Triple

T18303222
Position Surface form Disambiguated ID Type / Status
Subject Anson E438409 entity
Predicate hasVariantSpelling P457 FINISHED
Object Ansson 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: Ansson | Statement: [Anson, hasVariantSpelling, Ansson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ansson
Context triple: [Anson, hasVariantSpelling, Ansson]
  • A. Arnesson chosen
    Arnesson is a Scandinavian patronymic surname indicating descent from a father named Arne or a similar given name.
  • B. Ansen
    Ansen is a small village in the Dutch province of Drenthe, located within the municipality of De Wolden.
  • C. Asson
    Asson is a commune in the Pyrénées-Atlantiques department in southwestern France, situated in the foothills of the Pyrenees.
  • D. Andresen
    Andresen is a surname of Scandinavian origin, commonly used as a variant spelling of Andersen.
  • E. Asplund
    Asplund is a Swedish surname most notably associated with architect Gunnar Asplund, a key figure in Nordic Classicism and early modernist architecture.
  • 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_69d8b915e3e881909125d760c15d0c29 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e5018176d481909536f50689f878d2 completed April 19, 2026, 4:23 p.m.
Created at: April 10, 2026, 10:35 a.m.