Triple

T14670568
Position Surface form Disambiguated ID Type / Status
Subject Battle of Bedriacum E344500 entity
Predicate hasLocation P40 FINISHED
Object Bedriacum
Bedriacum was an ancient Roman settlement in northern Italy, near modern-day Cremona, known as the site of two major battles during the Year of the Four Emperors in 69 CE.
 E1113052 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: Bedriacum | Statement: [Battle of Bedriacum, hasLocation, Bedriacum]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Bedriacum
Context triple: [Battle of Bedriacum, hasLocation, Bedriacum]
  • A. Andecavorum
    Andecavorum is the ancient Latin name for the city now known as Angers in western France.
  • B. Sabagreia
    Sabagreia is a town located within the Kolokuma/Opokuma area of Bayelsa State in Nigeria.
  • C. Berchidda
    Berchidda is a small town in the Gallura region of northern Sardinia, Italy, known for its rural character and traditional Sardinian culture.
  • D. Gesoriacum
    Gesoriacum was the ancient Roman name for the port city later known as Bononia (modern Boulogne-sur-Mer) in northern Gaul, an important maritime and military hub facing Britain.
  • E. Argiletum
    Argiletum was an ancient street in Rome that connected the Roman Forum to the Subura district and later became partly occupied by the Forum of Nerva.
  • 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: Bedriacum
Triple: [Battle of Bedriacum, hasLocation, Bedriacum]
Generated description
Bedriacum was an ancient Roman settlement in northern Italy, near modern-day Cremona, known as the site of two major battles during the Year of the Four Emperors in 69 CE.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Bedriacum
Target entity description: Bedriacum was an ancient Roman settlement in northern Italy, near modern-day Cremona, known as the site of two major battles during the Year of the Four Emperors in 69 CE.
  • A. Andecavorum
    Andecavorum is the ancient Latin name for the city now known as Angers in western France.
  • B. Sabagreia
    Sabagreia is a town located within the Kolokuma/Opokuma area of Bayelsa State in Nigeria.
  • C. Berchidda
    Berchidda is a small town in the Gallura region of northern Sardinia, Italy, known for its rural character and traditional Sardinian culture.
  • D. Gesoriacum
    Gesoriacum was the ancient Roman name for the port city later known as Bononia (modern Boulogne-sur-Mer) in northern Gaul, an important maritime and military hub facing Britain.
  • E. Argiletum
    Argiletum was an ancient street in Rome that connected the Roman Forum to the Subura district and later became partly occupied by the Forum of Nerva.
  • 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_69d822e283fc8190a0e4c235cf880052 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb54ef2908190b189ced65eec434a completed April 14, 2026, 9:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69fde177ced48190a448cbee1f4c75bf completed May 8, 2026, 1:13 p.m.
NEDg Description generation batch_69fde249f1288190ac2e53c26ae7968b completed May 8, 2026, 1:16 p.m.
NED2 Entity disambiguation (via description) batch_69fde2ec348c8190bf5d6f5993d3246c completed May 8, 2026, 1:19 p.m.
Created at: April 10, 2026, 1:27 a.m.