Triple

T11212173
Position Surface form Disambiguated ID Type / Status
Subject Venta Belgarum E265334 entity
Predicate connectedTo P37 FINISHED
Object Sorbiodunum
Sorbiodunum was a Roman-era settlement and fort in southern Britain, located near modern Old Sarum in Wiltshire.
 E912035 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: Sorbiodunum | Statement: [Venta Belgarum, connectedTo, Sorbiodunum]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sorbiodunum
Context triple: [Venta Belgarum, connectedTo, Sorbiodunum]
  • A. Borgosesia
    Borgosesia is a town in the Piedmont region of northern Italy, situated in the Valsesia area and known for its textile industry and scenic Alpine surroundings.
  • B. Rhodogune
    Rhodogune was an Achaemenid Persian queen, known primarily as the mother of King Darius I of Persia.
  • C. Orbiana
    Orbiana was a Roman empress of the 3rd century, briefly married to Emperor Severus Alexander before falling victim to court intrigues that led to her exile.
  • D. Grombalia
    Grombalia is a town in northeastern Tunisia known for its agricultural production, particularly vineyards and olive groves.
  • E. Dertosa
    Dertosa is the ancient Roman name for the city now known as Tortosa, located in Catalonia, Spain, which served as an important settlement along the Ebro River.
  • 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: Sorbiodunum
Triple: [Venta Belgarum, connectedTo, Sorbiodunum]
Generated description
Sorbiodunum was a Roman-era settlement and fort in southern Britain, located near modern Old Sarum in Wiltshire.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sorbiodunum
Target entity description: Sorbiodunum was a Roman-era settlement and fort in southern Britain, located near modern Old Sarum in Wiltshire.
  • A. Borgosesia
    Borgosesia is a town in the Piedmont region of northern Italy, situated in the Valsesia area and known for its textile industry and scenic Alpine surroundings.
  • B. Rhodogune
    Rhodogune was an Achaemenid Persian queen, known primarily as the mother of King Darius I of Persia.
  • C. Orbiana
    Orbiana was a Roman empress of the 3rd century, briefly married to Emperor Severus Alexander before falling victim to court intrigues that led to her exile.
  • D. Grombalia
    Grombalia is a town in northeastern Tunisia known for its agricultural production, particularly vineyards and olive groves.
  • E. Dertosa
    Dertosa is the ancient Roman name for the city now known as Tortosa, located in Catalonia, Spain, which served as an important settlement along the Ebro River.
  • 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_69d6aac59460819089b9848b27f57848 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e8d6f5d4819086dcb776a0d469e8 completed April 9, 2026, 5:58 p.m.
NED1 Entity disambiguation (via context triple) batch_69e497569efc8190b8e9cb6b1db3f94d completed April 19, 2026, 8:50 a.m.
NEDg Description generation batch_69e49c0a92b08190ac5debb7d67ca776 completed April 19, 2026, 9:10 a.m.
NED2 Entity disambiguation (via description) batch_69e49e8dc4ec81908d0defe77827d197 completed April 19, 2026, 9:21 a.m.
Created at: April 8, 2026, 9:30 p.m.