Triple

T15427418
Position Surface form Disambiguated ID Type / Status
Subject Cumberland Bay E369547 entity
Predicate hasMouthNear P350 FINISHED
Object Grytviken E73752 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: Grytviken | Statement: [Cumberland Bay, hasMouthNear, Grytviken]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Grytviken
Context triple: [Cumberland Bay, hasMouthNear, Grytviken]
  • A. Grytviken chosen
    Grytviken is a former whaling station and now-abandoned settlement on the island of South Georgia, notable for its historical role in Antarctic exploration and as the burial place of Ernest Shackleton.
  • B. Gjoa Haven
    Gjoa Haven is a small Inuit community in Nunavut, Canada, known as a historic Arctic settlement linked to polar exploration and the Northwest Passage.
  • C. Barentsburg
    Barentsburg is a Russian mining settlement on the Norwegian archipelago of Svalbard, known for its coal industry and Soviet-era character.
  • D. Longyearbyen
    Longyearbyen is the world’s northernmost permanent settlement and the largest town in the Norwegian Arctic archipelago of Svalbard.
  • E. Hvalsey
    Hvalsey is the best-preserved Norse ruin site in Greenland, known for its stone church and remnants of a medieval farming settlement.
  • 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_69d85a1849f48190bf898068b2806fae completed April 10, 2026, 2:02 a.m.
NER Named-entity recognition batch_69e03ec31f4881908b26ff7c381d7bc9 completed April 16, 2026, 1:43 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff3d40d3388190b1bd724238f928b1 completed May 9, 2026, 1:57 p.m.
Created at: April 10, 2026, 3:20 a.m.