Triple

T15737498
Position Surface form Disambiguated ID Type / Status
Subject Annia Aurelia Galeria Lucilla E381510 entity
Predicate nobleTitle P914 FINISHED
Object Augusta
Augusta was an honorific title used in ancient Rome to designate an empress or highly esteemed imperial woman.
E196016 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: Augusta | Statement: [Annia Aurelia Galeria Lucilla, nobleTitle, Augusta]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Augusta
Context triple: [Annia Aurelia Galeria Lucilla, nobleTitle, Augusta]
  • A. Augusta
    Augusta is the given first name of Ada Lovelace, the 19th-century mathematician often regarded as the world's first computer programmer.
  • B. Augusta
    Augusta is a rural township in eastern Ontario, Canada, located along the St. Lawrence River in the United Counties of Leeds and Grenville.
  • C. Augusta
    Augusta is a coastal town and important industrial and port center in southeastern Sicily, Italy.
  • D. Augusta
    Augusta is a noblewoman historically recognized as the daughter of Galla.
  • E. Augusta
    Augusta is a feminine given name of Latin origin, historically used in English-speaking countries and often associated with dignity or grandeur.
  • 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: Augusta
Triple: [Annia Aurelia Galeria Lucilla, nobleTitle, Augusta]
Generated description
Augusta was an honorific title used in ancient Rome to designate an empress or highly esteemed imperial woman.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Augusta
Target entity description: Augusta was an honorific title used in ancient Rome to designate an empress or highly esteemed imperial woman.
  • A. Augusta chosen
    Augusta was an honorific title used for empresses and other high-ranking women in the Roman and Byzantine Empires, signifying imperial dignity and status.
  • B. Augusta
    Augusta is a feminine given name of Latin origin, historically used in English-speaking countries and often associated with dignity or grandeur.
  • C. Augusta
    Augusta is a noblewoman historically recognized as the daughter of Galla.
  • D. Augusta
    Augusta is the given first name of Ada Lovelace, the 19th-century mathematician often regarded as the world's first computer programmer.
  • E. Augusta
    Augusta is the first name of Lady Gregory, the influential Irish dramatist, folklorist, and co-founder of Dublin’s Abbey Theatre.
  • F. None of above.

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_69d86d9cdb648190bf3171be0bd7d872 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e04fd6eb888190b7a9b07b76e62c0d completed April 16, 2026, 2:56 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff9981e0d081909617b5d686905d3a completed May 9, 2026, 8:30 p.m.
NEDg Description generation batch_69ff9d4c62f08190ae6f87946272177f completed May 9, 2026, 8:47 p.m.
NED2 Entity disambiguation (via description) batch_69ff9dec2b988190878d7f59a638ecaa completed May 9, 2026, 8:49 p.m.
Created at: April 10, 2026, 4:46 a.m.