Triple

T14277571
Position Surface form Disambiguated ID Type / Status
Subject Siege of Montevideo (1807) E353953 entity
Predicate commander P1061 FINISHED
Object Rupert George
Rupert George was a British naval officer who commanded Royal Navy forces during the 1807 Siege of Montevideo in the Napoleonic Wars.
E1089206 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: Rupert George | Statement: [Siege of Montevideo (1807), commander, Rupert George]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rupert George
Context triple: [Siege of Montevideo (1807), commander, Rupert George]
  • A. Rupert Preston
    Rupert Preston is a British film producer known for his work on independent and genre films, including the crime drama "Bronson."
  • B. Rupert Angier
    Rupert Angier is a rival stage magician whose obsessive feud with Alfred Borden drives the central mystery and tragedy in Christopher Priest's novel "The Prestige."
  • C. Rupert
    Rupert is a small agricultural city in south-central Idaho known for its historic town square and role as a local farming hub.
  • D. Rupert
    Rupert is a masculine given name of Germanic origin, commonly used in English-speaking countries and borne by various notable figures.
  • E. Rupert
    Rupert is a small town located in Greenbrier County in the state of West Virginia, United States.
  • 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: Rupert George
Triple: [Siege of Montevideo (1807), commander, Rupert George]
Generated description
Rupert George was a British naval officer who commanded Royal Navy forces during the 1807 Siege of Montevideo in the Napoleonic Wars.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Rupert George
Target entity description: Rupert George was a British naval officer who commanded Royal Navy forces during the 1807 Siege of Montevideo in the Napoleonic Wars.
  • A. Rupert Preston
    Rupert Preston is a British film producer known for his work on independent and genre films, including the crime drama "Bronson."
  • B. Rupert Angier
    Rupert Angier is a rival stage magician whose obsessive feud with Alfred Borden drives the central mystery and tragedy in Christopher Priest's novel "The Prestige."
  • C. Rupert
    Rupert is a small agricultural city in south-central Idaho known for its historic town square and role as a local farming hub.
  • D. Rupert
    Rupert is a masculine given name of Germanic origin, commonly used in English-speaking countries and borne by various notable figures.
  • E. Rupert
    Rupert is a small town located in Greenbrier County in the state of West Virginia, United States.
  • 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_69d8278d25148190abf1a8c8f5f533ad completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de6583f0ec81909ebfc7a2c6351ff8 completed April 14, 2026, 4:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd326f62b4819084b1e984678991ae completed May 8, 2026, 12:46 a.m.
NEDg Description generation batch_69fd33e6e930819088c7479dc49c1bcd completed May 8, 2026, 12:52 a.m.
NED2 Entity disambiguation (via description) batch_69fd3453f7cc81909b183a8df2f5159f completed May 8, 2026, 12:54 a.m.
Created at: April 10, 2026, 1:10 a.m.