Triple

T19095568
Position Surface form Disambiguated ID Type / Status
Subject Irma Vep (TV miniseries) E467394 entity
Predicate castMember P1668 FINISHED
Object Lars Eidinger 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: Lars Eidinger | Statement: [Irma Vep (TV miniseries), castMember, Lars Eidinger]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lars Eidinger
Context triple: [Irma Vep (TV miniseries), castMember, Lars Eidinger]
  • A. Lars Eidinger chosen
    Lars Eidinger is a German actor known for his work in both arthouse cinema and mainstream films, as well as for acclaimed stage performances at Berlin's Schaubühne theatre.
  • B. Christian Hebel
    Christian Hebel is an American violinist and concertmaster known for his work on Broadway productions, film scores, and live performances with prominent recording artists.
  • C. Andreas Scholl
    Andreas Scholl is a renowned German countertenor celebrated for his interpretations of Baroque and early music.
  • D. Uli Wiesendanger
    Uli Wiesendanger is an advertising executive best known as a co-founder of the global advertising agency network TBWA Worldwide.
  • E. Andreas Bovenschulte
    Andreas Bovenschulte is a German politician who serves as the President of the Senate and Mayor of the federal state of Bremen.
  • 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_69d8dd05ac4c8190b1967d8f97f3fb2f completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e368f20c8190bd84d2ba320991ac completed April 20, 2026, 8:27 a.m.
Created at: April 10, 2026, 12:04 p.m.