Triple

T8915340
Position Surface form Disambiguated ID Type / Status
Subject gens Cornelia E212281 entity
Predicate hasCognomen P6662 FINISHED
Object Balbus E710717 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: Balbus | Statement: [gens Cornelia, hasCognomen, Balbus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Balbus
Context triple: [gens Cornelia, hasCognomen, Balbus]
  • A. Balbus chosen
    Balbus is a Roman cognomen historically borne by several notable individuals in the late Roman Republic and early Empire.
  • B. George Blagowidow
    George Blagowidow is a publisher and entrepreneur best known as the founder of the American mass-market paperback imprint Berkley Books.
  • C. Emenius Sleepus
    Emenius Sleepus is a song by the American punk rock band Green Day from their breakthrough 1994 album "Dookie."
  • D. Siricius
    Siricius was a late 4th-century Bishop of Rome recognized as one of the first popes to issue formal decretals that helped shape early canon law.
  • E. Cydamus
    Cydamus is the ancient Roman name for the oasis town now known as Ghadamès in western Libya.
  • 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_69ca8393b1808190bd4336787ffa2c40 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc660f6a088190b0af829ea809d8ad completed April 1, 2026, 12:25 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfba4102e881908441669e14e5c491 completed April 3, 2026, 1:01 p.m.
Created at: March 30, 2026, 6:56 p.m.