Triple

T131591
Position Surface form Disambiguated ID Type / Status
Subject John von Neumann E2665 entity
Predicate givenName P17 FINISHED
Object János E14792 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: János | Statement: [John von Neumann, givenName, János]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: János
Context triple: [John von Neumann, givenName, János]
  • A. Ľubomír Višňovský
    Ľubomír Višňovský is a Slovak former professional ice hockey defenseman known for his offensive skills and successful NHL career with teams such as the Los Angeles Kings, Edmonton Oilers, Anaheim Ducks, and New York Islanders.
  • B. Vojtech Tuka
    Vojtech Tuka was a leading Slovak nationalist politician and Nazi collaborator who served as prime minister of the wartime Slovak state and was later executed for war crimes.
  • C. Peter Šťastný
    Peter Šťastný is a Hall of Fame Slovak ice hockey center renowned for his prolific NHL career and status as one of the greatest European players in the sport’s history.
  • D. Aribert chosen
    Aribert is a Germanic given name, historically borne by medieval nobles and clergy, derived from elements meaning "army" and "bright."
  • E. Theodor
    Theodor "Ted" Nelson is an American pioneer of information technology best known for coining the term "hypertext" and envisioning global hyperlinked document systems.
  • 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_69a2520c0f3481908b0ed054a2fca8d0 completed Feb. 28, 2026, 2:25 a.m.
NER Named-entity recognition batch_69a25785ad5c819097c00f31719fea7e completed Feb. 28, 2026, 2:48 a.m.
NED1 Entity disambiguation (via context triple) batch_69a2b85e7e4881909322c67388d64247 completed Feb. 28, 2026, 9:41 a.m.
Created at: Feb. 28, 2026, 2:30 a.m.