Triple

T8403424
Position Surface form Disambiguated ID Type / Status
Subject Domenico E198432 entity
Predicate relatedName P3889 FINISHED
Object Dominikus E543181 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: Dominikus | Statement: [Domenico, relatedName, Dominikus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dominikus
Context triple: [Domenico, relatedName, Dominikus]
  • A. Dominikus Zimmermann chosen
    Dominikus Zimmermann was an 18th-century German Rococo architect and stuccoist renowned for designing richly ornamented pilgrimage churches in Bavaria.
  • B. Domenico
    Domenico is a masculine given name of Italian origin, historically borne by several notable figures including architects, artists, and religious leaders.
  • C. Dominik
    Dominik is a male given name of Slavic origin, commonly used in Central and Eastern Europe.
  • D. Martino
    Martino is a surname most prominently associated with Argentine football manager and former player Gerardo "Tata" Martino.
  • E. Maffeo
    Maffeo is the given name of Pope Urban VIII, the 17th-century head of the Catholic Church known for his patronage of the arts and involvement in the Galileo affair.
  • 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_69ca8310df9c8190b25f16161cca3e41 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cb82505e0c81909549db59b7c4eb00 completed March 31, 2026, 8:14 a.m.
NED1 Entity disambiguation (via context triple) batch_69ce02ece0a88190bf64abaa8d202de3 completed April 2, 2026, 5:47 a.m.
Created at: March 30, 2026, 6:04 p.m.