Triple

T17042441
Position Surface form Disambiguated ID Type / Status
Subject Graceland aircraft display E413477 entity
Predicate hasPart P35 FINISHED
Object Lisa Marie (airplane) E87807 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: Lisa Marie (airplane) | Statement: [Graceland aircraft display, hasPart, Lisa Marie (airplane)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lisa Marie (airplane)
Context triple: [Graceland aircraft display, hasPart, Lisa Marie (airplane)]
  • A. Marilyn
    Marilyn is the given first name of American country music singer Jeannie Seely.
  • B. Marilyn
    Marilyn is the middle name of Toni Marilyn Smith.
  • C. Marilyn
    A Marilyn is a type of British hill or mountain classified by having a prominence of at least 150 meters, regardless of its absolute height.
  • D. Lisa Marie Kurbikoff
    Lisa Marie Kurbikoff is an American photographer and occasional actress known for her work in film and celebrity portraiture.
  • E. Lisa Marie airplane chosen
    The Lisa Marie airplane is Elvis Presley’s customized Convair 880 jet, lavishly outfitted for his personal use and now displayed as a museum attraction at Graceland.
  • 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_69d886cd18288190b006abab23f811b7 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d8f771608190b596138ddec118c6 completed April 18, 2026, 7:18 p.m.
NED1 Entity disambiguation (via context triple) batch_6a012ed472d48190bc6aed49464dc1ff completed May 11, 2026, 1:20 a.m.
Created at: April 10, 2026, 5:33 a.m.