Triple

T1137478
Position Surface form Disambiguated ID Type / Status
Subject Ladin language E23172 entity
Predicate hasDialect P4251 FINISHED
Object Badiot
Badiot is a regional variety of the Ladin language spoken in parts of the Dolomite region of northern Italy.
 E132659 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: Badiot | Statement: [Ladin language, hasDialect, Badiot]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Badiot
Context triple: [Ladin language, hasDialect, Badiot]
  • A. Bertramus
    Bertramus is a Latinized variant of the given name Bertram, historically used in medieval and ecclesiastical contexts.
  • B. Buda
    Buda is the historic western part of modern-day Budapest, known for its hilly landscape, medieval castle district, and role as a former capital of the Kingdom of Hungary.
  • C. Micali
    Micali is an Italian surname most notably associated with Silvio Micali, a Turing Award–winning computer scientist and cryptographer.
  • D. Sebaste
    Sebaste was an ancient city in the central highlands of Samaria, refounded and expanded by Herod the Great as a major Hellenistic-Roman urban center.
  • E. Abbenes
    Abbenes is a small village in the Dutch province of North Holland, situated within the municipality of Haarlemmermeer.
  • 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: Badiot
Triple: [Ladin language, hasDialect, Badiot]
Generated description
Badiot is a regional variety of the Ladin language spoken in parts of the Dolomite region of northern Italy.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Badiot
Target entity description: Badiot is a regional variety of the Ladin language spoken in parts of the Dolomite region of northern Italy.
  • A. Bertramus
    Bertramus is a Latinized variant of the given name Bertram, historically used in medieval and ecclesiastical contexts.
  • B. Buda
    Buda is the historic western part of modern-day Budapest, known for its hilly landscape, medieval castle district, and role as a former capital of the Kingdom of Hungary.
  • C. Micali
    Micali is an Italian surname most notably associated with Silvio Micali, a Turing Award–winning computer scientist and cryptographer.
  • D. Sebaste
    Sebaste was an ancient city in the central highlands of Samaria, refounded and expanded by Herod the Great as a major Hellenistic-Roman urban center.
  • E. Abbenes
    Abbenes is a small village in the Dutch province of North Holland, situated within the municipality of Haarlemmermeer.
  • 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_69a493ec75988190b63a11bafaec29b4 completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4bc2450c481909b9264e170070326 completed March 1, 2026, 10:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac5eaf952c81908c45b511f0231340 completed March 7, 2026, 5:21 p.m.
NEDg Description generation batch_69ac5f15c2808190905e40c6db9d957c completed March 7, 2026, 5:23 p.m.
NED2 Entity disambiguation (via description) batch_69ac633749008190bae63644d5ee7cea completed March 7, 2026, 5:41 p.m.
Created at: March 1, 2026, 7:44 p.m.