Triple

T4539159
Position Surface form Disambiguated ID Type / Status
Subject Landtag of Liechtenstein E107483 entity
Predicate electoralDistrict P9598 FINISHED
Object Unterland
Unterland is one of the two electoral districts of Liechtenstein, encompassing the country's northern municipalities along the Rhine.
E451026 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: Unterland | Statement: [Landtag of Liechtenstein, electoralDistrict, Unterland]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Unterland
Context triple: [Landtag of Liechtenstein, electoralDistrict, Unterland]
  • A. Löwenberger Land
    Löwenberger Land is a rural municipality in the Oberhavel district of Brandenburg, Germany, known for its agricultural landscape and small villages north of Berlin.
  • B. Rübeland
    Rübeland is a village in the Harz Mountains of central Germany, known for its show caves and scenic natural surroundings.
  • C. Flachsland
    Flachsland is a German-language surname associated with individuals such as Maria Karoline Flachsland.
  • D. Rietlanden
    Rietlanden is a waterfront area in Amsterdam’s Eastern Docklands, known for its former industrial port functions and subsequent urban redevelopment.
  • E. Wiehe
    Wiehe is a small town in the German state of Thuringia, historically notable as the birthplace of the influential 19th-century historian Leopold von Ranke.
  • 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: Unterland
Triple: [Landtag of Liechtenstein, electoralDistrict, Unterland]
Generated description
Unterland is one of the two electoral districts of Liechtenstein, encompassing the country's northern municipalities along the Rhine.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Unterland
Target entity description: Unterland is one of the two electoral districts of Liechtenstein, encompassing the country's northern municipalities along the Rhine.
  • A. Löwenberger Land
    Löwenberger Land is a rural municipality in the Oberhavel district of Brandenburg, Germany, known for its agricultural landscape and small villages north of Berlin.
  • B. Rübeland
    Rübeland is a village in the Harz Mountains of central Germany, known for its show caves and scenic natural surroundings.
  • C. Flachsland
    Flachsland is a German-language surname associated with individuals such as Maria Karoline Flachsland.
  • D. Rietlanden
    Rietlanden is a waterfront area in Amsterdam’s Eastern Docklands, known for its former industrial port functions and subsequent urban redevelopment.
  • E. Wiehe
    Wiehe is a small town in the German state of Thuringia, historically notable as the birthplace of the influential 19th-century historian Leopold von Ranke.
  • 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_69bd43f922788190b7edfa294e39b178 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd57ba327c8190a7f12e14077b1fa7 completed March 20, 2026, 2:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69bdacfff41481908a5c97ab4fcb9259 completed March 20, 2026, 8:24 p.m.
NEDg Description generation batch_69bdb32911cc8190a8624d54dad6355e completed March 20, 2026, 8:50 p.m.
NED2 Entity disambiguation (via description) batch_69bdb3a0bf908190b9a029f47e6be941 completed March 20, 2026, 8:52 p.m.
Created at: March 20, 2026, 1:04 p.m.