Triple

T6712388
Position Surface form Disambiguated ID Type / Status
Subject Connie Nielsen E153176 entity
Predicate portrayed P1668 FINISHED
Object Lucilla in Gladiator
Lucilla in Gladiator is the politically astute and conflicted daughter of Emperor Marcus Aurelius who navigates loyalty, power, and survival amid her brother Commodus’s tyrannical rule.
E613151 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 in Gladiator | Statement: [Connie Nielsen, portrayed, Lucilla in Gladiator]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lucilla in Gladiator
Context triple: [Connie Nielsen, portrayed, Lucilla in Gladiator]
  • A. Claudia
    Claudia is a feminine given name used in various cultures, derived from the ancient Roman family name Claudius.
  • B. Domina
    Domina is a historical drama television series that chronicles the life and political rise of Livia Drusilla in ancient Rome.
  • C. Livia Stone
    Livia Stone is the wife of Biz Stone, the co-founder of Twitter and a prominent American entrepreneur.
  • D. Lollia
    Lollia was the family name (nomen) of the ancient Roman gens Lollia, to which the noblewoman Lollia Paulina belonged.
  • E. Julias
    Julias was a city in the ancient region of Gaulonitis, near the Sea of Galilee, known from the Roman and New Testament historical context.
  • 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 in Gladiator
Triple: [Connie Nielsen, portrayed, Lucilla in Gladiator]
Generated description
Lucilla in Gladiator is the politically astute and conflicted daughter of Emperor Marcus Aurelius who navigates loyalty, power, and survival amid her brother Commodus’s tyrannical rule.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Lucilla in Gladiator
Target entity description: Lucilla in Gladiator is the politically astute and conflicted daughter of Emperor Marcus Aurelius who navigates loyalty, power, and survival amid her brother Commodus’s tyrannical rule.
  • A. Claudia
    Claudia is a feminine given name used in various cultures, derived from the ancient Roman family name Claudius.
  • B. Domina
    Domina is a historical drama television series that chronicles the life and political rise of Livia Drusilla in ancient Rome.
  • C. Livia Stone
    Livia Stone is the wife of Biz Stone, the co-founder of Twitter and a prominent American entrepreneur.
  • D. Lollia
    Lollia was the family name (nomen) of the ancient Roman gens Lollia, to which the noblewoman Lollia Paulina belonged.
  • E. Julias
    Julias was a city in the ancient region of Gaulonitis, near the Sea of Galilee, known from the Roman and New Testament historical context.
  • 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_69c68809b4608190a2509ddb5ab87f05 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d108acc08190b38b43161d8912b9 completed March 27, 2026, 6:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69c700924fdc8190990187fbc1b3ab20 completed March 27, 2026, 10:11 p.m.
NEDg Description generation batch_69c70386196c81909d46894f783ef87a completed March 27, 2026, 10:24 p.m.
NED2 Entity disambiguation (via description) batch_69c7045cda0481908982c7c7e8dc11e5 completed March 27, 2026, 10:27 p.m.
Created at: March 27, 2026, 2:07 p.m.