Triple

T21165471
Position Surface form Disambiguated ID Type / Status
Subject Nicole Johnson E521548 entity
Predicate spouse P13 FINISHED
Object Michael Phelps 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: Michael Phelps | Statement: [Nicole Johnson, spouse, Michael Phelps]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michael Phelps
Context triple: [Nicole Johnson, spouse, Michael Phelps]
  • A. Michael Phelps chosen
    Michael Phelps is an American swimmer widely regarded as the most decorated Olympian of all time, known for his record-breaking medal haul and dominance in multiple Olympic Games.
  • B. Jason Lezak
    Jason Lezak is an American former competitive swimmer and four-time Olympic gold medalist best known for his dramatic anchor leg in the 4×100-meter freestyle relay at the 2008 Beijing Games.
  • C. Mark Spitz
    Mark Spitz is an American former competitive swimmer who became legendary for winning seven gold medals at the 1972 Munich Olympics, a record at the time.
  • D. Jon Ledecky
    Jon Ledecky is an American businessman and investor best known as a co-owner of the NHL’s New York Islanders.
  • E. Michael Klim
    Michael Klim is a retired Australian swimmer renowned for his multiple Olympic gold medals and world records in freestyle and butterfly events.
  • 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_69e0b50e30748190b186824a206d39b9 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7270efe3081908a50fc601c2f958c completed April 21, 2026, 7:28 a.m.
Created at: April 16, 2026, 2:59 p.m.