Triple

T2487255
Position Surface form Disambiguated ID Type / Status
Subject Howard Hughes E55953 entity
Predicate spouse P13 FINISHED
Object Jean Peters E268230 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: Jean Peters | Statement: [Howard Hughes, spouse, Jean Peters]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jean Peters
Context triple: [Howard Hughes, spouse, Jean Peters]
  • A. Jean Peters chosen
    Jean Peters was an American film actress best known for her leading roles in 1940s and 1950s Hollywood adventure and drama films.
  • B. Charles F. Roos
    Charles F. Roos was an American economist and mathematician known for his pioneering work in econometrics and contributions to the formalization of economic theory.
  • C. James Nourse
    James Nourse was an 18th-century British sea captain involved in the transatlantic slave trade.
  • D. John Clarence Karcher
    John Clarence Karcher was an American geophysicist and pioneer of reflection seismology whose work helped lay the foundations of modern petroleum exploration.
  • E. Vincent Ostrom
    Vincent Ostrom was an American political scientist known for his foundational work on public choice theory, polycentric governance, and for co-founding the Workshop in Political Theory and Policy Analysis at Indiana University.
  • 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_69ab49e670a88190b928e08302381710 completed March 6, 2026, 9:40 p.m.
NER Named-entity recognition batch_69abd1782ca081909645164a6acf0ea0 completed March 7, 2026, 7:19 a.m.
NED1 Entity disambiguation (via context triple) batch_69af1f8ee974819082a2a29f8b72d131 completed March 9, 2026, 7:29 p.m.
Created at: March 6, 2026, 9:45 p.m.