Triple

T8557210
Position Surface form Disambiguated ID Type / Status
Subject Richterswil E202600 entity
Predicate hasHeritageSite P923 FINISHED
Object country estate Boden
Country estate Boden is a historic manor property in Richterswil, Switzerland, recognized as a cultural heritage site of regional significance.
 E743275 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: country estate Boden | Statement: [Richterswil, hasHeritageSite, country estate Boden]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: country estate Boden
Context triple: [Richterswil, hasHeritageSite, country estate Boden]
  • A. Boden
    Boden is a northern Swedish town known for its strategic military significance and large army garrison.
  • B. Hartekamp estate
    Hartekamp estate is a historic Dutch country estate in Heemstede, best known as the place where botanist Carl Linnaeus worked on his influential botanical studies in the 18th century.
  • C. Land
    Land is a municipality in Innlandet county, Norway, known for its rural landscapes and proximity to Randsfjorden.
  • D. Land
    "Land" is a poem by Seamus Heaney that reflects on the Irish landscape and rural life, blending physical detail with themes of history and identity.
  • E. Land
    Land Morrow Lindbergh is the son of aviator Charles Lindbergh and writer Anne Morrow Lindbergh.
  • 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: country estate Boden
Triple: [Richterswil, hasHeritageSite, country estate Boden]
Generated description
Country estate Boden is a historic manor property in Richterswil, Switzerland, recognized as a cultural heritage site of regional significance.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: country estate Boden
Target entity description: Country estate Boden is a historic manor property in Richterswil, Switzerland, recognized as a cultural heritage site of regional significance.
  • A. Boden
    Boden is a northern Swedish town known for its strategic military significance and large army garrison.
  • B. Hartekamp estate
    Hartekamp estate is a historic Dutch country estate in Heemstede, best known as the place where botanist Carl Linnaeus worked on his influential botanical studies in the 18th century.
  • C. Land
    Land is a municipality in Innlandet county, Norway, known for its rural landscapes and proximity to Randsfjorden.
  • D. Land
    "Land" is a poem by Seamus Heaney that reflects on the Irish landscape and rural life, blending physical detail with themes of history and identity.
  • E. Land
    Land Morrow Lindbergh is the son of aviator Charles Lindbergh and writer Anne Morrow Lindbergh.
  • 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_69ca8326e6c881908ff720d6abaebdc5 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe946d1408190adc7dfb7b2173f9d completed March 31, 2026, 3:33 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce893b24c0819094fead15749fe1ee completed April 2, 2026, 3:20 p.m.
NEDg Description generation batch_69ce8a9ba0448190ae7637f24b8a8032 completed April 2, 2026, 3:26 p.m.
NED2 Entity disambiguation (via description) batch_69ce8bda33548190a8f6985a48d65a39 completed April 2, 2026, 3:31 p.m.
Created at: March 30, 2026, 6:20 p.m.