Triple

T1704046
Position Surface form Disambiguated ID Type / Status
Subject Julius Caesar E36828 entity
Predicate spouse P13 FINISHED
Object Cornelia E162833 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: Cornelia | Statement: [Julius Caesar, spouse, Cornelia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cornelia
Context triple: [Julius Caesar, spouse, Cornelia]
  • A. Cornelia chosen
    Cornelia is a feminine given name of Latin origin, historically associated with several notable women in European history.
  • B. Julia Livilla
    Julia Livilla was a Roman imperial princess of the Julio-Claudian dynasty, known as the sister of Emperor Caligula and for her involvement in the turbulent politics of the early Roman Empire.
  • C. Arria
    Arria is a family of mid-range field-programmable gate arrays (FPGAs) developed by Altera (now part of Intel) for high-performance, power-efficient digital logic applications.
  • D. Clementina
    Clementina is a feminine given name, often considered a variant of Clementine, used in various European and Latin American cultures.
  • E. Livia Stone
    Livia Stone is the wife of Biz Stone, the co-founder of Twitter and a prominent American entrepreneur.
  • 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_69a88617439c819094ffb5d16a0f6307 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69aa62f25bac8190977d6f3bd79363cb completed March 6, 2026, 5:15 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad8acf74848190a18e41988647edcd completed March 8, 2026, 2:42 p.m.
Created at: March 4, 2026, 7:30 p.m.