Triple

T8864007
Position Surface form Disambiguated ID Type / Status
Subject Robert Peel E210965 entity
Predicate spouse P13 FINISHED
Object Julia Floyd E210965 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: Julia Floyd | Statement: [Robert Peel, spouse, Julia Floyd]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Julia Floyd
Context triple: [Robert Peel, spouse, Julia Floyd]
  • A. Julia Floyd chosen
    Julia Floyd was the wife of British statesman Sir Robert Peel, serving as a prominent Victorian-era political hostess and member of the English gentry.
  • B. Julia Procilla
    Julia Procilla was a Roman noblewoman of the 1st century AD, best known as the mother of the prominent general and governor Gnaeus Julius Agricola.
  • C. Julia Smith
    Julia Smith was a British television producer and director best known for co-creating the long-running BBC soap opera EastEnders.
  • D. Julia Hoyt
    Julia Hoyt was an American stage and silent film actress and socialite active in the early 20th century.
  • E. Julia Wright
    Julia Wright is the daughter of renowned American author Richard Wright and has been involved in preserving and promoting his literary legacy.
  • 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_69ca838bbddc8190ab546d737e5d350f completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc610416b48190a26f0c457089ffca completed April 1, 2026, 12:04 a.m.
NED1 Entity disambiguation (via context triple) batch_69d6523db338819088e2fadf346ad845 completed April 8, 2026, 1:03 p.m.
Created at: March 30, 2026, 6:50 p.m.