Triple

T2327716
Position Surface form Disambiguated ID Type / Status
Subject Chris Cornell E48327 entity
Predicate spouse P13 FINISHED
Object Vicky Karayiannis E25777 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: Vicky Karayiannis | Statement: [Chris Cornell, spouse, Vicky Karayiannis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Vicky Karayiannis
Context triple: [Chris Cornell, spouse, Vicky Karayiannis]
  • A. Vicky Karayiannis chosen
    Vicky Karayiannis is a Greek-American publicist and philanthropist best known as the widow of Soundgarden and Audioslave frontman Chris Cornell.
  • B. Maria Pappadimos
    Maria Pappadimos is a key resistance fighter character in the World War II adventure film "The Guns of Navarone."
  • C. Eleni Kounalakis
    Eleni Kounalakis is an American politician and former U.S. ambassador who serves as the lieutenant governor of California.
  • D. Eirini Lelekou
    Eirini Lelekou is the birth name of Irene Papas, the renowned Greek actress and singer celebrated for her powerful performances in international cinema and theater.
  • E. Clelia Haji-Ioannou
    Clelia Haji-Ioannou is a member of the prominent Haji-Ioannou family, known for its substantial shipping and aviation business interests and associated wealth.
  • 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_69a88aa308a88190b0b86c011fda7fce completed March 4, 2026, 7:40 p.m.
NER Named-entity recognition batch_69abc64c7f1881909b0d847f7782e803 completed March 7, 2026, 6:31 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae9615f000819092f9dc4700998b25 completed March 9, 2026, 9:42 a.m.
Created at: March 4, 2026, 7:50 p.m.