Triple

T4127995
Position Surface form Disambiguated ID Type / Status
Subject Micky Arison E92769 entity
Predicate relative P37 FINISHED
Object Shari Arison E415935 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: Shari Arison | Statement: [Micky Arison, relative, Shari Arison]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Shari Arison
Context triple: [Micky Arison, relative, Shari Arison]
  • A. Shari Arison chosen
    Shari Arison is an Israeli-American businesswoman and philanthropist known as one of Israel’s wealthiest women and a major shareholder in Bank Hapoalim.
  • B. Laurie Tisch
    Laurie Tisch is an American philanthropist and arts patron known for her significant contributions to education, culture, and community initiatives in New York City.
  • C. Penny Vinik
    Penny Vinik is a philanthropist and community leader known for her extensive charitable work, particularly in the arts, education, and health initiatives, often associated with the Tampa Bay area.
  • D. Abigail S. Wexner
    Abigail S. Wexner is an American philanthropist and attorney known for her leadership in charitable, educational, and community initiatives, particularly in Ohio.
  • E. Margo Winkler
    Margo Winkler is an American actress known for her frequent small roles in films produced or directed by her husband, filmmaker Irwin Winkler.
  • 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_69aed9685f70819086932777aec8d959 completed March 9, 2026, 2:30 p.m.
NER Named-entity recognition batch_69af021b17a08190b520101f54ec1e33 completed March 9, 2026, 5:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69b57f29865c8190b0ecb7acc9901765 completed March 14, 2026, 3:30 p.m.
Created at: March 9, 2026, 3:42 p.m.