Triple

T5965798
Position Surface form Disambiguated ID Type / Status
Subject Ambler E132747 entity
Predicate partOf P40 FINISHED
Object Kobuk River valley E172618 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: Kobuk River valley | Statement: [Ambler, partOf, Kobuk River valley]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kobuk River valley
Context triple: [Ambler, partOf, Kobuk River valley]
  • A. Kobuk
    Kobuk is a small, remote city in northwestern Alaska located along the Kobuk River above the Arctic Circle.
  • B. Susitna Valley
    Susitna Valley is a scenic region in south-central Alaska known for its rivers, wilderness landscapes, and views of Denali.
  • C. Kobuk River chosen
    The Kobuk River is a major river in northwestern Alaska that flows westward through remote wilderness to Kotzebue Sound above the Arctic Circle.
  • D. Koyukon
    Koyukon is an Athabaskan (Dene) language traditionally spoken by the Koyukon people of interior Alaska along the Koyukuk and middle Yukon rivers.
  • E. Matanuska Valley
    Matanuska Valley is a fertile agricultural region in south-central Alaska known for its dramatic glacial landscapes and large, fast-growing produce.
  • 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_69c0086c2364819091e9fe2f58fa2517 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c03a3ca1dc819098cde8ae5ec1d845 completed March 22, 2026, 6:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69c113585ad88190a35d549448b10def completed March 23, 2026, 10:18 a.m.
Created at: March 22, 2026, 4:03 p.m.