Triple

T141878
Position Surface form Disambiguated ID Type / Status
Subject Warren Delano Jr. E2870 entity
Predicate child P120 FINISHED
Object Sara Ann Delano E10618 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: Sara Ann Delano | Statement: [Warren Delano Jr., child, Sara Ann Delano]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sara Ann Delano
Context triple: [Warren Delano Jr., child, Sara Ann Delano]
  • A. Sara Ann Delano chosen
    Sara Ann Delano was an American socialite and the mother of U.S. President Franklin D. Roosevelt.
  • B. Amabel James
    Amabel James is known as the spouse of British businessman and hedge fund manager Tony James.
  • C. Mary Hoyt Sherman
    Mary Hoyt Sherman was the mother of American Civil War general William Tecumseh Sherman and a member of the prominent Sherman family of Ohio.
  • D. Helen Dinsmore Huntington
    Helen Dinsmore Huntington was an American socialite and arts patron from a prominent New York family, best known for her influential role in early 20th-century high society and cultural philanthropy.
  • E. Susan Packard Orr
    Susan Packard Orr is an American philanthropist and former technology executive known for her leadership roles in the David and Lucile Packard Foundation and on the board of Hewlett-Packard.
  • 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_69a2521e35c08190b28e5c9f1e3c9b59 completed Feb. 28, 2026, 2:25 a.m.
NER Named-entity recognition batch_69a257c9cab8819095e8d9fa32c1fbc6 completed Feb. 28, 2026, 2:49 a.m.
NED1 Entity disambiguation (via context triple) batch_69a4efc821b48190af6d3cd88ab3f980 completed March 2, 2026, 2:02 a.m.
Created at: Feb. 28, 2026, 2:31 a.m.