Triple

T20916722
Position Surface form Disambiguated ID Type / Status
Subject Upper Engadine E515091 entity
Predicate containsSettlement P847 FINISHED
Object Celerina 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: Celerina | Statement: [Upper Engadine, containsSettlement, Celerina]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Celerina
Context triple: [Upper Engadine, containsSettlement, Celerina]
  • A. Celerina chosen
    Celerina is a picturesque alpine village and ski resort in the Upper Engadine region of Switzerland, known for its sunny climate and proximity to St. Moritz.
  • B. Andrina
    Andrina is one of King Triton’s mermaid daughters and a supporting character in Disney’s "The Little Mermaid" franchise.
  • C. Caila
    Caila is an alternate given name associated with American actress and producer Marsai Martin.
  • D. Emeline
    Emeline is a feminine given name of French origin, historically used in English-speaking countries.
  • E. Verna
    Verna is a feminine given name that gained particular recognition through film editor Verna Fields, known for her work on movies like "Jaws."
  • 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_69e0b4f9d5ec8190bb2bd27350ed341c completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6ec635f4881909a560fb891100d8c completed April 21, 2026, 3:17 a.m.
Created at: April 16, 2026, 12:48 p.m.