Triple

T23181376
Position Surface form Disambiguated ID Type / Status
Subject Tulsa McLean E579464 entity
Predicate notableSongPerformance P11145 FINISHED
Object “Frankfort Special” 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: “Frankfort Special” | Statement: [Tulsa McLean, notableSongPerformance, “Frankfort Special”]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: “Frankfort Special”
Context triple: [Tulsa McLean, notableSongPerformance, “Frankfort Special”]
  • A. Frankfort Special chosen
    "Frankfort Special" is a rock-and-roll song performed by Elvis Presley, best known from the soundtrack of his 1960 film *G.I. Blues*.
  • B. the Boilermaker Special
    The Boilermaker Special is the official train-themed mascot of Purdue University, designed to resemble a Victorian-era locomotive and symbolize the school’s engineering heritage.
  • C. The Special
    The Special is the prophesied hero persona of Emmet Brickowski in "The LEGO Movie," representing an ordinary construction worker who becomes an unlikely savior of the LEGO universe.
  • D. Special K
    Special K is a music producer best known for his work with the hip hop group Conspiracy.
  • E. Special K
    Special K is a popular Kellogg’s breakfast cereal brand known for its lightly toasted flakes and association with weight management and healthy eating.
  • 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_69e245ff8000819090d12008805315b7 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f18f6f770c81908622085693e37123 completed April 29, 2026, 4:56 a.m.
Created at: April 17, 2026, 4:05 p.m.