Triple

T8295855
Position Surface form Disambiguated ID Type / Status
Subject John Kamps E194214 entity
Predicate coWrote P7732 FINISHED
Object Zathura: A Space Adventure E11839 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: Zathura: A Space Adventure | Statement: [John Kamps, coWrote, Zathura: A Space Adventure]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Zathura: A Space Adventure
Context triple: [John Kamps, coWrote, Zathura: A Space Adventure]
  • A. Zathura: A Space Adventure chosen
    Zathura: A Space Adventure is a 2005 science fiction adventure film about two brothers whose house is hurled into outer space after they begin playing a mysterious board game.
  • B. Zero G
    Zero G is a roller coaster attraction located at Beech Bend Park in Kentucky.
  • C. Escape from Planet Earth
    Escape from Planet Earth is a 2013 animated science-fiction comedy film that follows alien brothers on a rescue mission to Earth after one is lured into a trap.
  • D. Treasure Planet
    Treasure Planet is a 2002 Disney animated science-fiction adventure film that reimagines Robert Louis Stevenson’s "Treasure Island" in a futuristic space setting.
  • E. Tomorrowland
    Tomorrowland is one of the world’s largest and most famous electronic dance music festivals, held annually in Boom, Belgium.
  • 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_69ca82e50ebc81909aa7b260c76bd757 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb7df73d4c81909ad9cf0786eb5a20 completed March 31, 2026, 7:55 a.m.
NED1 Entity disambiguation (via context triple) batch_69cd952e038c819090023cbcdab1e3ae completed April 1, 2026, 9:59 p.m.
Created at: March 30, 2026, 5:53 p.m.