Triple

T14176103
Position Surface form Disambiguated ID Type / Status
Subject Peter Hermann E351336 entity
Predicate spouse P13 FINISHED
Object Mariska Hargitay E69229 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: Mariska Hargitay | Statement: [Peter Hermann, spouse, Mariska Hargitay]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mariska Hargitay
Context triple: [Peter Hermann, spouse, Mariska Hargitay]
  • A. Mariska Hargitay chosen
    Mariska Hargitay is an American actress best known for her long-running role as Detective Olivia Benson on the television series "Law & Order: Special Victims Unit."
  • B. Maura West
    Maura West is an American actress best known for her long-running, Emmy-winning work in daytime soap operas.
  • C. Kelli Giddish
    Kelli Giddish is an American actress best known for her role as Detective Amanda Rollins on the television series "Law & Order: Special Victims Unit."
  • D. Colleen Ventimiglia
    Colleen Ventimiglia is a screenwriter best known for her work on the animated Disney sequel "Cinderella III: A Twist in Time."
  • E. Edie Falco
    Edie Falco is an American actress best known for her acclaimed television roles, particularly as Carmela Soprano on "The Sopranos" and Jackie Peyton on "Nurse Jackie."
  • 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_69d8278834a08190b0f1784e58d7b99c completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de61c76e8081909994b95b631100e9 completed April 14, 2026, 3:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcf80cdae88190ae987b49218c281d completed May 7, 2026, 8:37 p.m.
Created at: April 10, 2026, 1:02 a.m.