Triple

T20610187
Position Surface form Disambiguated ID Type / Status
Subject Angela Thorne E506426 entity
Predicate appearedIn P795 FINISHED
Object Three Up, Two Down 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: Three Up, Two Down | Statement: [Angela Thorne, appearedIn, Three Up, Two Down]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Three Up, Two Down
Context triple: [Angela Thorne, appearedIn, Three Up, Two Down]
  • A. Three Up, Two Down chosen
    Three Up, Two Down is a British television sitcom best known for its comedic portrayal of two very different families forced to share a suburban house.
  • B. Two by Two
    "Two by Two" is a musical number from the Broadway show The Book of Mormon, performed by the original cast and featured on its cast recording.
  • C. Time for Three
    Time for Three is a genre-blending string trio known for fusing classical music with jazz, pop, and other contemporary styles in highly energetic performances.
  • D. Up and Down
    "Up and Down" is a song by Doja Cat from her genre-blending, futuristic-themed album *Planet Her*.
  • E. On the Count of Three
    On the Count of Three is a dark comedy-drama film centered on two friends who make a suicide pact and decide to live out their final day settling unfinished business.
  • 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_69e0b4bb2b4081908fa4a72444120f35 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6aad6f53481908fb242947dda7028 completed April 20, 2026, 10:38 p.m.
Created at: April 16, 2026, 11:41 a.m.