Triple

T11007862
Position Surface form Disambiguated ID Type / Status
Subject gens Aemilia E260166 entity
Predicate hasCognomen P6662 FINISHED
Object Barbula
Barbula was a cognomen of the ancient Roman gens Aemilia, borne by several members of this prominent patrician family.
 E900026 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: Barbula | Statement: [gens Aemilia, hasCognomen, Barbula]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Barbula
Context triple: [gens Aemilia, hasCognomen, Barbula]
  • A. Gomba
    Gomba is a district within the Buganda region of central Uganda, known primarily for its rural communities and agricultural activities.
  • B. Naubise
    Naubise is a small but important town in central Nepal that serves as a key junction and gateway between Kathmandu and the country’s western regions.
  • C. Baflo
    Baflo is a village in the Dutch province of Groningen, known for its historic church and rural character.
  • D. Scallabis
    Scallabis was the ancient Roman name for the city now known as Santarém in central Portugal, an important settlement in the Roman province of Lusitania.
  • E. Borzna
    Borzna is a historic town in northern Ukraine, known as a former regional center within various administrative divisions over the centuries.
  • 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: Barbula
Triple: [gens Aemilia, hasCognomen, Barbula]
Generated description
Barbula was a cognomen of the ancient Roman gens Aemilia, borne by several members of this prominent patrician family.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Barbula
Target entity description: Barbula was a cognomen of the ancient Roman gens Aemilia, borne by several members of this prominent patrician family.
  • A. Gomba
    Gomba is a district within the Buganda region of central Uganda, known primarily for its rural communities and agricultural activities.
  • B. Naubise
    Naubise is a small but important town in central Nepal that serves as a key junction and gateway between Kathmandu and the country’s western regions.
  • C. Baflo
    Baflo is a village in the Dutch province of Groningen, known for its historic church and rural character.
  • D. Scallabis
    Scallabis was the ancient Roman name for the city now known as Santarém in central Portugal, an important settlement in the Roman province of Lusitania.
  • E. Borzna
    Borzna is a historic town in northern Ukraine, known as a former regional center within various administrative divisions over the centuries.
  • 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_69d6aa9687448190b28d353b1b6a610e completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d79757bdcc8190900b267826eece21 completed April 9, 2026, 12:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69e37486b23081909ad282397c50a913 completed April 18, 2026, 12:09 p.m.
NEDg Description generation batch_69e37ab6ca788190ac41f9494ad9a47f completed April 18, 2026, 12:36 p.m.
NED2 Entity disambiguation (via description) batch_69e37c9439fc8190a69cfb1a13da4c19 completed April 18, 2026, 12:44 p.m.
Created at: April 8, 2026, 9:25 p.m.