Triple

T16147597
Position Surface form Disambiguated ID Type / Status
Subject Stephen Petranek E391825 entity
Predicate hasGivenPresentation P61190 FINISHED
Object TED talk on 10 ways the world could end LITERAL 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: TED talk on 10 ways the world could end | Statement: [Stephen Petranek, hasGivenPresentation, TED talk on 10 ways the world could end]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasGivenPresentation
Context triple: [Stephen Petranek, hasGivenPresentation, TED talk on 10 ways the world could end]
  • A. hasPresented chosen
    Indicates that one entity has formally given, delivered, or shown something (such as information, a work, or an award) to another entity.
  • B. hasPresentation
    Indicates that an entity delivers, contains, or is associated with a specific presentation (such as a talk, slide deck, or formal display of information).
  • C. hasGiven
    Indicates that one entity has transferred or presented something to another entity.
  • D. presentedAfter
    Indicates that one entity is presented or displayed at a later time or sequence position than another entity.
  • E. hasArtFormPresented
    Indicates that an entity presents, showcases, or features a particular art form.
  • F. None of above.

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_69d87f1c65e48190aa2b4c472e9bafc4 completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e21d947e68819081b4b7c757ce71b6 completed April 17, 2026, 11:46 a.m.
PD Predicate disambiguation batch_69e182885bc08190822ae7e8a4b8ac1f completed April 17, 2026, 12:44 a.m.
Created at: April 10, 2026, 5:01 a.m.