Triple

T14866206
Position Surface form Disambiguated ID Type / Status
Subject Zugló E349621 entity
Predicate hasLandmark P105 FINISHED
Object Puskás Aréna E574532 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: Puskás Aréna | Statement: [Zugló, hasLandmark, Puskás Aréna]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Puskás Aréna
Context triple: [Zugló, hasLandmark, Puskás Aréna]
  • A. Puskás Aréna chosen
    Puskás Aréna is a modern football stadium in Budapest, Hungary, named after legendary footballer Ferenc Puskás and used for major international matches and tournaments.
  • B. Kaposvár Arena
    Kaposvár Arena is a modern indoor sports and events venue located in the city of Kaposvár, Hungary.
  • C. Szusza Ferenc Stadium
    Szusza Ferenc Stadium is a historic football stadium in Budapest, Hungary, primarily serving as the home ground of Újpest FC.
  • D. Danube Arena
    Danube Arena is a modern indoor swimming and diving complex in Budapest, Hungary, known for hosting major international aquatic competitions.
  • E. Nagyerdei Stadium
    Nagyerdei Stadium is a modern multi-purpose stadium in Debrecen, Hungary, best known as a key venue for major cultural and sporting events in the city.
  • 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_69d822ed7e1881909b90fca143ad7e34 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69ded5761c688190b4477cb081554b51 completed April 15, 2026, 12:01 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe6b5101a48190937a86b6eda79c55 completed May 8, 2026, 11:01 p.m.
Created at: April 10, 2026, 1:55 a.m.