Triple

T3807357
Position Surface form Disambiguated ID Type / Status
Subject Corte E93039 entity
Predicate hasLandmark P105 FINISHED
Object Corte Citadel E391624 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: Corte Citadel | Statement: [Corte, hasLandmark, Corte Citadel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Corte Citadel
Context triple: [Corte, hasLandmark, Corte Citadel]
  • A. Corte Citadel chosen
    Corte Citadel is a historic fortified stronghold overlooking the town of Corte in central Corsica, France.
  • B. Citadella
    Citadella is a 19th-century fortress and popular panoramic lookout situated atop Gellért Hill in Budapest, Hungary.
  • C. Verne Citadel
    Verne Citadel is a 19th-century fortress on the Isle of Portland in Dorset, England, historically used for coastal defense and later as a prison and immigration removal centre.
  • D. Loulé Castle
    Loulé Castle is a medieval fortress in the town of Loulé in Portugal’s Algarve region, known for its preserved walls, towers, and archaeological museum.
  • E. Citadel of Ajaccio
    The Citadel of Ajaccio is a historic coastal fortress in Ajaccio, Corsica, built to defend the town and its harbor and now recognized as a prominent symbol of the city’s heritage.
  • 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_69aed96a60088190ab1df8390fffc935 completed March 9, 2026, 2:30 p.m.
NER Named-entity recognition batch_69aee80b02888190b2d778feef14f576 completed March 9, 2026, 3:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69b503f107148190bf7ce74eb7dee9b2 completed March 14, 2026, 6:45 a.m.
Created at: March 9, 2026, 3:16 p.m.