Triple

T11887726
Position Surface form Disambiguated ID Type / Status
Subject Licinius II E282830 entity
Predicate motherTitle P19833 FINISHED
Object Augusta
Augusta was an honorific title used in the Roman Empire to designate an empress or other 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: [Licinius II, motherTitle, Augusta]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Augusta
Context triple: [Licinius II, motherTitle, 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: [Licinius II, motherTitle, Augusta]
Generated description
Augusta was an honorific title used in the Roman Empire to designate an empress or other 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 Empire to designate an empress or other 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_69d6ab2a90b08190a4e818821cc93e6d completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d8d3a13370819086386fecb99e4f0b completed April 10, 2026, 10:40 a.m.
NED1 Entity disambiguation (via context triple) batch_69f417e919548190acbc248879f957ec completed May 1, 2026, 3:03 a.m.
NEDg Description generation batch_69f41f1abaa481908b8a6873a07af848 completed May 1, 2026, 3:33 a.m.
NED2 Entity disambiguation (via description) batch_69f422778a10819093bc2473ef30fe71 completed May 1, 2026, 3:48 a.m.
Created at: April 8, 2026, 9:44 p.m.