Triple

T9435419
Position Surface form Disambiguated ID Type / Status
Subject Llandaff E227491 entity
Predicate nearbyArea P2064 FINISHED
Object Danescourt
Danescourt is a suburban residential area of Cardiff, Wales, situated close to the historic district of Llandaff.
E799961 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: Danescourt | Statement: [Llandaff, nearbyArea, Danescourt]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Danescourt
Context triple: [Llandaff, nearbyArea, Danescourt]
  • A. Crystal Court
    Crystal Court is a local shopping center serving the community of Crystal Lake, Illinois with a variety of retail and service businesses.
  • B. Killian Court
    Killian Court is a large, iconic open space at the heart of MIT’s Cambridge campus, framed by neoclassical buildings and often used for major ceremonies and gatherings.
  • C. Sunningdale
    Sunningdale is an affluent village in Berkshire, England, known for its prestigious golf courses and leafy residential character.
  • D. Marsh Court
    Marsh Court is an early 20th-century English country house in Hampshire, celebrated as a quintessential example of Sir Edwin Lutyens’ Arts and Crafts domestic architecture.
  • E. Riversdale
    Riversdale is a residential suburb in Melbourne, Australia, known for its access to public transport and proximity to local amenities and green spaces.
  • 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: Danescourt
Triple: [Llandaff, nearbyArea, Danescourt]
Generated description
Danescourt is a suburban residential area of Cardiff, Wales, situated close to the historic district of Llandaff.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Danescourt
Target entity description: Danescourt is a suburban residential area of Cardiff, Wales, situated close to the historic district of Llandaff.
  • A. Crystal Court
    Crystal Court is a local shopping center serving the community of Crystal Lake, Illinois with a variety of retail and service businesses.
  • B. Killian Court
    Killian Court is a large, iconic open space at the heart of MIT’s Cambridge campus, framed by neoclassical buildings and often used for major ceremonies and gatherings.
  • C. Sunningdale
    Sunningdale is an affluent village in Berkshire, England, known for its prestigious golf courses and leafy residential character.
  • D. Marsh Court
    Marsh Court is an early 20th-century English country house in Hampshire, celebrated as a quintessential example of Sir Edwin Lutyens’ Arts and Crafts domestic architecture.
  • E. Riversdale
    Riversdale is a residential suburb in Melbourne, Australia, known for its access to public transport and proximity to local amenities and green spaces.
  • 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_69ca8437a7ac81908651de48f2d2141d completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd7e64109081908222f590928bc572 completed April 1, 2026, 8:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1104a002481909ca805893bac61c6 completed April 4, 2026, 1:21 p.m.
NEDg Description generation batch_69d110ffda7881908e4edd692b818464 completed April 4, 2026, 1:24 p.m.
NED2 Entity disambiguation (via description) batch_69d11190dd6c8190b6318df44daa9858 completed April 4, 2026, 1:26 p.m.
Created at: March 30, 2026, 7:50 p.m.