Triple

T19581754
Position Surface form Disambiguated ID Type / Status
Subject Kumna E490006 entity
Predicate hasHeritageSite P923 FINISHED
Object Kumna manor
Kumna manor is a historic Estonian manor estate known for its architectural and cultural heritage significance.
E490006 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: Kumna manor | Statement: [Kumna, hasHeritageSite, Kumna manor]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kumna manor
Context triple: [Kumna, hasHeritageSite, Kumna manor]
  • A. Dodona Manor
    Dodona Manor is a historic house museum in Leesburg, Virginia, best known as the former home of General George C. Marshall.
  • B. Sagtikos Manor
    Sagtikos Manor is a historic estate and manor house on Long Island, New York, notable for its colonial-era origins and association with prominent local families.
  • C. Ambard’s House
    Ambard’s House is a historic mansion in Trinidad and Tobago, renowned for its ornate colonial architecture and status as one of the country’s most iconic heritage homes.
  • D. Munxar
    Munxar is a small village on the island of Gozo in Malta, known for its rural character and scenic coastal surroundings.
  • E. Kumna
    Kumna is a village located in Harku Parish in northern Estonia.
  • 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: Kumna manor
Triple: [Kumna, hasHeritageSite, Kumna manor]
Generated description
Kumna manor is a historic Estonian manor estate known for its architectural and cultural heritage significance.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kumna manor
Target entity description: Kumna manor is a historic Estonian manor estate known for its architectural and cultural heritage significance.
  • A. Dodona Manor
    Dodona Manor is a historic house museum in Leesburg, Virginia, best known as the former home of General George C. Marshall.
  • B. Sagtikos Manor
    Sagtikos Manor is a historic estate and manor house on Long Island, New York, notable for its colonial-era origins and association with prominent local families.
  • C. Ambard’s House
    Ambard’s House is a historic mansion in Trinidad and Tobago, renowned for its ornate colonial architecture and status as one of the country’s most iconic heritage homes.
  • D. Munxar
    Munxar is a small village on the island of Gozo in Malta, known for its rural character and scenic coastal surroundings.
  • E. Kumna chosen
    Kumna is a village located in Harku Parish in northern Estonia.
  • F. None of above.

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_69d8e8dd9374819098e36349b3211663 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e6404e18f88190b7fec59499dd25e8 completed April 20, 2026, 3:03 p.m.
NED1 Entity disambiguation (via context triple) batch_6a075f0d5f608190b28b877fd8c1dfb6 completed May 15, 2026, 5:59 p.m.
NEDg Description generation batch_6a0760f5a32c81908a0b405a72f859f1 completed May 15, 2026, 6:07 p.m.
NED2 Entity disambiguation (via description) batch_6a0761c8b3008190bbc7a29412b49045 completed May 15, 2026, 6:11 p.m.
Created at: April 10, 2026, 1:42 p.m.