Triple

T15940440
Position Surface form Disambiguated ID Type / Status
Subject canton of Appenzell Ausserrhoden E386544 entity
Predicate capital P234 FINISHED
Object Herisau
Herisau is a Swiss town that serves as the administrative and economic center of the canton of Appenzell Ausserrhoden.
 E1216025 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: Herisau | Statement: [canton of Appenzell Ausserrhoden, capital, Herisau]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Herisau
Context triple: [canton of Appenzell Ausserrhoden, capital, Herisau]
  • A. Haslach
    Haslach is a district or locality that forms part of the town of Oberkirch in the German state of Baden-Württemberg.
  • B. Haslach
    Haslach is a town in southern Germany historically noted as the site of the Battle of Haslach-Jungingen during the Napoleonic Wars.
  • C. Machtolsheim
    Machtolsheim is a village in the Alb-Donau district of Baden-Württemberg, Germany, that forms part of the town of Laichingen.
  • D. Heretsried
    Heretsried is a small municipality in the Swabian region of Bavaria, Germany, situated within the rural surroundings of the Augsburg district.
  • E. Tapfheim
    Tapfheim is a small municipality in the Donau-Ries district of Bavaria in southern Germany.
  • 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: Herisau
Triple: [canton of Appenzell Ausserrhoden, capital, Herisau]
Generated description
Herisau is a Swiss town that serves as the administrative and economic center of the canton of Appenzell Ausserrhoden.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Herisau
Target entity description: Herisau is a Swiss town that serves as the administrative and economic center of the canton of Appenzell Ausserrhoden.
  • A. Haslach
    Haslach is a district or locality that forms part of the town of Oberkirch in the German state of Baden-Württemberg.
  • B. Haslach
    Haslach is a town in southern Germany historically noted as the site of the Battle of Haslach-Jungingen during the Napoleonic Wars.
  • C. Machtolsheim
    Machtolsheim is a village in the Alb-Donau district of Baden-Württemberg, Germany, that forms part of the town of Laichingen.
  • D. Heretsried
    Heretsried is a small municipality in the Swabian region of Bavaria, Germany, situated within the rural surroundings of the Augsburg district.
  • E. Tapfheim
    Tapfheim is a small municipality in the Donau-Ries district of Bavaria in southern Germany.
  • 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_69d86da750008190987eb26be3f6c118 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e156cd3a188190a1a7dcbfdd38284c completed April 16, 2026, 9:38 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00580789c08190994c5c71525aadc6 completed May 10, 2026, 10:03 a.m.
NEDg Description generation batch_6a0058b298448190aab32ec1583f7c86 completed May 10, 2026, 10:06 a.m.
NED2 Entity disambiguation (via description) batch_6a00595837c4819093f1a1a35185bc4b completed May 10, 2026, 10:09 a.m.
Created at: April 10, 2026, 4:53 a.m.