Triple

T4237191
Position Surface form Disambiguated ID Type / Status
Subject Gallura E94721 entity
Predicate containsCity P294 FINISHED
Object Usini
Usini is a small town in the Sardinian region of Gallura in Italy, known for its traditional rural character and local wine production.
 E423888 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: Usini | Statement: [Gallura, containsCity, Usini]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Usini
Context triple: [Gallura, containsCity, Usini]
  • A. Beni
    Beni is a sparsely populated, largely Amazonian department in northeastern Bolivia known for its tropical lowlands, cattle ranching, and rich indigenous cultures.
  • B. Beni
    Beni is a city in the eastern Democratic Republic of the Congo that became internationally known as a major hotspot of conflict and public health crises, including serving as the epicenter of the 2018–2020 Kivu Ebola epidemic.
  • C. Beni
    Beni is a town in western Nepal that serves as a gateway to the Dhaulagiri and Annapurna mountain regions.
  • D. Mutoko
    Mutoko is a town in northeastern Zimbabwe known as a commercial and administrative center for the surrounding rural district in Mashonaland.
  • E. Mugatu
    Mugatu is the flamboyant, villainous fashion designer portrayed by Will Ferrell in the comedy film "Zoolander."
  • 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: Usini
Triple: [Gallura, containsCity, Usini]
Generated description
Usini is a small town in the Sardinian region of Gallura in Italy, known for its traditional rural character and local wine production.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Usini
Target entity description: Usini is a small town in the Sardinian region of Gallura in Italy, known for its traditional rural character and local wine production.
  • A. Beni
    Beni is a sparsely populated, largely Amazonian department in northeastern Bolivia known for its tropical lowlands, cattle ranching, and rich indigenous cultures.
  • B. Beni
    Beni is a city in the eastern Democratic Republic of the Congo that became internationally known as a major hotspot of conflict and public health crises, including serving as the epicenter of the 2018–2020 Kivu Ebola epidemic.
  • C. Beni
    Beni is a town in western Nepal that serves as a gateway to the Dhaulagiri and Annapurna mountain regions.
  • D. Mutoko
    Mutoko is a town in northeastern Zimbabwe known as a commercial and administrative center for the surrounding rural district in Mashonaland.
  • E. Mugatu
    Mugatu is the flamboyant, villainous fashion designer portrayed by Will Ferrell in the comedy film "Zoolander."
  • 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_69b34537cc6481909cd0a96acbb33ef7 completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b34e7589b48190a16e7ff29fb6a162 completed March 12, 2026, 11:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5a86996f48190987d3ac234a9b7f4 completed March 14, 2026, 6:26 p.m.
NEDg Description generation batch_69b5a9f58de48190b6f2f56804bc6d30 completed March 14, 2026, 6:33 p.m.
NED2 Entity disambiguation (via description) batch_69b5aabd2080819091d65362cf02120b completed March 14, 2026, 6:36 p.m.
Created at: March 12, 2026, 11:05 p.m.