Triple

T8882040
Position Surface form Disambiguated ID Type / Status
Subject Rauma-class fast attack craft E211433 entity
Predicate builtBy P972 FINISHED
Object Rauma-Repola
Rauma-Repola was a Finnish shipbuilding and heavy engineering company known for constructing naval vessels and other maritime equipment.
 E212942 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: Rauma-Repola | Statement: [Rauma-class fast attack craft, builtBy, Rauma-Repola]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Rauma-Repola
Context triple: [Rauma-class fast attack craft, builtBy, Rauma-Repola]
  • A. Rauma
    Rauma is a coastal town in western Finland known for its well-preserved wooden Old Town, a UNESCO World Heritage Site, and its maritime and industrial heritage.
  • B. Rauma
    Rauma is a municipality in western Norway known for its dramatic fjord and mountain landscapes, including the Romsdalen valley and Trollveggen cliff.
  • C. Marttila
    Marttila is a small rural municipality in southwestern Finland known for its agricultural landscape and tranquil countryside.
  • D. Rieste
    Rieste is a small municipality in Lower Saxony, Germany, situated within the Osnabrück district.
  • E. Sastamala
    Sastamala is a town and municipality in southwestern Finland known for its historical churches, cultural heritage, and scenic lakeside landscapes.
  • 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: Rauma-Repola
Triple: [Rauma-class fast attack craft, builtBy, Rauma-Repola]
Generated description
Rauma-Repola was a Finnish shipbuilding and heavy engineering company known for constructing naval vessels and other maritime equipment.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Rauma-Repola
Target entity description: Rauma-Repola was a Finnish shipbuilding and heavy engineering company known for constructing naval vessels and other maritime equipment.
  • A. Rauma
    Rauma is a municipality in western Norway known for its dramatic fjord and mountain landscapes, including the Romsdalen valley and Trollveggen cliff.
  • B. Rauma chosen
    Rauma is a coastal town in western Finland known for its well-preserved wooden Old Town, a UNESCO World Heritage Site, and its maritime and industrial heritage.
  • C. Marttila
    Marttila is a small rural municipality in southwestern Finland known for its agricultural landscape and tranquil countryside.
  • D. Rieste
    Rieste is a small municipality in Lower Saxony, Germany, situated within the Osnabrück district.
  • E. Sastamala
    Sastamala is a town and municipality in southwestern Finland known for its historical churches, cultural heritage, and scenic lakeside landscapes.
  • F. None of above.

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_69ca838f9e20819096ab1f236a70381a completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc616a01f48190b8bbde0e898a38c7 completed April 1, 2026, 12:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfabca74888190934593d6504fbed1 completed April 3, 2026, noon
NEDg Description generation batch_69cfac9c743c8190a26f753111f07281 completed April 3, 2026, 12:03 p.m.
NED2 Entity disambiguation (via description) batch_69cfad54cf5c81908558fd4c21f2f3b6 completed April 3, 2026, 12:06 p.m.
Created at: March 30, 2026, 6:53 p.m.