Triple

T13049545
Position Surface form Disambiguated ID Type / Status
Subject Province of Macerata E327414 entity
Predicate contains P35 FINISHED
Object Matelica
Matelica is a historic town in Italy’s Marche region known for its medieval architecture, wine production, and scenic Apennine surroundings.
E1022754 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: Matelica | Statement: [Province of Macerata, contains, Matelica]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Matelica
Context triple: [Province of Macerata, contains, Matelica]
  • A. Moravice
    Moravice is a river in the northern part of the historical Moravia region of the Czech Republic.
  • B. Gelnica
    Gelnica is a historic mining town in eastern Slovakia known for its medieval heritage and location in the Slovak Ore Mountains.
  • C. Husinec
    Husinec is a small Czech town best known as the birthplace of the religious reformer Jan Hus.
  • D. Taibach
    Taibach is a residential area and community within the county borough of Neath Port Talbot in South Wales, historically associated with the steel industry and the town of Port Talbot.
  • E. Pálava
    Pálava is a renowned wine-producing region in the Czech Republic, noted for its limestone hills and high-quality white wines, especially aromatic varieties.
  • 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: Matelica
Triple: [Province of Macerata, contains, Matelica]
Generated description
Matelica is a historic town in Italy’s Marche region known for its medieval architecture, wine production, and scenic Apennine surroundings.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Matelica
Target entity description: Matelica is a historic town in Italy’s Marche region known for its medieval architecture, wine production, and scenic Apennine surroundings.
  • A. Moravice
    Moravice is a river in the northern part of the historical Moravia region of the Czech Republic.
  • B. Gelnica
    Gelnica is a historic mining town in eastern Slovakia known for its medieval heritage and location in the Slovak Ore Mountains.
  • C. Husinec
    Husinec is a small Czech town best known as the birthplace of the religious reformer Jan Hus.
  • D. Taibach
    Taibach is a residential area and community within the county borough of Neath Port Talbot in South Wales, historically associated with the steel industry and the town of Port Talbot.
  • E. Pálava
    Pálava is a renowned wine-producing region in the Czech Republic, noted for its limestone hills and high-quality white wines, especially aromatic varieties.
  • 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_69d8076e64308190904fb5c93517c901 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69d980b8811c81908577f092e2736610 completed April 10, 2026, 10:59 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6e26c1f0081908100cae2cf39ac90 completed May 3, 2026, 5:51 a.m.
NEDg Description generation batch_69f6e42cd5408190b687dfae73e2a720 completed May 3, 2026, 5:59 a.m.
NED2 Entity disambiguation (via description) batch_69f6e5293ee481908d9a90266ac5c3e6 completed May 3, 2026, 6:03 a.m.
Created at: April 9, 2026, 8:57 p.m.