Triple

T17010305
Position Surface form Disambiguated ID Type / Status
Subject Passau E412680 entity
Predicate hasLandmark P105 FINISHED
Object Dreiflüsseeck
Dreiflüsseeck is the scenic point in Passau, Germany, where the rivers Danube, Inn, and Ilz converge.
E1244662 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: Dreiflüsseeck | Statement: [Passau, hasLandmark, Dreiflüsseeck]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dreiflüsseeck
Context triple: [Passau, hasLandmark, Dreiflüsseeck]
  • A. Streuben
    Streuben is a locality or district that forms part of the town of Wurzen in the German state of Saxony.
  • B. Eschbach
    Eschbach is a village and district of the town of Usingen in the Hochtaunus region of Hesse, Germany.
  • C. Eschwege
    Eschwege is a small historic town in the German state of Hesse, known for its medieval architecture and location near the Werra River.
  • D. Königsbach
    Königsbach is a village and wine-growing district that forms part of the town of Neustadt an der Weinstraße in Rhineland-Palatinate, Germany.
  • E. Eckersbach
    Eckersbach is a district of the city of Zwickau in the German state of Saxony, known primarily as a residential area.
  • 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: Dreiflüsseeck
Triple: [Passau, hasLandmark, Dreiflüsseeck]
Generated description
Dreiflüsseeck is the scenic point in Passau, Germany, where the rivers Danube, Inn, and Ilz converge.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Dreiflüsseeck
Target entity description: Dreiflüsseeck is the scenic point in Passau, Germany, where the rivers Danube, Inn, and Ilz converge.
  • A. Streuben
    Streuben is a locality or district that forms part of the town of Wurzen in the German state of Saxony.
  • B. Eschbach
    Eschbach is a village and district of the town of Usingen in the Hochtaunus region of Hesse, Germany.
  • C. Eschwege
    Eschwege is a small historic town in the German state of Hesse, known for its medieval architecture and location near the Werra River.
  • D. Königsbach
    Königsbach is a village and wine-growing district that forms part of the town of Neustadt an der Weinstraße in Rhineland-Palatinate, Germany.
  • E. Eckersbach
    Eckersbach is a district of the city of Zwickau in the German state of Saxony, known primarily as a residential area.
  • 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_69d886cc4170819093deddc7b8b4b6a7 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d47a8444819081f1262eb7dbda40 completed April 18, 2026, 6:59 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00dc241ec88190a3e868ab88b26f09 completed May 10, 2026, 7:27 p.m.
NEDg Description generation batch_6a0114d7d03c8190943777f4eac956fd completed May 10, 2026, 11:29 p.m.
NED2 Entity disambiguation (via description) batch_6a01159a08b081908fc82adc7cca532a completed May 10, 2026, 11:32 p.m.
Created at: April 10, 2026, 5:33 a.m.