Triple

T14148389
Position Surface form Disambiguated ID Type / Status
Subject Gellért-hegy E350610 entity
Predicate hasStructure P35 FINISHED
Object Citadella E349578 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: Citadella | Statement: [Gellért-hegy, hasStructure, Citadella]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Citadella
Context triple: [Gellért-hegy, hasStructure, Citadella]
  • A. Citadella chosen
    Citadella is a 19th-century fortress and popular panoramic lookout situated atop Gellért Hill in Budapest, Hungary.
  • B. Corte Citadel
    Corte Citadel is a historic fortified stronghold overlooking the town of Corte in central Corsica, France.
  • C. Cittadella
    Cittadella is a medieval walled town in northeastern Italy renowned for its remarkably well-preserved circular fortifications and historic center.
  • D. Citadella fortress
    The Citadella fortress is a 19th-century military stronghold and prominent lookout point in Budapest, offering panoramic views over the city and the Danube River.
  • E. Citadel of Bastia
    The Citadel of Bastia is a historic fortified complex overlooking the old port of Bastia in Corsica, known for its Genoese-era ramparts, narrow streets, and panoramic sea views.
  • 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_69d827865f608190b311820428ae027b completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de61237ef481909374c1f68a2370b7 completed April 14, 2026, 3:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcf7e86820819099d6e3d3d4229f0d completed May 7, 2026, 8:36 p.m.
Created at: April 10, 2026, 12:55 a.m.