Triple

T18003507
Position Surface form Disambiguated ID Type / Status
Subject Coral Harbour E430685 entity
Predicate region P40 FINISHED
Object Kivalliq Region 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: Kivalliq Region | Statement: [Coral Harbour, region, Kivalliq Region]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kivalliq Region
Context triple: [Coral Harbour, region, Kivalliq Region]
  • A. Kivalliq Region chosen
    Kivalliq Region is an administrative region of Nunavut in northern Canada, known for its Inuit communities, tundra landscapes, and Arctic wildlife.
  • B. Resava region
    The Resava region is a historical and geographical area in central Serbia, known for its medieval monasteries, caves, and traditional mining heritage.
  • C. Tver Karelia
    Tver Karelia is a historical region of the Karelian people located in the Tver Oblast of Russia, formed by Karelian resettlements from their traditional northern homelands.
  • D. Yalta region
    The Yalta region is a coastal area on the southern shore of the Crimean Peninsula, known for its resort towns, mild climate, and scenic Black Sea landscapes.
  • E. Elets Uyezd
    Elets Uyezd was an administrative subdivision (uyezd) of the Russian Empire, historically located within the Tula Governorate.
  • 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_69d8b904530081908bf341d842464856 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4b3ea60608190b977644e946407b7 completed April 19, 2026, 10:52 a.m.
Created at: April 10, 2026, 10:23 a.m.