Triple

T12968456
Position Surface form Disambiguated ID Type / Status
Subject Alfonso IV of Aragon E321329 entity
Predicate spouse P13 FINISHED
Object Teresa d’Entença E912818 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: Teresa d’Entença | Statement: [Alfonso IV of Aragon, spouse, Teresa d’Entença]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Teresa d’Entença
Context triple: [Alfonso IV of Aragon, spouse, Teresa d’Entença]
  • A. Teresa d’Entença chosen
    Teresa d’Entença was a 14th-century noblewoman who became Queen consort of Aragon through her marriage to King Alfonso IV.
  • B. Joan Prat
    Joan Prat is a notable individual who carries the surname Prat, recognized as a distinguished bearer of this family name.
  • C. Eulalia Ramón
    Eulalia Ramón is a Spanish actress known for her work in film and television, including frequent collaborations with director Carlos Saura.
  • D. Josefa Bayeu
    Josefa Bayeu was the wife of Spanish painter Francisco Goya and a member of the artistic Bayeu family connected to the royal court in 18th-century Spain.
  • E. Maria de la Pau Tortelier
    Maria de la Pau Tortelier is a Spanish pianist known for her concert and recording career, including collaborations with her father, the renowned cellist Paul Tortelier.
  • 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_69d80763bd6c819094437da5b20b01d2 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69d97e407e5081909424fc0c22483c28 completed April 10, 2026, 10:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6b8e6b31c8190b09276003f284f25 completed May 3, 2026, 2:54 a.m.
Created at: April 9, 2026, 8:32 p.m.