Triple

T3117000
Position Surface form Disambiguated ID Type / Status
Subject Julia Livilla E65086 entity
Predicate spouse P13 FINISHED
Object Marcus Vinicius
Marcus Vinicius was a Roman senator and aristocrat of the early Imperial period, known for his marriage into the Julio-Claudian dynasty.
 E329610 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: Marcus Vinicius | Statement: [Julia Livilla, spouse, Marcus Vinicius]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Marcus Vinicius
Context triple: [Julia Livilla, spouse, Marcus Vinicius]
  • A. Cícero Dias
    Cícero Dias was a prominent Brazilian modernist painter known for his vibrant, dreamlike compositions and contributions to 20th-century Latin American art.
  • B. Lúcio
    Lúcio is a Brazilian architect and urban planner best known as the principal designer of Brasília, the country’s modernist capital city.
  • C. Horácio
    Horácio is the Portuguese form of the name Horace, historically associated with the Roman poet Quintus Horatius Flaccus.
  • D. Flaminio
    Flaminio is a central district of Rome known for its cultural institutions, modern architecture, and proximity to the Tiber River and major city landmarks.
  • E. Marcus Viscidi
    Marcus Viscidi is a film producer known for his work on major studio projects, including the erotic romantic drama sequel "Fifty Shades Darker."
  • 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: Marcus Vinicius
Triple: [Julia Livilla, spouse, Marcus Vinicius]
Generated description
Marcus Vinicius was a Roman senator and aristocrat of the early Imperial period, known for his marriage into the Julio-Claudian dynasty.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Marcus Vinicius
Target entity description: Marcus Vinicius was a Roman senator and aristocrat of the early Imperial period, known for his marriage into the Julio-Claudian dynasty.
  • A. Cícero Dias
    Cícero Dias was a prominent Brazilian modernist painter known for his vibrant, dreamlike compositions and contributions to 20th-century Latin American art.
  • B. Lúcio
    Lúcio is a Brazilian architect and urban planner best known as the principal designer of Brasília, the country’s modernist capital city.
  • C. Horácio
    Horácio is the Portuguese form of the name Horace, historically associated with the Roman poet Quintus Horatius Flaccus.
  • D. Flaminio
    Flaminio is a central district of Rome known for its cultural institutions, modern architecture, and proximity to the Tiber River and major city landmarks.
  • E. Marcus Viscidi
    Marcus Viscidi is a film producer known for his work on major studio projects, including the erotic romantic drama sequel "Fifty Shades Darker."
  • F. None of above. chosen

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_69ad857fcc088190b0c4d45a5cde6f61 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada4e5d1488190a2ab199625fdf05d completed March 8, 2026, 4:33 p.m.
NED1 Entity disambiguation (via context triple) batch_69b20f606fc881908754a78e6aa2de64 completed March 12, 2026, 12:57 a.m.
NEDg Description generation batch_69b2134b5eac8190adadc4a27cfe10c7 completed March 12, 2026, 1:13 a.m.
NED2 Entity disambiguation (via description) batch_69b216fcb1a881908edeadc639de31ae completed March 12, 2026, 1:29 a.m.
Created at: March 8, 2026, 3:04 p.m.