Triple

T18408086
Position Surface form Disambiguated ID Type / Status
Subject Waglisla E441678 entity
Predicate locatedNear P294 FINISHED
Object Bella Bella 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: Bella Bella | Statement: [Waglisla, locatedNear, Bella Bella]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bella Bella
Context triple: [Waglisla, locatedNear, Bella Bella]
  • A. Bella Bella chosen
    Bella Bella is a small Heiltsuk First Nation community and coastal village located on Campbell Island in British Columbia, Canada.
  • B. Klawock
    Klawock is a small Tlingit community and former salmon cannery town on Prince of Wales Island in Southeast Alaska.
  • C. Hoonah
    Hoonah is a small Tlingit community and fishing town on Chichagof Island in Southeast Alaska, known for its rich Indigenous culture and proximity to wilderness and wildlife.
  • D. Angoon
    Angoon is a small, predominantly Tlingit community and city located on Admiralty Island in Alaska’s Alexander Archipelago.
  • E. Savoonga
    Savoonga is a remote Alaska Native village on St. Lawrence Island in the Bering Sea, known for its Siberian Yupik culture and subsistence hunting lifestyle.
  • 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_69d8b9eb8a508190a942fd75ebd8b1dc completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e5195a49e08190b31f1767239bbe28 completed April 19, 2026, 6:05 p.m.
Created at: April 10, 2026, 10:46 a.m.