Triple

T15320325
Position Surface form Disambiguated ID Type / Status
Subject James Tisch E366269 entity
Predicate relative P37 FINISHED
Object Preston Robert Tisch E70073 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: Preston Robert Tisch | Statement: [James Tisch, relative, Preston Robert Tisch]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Preston Robert Tisch
Context triple: [James Tisch, relative, Preston Robert Tisch]
  • A. Preston Robert Tisch chosen
    Preston Robert Tisch was an American businessman and philanthropist best known as co-owner of the New York Giants and former Postmaster General of the United States.
  • B. Laurence Tisch
    Laurence Tisch was an American businessman and investor best known as the co-owner of Loews Corporation and former CEO of CBS.
  • C. Jonathan Tisch
    Jonathan Tisch is an American businessman and philanthropist best known as the chairman and CEO of Loews Hotels and co-owner of the New York Giants.
  • D. Andrew Tisch
    Andrew Tisch is an American businessman and co-chair of Loews Corporation, known for his leadership in the family-controlled conglomerate and his involvement in civic and philanthropic initiatives.
  • E. Louis M. Silverstein
    Louis M. Silverstein is a film producer known for his work on the comedy movie "Strange Brew."
  • 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_69d85a121520819093dcce999fdefe1a completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03dd460288190b5c41f0a0aeee949 completed April 16, 2026, 1:39 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff0b3dac6c81908eaa0aaad29113ee completed May 9, 2026, 10:23 a.m.
Created at: April 10, 2026, 3:16 a.m.