Triple

T10364278
Position Surface form Disambiguated ID Type / Status
Subject Nordisk Film E244212 entity
Predicate notableWork P4 FINISHED
Object Kon-Tiki E287605 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: Kon-Tiki | Statement: [Nordisk Film, notableWork, Kon-Tiki]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kon-Tiki
Context triple: [Nordisk Film, notableWork, Kon-Tiki]
  • A. Kon-Tiki raft
    The Kon-Tiki raft is the balsa-wood vessel used by Norwegian explorer Thor Heyerdahl in his 1947 Pacific Ocean expedition to demonstrate the possibility of ancient transoceanic contact.
  • B. Kon-Tiki (book)
    Kon-Tiki is Thor Heyerdahl’s classic 1948 nonfiction account of his experimental raft voyage across the Pacific Ocean to support his theories about Polynesian migration.
  • C. Kon-Tiki (2012 film) chosen
    Kon-Tiki (2012 film) is a historical adventure drama depicting Thor Heyerdahl’s 1947 Pacific raft expedition, co-written by screenwriter Allan Scott.
  • D. Kontiki
    Kontiki is a peer-to-peer enterprise video and content delivery company co-founded by technology executive Mike Homer.
  • E. The Explorer
    The Explorer is the adventurous mascot representing La Salle University's spirit of discovery and exploration.
  • 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_69d381b3e328819094b23b8edcd29b5a completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4e964a53c8190b748e80850e96656 completed April 7, 2026, 11:24 a.m.
NED1 Entity disambiguation (via context triple) batch_69d750c2d2748190b871b928d5a094f8 completed April 9, 2026, 7:09 a.m.
Created at: April 6, 2026, noon