Triple

T5033791
Position Surface form Disambiguated ID Type / Status
Subject Roger I of Sicily E113370 entity
Predicate title P38 FINISHED
Object Count of Sicily E99664 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: Count of Sicily | Statement: [Roger I of Sicily, title, Count of Sicily]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Count of Sicily
Context triple: [Roger I of Sicily, title, Count of Sicily]
  • A. King of Naples
    The King of Naples was the sovereign ruler of the historical Kingdom of Naples in southern Italy, a title held at various times by different European dynasties.
  • B. Count of Calabria chosen
    Count of Calabria was a medieval noble title in southern Italy associated with Norman rule and later held by rulers such as Roger I of Sicily.
  • C. County of Sicily
    The County of Sicily was a Norman-ruled medieval state in southern Italy that served as the political foundation for the later Kingdom of Sicily.
  • D. Kings of Parma
    Kings of Parma were the monarchs of the Duchy of Parma, an Italian state historically ruled by members of prominent European dynasties such as the Bourbons.
  • E. El Maasara
    El Maasara is a district and suburban area in the southern part of Greater Cairo, Egypt, known for its residential neighborhoods and industrial zones.
  • 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_69bd443775e48190a646ffbfc4334723 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd73b68d8c8190b8e04fb406abdb0f completed March 20, 2026, 4:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69bea477efec8190a84a0186f5517a43 completed March 21, 2026, 2 p.m.
Created at: March 20, 2026, 1:36 p.m.