Triple

T19790232
Position Surface form Disambiguated ID Type / Status
Subject Modern Talking E475389 entity
Predicate hasLeadVocalist P9645 FINISHED
Object Thomas Anders 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: Thomas Anders | Statement: [Modern Talking, hasLeadVocalist, Thomas Anders]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Thomas Anders
Context triple: [Modern Talking, hasLeadVocalist, Thomas Anders]
  • A. Thomas Anders chosen
    Thomas Anders is a German singer, songwriter, and producer best known as one half of the 1980s pop duo Modern Talking.
  • B. David Garth
    David Garth was a British character actor known for his supporting roles in mid-20th-century film and television, including appearances in science fiction and drama series.
  • C. Joshua Scott Chasez
    Joshua Scott Chasez is an American singer, songwriter, and producer best known as a member of the boy band *NSYNC.
  • D. Max Johnston
    Max Johnston is an American multi-instrumentalist best known for his work in the alt-country and Americana scenes, including early contributions to bands like Wilco and Uncle Tupelo.
  • E. Erik Andersen
    Erik Andersen is a software engineer best known for his major contributions to the BusyBox project, a compact suite of Unix utilities widely used in embedded Linux systems.
  • 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_69d8e51b014081908b263e167370529a completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6538ae5108190b80eb7de6f445f02 completed April 20, 2026, 4:25 p.m.
Created at: April 10, 2026, 1:49 p.m.