Triple

T14402403
Position Surface form Disambiguated ID Type / Status
Subject Customs of Finland E357103 entity
Predicate nativeName P15 FINISHED
Object Tulli
Tulli is the Finnish Customs authority responsible for overseeing customs control, collecting duties and taxes, and facilitating international trade in Finland.
E1097384 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: Tulli | Statement: [Customs of Finland, nativeName, Tulli]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tulli
Context triple: [Customs of Finland, nativeName, Tulli]
  • A. Maenza
    Maenza is a small historic town in the Lazio region of central Italy, known for its medieval architecture and hilltop setting.
  • B. Tullio
    Tullio is an Italian given name most famously borne by the mathematician Tullio Levi-Civita, known for his work in tensor calculus and differential geometry.
  • C. Delle
    Delle is a small commune in northeastern France near the Swiss border, known as a local administrative and economic center in the Territoire de Belfort department.
  • D. Tull
    Tull is a surname most prominently associated with American film producer and entrepreneur Thomas Tull.
  • E. Statilia
    Statilia is an ancient Roman feminine praenomen (given name) most notably borne by the empress Statilia Messalina, wife of Emperor Nero.
  • 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: Tulli
Triple: [Customs of Finland, nativeName, Tulli]
Generated description
Tulli is the Finnish Customs authority responsible for overseeing customs control, collecting duties and taxes, and facilitating international trade in Finland.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Tulli
Target entity description: Tulli is the Finnish Customs authority responsible for overseeing customs control, collecting duties and taxes, and facilitating international trade in Finland.
  • A. Maenza
    Maenza is a small historic town in the Lazio region of central Italy, known for its medieval architecture and hilltop setting.
  • B. Tullio
    Tullio is an Italian given name most famously borne by the mathematician Tullio Levi-Civita, known for his work in tensor calculus and differential geometry.
  • C. Delle
    Delle is a small commune in northeastern France near the Swiss border, known as a local administrative and economic center in the Territoire de Belfort department.
  • D. Tull
    Tull is a surname most prominently associated with American film producer and entrepreneur Thomas Tull.
  • E. Statilia
    Statilia is an ancient Roman feminine praenomen (given name) most notably borne by the empress Statilia Messalina, wife of Emperor Nero.
  • 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_69d827927c988190ad98bb0360981783 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de908500048190bb6a20fe318d5c62 completed April 14, 2026, 7:07 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd5520c07c8190bfdaf224dd779ced completed May 8, 2026, 3:14 a.m.
NEDg Description generation batch_69fd56bbd6e481909fd97f3808bc99fd completed May 8, 2026, 3:21 a.m.
NED2 Entity disambiguation (via description) batch_69fd5755156c8190bc27df83e940c403 completed May 8, 2026, 3:24 a.m.
Created at: April 10, 2026, 1:17 a.m.