Triple

T2216382
Position Surface form Disambiguated ID Type / Status
Subject Marv Films E48040 entity
Predicate workOn P30363 FINISHED
Object Stardust E158659 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: Stardust | Statement: [Marv Films, workOn, Stardust]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Stardust
Context triple: [Marv Films, workOn, Stardust]
  • A. Stardust
    "Stardust" is a classic popular song, widely regarded as a jazz and American Songbook standard, famously interpreted by Louis Armstrong and many other artists.
  • B. Stardust chosen
    Stardust is a fantasy novel by Neil Gaiman that blends fairy-tale romance and adventure in a magical realm bordering Victorian England.
  • C. Starlight
    Starlight is a fictional character or element associated with the Evolver universe, likely representing a key component or aspect within that setting.
  • D. Shine
    Shine is a critically acclaimed 1996 biographical drama film in which Geoffrey Rush delivers an Oscar-winning performance as pianist David Helfgott.
  • E. Shine
    Shine is a studio album by British R&B singer Estelle that showcases her blend of soul, hip hop, and pop influences.
  • 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_69a88aa1ee708190862c8c378c41e9eb completed March 4, 2026, 7:40 p.m.
NER Named-entity recognition batch_69abc00f4c3881909d03301fcdfa8b67 completed March 7, 2026, 6:05 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae95fb20b88190b7e959b5d718fe73 completed March 9, 2026, 9:42 a.m.
Created at: March 4, 2026, 7:46 p.m.