Triple

T10187888
Position Surface form Disambiguated ID Type / Status
Subject SMS König E236956 entity
Predicate sisterShip P3142 FINISHED
Object SMS Markgraf
SMS Markgraf was a German Kaiser-class dreadnought battleship of the Imperial German Navy that served in World War I, including at the Battle of Jutland.
E847216 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: SMS Markgraf | Statement: [SMS König, sisterShip, SMS Markgraf]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: SMS Markgraf
Context triple: [SMS König, sisterShip, SMS Markgraf]
  • A. Senden
    Senden is a town in the district of Neu-Ulm in Bavaria, Germany, known for its residential character and proximity to the cities of Ulm and Neu-Ulm.
  • B. Schmarbeck
    Schmarbeck is a small watercourse in Lower Saxony, Germany, known as one of the minor streams feeding into the Örtze River within the Lüneburg Heath region.
  • C. Schiffhauer
    Schiffhauer is a surname, likely a variant of the German family name "Schiff."
  • D. Schwartau
    Schwartau is a river in northern Germany that flows through the state of Schleswig-Holstein before joining the Trave.
  • E. Graf
    Graf is a historical German noble title roughly equivalent to a count in other European aristocratic systems.
  • 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: SMS Markgraf
Triple: [SMS König, sisterShip, SMS Markgraf]
Generated description
SMS Markgraf was a German Kaiser-class dreadnought battleship of the Imperial German Navy that served in World War I, including at the Battle of Jutland.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: SMS Markgraf
Target entity description: SMS Markgraf was a German Kaiser-class dreadnought battleship of the Imperial German Navy that served in World War I, including at the Battle of Jutland.
  • A. Senden
    Senden is a town in the district of Neu-Ulm in Bavaria, Germany, known for its residential character and proximity to the cities of Ulm and Neu-Ulm.
  • B. Schmarbeck
    Schmarbeck is a small watercourse in Lower Saxony, Germany, known as one of the minor streams feeding into the Örtze River within the Lüneburg Heath region.
  • C. Schiffhauer
    Schiffhauer is a surname, likely a variant of the German family name "Schiff."
  • D. Schwartau
    Schwartau is a river in northern Germany that flows through the state of Schleswig-Holstein before joining the Trave.
  • E. Graf
    Graf is a historical German noble title roughly equivalent to a count in other European aristocratic systems.
  • 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_69ca84d7260c8190bfbec36762943f37 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cded7a7aac8190af8dcb8374e62d68 completed April 2, 2026, 4:15 a.m.
NED1 Entity disambiguation (via context triple) batch_69d317adddc88190a41d0eabe64f952b completed April 6, 2026, 2:17 a.m.
NEDg Description generation batch_69d31b9f32c08190af2e71641e9542b0 completed April 6, 2026, 2:34 a.m.
NED2 Entity disambiguation (via description) batch_69d31c421e1081908763cc97e0b1317c completed April 6, 2026, 2:36 a.m.
Created at: March 30, 2026, 9:12 p.m.