Triple

T20858468
Position Surface form Disambiguated ID Type / Status
Subject Biorka Island E513546 entity
Predicate near P350 FINISHED
Object Sitka 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: Sitka | Statement: [Biorka Island, near, Sitka]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sitka
Context triple: [Biorka Island, near, Sitka]
  • A. Sitka chosen
    Sitka is a historic coastal city in southeastern Alaska known for its Tlingit and Russian heritage, scenic island setting, and abundant wildlife.
  • B. Ketchikan
    Ketchikan is a coastal city in southeastern Alaska known for its rich Native Alaskan culture, historic downtown, and status as a major cruise ship and fishing port.
  • C. Petersburg, Alaska
    Petersburg, Alaska is a small fishing town in Southeast Alaska known for its strong Norwegian heritage and thriving commercial fishing industry.
  • D. Palmer, Alaska
    Palmer, Alaska is a small agricultural city in the Matanuska-Susitna Valley known for its farming heritage, scenic mountain surroundings, and role as a regional hub northeast of Anchorage.
  • E. Yakutat
    Yakutat is a small coastal city in southeastern Alaska known for its remote location, fishing industry, and access to the Gulf of Alaska’s rugged natural landscapes.
  • 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_69e0b4f5b01081909452f654d2fc3f50 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c3a9fd7881908ae4c5c63f64efc0 completed April 21, 2026, 12:24 a.m.
Created at: April 16, 2026, 12:44 p.m.