Triple

T15159321
Position Surface form Disambiguated ID Type / Status
Subject Jack Haley E362163 entity
Predicate spouse P13 FINISHED
Object Florence McFadden NE NERFINISHED

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: Florence McFadden | Statement: [Jack Haley, spouse, Florence McFadden]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Florence McFadden
Context triple: [Jack Haley, spouse, Florence McFadden]
  • A. Florence McFadden chosen
    Florence McFadden was the wife of American actor and vaudevillian Jack Haley, best known for his role as the Tin Man in the classic film "The Wizard of Oz."
  • B. Florence Howard
    Florence Howard is a person known primarily through her family connection to Rome Howard.
  • C. Florence Crawford
    Florence Crawford was an early 20th-century Pentecostal evangelist and leader who helped spread the Azusa Street Revival’s message across the United States, particularly through her work in the Pacific Northwest.
  • D. Florence Ryerson
    Florence Ryerson was an American screenwriter best known for co-writing the screenplay for the classic 1939 film adaptation of "The Wizard of Oz."
  • E. Florence Williamson
    Florence Williamson is a film editor known for her work on the 1972 musical historical comedy film "1776."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d85a087b7c81908baa94a53dac8d68 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e0060dd71881908ecc4a4f52d438a5 completed April 15, 2026, 9:41 p.m.
Created at: April 10, 2026, 3:08 a.m.