Triple

T19282707
Position Surface form Disambiguated ID Type / Status
Subject Avlona E482228 entity
Predicate hasAlternativeName P39 FINISHED
Object Avlonas
Avlonas is a town in Greece, known as a small settlement in the Attica region.
 E1368276 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: Avlonas | Statement: [Avlona, hasAlternativeName, Avlonas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Avlonas
Context triple: [Avlona, hasAlternativeName, Avlonas]
  • A. Avlona
    Avlona is the historical name of the coastal Albanian city now known as Vlora, an important port and cultural center on the Adriatic Sea.
  • B. Dainava
    Dainava is a historical region in the territory of present-day Lithuania and northeastern Poland, traditionally associated with the Baltic Yotvingian and Lithuanian tribes.
  • C. Atsina
    The Atsina, also known as the Gros Ventre of the Prairie, are a Native American people of the Northern Plains historically associated with the Algonquian-speaking cultural and linguistic group.
  • D. Agenais
    Agenais refers to the inhabitants or natives of Agen, a historic town in southwestern France.
  • E. Sprota
    Sprota was a 10th-century Norman noblewoman of Breton origin, known primarily as the concubine or wife of William I Longsword and the mother of Richard I, Duke of Normandy.
  • 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: Avlonas
Triple: [Avlona, hasAlternativeName, Avlonas]
Generated description
Avlonas is a town in Greece, known as a small settlement in the Attica region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Avlonas
Target entity description: Avlonas is a town in Greece, known as a small settlement in the Attica region.
  • A. Avlona
    Avlona is the historical name of the coastal Albanian city now known as Vlora, an important port and cultural center on the Adriatic Sea.
  • B. Dainava
    Dainava is a historical region in the territory of present-day Lithuania and northeastern Poland, traditionally associated with the Baltic Yotvingian and Lithuanian tribes.
  • C. Atsina
    The Atsina, also known as the Gros Ventre of the Prairie, are a Native American people of the Northern Plains historically associated with the Algonquian-speaking cultural and linguistic group.
  • D. Agenais
    Agenais refers to the inhabitants or natives of Agen, a historic town in southwestern France.
  • E. Sprota
    Sprota was a 10th-century Norman noblewoman of Breton origin, known primarily as the concubine or wife of William I Longsword and the mother of Richard I, Duke of Normandy.
  • 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_69d8e8cf61b0819096fe3e4107827c4e completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e5fbffda78819088bf8dbc61756831 completed April 20, 2026, 10:12 a.m.
NED1 Entity disambiguation (via context triple) batch_6a070e7e2b7881909e3461175f8b3c8c completed May 15, 2026, 12:15 p.m.
NEDg Description generation batch_6a070f8b626c819083a31123cd6035cf completed May 15, 2026, 12:20 p.m.
NED2 Entity disambiguation (via description) batch_6a071018f61881908ace460b83dac186 completed May 15, 2026, 12:22 p.m.
Created at: April 10, 2026, 1:30 p.m.