Triple

T10738580
Position Surface form Disambiguated ID Type / Status
Subject Almost Heaven E253259 entity
Predicate stars P1956 FINISHED
Object Heike Makatsch E51658 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: Heike Makatsch | Statement: [Almost Heaven, stars, Heike Makatsch]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Heike Makatsch
Context triple: [Almost Heaven, stars, Heike Makatsch]
  • A. Heike Makatsch chosen
    Heike Makatsch is a German actress and former television presenter known internationally for her roles in films such as "Love Actually" and "Resident Evil."
  • B. Luzi von Sonnenthal
    Luzi von Sonnenthal was the wife of Austrian composer Erich Wolfgang Korngold and a member of the prominent Viennese theatrical Sonnenthal family.
  • C. Julie von Webenau
    Julie von Webenau was a 19th-century Austrian pianist and composer known for her salon pieces and connections with prominent Romantic-era musicians.
  • D. Alexandra Freifrau von Berlichingen
    Alexandra Freifrau von Berlichingen is a German noblewoman best known as the wife of former German President Roman Herzog.
  • E. Franziska
    Franziska is a feminine given name of German origin, closely related to and cognate with the name Frances.
  • 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_69d6aa5e51e8819095f06881cecf152e completed April 8, 2026, 7:19 p.m.
NER Named-entity recognition batch_69d710424d8c81908ee9b59d622f2af5 completed April 9, 2026, 2:34 a.m.
NED1 Entity disambiguation (via context triple) batch_69deb0a03a1481908edb933b1613a027 completed April 14, 2026, 9:24 p.m.
Created at: April 8, 2026, 9:14 p.m.