Triple

T21548093
Position Surface form Disambiguated ID Type / Status
Subject Susitnu E531682 entity
Predicate hasAlternativeName P39 FINISHED
Object Susitna 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: Susitna | Statement: [Susitnu, hasAlternativeName, Susitna]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Susitna
Context triple: [Susitnu, hasAlternativeName, Susitna]
  • A. Susitna North
    Susitna North is a small census-designated community in south-central Alaska known for its rural character and proximity to the Susitna River.
  • B. Susitna Valley chosen
    Susitna Valley is a scenic region in south-central Alaska known for its rivers, wilderness landscapes, and views of Denali.
  • C. Takuu
    Takuu is a remote Polynesian outlier atoll near Papua New Guinea, known for its distinct Polynesian culture and language isolated within Melanesia.
  • D. Sugpiaq
    Sugpiaq are an Indigenous people of south-central Alaska, particularly Kodiak Island and the surrounding coastal regions, with a distinct Alutiiq language and maritime culture.
  • E. Kivalina
    Kivalina is a small Inupiat village in northwestern Alaska known for its severe coastal erosion and vulnerability to climate change–driven sea level rise.
  • 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_69e0c45f17148190949c330ab9c27706 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69eeb590bb0881908cd849096696db10 completed April 27, 2026, 1:02 a.m.
Created at: April 16, 2026, 6:28 p.m.