Triple

T1901252
Position Surface form Disambiguated ID Type / Status
Subject Moesia E37692 entity
Predicate importantCity P3940 FINISHED
Object Oescus
Oescus was an important ancient Roman city and military base in the province of Moesia, located near the Danube River in what is now northern Bulgaria.
 E211819 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: Oescus | Statement: [Moesia, importantCity, Oescus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Oescus
Context triple: [Moesia, importantCity, Oescus]
  • A. Viadrus
    Viadrus is the ancient Latin name historically used to refer to the Oder River in Central Europe.
  • B. Caesonia
    Caesonia is a Roman cognomen (family name) used by women of the gens Atia in ancient Rome.
  • C. Bernicia
    Bernicia was an early medieval Anglo-Saxon kingdom in northern Britain that later became part of the larger kingdom of Northumbria.
  • D. Paeligni
    The Paeligni were an ancient Italic tribe of central Italy, closely associated with the Samnites and known for their role in early Roman history and the Social War.
  • E. Derbion
    Derbion is a major retail and leisure shopping centre located in the city centre of Derby, England.
  • 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: Oescus
Triple: [Moesia, importantCity, Oescus]
Generated description
Oescus was an important ancient Roman city and military base in the province of Moesia, located near the Danube River in what is now northern Bulgaria.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Oescus
Target entity description: Oescus was an important ancient Roman city and military base in the province of Moesia, located near the Danube River in what is now northern Bulgaria.
  • A. Viadrus
    Viadrus is the ancient Latin name historically used to refer to the Oder River in Central Europe.
  • B. Caesonia
    Caesonia is a Roman cognomen (family name) used by women of the gens Atia in ancient Rome.
  • C. Bernicia
    Bernicia was an early medieval Anglo-Saxon kingdom in northern Britain that later became part of the larger kingdom of Northumbria.
  • D. Paeligni
    The Paeligni were an ancient Italic tribe of central Italy, closely associated with the Samnites and known for their role in early Roman history and the Social War.
  • E. Derbion
    Derbion is a major retail and leisure shopping centre located in the city centre of Derby, England.
  • 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_69a8861be7148190a680937ec451a304 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69abb18da27c8190b315b462c857f4c2 completed March 7, 2026, 5:03 a.m.
NED1 Entity disambiguation (via context triple) batch_69adeaf558148190b920693e2348190f completed March 8, 2026, 9:32 p.m.
NEDg Description generation batch_69adebafc474819092f9e2ec9768cf3f completed March 8, 2026, 9:35 p.m.
NED2 Entity disambiguation (via description) batch_69adec28f9188190a58e1a9d792943f6 completed March 8, 2026, 9:37 p.m.
Created at: March 4, 2026, 7:35 p.m.