Triple

T15981725
Position Surface form Disambiguated ID Type / Status
Subject Graz Cathedral E387591 entity
Predicate nativeName P15 FINISHED
Object Grazer Dom E387591 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: Grazer Dom | Statement: [Graz Cathedral, nativeName, Grazer Dom]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Grazer Dom
Context triple: [Graz Cathedral, nativeName, Grazer Dom]
  • A. Stadelheim
    Stadelheim is a district in Munich, Germany, best known for housing the large and historically significant Stadelheim Prison.
  • B. Krailling
    Krailling is a municipality in the district of Starnberg in Bavaria, Germany, known as a residential community within the Munich metropolitan area.
  • C. Graz Cathedral chosen
    Graz Cathedral is a prominent Gothic-style Roman Catholic cathedral in Graz, Austria, known for its historic architecture and richly decorated interior.
  • D. Graz Opera House
    Graz Opera House is a historic and architecturally significant opera and theatre venue in Graz, Austria, renowned for its classical repertoire and cultural importance.
  • E. Landhaus Graz
    Landhaus Graz is a historic Renaissance-style palace in Graz, Austria, renowned for its arcaded courtyard and role as the seat of the Styrian provincial government.
  • 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_69d86da94ccc819083d187f5dc6a123e completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e15754e8648190a93b73184db089a7 completed April 16, 2026, 9:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffc3cb0ed48190b35c19f3961f183b completed May 9, 2026, 11:31 p.m.
Created at: April 10, 2026, 4:54 a.m.