Triple

T16249114
Position Surface form Disambiguated ID Type / Status
Subject Oskar Homolka E394450 entity
Predicate notableWork P4 FINISHED
Object Ball of Fire E101038 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: Ball of Fire | Statement: [Oskar Homolka, notableWork, Ball of Fire]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ball of Fire
Context triple: [Oskar Homolka, notableWork, Ball of Fire]
  • A. Ball of Fire chosen
    Ball of Fire is a 1941 screwball comedy film starring Gary Cooper and Barbara Stanwyck, known for its witty dialogue and playful take on academic life and gangster culture.
  • B. Ball of Fire
    Ball of Fire is the nickname of the Indian 5th Infantry Division, a distinguished World War II formation noted for its rapid, hard-fought campaigns in multiple theaters.
  • C. Bed of Roses
    Bed of Roses is a 1996 romantic drama film best known for its tender love story and emotive musical score.
  • D. Bed of Roses
    "Bed of Roses" is a power ballad by American rock band Bon Jovi, known for its emotional lyrics and soaring melody, released in the early 1990s.
  • E. Bed of Roses
    Bed of Roses is a 1933 romantic comedy film starring Constance Bennett as a savvy former prostitute who schemes her way into high society but unexpectedly falls in love.
  • 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_69d87f2171208190951025e526947816 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e24594f23c8190bd59fcb2585cb5e3 completed April 17, 2026, 2:37 p.m.
NED1 Entity disambiguation (via context triple) batch_6a000ee3bbc48190a56ce2807a9510f0 completed May 10, 2026, 4:51 a.m.
Created at: April 10, 2026, 5:04 a.m.