Triple

T19266879
Position Surface form Disambiguated ID Type / Status
Subject Geisenfeld E481806 entity
Predicate locatedOnRiver P165 FINISHED
Object Ilm (Bavaria)
Ilm is a river in Bavaria, Germany, that flows through the town of Geisenfeld and is a tributary of the Abens River.
 E1368435 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: Ilm (Bavaria) | Statement: [Geisenfeld, locatedOnRiver, Ilm (Bavaria)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Ilm (Bavaria)
Context triple: [Geisenfeld, locatedOnRiver, Ilm (Bavaria)]
  • A. Seßlach
    Seßlach is a small, well-preserved medieval town in northern Bavaria, Germany, known for its intact city walls and historic half-timbered houses.
  • B. Maroldsweisach
    Maroldsweisach is a municipality in the Haßberge district of northern Bavaria, Germany, known for its rural setting and historic Franconian character.
  • 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. Wuhletal
    Wuhletal is a valley landscape in Berlin shaped by the course of the Wuhle river, featuring green spaces, walking paths, and recreational areas.
  • E. Meißner
    Meißner is a municipality in the Werra-Meißner district of the German state of Hesse, known for its proximity to the Meißner mountain range.
  • 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: Ilm (Bavaria)
Triple: [Geisenfeld, locatedOnRiver, Ilm (Bavaria)]
Generated description
Ilm is a river in Bavaria, Germany, that flows through the town of Geisenfeld and is a tributary of the Abens River.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Ilm (Bavaria)
Target entity description: Ilm is a river in Bavaria, Germany, that flows through the town of Geisenfeld and is a tributary of the Abens River.
  • A. Seßlach
    Seßlach is a small, well-preserved medieval town in northern Bavaria, Germany, known for its intact city walls and historic half-timbered houses.
  • B. Maroldsweisach
    Maroldsweisach is a municipality in the Haßberge district of northern Bavaria, Germany, known for its rural setting and historic Franconian character.
  • 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. Wuhletal
    Wuhletal is a valley landscape in Berlin shaped by the course of the Wuhle river, featuring green spaces, walking paths, and recreational areas.
  • E. Meißner
    Meißner is a municipality in the Werra-Meißner district of the German state of Hesse, known for its proximity to the Meißner mountain range.
  • 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_69d8e8ce54cc8190998418ff1f66ef28 completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e5fb8d58988190a942627b1fb79285 completed April 20, 2026, 10:10 a.m.
NED1 Entity disambiguation (via context triple) batch_6a070e6ec97c81909944d41943b94b34 completed May 15, 2026, 12:15 p.m.
NEDg Description generation batch_6a070fc891448190a5061c0d340548d5 completed May 15, 2026, 12:21 p.m.
NED2 Entity disambiguation (via description) batch_6a0710836b608190a89900ba3f6916bb completed May 15, 2026, 12:24 p.m.
Created at: April 10, 2026, 1:29 p.m.