Triple

T21371826
Position Surface form Disambiguated ID Type / Status
Subject Isabel de Verdun E527082 entity
Predicate associatedWithLocation P2830 FINISHED
Object Ireland 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: Ireland | Statement: [Isabel de Verdun, associatedWithLocation, Ireland]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ireland
Context triple: [Isabel de Verdun, associatedWithLocation, Ireland]
  • A. Ireland chosen
    Ireland is a European island nation in the North Atlantic, known for its distinct Celtic heritage, complex history with the United Kingdom, and transformation into a modern, high-income economy.
  • B. Irisha
    Irisha is a diminutive, affectionate form of the female given name Irina, commonly used in Russian and other Slavic languages.
  • C. Éirígí
    Éirígí is a socialist republican political party and activist organization in Ireland that advocates for Irish reunification and left-wing social and economic policies.
  • D. Irles
    Irles is a small commune in northern France situated along the Ancre River in the Somme department.
  • E. Airgíalla
    Airgíalla was a medieval Irish over-kingdom and confederation of tribes located in northern Ireland, known for its shifting alliances and role as a buffer between larger regional powers.
  • 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_69e0b51e80808190ba5cb05667af02a9 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e8b0af44d88190aedd3b2127bb297d completed April 22, 2026, 11:27 a.m.
Created at: April 16, 2026, 5:10 p.m.