Triple

T22001663
Position Surface form Disambiguated ID Type / Status
Subject Casey Silver E543339 entity
Predicate notableWork P4 FINISHED
Object Dragonheart 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: Dragonheart | Statement: [Casey Silver, notableWork, Dragonheart]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dragonheart
Context triple: [Casey Silver, notableWork, Dragonheart]
  • A. Dragonheart chosen
    Dragonheart is a 1996 fantasy adventure film renowned for its groundbreaking CGI dragon and the voice performance of Sean Connery.
  • B. Dragonslayer
    Dragonslayer is a 1981 dark fantasy film renowned for its groundbreaking dragon visual effects and creature design.
  • C. Willow
    Willow is a 1988 fantasy adventure film directed by Ron Howard that follows an aspiring sorcerer who must protect a prophesied child from an evil queen.
  • D. Willow
    Willow is a small community in south-central Alaska known as a gateway to outdoor recreation, including fishing, hiking, and dog mushing.
  • E. Willow
    Willow is a feminine given name often associated with the graceful willow tree and commonly used in English-speaking countries.
  • 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_69e11e2c814c8190837d072789000486 completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f1276ae4e0819097bf1b978451f776 completed April 28, 2026, 9:32 p.m.
Created at: April 16, 2026, 8:20 p.m.