Triple

T8345624
Position Surface form Disambiguated ID Type / Status
Subject Marcus Junius Brutus E196026 entity
Predicate familyName P18 FINISHED
Object Junius
Junius is the ancient Roman gens (clan) to which the famous senator and Caesar-assassin Marcus Junius Brutus belonged.
E120812 NE FINISHED

How this triple was built (4 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: Junius | Statement: [Marcus Junius Brutus, familyName, Junius]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Junius
Context triple: [Marcus Junius Brutus, familyName, Junius]
  • A. Junius
    Junius is the given name of Junius Brutus Booth, a prominent 19th-century English actor and father of John Wilkes Booth.
  • B. Count Julian
    Count Julian is a legendary Gothic nobleman best known in literature and legend for his pivotal role in the downfall of the Visigothic kingdom in Spain.
  • C. Newton Pulsifer
    Newton Pulsifer is a bumbling yet well-meaning young witchfinder who becomes an unlikely hero in Neil Gaiman and Terry Pratchett’s comic apocalyptic novel *Good Omens*.
  • D. Anastasio
    Anastasio is a masculine given name of Greek origin, commonly used in Spanish-speaking countries and derived from a term meaning "resurrection."
  • E. Éleuthère
    Éleuthère is the given name of Éleuthère Irénée du Pont, the French-American chemist and industrialist who founded the DuPont company in the early 19th century.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Junius
Triple: [Marcus Junius Brutus, familyName, Junius]
Generated description
Junius is the ancient Roman gens (clan) to which the famous senator and Caesar-assassin Marcus Junius Brutus belonged.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Junius
Target entity description: Junius is the ancient Roman gens (clan) to which the famous senator and Caesar-assassin Marcus Junius Brutus belonged.
  • A. Junius chosen
    Junius is the given name of Junius Brutus Booth, a prominent 19th-century English actor and father of John Wilkes Booth.
  • B. Count Julian
    Count Julian is a legendary Gothic nobleman best known in literature and legend for his pivotal role in the downfall of the Visigothic kingdom in Spain.
  • C. Newton Pulsifer
    Newton Pulsifer is a bumbling yet well-meaning young witchfinder who becomes an unlikely hero in Neil Gaiman and Terry Pratchett’s comic apocalyptic novel *Good Omens*.
  • D. Anastasio
    Anastasio is a masculine given name of Greek origin, commonly used in Spanish-speaking countries and derived from a term meaning "resurrection."
  • E. Éleuthère
    Éleuthère is the given name of Éleuthère Irénée du Pont, the French-American chemist and industrialist who founded the DuPont company in the early 19th century.
  • F. None of above.

Provenance (5 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_69ca82edd63c8190b876b8465464c5fa completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb7feef7e8819084ca0441d146bac7 completed March 31, 2026, 8:03 a.m.
NED1 Entity disambiguation (via context triple) batch_69cdc73ccfb481908d0d189362404e09 completed April 2, 2026, 1:32 a.m.
NEDg Description generation batch_69cdcb90bec88190a2c19681405aa13e completed April 2, 2026, 1:51 a.m.
NED2 Entity disambiguation (via description) batch_69cdcd0fc9488190a0a576c385b9bc1f completed April 2, 2026, 1:57 a.m.
Created at: March 30, 2026, 5:58 p.m.