Triple

T11990401
Position Surface form Disambiguated ID Type / Status
Subject Aelia Eudocia E285388 entity
Predicate title P38 FINISHED
Object Augusta
Augusta was an honorific title used in the Roman and Byzantine Empires 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: [Aelia Eudocia, title, Augusta]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Augusta
Context triple: [Aelia Eudocia, title, 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 small coastal town in the far southwest of Western Australia, known for its scenic coastline, proximity to Cape Leeuwin, and role as a popular tourist and fishing destination.
  • 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: [Aelia Eudocia, title, Augusta]
Generated description
Augusta was an honorific title used in the Roman and Byzantine Empires 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 the Roman and Byzantine Empires 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 noblewoman historically recognized as the daughter of Galla.
  • C. Augusta
    Augusta is the given first name of Ada Lovelace, the 19th-century mathematician often regarded as the world's first computer programmer.
  • D. Augusta
    Augusta is the first name of Lady Gregory, the influential Irish dramatist, folklorist, and co-founder of Dublin’s Abbey Theatre.
  • E. Augusta
    Augusta is a coastal town and important industrial and port center in southeastern Sicily, Italy.
  • 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_69d6ab44a77c8190a652f4b27164e4ef completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d903afe4388190a2cf2328e85adf9b completed April 10, 2026, 2:05 p.m.
NED1 Entity disambiguation (via context triple) batch_69f471c931a88190a9d29262c62b9472 completed May 1, 2026, 9:26 a.m.
NEDg Description generation batch_69f47b7c5af08190ab0bff1232530a0c completed May 1, 2026, 10:07 a.m.
NED2 Entity disambiguation (via description) batch_69f47dd51e648190bddd41766221e22d completed May 1, 2026, 10:17 a.m.
Created at: April 8, 2026, 9:46 p.m.