Triple

T11842412
Position Surface form Disambiguated ID Type / Status
Subject Veronica Porsche E281685 entity
Predicate name P16 FINISHED
Object Veronica Porsche E281685 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: Veronica Porsche | Statement: [Veronica Porsche, name, Veronica Porsche]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Veronica Porsche
Context triple: [Veronica Porsche, name, Veronica Porsche]
  • A. Veronica Porsche chosen
    Veronica Porsche is an American actress and model best known as the third wife of boxing legend Muhammad Ali.
  • B. Maria Mattea Pagani
    Maria Mattea Pagani was the wife of Venetian painter Francesco Guardi and a member of the artistic Pagani family active in 18th-century Venice.
  • C. Martha Diesel
    Martha Diesel was the wife of Rudolf Diesel, the German inventor of the diesel engine.
  • D. Louise Piëch
    Louise Piëch was an Austrian businesswoman and key member of the Porsche–Piëch family who helped manage and expand the Porsche automotive legacy.
  • E. Lola Van Wagenen
    Lola Van Wagenen is an American historian, activist, and co-founder of the consumer education organization Consumer Action Now, known also for her longtime marriage to actor Robert Redford.
  • 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_69d6ab287ba48190a5178779fd19b9b7 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d8a65a597c8190b09f57463b279afc completed April 10, 2026, 7:27 a.m.
NED1 Entity disambiguation (via context triple) batch_69f1678668ac81909bddf67e8c176757 completed April 29, 2026, 2:05 a.m.
Created at: April 8, 2026, 9:43 p.m.