Triple

T621252
Position Surface form Disambiguated ID Type / Status
Subject Marcus Aurelius E14517 entity
Predicate child P120 FINISHED
Object Lucilla
Lucilla was a Roman imperial princess and daughter of Emperor Marcus Aurelius who became Empress as the wife of Lucius Verus and was later implicated in a plot against her brother Commodus.
 E102305 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: Lucilla | Statement: [Marcus Aurelius, child, Lucilla]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Lucilla
Context triple: [Marcus Aurelius, child, Lucilla]
  • A. Luisa
    Luisa is a feminine given name used in various languages, particularly Romance languages, as a form of the name Louise.
  • B. Clementina
    Clementina is a feminine given name, often considered a variant of Clementine, used in various European and Latin American cultures.
  • C. Hilda
    Hilda is the middle name of Margaret Thatcher, the former Prime Minister of the United Kingdom.
  • D. Lydia
    Lydia was an ancient Iron Age kingdom in western Anatolia, renowned for its wealth, early coinage, and powerful kings such as Croesus.
  • E. Lydia
    Lydia is a woman mentioned in the New Testament book of Acts, known as a dealer in purple cloth from Thyatira and one of the first recorded converts to Christianity in Europe.
  • 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: Lucilla
Triple: [Marcus Aurelius, child, Lucilla]
Generated description
Lucilla was a Roman imperial princess and daughter of Emperor Marcus Aurelius who became Empress as the wife of Lucius Verus and was later implicated in a plot against her brother Commodus.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Lucilla
Target entity description: Lucilla was a Roman imperial princess and daughter of Emperor Marcus Aurelius who became Empress as the wife of Lucius Verus and was later implicated in a plot against her brother Commodus.
  • A. Luisa
    Luisa is a feminine given name used in various languages, particularly Romance languages, as a form of the name Louise.
  • B. Clementina
    Clementina is a feminine given name, often considered a variant of Clementine, used in various European and Latin American cultures.
  • C. Hilda
    Hilda is the middle name of Margaret Thatcher, the former Prime Minister of the United Kingdom.
  • D. Lydia
    Lydia was an ancient Iron Age kingdom in western Anatolia, renowned for its wealth, early coinage, and powerful kings such as Croesus.
  • E. Lydia
    Lydia is a woman mentioned in the New Testament book of Acts, known as a dealer in purple cloth from Thyatira and one of the first recorded converts to Christianity in Europe.
  • 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_69a4934b17c881909ace8270e8ddd202 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a49e3e5d80819096e72e11b533f931 completed March 1, 2026, 8:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69a7a3a48ac88190bea34fc7df8b503e completed March 4, 2026, 3:14 a.m.
NEDg Description generation batch_69a7a533ce808190b4667c9485bac49d completed March 4, 2026, 3:21 a.m.
NED2 Entity disambiguation (via description) batch_69a7a5c2a95c8190b0d0a385ef035880 completed March 4, 2026, 3:23 a.m.
Created at: March 1, 2026, 7:35 p.m.