Triple

T2098752
Position Surface form Disambiguated ID Type / Status
Subject Scribonia E37043 entity
Predicate child P120 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: [Scribonia, child, Cornelia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cornelia
Context triple: [Scribonia, child, 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. gens Cornelia
    Gens Cornelia was one of the most prominent and influential patrician families of ancient Rome, producing numerous famous statesmen and generals, including Scipio Africanus.
  • E. Clementina
    Clementina is a feminine given name, often considered a variant of Clementine, used in various European and Latin American cultures.
  • 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_69a8861828948190924aa30c08806b3a completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69abba9de75c81909770409b5ae62c24 completed March 7, 2026, 5:41 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae306386588190a1013c32a9b8e0c1 completed March 9, 2026, 2:28 a.m.
Created at: March 4, 2026, 7:43 p.m.