Triple

T11592146
Position Surface form Disambiguated ID Type / Status
Subject Constance of Aragon E274906 entity
Predicate placeOfDeath P21 FINISHED
Object Catania E82307 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: Catania | Statement: [Constance of Aragon, placeOfDeath, Catania]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Catania
Context triple: [Constance of Aragon, placeOfDeath, Catania]
  • A. Catania chosen
    Catania is a historic port city on the eastern coast of Sicily, Italy, known for its Baroque architecture and proximity to Mount Etna.
  • B. Palermo
    Palermo is a large, upscale neighborhood in Buenos Aires known for its parks, nightlife, cultural attractions, and trendy dining and shopping areas.
  • C. Palermo
    Palermo is a 90 nm, low-power, budget-oriented core used in AMD's Sempron line of processors.
  • D. Palermo
    Palermo is an unincorporated community and census-designated place within Upper Township in Cape May County, New Jersey, known for its residential character and proximity to the Jersey Shore.
  • E. Palermo
    Palermo is the historic capital of Sicily, renowned for its rich multicultural heritage, including a significant medieval Jewish presence, and its blend of Arab-Norman architecture, vibrant markets, and coastal setting.
  • 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_69d6aae6b14c81908dc5a74bad7591f9 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8946594348190935106132fd18028 completed April 10, 2026, 6:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69f716adaed081909a6c026f9e232381 completed May 3, 2026, 9:34 a.m.
Created at: April 8, 2026, 9:38 p.m.