Triple

T15520100
Position Surface form Disambiguated ID Type / Status
Subject Richard Castle E368940 entity
Predicate designed P184 FINISHED
Object Hazelwood House
Hazelwood House is a notable building in Sligo, Ireland, recognized as an important example of 18th-century country house architecture.
 E1162839 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: Hazelwood House | Statement: [Richard Castle, designed, Hazelwood House]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Hazelwood House
Context triple: [Richard Castle, designed, Hazelwood House]
  • A. Hawthorn Hill
    Hawthorn Hill is the historic Oakwood, Ohio mansion built for aviation pioneer Orville Wright and renowned as his longtime residence.
  • B. Hazel Court
    Hazel Court was a British actress best known for her roles in classic horror films of the 1950s and 1960s, particularly in collaborations with Hammer Films and Roger Corman.
  • C. Clementswood
    Clementswood is a residential district within the London Borough of Redbridge in East London, England.
  • D. Hillcrest
    Hillcrest is a residential suburb within the coastal city of Burnie in north-west Tasmania, Australia.
  • E. Hillcrest
    Hillcrest is a residential neighbourhood in Toronto, Ontario, known for its tree-lined streets, family-friendly character, and convenient access to local shops and transit.
  • 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: Hazelwood House
Triple: [Richard Castle, designed, Hazelwood House]
Generated description
Hazelwood House is a notable building in Sligo, Ireland, recognized as an important example of 18th-century country house architecture.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Hazelwood House
Target entity description: Hazelwood House is a notable building in Sligo, Ireland, recognized as an important example of 18th-century country house architecture.
  • A. Hawthorn Hill
    Hawthorn Hill is the historic Oakwood, Ohio mansion built for aviation pioneer Orville Wright and renowned as his longtime residence.
  • B. Hazel Court
    Hazel Court was a British actress best known for her roles in classic horror films of the 1950s and 1960s, particularly in collaborations with Hammer Films and Roger Corman.
  • C. Clementswood
    Clementswood is a residential district within the London Borough of Redbridge in East London, England.
  • D. Hillcrest
    Hillcrest is a residential suburb within the coastal city of Burnie in north-west Tasmania, Australia.
  • E. Hillcrest
    Hillcrest is a residential neighbourhood in Toronto, Ontario, known for its tree-lined streets, family-friendly character, and convenient access to local shops and transit.
  • 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_69d85a1794cc8190b0b428716296e63e completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e040343d9c8190a7d1f197c108bd9d completed April 16, 2026, 1:49 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff3d52cf1c8190b18bff0b925355a3 completed May 9, 2026, 1:57 p.m.
NEDg Description generation batch_69ff414a6e888190969b6ccde070ff24 completed May 9, 2026, 2:14 p.m.
NED2 Entity disambiguation (via description) batch_69ff41acd1cc8190a78f23234c8179d3 completed May 9, 2026, 2:16 p.m.
Created at: April 10, 2026, 4:04 a.m.