Triple

T2100723
Position Surface form Disambiguated ID Type / Status
Subject Lucius Cornelius Sulla E37084 entity
Predicate spouse P13 FINISHED
Object Valeria
Valeria was a Roman noblewoman best known as the last wife of the dictator Lucius Cornelius Sulla during the late Roman Republic.
E241838 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: Valeria | Statement: [Lucius Cornelius Sulla, spouse, Valeria]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Valeria
Context triple: [Lucius Cornelius Sulla, spouse, Valeria]
  • A. Valeria
    Valeria was a Roman imperial princess and later empress, best known as the daughter of Emperor Diocletian and for her tragic fate during the political turmoil of the Tetrarchy.
  • B. Valeria
    Valeria is the clever, sharp-tongued heroine of George Farquhar’s Restoration comedy "The Witty Fair One."
  • C. Luciana
    Luciana is a feminine given name of Latin origin, commonly used in Spanish- and Portuguese-speaking countries.
  • D. Lucia
    Lucia is a feminine given name of Latin origin, commonly associated with light and used in various European cultures.
  • E. Valentina
    Valentina is a feminine given name of Latin origin, commonly used in various countries and associated with meanings related to strength and health.
  • 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: Valeria
Triple: [Lucius Cornelius Sulla, spouse, Valeria]
Generated description
Valeria was a Roman noblewoman best known as the last wife of the dictator Lucius Cornelius Sulla during the late Roman Republic.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Valeria
Target entity description: Valeria was a Roman noblewoman best known as the last wife of the dictator Lucius Cornelius Sulla during the late Roman Republic.
  • A. Valeria
    Valeria was a Roman imperial princess and later empress, best known as the daughter of Emperor Diocletian and for her tragic fate during the political turmoil of the Tetrarchy.
  • B. Valeria
    Valeria is the clever, sharp-tongued heroine of George Farquhar’s Restoration comedy "The Witty Fair One."
  • C. Luciana
    Luciana is a feminine given name of Latin origin, commonly used in Spanish- and Portuguese-speaking countries.
  • D. Lucia
    Lucia is a feminine given name of Latin origin, commonly associated with light and used in various European cultures.
  • E. Valentina
    Valentina is a feminine given name of Latin origin, commonly used in various countries and associated with meanings related to strength and health.
  • 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_69a8861828948190924aa30c08806b3a completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69abbabb512c819087b1d5ec8ef11e63 completed March 7, 2026, 5:42 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae5d8bffd0819095629956f9584222 completed March 9, 2026, 5:41 a.m.
NEDg Description generation batch_69ae5e48eefc8190b459278860bb3217 completed March 9, 2026, 5:44 a.m.
NED2 Entity disambiguation (via description) batch_69ae5ec233788190a52dc1a135f7dfb9 completed March 9, 2026, 5:46 a.m.
Created at: March 4, 2026, 7:43 p.m.