Triple

T11221526
Position Surface form Disambiguated ID Type / Status
Subject Linda Keene E265578 entity
Predicate loveInterestOf P7325 FINISHED
Object Peter P. Peters E229583 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: Peter P. Peters | Statement: [Linda Keene, loveInterestOf, Peter P. Peters]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Peter P. Peters
Context triple: [Linda Keene, loveInterestOf, Peter P. Peters]
  • A. Peter P. Peters chosen
    Peter P. Peters is the tap-dancing American ballet star played by Fred Astaire in the 1937 musical film "Shall We Dance."
  • B. Peter J. Peters
    Peter J. Peters is a researcher noted for his taxonomic and descriptive work on the Antarctic fur seal.
  • C. Peter C. Frank
    Peter C. Frank is an editor known for his work on the publication "The Verdict."
  • D. H. Peter Hofstee
    H. Peter Hofstee is a computer engineer and microprocessor architect best known for his work on advanced processor designs, including contributions at Transmeta and IBM.
  • E. Peter E. Haas
    Peter E. Haas was an American businessman and philanthropist best known for his leadership role at Levi Strauss & Co. and his prominent involvement in civic and charitable causes in San Francisco.
  • 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_69d6aac59460819089b9848b27f57848 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e8ec8fb08190b27144ab65f85957 completed April 9, 2026, 5:59 p.m.
NED1 Entity disambiguation (via context triple) batch_69ef127eaf588190aaca151ee4022f3c completed April 27, 2026, 7:38 a.m.
Created at: April 8, 2026, 9:30 p.m.