Triple

T21311497
Position Surface form Disambiguated ID Type / Status
Subject Michael Sacks E525347 entity
Predicate appearedIn P795 FINISHED
Object Split Image 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: Split Image | Statement: [Michael Sacks, appearedIn, Split Image]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Split Image
Context triple: [Michael Sacks, appearedIn, Split Image]
  • A. Split Image chosen
    Split Image is a 1982 drama film about a young man drawn into a religious cult and his family's struggle to rescue him.
  • B. Double Split
    The Double Split is a high-end mechanical chronograph by German watchmaker A. Lange & Söhne, renowned for its sophisticated double rattrapante (double split-seconds) complication that allows timing of multiple intervals simultaneously.
  • C. ImageMosaic
    ImageMosaic is a GeoServer data store type used to efficiently serve large collections of georeferenced raster images as a single seamless mosaic layer.
  • D. Cropper
    Cropper is an English-language surname borne by various notable individuals, including musicians and public figures.
  • E. Partition
    Partition is a 2007 historical drama film set during the 1947 partition of India, focusing on the tragic human consequences of the subcontinent’s division.
  • 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_69e0b518b8948190ad69cf9a8784d397 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e75dc926c881909d70a317070ef295 completed April 21, 2026, 11:21 a.m.
Created at: April 16, 2026, 4:17 p.m.