Triple

T10210605
Position Surface form Disambiguated ID Type / Status
Subject James A. Michener E242315 entity
Predicate spouse P13 FINISHED
Object Vange Nord E242315 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: Vange Nord | Statement: [James A. Michener, spouse, Vange Nord]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Vange Nord
Context triple: [James A. Michener, spouse, Vange Nord]
  • A. Vange Nord chosen
    Vange Nord was the wife of American author James A. Michener.
  • B. Knudshoved
    Knudshoved is a coastal area on the Danish island of Funen that serves as a key transport hub and former ferry terminal at the western end of the Great Belt crossing.
  • C. Gad Valley
    Gad Valley is a prominent ski and snowboard area within Utah’s Snowbird resort, known for its steep terrain and deep powder.
  • D. Vinge
    Vinge is a surname most notably associated with Vernor Vinge, the American science fiction author and mathematician known for popularizing the concept of the technological singularity.
  • E. Vårby
    Vårby is a suburban district in the southern Stockholm area of Sweden, known for its residential neighborhoods and proximity to Lake Mälaren.
  • 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_69d381ae26c48190985abd0e25ee5d04 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d395fbed008190b66996f5bb397853 completed April 6, 2026, 11:16 a.m.
NED1 Entity disambiguation (via context triple) batch_69d652d8088c819084040883f2ab9dc6 completed April 8, 2026, 1:06 p.m.
Created at: April 6, 2026, 11:01 a.m.