Triple

T4558883
Position Surface form Disambiguated ID Type / Status
Subject Roman magistracy E120545 entity
Predicate hasOffice P1268 FINISHED
Object aedile
An aedile was a Roman public official responsible for overseeing city infrastructure, public games, markets, and the maintenance of order in urban life.
 E453181 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: aedile | Statement: [Roman magistracy, hasOffice, aedile]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: aedile
Context triple: [Roman magistracy, hasOffice, aedile]
  • A. Aelius
    Aelius is an ancient Roman family name (nomen) associated with several notable figures of the Roman Empire, including emperors and high-ranking officials.
  • B. Ade
    Ade is a British actor best known for his role as Tyrone in the 2000 crime film "Snatch."
  • C. Aisch
    The Aisch is a river in the German state of Bavaria that flows through the region of Middle Franconia and is known for its scenic valleys and traditional carp-farming areas.
  • D. Amed
    Amed is the historical name of the city now known as Diyarbakır, a major cultural and political center in southeastern Turkey, especially significant for Kurdish heritage.
  • E. Augustoritum
    Augustoritum was the ancient Roman city that later became modern-day Limoges in central France.
  • 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: aedile
Triple: [Roman magistracy, hasOffice, aedile]
Generated description
An aedile was a Roman public official responsible for overseeing city infrastructure, public games, markets, and the maintenance of order in urban life.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: aedile
Target entity description: An aedile was a Roman public official responsible for overseeing city infrastructure, public games, markets, and the maintenance of order in urban life.
  • A. Aelius
    Aelius is an ancient Roman family name (nomen) associated with several notable figures of the Roman Empire, including emperors and high-ranking officials.
  • B. Ade
    Ade is a British actor best known for his role as Tyrone in the 2000 crime film "Snatch."
  • C. Aisch
    The Aisch is a river in the German state of Bavaria that flows through the region of Middle Franconia and is known for its scenic valleys and traditional carp-farming areas.
  • D. Amed
    Amed is the historical name of the city now known as Diyarbakır, a major cultural and political center in southeastern Turkey, especially significant for Kurdish heritage.
  • E. Augustoritum
    Augustoritum was the ancient Roman city that later became modern-day Limoges in central France.
  • 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_69bd4636f1648190a701445c2fcd9c17 completed March 20, 2026, 1:05 p.m.
NER Named-entity recognition batch_69bd5829cc34819086ad2ae58446502e completed March 20, 2026, 2:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69bdc58c3fb08190ae1bc599d53e6e76 completed March 20, 2026, 10:09 p.m.
NEDg Description generation batch_69bdc975c07c8190b506bf8ece290739 completed March 20, 2026, 10:25 p.m.
NED2 Entity disambiguation (via description) batch_69bdc9f824a081909df0ae6d89fc8448 completed March 20, 2026, 10:28 p.m.
Created at: March 20, 2026, 1:09 p.m.