Triple

T10633344
Position Surface form Disambiguated ID Type / Status
Subject Kehl E250513 entity
Predicate hasSubdivision P747 FINISHED
Object Sundheim
Sundheim is a district of the German town of Kehl in the state of Baden-Württemberg.
E876400 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: Sundheim | Statement: [Kehl, hasSubdivision, Sundheim]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sundheim
Context triple: [Kehl, hasSubdivision, Sundheim]
  • A. Gangstad
    Gangstad is a small settlement located within the municipality of Inderøy in Trøndelag county, Norway.
  • B. Storvik
    Storvik is a locality in Gävleborg County, Sweden, known historically as a railway junction and small industrial community.
  • C. Hedesunda
    Hedesunda is a small locality in east-central Sweden known for its rural character and proximity to forests, lakes, and the Dalälven River.
  • D. Stordal
    Stordal is a small village and former municipality in western Norway, known for its scenic fjord landscape and traditional Norwegian architecture.
  • E. Midsund
    Midsund is a former island municipality and village area in Western Norway known for its coastal scenery and hiking trails in the Romsdal region.
  • 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: Sundheim
Triple: [Kehl, hasSubdivision, Sundheim]
Generated description
Sundheim is a district of the German town of Kehl in the state of Baden-Württemberg.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sundheim
Target entity description: Sundheim is a district of the German town of Kehl in the state of Baden-Württemberg.
  • A. Gangstad
    Gangstad is a small settlement located within the municipality of Inderøy in Trøndelag county, Norway.
  • B. Storvik
    Storvik is a locality in Gävleborg County, Sweden, known historically as a railway junction and small industrial community.
  • C. Hedesunda
    Hedesunda is a small locality in east-central Sweden known for its rural character and proximity to forests, lakes, and the Dalälven River.
  • D. Stordal
    Stordal is a small village and former municipality in western Norway, known for its scenic fjord landscape and traditional Norwegian architecture.
  • E. Midsund
    Midsund is a former island municipality and village area in Western Norway known for its coastal scenery and hiking trails in the Romsdal region.
  • 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_69d6aa5993448190a493b790b8f85010 completed April 8, 2026, 7:19 p.m.
NER Named-entity recognition batch_69d6df95f5e88190b34ce3ec972759ef completed April 8, 2026, 11:07 p.m.
NED1 Entity disambiguation (via context triple) batch_69d96bbd64d8819089d55af875d39e45 completed April 10, 2026, 9:29 p.m.
NEDg Description generation batch_69d9701de92881908c0b8f05eae97e35 completed April 10, 2026, 9:48 p.m.
NED2 Entity disambiguation (via description) batch_69d970f3f78081909bcb2dae6dae06d5 completed April 10, 2026, 9:51 p.m.
Created at: April 8, 2026, 9:02 p.m.