Triple

T4361994
Position Surface form Disambiguated ID Type / Status
Subject Battle of Navarino E98679 entity
Predicate hasShipInvolved P862 FINISHED
Object Gangut
Gangut was a Russian ship of the line that served in the Imperial Russian Navy and took part in major 19th-century naval engagements.
 E433286 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: Gangut | Statement: [Battle of Navarino, hasShipInvolved, Gangut]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Gangut
Context triple: [Battle of Navarino, hasShipInvolved, Gangut]
  • A. Dukenburg
    Dukenburg is a residential district in the southwest of Nijmegen in the Netherlands, known for its post-war urban planning and local railway connectivity.
  • B. Tsarevich
    Tsarevich was the traditional title given to the heir apparent to the Russian imperial throne.
  • C. Zułów
    Zułów is a village in present-day Lithuania best known as the birthplace of Polish statesman and military leader Józef Piłsudski.
  • D. The Kursk
    The Kursk is a 2018 disaster drama film that depicts the real-life sinking of the Russian nuclear submarine Kursk and the tragic aftermath of the failed rescue efforts.
  • E. Heemskerck
    Heemskerck was one of the Dutch East India Company ships commanded by explorer Abel Tasman during his 17th-century voyages of discovery in the Southern Hemisphere.
  • 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: Gangut
Triple: [Battle of Navarino, hasShipInvolved, Gangut]
Generated description
Gangut was a Russian ship of the line that served in the Imperial Russian Navy and took part in major 19th-century naval engagements.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Gangut
Target entity description: Gangut was a Russian ship of the line that served in the Imperial Russian Navy and took part in major 19th-century naval engagements.
  • A. Dukenburg
    Dukenburg is a residential district in the southwest of Nijmegen in the Netherlands, known for its post-war urban planning and local railway connectivity.
  • B. Tsarevich
    Tsarevich was the traditional title given to the heir apparent to the Russian imperial throne.
  • C. Zułów
    Zułów is a village in present-day Lithuania best known as the birthplace of Polish statesman and military leader Józef Piłsudski.
  • D. The Kursk
    The Kursk is a 2018 disaster drama film that depicts the real-life sinking of the Russian nuclear submarine Kursk and the tragic aftermath of the failed rescue efforts.
  • E. Heemskerck
    Heemskerck was one of the Dutch East India Company ships commanded by explorer Abel Tasman during his 17th-century voyages of discovery in the Southern Hemisphere.
  • 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_69b3454c772081908e20173e379e8ebe completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b351e47d388190b31500189577cd75 completed March 12, 2026, 11:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5dbc357988190a2982a86847e2c42 completed March 14, 2026, 10:05 p.m.
NEDg Description generation batch_69b5dc6a97208190b91d784285657bff completed March 14, 2026, 10:08 p.m.
NED2 Entity disambiguation (via description) batch_69b5dce749708190b9daf2c192b32de3 completed March 14, 2026, 10:10 p.m.
Created at: March 12, 2026, 11:16 p.m.