Triple

T14736565
Position Surface form Disambiguated ID Type / Status
Subject Isabel Preysler E346224 entity
Predicate givenName P17 FINISHED
Object María Isabel E1168584 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: María Isabel | Statement: [Isabel Preysler, givenName, María Isabel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: María Isabel
Context triple: [Isabel Preysler, givenName, María Isabel]
  • A. María Isabel
    María Isabel is the birth name of Spanish actress Maribel Verdú, known for her prominent roles in films such as "Y Tu Mamá También" and "Pan's Labyrinth."
  • B. María Isabel
    María Isabel is a Spanish infanta (princess) of the Bourbon dynasty, known as a daughter of King Charles IV of Spain and later Queen consort of the Two Sicilies.
  • C. María Isabel chosen
    María Isabel, better known as Chábeli Iglesias, is a Spanish journalist and television personality from the prominent Iglesias entertainment family.
  • D. María Teresa
    María Teresa is the Cuban-born Grand Duchess of Luxembourg, known for her humanitarian work and role as the consort of Grand Duke Henri.
  • E. María de la Paz
    María de la Paz is the full given name of Spanish actress Paz Vega, known for her work in both Spanish and international cinema.
  • 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_69d822e6f1c88190bc494d491a907114 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69dec73114cc819088e1101b689fc70b completed April 14, 2026, 11:01 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffdbb7b1e48190b55c40e0cb837446 completed May 10, 2026, 1:13 a.m.
Created at: April 10, 2026, 1:29 a.m.