Triple

T11334891
Position Surface form Disambiguated ID Type / Status
Subject Marcia E268445 entity
Predicate spouse P13 FINISHED
Object Hortensius
Hortensius was a prominent Roman orator and statesman of the late Republic, renowned for his eloquence and as a contemporary rival of Cicero.
 E918289 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: Hortensius | Statement: [Marcia, spouse, Hortensius]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Hortensius
Context triple: [Marcia, spouse, Hortensius]
  • A. Pomponius
    Pomponius is a figure from early Roman tradition known primarily as a son of the legendary second king of Rome, Numa Pompilius.
  • B. Proculeius
    Proculeius is a loyal Roman officer in Shakespeare’s tragedy "Antony and Cleopatra," known for his role in securing Cleopatra’s surrender on Octavius Caesar’s behalf.
  • C. Caecilius
    Caecilius is the family name of a prominent ancient Roman gens that included influential politicians and military leaders such as Quintus Caecilius Metellus Numidicus.
  • D. Lucilius
    Lucilius was an early Roman satirist, often regarded as the founder of Roman verse satire and a major influence on later satirists like Juvenal.
  • E. Cicero
    Cicero is a rapid transit station in Chicago serving the Chicago Transit Authority’s Blue Line.
  • 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: Hortensius
Triple: [Marcia, spouse, Hortensius]
Generated description
Hortensius was a prominent Roman orator and statesman of the late Republic, renowned for his eloquence and as a contemporary rival of Cicero.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Hortensius
Target entity description: Hortensius was a prominent Roman orator and statesman of the late Republic, renowned for his eloquence and as a contemporary rival of Cicero.
  • A. Pomponius
    Pomponius is a figure from early Roman tradition known primarily as a son of the legendary second king of Rome, Numa Pompilius.
  • B. Proculeius
    Proculeius is a loyal Roman officer in Shakespeare’s tragedy "Antony and Cleopatra," known for his role in securing Cleopatra’s surrender on Octavius Caesar’s behalf.
  • C. Caecilius
    Caecilius is the family name of a prominent ancient Roman gens that included influential politicians and military leaders such as Quintus Caecilius Metellus Numidicus.
  • D. Lucilius
    Lucilius was an early Roman satirist, often regarded as the founder of Roman verse satire and a major influence on later satirists like Juvenal.
  • E. Cicero
    Cicero is a rapid transit station in Chicago serving the Chicago Transit Authority’s Blue Line.
  • 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_69d6aacb1f0881908c84a349fd1be047 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e9ff62c88190a089dd84e2ac1d17 completed April 9, 2026, 6:03 p.m.
NED1 Entity disambiguation (via context triple) batch_69e5263cce588190a91f91cbdf023d5e completed April 19, 2026, 7 p.m.
NEDg Description generation batch_69e52c84518881909e6e2a593348a81a completed April 19, 2026, 7:27 p.m.
NED2 Entity disambiguation (via description) batch_69e531d0ab5881909814160b86c8e76b completed April 19, 2026, 7:49 p.m.
Created at: April 8, 2026, 9:33 p.m.