Triple

T8962241
Position Surface form Disambiguated ID Type / Status
Subject Landkreis Neu-Ulm E214034 entity
Predicate hasTown P847 FINISHED
Object Illertissen
Illertissen is a small Bavarian town in southern Germany known for its historic center and location near the Iller River in the district of Neu-Ulm.
 E769117 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: Illertissen | Statement: [Landkreis Neu-Ulm, hasTown, Illertissen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Illertissen
Context triple: [Landkreis Neu-Ulm, hasTown, Illertissen]
  • A. Rondane
    Rondane is a mountainous national park in central Norway known for its high peaks, alpine plateaus, and rich wildlife, including wild reindeer.
  • B. Kjerkeberget
    Kjerkeberget is a forested hill in Norway that marks the highest natural point within Oslo’s municipal boundaries.
  • C. Skraperudtjern
    Skraperudtjern is a small lake located in the Østensjø area of Oslo, Norway, known for its natural surroundings and local recreational use.
  • D. Samnaun
    Samnaun is a Swiss alpine village and duty-free ski resort in the Engadin valley, known for its extensive cross-border ski area shared with the Austrian resort of Ischgl.
  • E. Lysthaugen
    Lysthaugen is a small settlement located in the municipality of Verdal in Trøndelag county, Norway.
  • 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: Illertissen
Triple: [Landkreis Neu-Ulm, hasTown, Illertissen]
Generated description
Illertissen is a small Bavarian town in southern Germany known for its historic center and location near the Iller River in the district of Neu-Ulm.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Illertissen
Target entity description: Illertissen is a small Bavarian town in southern Germany known for its historic center and location near the Iller River in the district of Neu-Ulm.
  • A. Rondane
    Rondane is a mountainous national park in central Norway known for its high peaks, alpine plateaus, and rich wildlife, including wild reindeer.
  • B. Kjerkeberget
    Kjerkeberget is a forested hill in Norway that marks the highest natural point within Oslo’s municipal boundaries.
  • C. Skraperudtjern
    Skraperudtjern is a small lake located in the Østensjø area of Oslo, Norway, known for its natural surroundings and local recreational use.
  • D. Samnaun
    Samnaun is a Swiss alpine village and duty-free ski resort in the Engadin valley, known for its extensive cross-border ski area shared with the Austrian resort of Ischgl.
  • E. Lysthaugen
    Lysthaugen is a small settlement located in the municipality of Verdal in Trøndelag county, Norway.
  • 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_69ca839cd6008190a1546a701a56710c completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc6749e5008190a01f42a2e772dd54 completed April 1, 2026, 12:31 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfc94e088881909506b229d1fff44a completed April 3, 2026, 2:06 p.m.
NEDg Description generation batch_69cfc9ef5e548190a134c2bf0aa380b5 completed April 3, 2026, 2:08 p.m.
NED2 Entity disambiguation (via description) batch_69cfca735c50819088c2805c62d96d62 completed April 3, 2026, 2:10 p.m.
Created at: March 30, 2026, 7:01 p.m.