural beauty.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69a2e801e1d48190b505d1dd336b52ac completed Feb. 28, 2026, 1:05 p.m.
NER Named-entity recognition batch_69a2f01d8fa88190849d720b029db479 completed Feb. 28, 2026, 1:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69a447fa97ac8190b8a19ded2d0f520e completed March 1, 2026, 2:06 p.m.
Created at: Feb. 28, 2026, 1:11 p.m.