Triple

T6926278
Position Surface form Disambiguated ID Type / Status
Subject Gwen Kopechne E160317 entity
Predicate spouse P13 FINISHED
Object Joseph Kopechne E220705 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: Joseph Kopechne | Statement: [Gwen Kopechne, spouse, Joseph Kopechne]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Joseph Kopechne
Context triple: [Gwen Kopechne, spouse, Joseph Kopechne]
  • A. Joseph Kopechne chosen
    Joseph Kopechne was the father of Mary Jo Kopechne, the young political campaign worker who died in the 1969 Chappaquiddick incident involving Senator Ted Kennedy.
  • B. Karol J. Bobko
    Karol J. Bobko was an American astronaut and Air Force officer who flew on three Space Shuttle missions and became the first commander of Space Shuttle Atlantis.
  • C. Zhozef Kotin
    Zhozef Kotin was a prominent Soviet tank designer best known for leading the development of several heavy tanks used during World War II.
  • D. Raymond Kopaszewski
    Raymond Kopaszewski, better known as Raymond Kopa, was a legendary French footballer renowned for his playmaking brilliance with Stade de Reims and Real Madrid in the 1950s.
  • E. Victor Slezak
    Victor Slezak is an American actor known for his work in film, television, and theater, including roles in dramas such as "The Bridges of Madison County."
  • 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_69c6884d350081908d8a970e4d40ad78 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6da1aa9c48190b63a04be2ed9e266 completed March 27, 2026, 7:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69c769f6340c8190adab3e28cfe67e4a completed March 28, 2026, 5:41 a.m.
Created at: March 27, 2026, 2:27 p.m.