Triple

T10687573
Position Surface form Disambiguated ID Type / Status
Subject Portland E251918 entity
Predicate hasLandmark P105 FINISHED
Object Verne Citadel E144923 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: Verne Citadel | Statement: [Portland, hasLandmark, Verne Citadel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Verne Citadel
Context triple: [Portland, hasLandmark, Verne Citadel]
  • A. Verne Citadel chosen
    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.
  • B. Corte Citadel
    Corte Citadel is a historic fortified stronghold overlooking the town of Corte in central Corsica, France.
  • C. Citadella
    Citadella is a 19th-century fortress and popular panoramic lookout situated atop Gellért Hill in Budapest, Hungary.
  • D. Fort of the Lion
    Fort of the Lion is the English meaning of the name of Sinhagad Fort, a historic hill fortress near Pune in Maharashtra, India.
  • E. Fort of Exilles
    Fort of Exilles is a historic alpine fortress in Italy’s Susa Valley, long used to control a key passage between Italy and France.
  • 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_69d6aa5bd7c08190a816e733b4045c23 completed April 8, 2026, 7:19 p.m.
NER Named-entity recognition batch_69d6fd19f0f481909eeaa75d17d9c060 completed April 9, 2026, 1:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69d9889d1f988190938be54771161b00 completed April 10, 2026, 11:32 p.m.
Created at: April 8, 2026, 9:10 p.m.