Triple

T1940030
Position Surface form Disambiguated ID Type / Status
Subject Africa Proconsularis E41531 entity
Predicate hasPart P35 FINISHED
Object Byzacena
Byzacena was a Roman province in North Africa, centered in what is now central and eastern Tunisia, known for its agricultural productivity and important cities such as Hadrumetum.
 E216961 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: Byzacena | Statement: [Africa Proconsularis, hasPart, Byzacena]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Byzacena
Context triple: [Africa Proconsularis, hasPart, Byzacena]
  • A. Baniata
    Baniata is an Oceanic language of the Meso-Melanesian group spoken in the Solomon Islands.
  • B. Orzola
    Orzola is a small fishing village and port at the northern tip of Lanzarote in the Canary Islands, known as the main departure point for ferries to the nearby island of La Graciosa.
  • C. Zimeysa
    Zimeysa is a railway station in the canton of Geneva, Switzerland, serving local and regional train services on the Geneva–La Plaine line.
  • D. Barbalha
    Barbalha is a municipality in northeastern Brazil known for its traditional cultural festivals and location in the state of Ceará.
  • E. Zenati
    Zenati is a branch of the Northern Berber languages spoken in North Africa, encompassing several closely related dialect groups.
  • 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: Byzacena
Triple: [Africa Proconsularis, hasPart, Byzacena]
Generated description
Byzacena was a Roman province in North Africa, centered in what is now central and eastern Tunisia, known for its agricultural productivity and important cities such as Hadrumetum.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Byzacena
Target entity description: Byzacena was a Roman province in North Africa, centered in what is now central and eastern Tunisia, known for its agricultural productivity and important cities such as Hadrumetum.
  • A. Baniata
    Baniata is an Oceanic language of the Meso-Melanesian group spoken in the Solomon Islands.
  • B. Orzola
    Orzola is a small fishing village and port at the northern tip of Lanzarote in the Canary Islands, known as the main departure point for ferries to the nearby island of La Graciosa.
  • C. Zimeysa
    Zimeysa is a railway station in the canton of Geneva, Switzerland, serving local and regional train services on the Geneva–La Plaine line.
  • D. Barbalha
    Barbalha is a municipality in northeastern Brazil known for its traditional cultural festivals and location in the state of Ceará.
  • E. Zenati
    Zenati is a branch of the Northern Berber languages spoken in North Africa, encompassing several closely related dialect groups.
  • 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_69a88649b24c819080047f26b6db2ded completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69abb2ca385c8190ad0e4bafbb9b5e5c completed March 7, 2026, 5:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69adf3f81e0c819090e3f2154215ff18 completed March 8, 2026, 10:11 p.m.
NEDg Description generation batch_69adf4e94b5081909d4010612d81b917 completed March 8, 2026, 10:15 p.m.
NED2 Entity disambiguation (via description) batch_69adf60463d88190896cedb2b45a67ed completed March 8, 2026, 10:19 p.m.
Created at: March 4, 2026, 7:36 p.m.