Triple

T16391820
Position Surface form Disambiguated ID Type / Status
Subject Johan Sverdrup E398070 entity
Predicate familyName P18 FINISHED
Object Sverdrup E923263 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: Sverdrup | Statement: [Johan Sverdrup, familyName, Sverdrup]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sverdrup
Context triple: [Johan Sverdrup, familyName, Sverdrup]
  • A. Sverdrup chosen
    A sverdrup is an oceanographic unit of volume transport equal to one million cubic meters of seawater per second, commonly used to quantify large-scale ocean currents.
  • B. Bjerknes
    Bjerknes is a Norwegian surname most notably associated with the influential family of physicists and meteorologists who helped found modern weather forecasting and climate science.
  • C. Heiskell
    Heiskell is a surname most notably associated with Andrew Heiskell, an influential American magazine publisher and philanthropist.
  • D. Ekman
    Ekman is a Swedish surname borne by several notable figures in Sweden’s cultural and public life.
  • E. Otto Sverdrup
    Otto Sverdrup was a Norwegian Arctic explorer and sea captain best known for leading major polar expeditions and commanding the ship Fram.
  • 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_69d87f2880b48190ae1a9673a3bbef80 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e326436ce881909f0f3899b8d931aa completed April 18, 2026, 6:35 a.m.
NED1 Entity disambiguation (via context triple) batch_6a003573c6d48190979201b9619c5103 completed May 10, 2026, 7:36 a.m.
Created at: April 10, 2026, 5:08 a.m.