Triple

T11987434
Position Surface form Disambiguated ID Type / Status
Subject Francesca Johnson E285316 entity
Predicate child P120 FINISHED
Object Michael Johnson E231861 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: Michael Johnson | Statement: [Francesca Johnson, child, Michael Johnson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michael Johnson
Context triple: [Francesca Johnson, child, Michael Johnson]
  • A. Michael Johnson chosen
    Michael Johnson is an American sprinter renowned for his dominance in the 200m and 400m events, multiple world records, and several Olympic gold medals.
  • B. Maurice Greene
    Maurice Greene is an American former sprinter and Olympic gold medalist who dominated the 100-meter dash in the late 1990s and early 2000s.
  • C. Edwin Moses
    Edwin Moses is an American track and field legend best known for his dominance in the 400-meter hurdles, including an unprecedented winning streak and multiple Olympic gold medals.
  • D. Donovan Bailey
    Donovan Bailey is a retired Canadian sprinter and former 100-metre world record holder who won double gold at the 1996 Atlanta Olympics.
  • E. Leroy Burrell
    Leroy Burrell is an American former sprinter and former 100 metres world record holder who was one of the leading figures in men's sprinting during the late 1980s and early 1990s.
  • 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_69d6ab44a77c8190a652f4b27164e4ef completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d903ae28708190a826bad1624343eb completed April 10, 2026, 2:05 p.m.
NED1 Entity disambiguation (via context triple) batch_69f472492ebc8190b064e691bb70e356 completed May 1, 2026, 9:28 a.m.
Created at: April 8, 2026, 9:46 p.m.