Triple

T17197076
Position Surface form Disambiguated ID Type / Status
Subject Powder Tower (Heidelberg Castle) E417379 entity
Predicate hasNameInGerman P22792 FINISHED
Object Pulverturm
Pulverturm is the German name for the historic Powder Tower that forms part of Heidelberg Castle in Heidelberg, Germany.
E1256544 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: Pulverturm | Statement: [Powder Tower (Heidelberg Castle), hasNameInGerman, Pulverturm]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pulverturm
Context triple: [Powder Tower (Heidelberg Castle), hasNameInGerman, Pulverturm]
  • A. Pulverturm
    Pulverturm is a historic tower in the German town of Eberbach, traditionally associated with the town’s medieval fortifications and former gunpowder storage.
  • B. Pulverturm
    Pulverturm is a historic defensive tower that forms part of the medieval Musegg Wall fortifications in Lucerne, Switzerland.
  • C. Storchenturm
    Storchenturm is a historic tower and notable architectural landmark in the town of Gernsbach, Germany.
  • D. Schimmelturm
    Schimmelturm is a historic tower and prominent architectural landmark in the Bavarian town of Lauingen, Germany.
  • E. Spremberger Turm
    Spremberger Turm is a historic medieval city tower and prominent architectural landmark in the German city of Cottbus.
  • 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: Pulverturm
Triple: [Powder Tower (Heidelberg Castle), hasNameInGerman, Pulverturm]
Generated description
Pulverturm is the German name for the historic Powder Tower that forms part of Heidelberg Castle in Heidelberg, Germany.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Pulverturm
Target entity description: Pulverturm is the German name for the historic Powder Tower that forms part of Heidelberg Castle in Heidelberg, Germany.
  • A. Pulverturm
    Pulverturm is a historic defensive tower that forms part of the medieval Musegg Wall fortifications in Lucerne, Switzerland.
  • B. Pulverturm
    Pulverturm is a historic tower in the German town of Eberbach, traditionally associated with the town’s medieval fortifications and former gunpowder storage.
  • C. Storchenturm
    Storchenturm is a historic tower and notable architectural landmark in the town of Gernsbach, Germany.
  • D. Schimmelturm
    Schimmelturm is a historic tower and prominent architectural landmark in the Bavarian town of Lauingen, Germany.
  • E. Spremberger Turm
    Spremberger Turm is a historic medieval city tower and prominent architectural landmark in the German city of Cottbus.
  • 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_69d886d6ba8c819093215917b3d01689 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e42dab718c8190b6f5b08189cf2eb2 completed April 19, 2026, 1:19 a.m.
NED1 Entity disambiguation (via context triple) batch_6a015fd7ef048190b0828ec6ea0e119c completed May 11, 2026, 4:49 a.m.
NEDg Description generation batch_6a01636d8f008190975bcd8d9124ec88 completed May 11, 2026, 5:04 a.m.
NED2 Entity disambiguation (via description) batch_6a0163d510908190906a3b186e840688 completed May 11, 2026, 5:06 a.m.
Created at: April 10, 2026, 5:38 a.m.