Triple

T19898074
Position Surface form Disambiguated ID Type / Status
Subject Beatrice of Lorraine E478203 entity
Predicate residence P75 FINISHED
Object Canossa NE NERFINISHED

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: Canossa | Statement: [Beatrice of Lorraine, residence, Canossa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Canossa
Context triple: [Beatrice of Lorraine, residence, Canossa]
  • A. Canossa chosen
    Canossa is a historic village in northern Italy best known for the 1077 "Walk to Canossa," when Holy Roman Emperor Henry IV sought absolution from Pope Gregory VII at its castle.
  • B. Gujan-Mestras
    Gujan-Mestras is a coastal commune in southwestern France known for its oyster farming and location along the Arcachon Bay.
  • C. Canossa Column
    The Canossa Column is a historical monument in Bad Harzburg, Germany, commemorating Emperor Henry IV’s Walk to Canossa and symbolizing the medieval conflict between secular and papal power.
  • D. Resaena
    Resaena was an ancient city in northern Mesopotamia, strategically located on key trade and military routes between the Roman and Persian empires.
  • E. Azaña
    Azaña is the surname of Manuel Azaña, a prominent Spanish politician and writer who served as President of the Second Spanish Republic.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8e520682081909892916424699bd5 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6593ef8dc8190be5b64988eceafac completed April 20, 2026, 4:50 p.m.
Created at: April 10, 2026, 1:52 p.m.