Triple

T334194
Position Surface form Disambiguated ID Type / Status
Subject Ivanka Trump E6687 entity
Predicate givenName P17 FINISHED
Object Ivana E3346 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: Ivana | Statement: [Ivanka Trump, givenName, Ivana]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ivana
Context triple: [Ivanka Trump, givenName, Ivana]
  • A. Ivana Marie Zelníčková
    Ivana Marie Zelníčková, better known as Ivana Trump, was a Czech-American businesswoman, former model, and the first wife of Donald Trump, noted for her role in his early real estate empire and her own fashion and lifestyle ventures.
  • B. Ivana Trump chosen
    Ivana Trump was a Czech-American businesswoman, former model, and socialite best known as the first wife of Donald Trump and a prominent figure in New York high society in the 1980s and 1990s.
  • C. Livia Giuggioli
    Livia Giuggioli is an Italian film producer and environmental activist known for her work in sustainable fashion and documentary filmmaking.
  • D. Irina Korina
    Irina Korina is the mother of late Russian-American actor Anton Yelchin.
  • E. Anastasie Arapova
    Anastasie Arapova was the Russian-born first wife of Finnish military leader and statesman Carl Gustaf Emil Mannerheim.
  • 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_69a2e79434908190a9d5afe415153ad9 completed Feb. 28, 2026, 1:03 p.m.
NER Named-entity recognition batch_69a2eac641708190b85fa21368e5de8e completed Feb. 28, 2026, 1:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69a3d245be0c819093acff963b041d01 completed March 1, 2026, 5:44 a.m.
Created at: Feb. 28, 2026, 1:08 p.m.