Triple

T13761493
Position Surface form Disambiguated ID Type / Status
Subject Ancient Roman nomen E330619 entity
Predicate example P1259 FINISHED
Object Cornelius E233935 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: Cornelius | Statement: [Ancient Roman nomen, example, Cornelius]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cornelius
Context triple: [Ancient Roman nomen, example, Cornelius]
  • A. Cornelius
    Cornelius is the given first name of Connie Mack, the legendary early 20th-century Major League Baseball manager and team owner.
  • B. Cornelius chosen
    Cornelius is the ancient Roman gens (clan) to which the dictator Lucius Cornelius Sulla belonged.
  • C. Cornelius
    Cornelius is a masculine given name of Latin origin, historically associated with Roman families and later adopted in various European and English-speaking cultures.
  • D. Cornelius the centurion
    Cornelius the centurion is a Roman army officer in the New Testament whose conversion in Acts marks a pivotal moment in the early Christian mission to Gentiles.
  • E. Henry Cornelius
    Henry Cornelius was a British film director best known for his work on classic mid-20th-century comedies produced by Ealing Studios.
  • 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_69d81c573f288190aa2403d484fa3d49 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de02250f4881908d5193b3d5d25844 completed April 14, 2026, 9 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7a8606dbc8190b0f7c38583986141 completed May 3, 2026, 7:56 p.m.
Created at: April 9, 2026, 10:09 p.m.