Triple

T6383073
Position Surface form Disambiguated ID Type / Status
Subject 87th Academy Awards E143632 entity
Predicate alsoKnownAs P39 FINISHED
Object Oscars 2015 E143632 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: Oscars 2015 | Statement: [87th Academy Awards, alsoKnownAs, Oscars 2015]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Oscars 2015
Context triple: [87th Academy Awards, alsoKnownAs, Oscars 2015]
  • A. 85th Academy Awards
    The 85th Academy Awards was the 2013 ceremony honoring the best films of 2012, held in Hollywood and broadcast worldwide as part of the annual Oscars tradition.
  • B. 95th Academy Awards
    The 95th Academy Awards was the 2023 ceremony honoring the best films of 2022, held in Los Angeles and presented by the Academy of Motion Picture Arts and Sciences.
  • C. 87th Academy Awards chosen
    The 87th Academy Awards was the 2015 ceremony in Hollywood honoring the best films of 2014, hosted by Neil Patrick Harris.
  • D. 89th Academy Awards
    The 89th Academy Awards was the 2017 ceremony honoring the best films of 2016, notable for its Best Picture mix-up between "La La Land" and "Moonlight."
  • E. 84th Academy Awards
    The 84th Academy Awards was the 2012 ceremony honoring the best films of 2011, held in Hollywood and presented by the Academy of Motion Picture Arts and Sciences.
  • 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_69c008dac1ec81909cef8157ccd69962 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c06854eb608190acb6bb4dc466f0fc completed March 22, 2026, 10:08 p.m.
NED1 Entity disambiguation (via context triple) batch_69c638791ce8819081aeec3b11e1c96e completed March 27, 2026, 7:57 a.m.
Created at: March 22, 2026, 4:34 p.m.