Triple

T20220817
Position Surface form Disambiguated ID Type / Status
Subject Hans v. Louisiana E495248 entity
Predicate plaintiff P660 FINISHED
Object Bernard Hans 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: Bernard Hans | Statement: [Hans v. Louisiana, plaintiff, Bernard Hans]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bernard Hans
Context triple: [Hans v. Louisiana, plaintiff, Bernard Hans]
  • A. Bernard Hans chosen
    Bernard Hans was the plaintiff in the landmark U.S. Supreme Court case Hans v. Louisiana, which helped define the scope of state sovereign immunity under the Eleventh Amendment.
  • B. Bernard Schubert
    Bernard Schubert was an American screenwriter best known for his work on mid-20th-century Hollywood genre films, including classic horror entries.
  • C. Bernard Baars
    Bernard Baars is a cognitive scientist best known for developing global workspace theory, a prominent model of human consciousness.
  • D. Théodore Hanssen
    Théodore Hanssen was a stained-glass artist known for creating notable windows, including works in Metz Cathedral.
  • E. Hans Scherenberg
    Hans Scherenberg was a German automotive engineer and influential Mercedes-Benz technical director known for advancing racing and production car technology in the mid-20th century.
  • 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_69da626cff80819097b530718a7c98b6 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66edc88148190b003b72eb4c69da5 completed April 20, 2026, 6:22 p.m.
Created at: April 11, 2026, 11:39 p.m.