Triple

T7805731
Position Surface form Disambiguated ID Type / Status
Subject Guy’s Hospital E180543 entity
Predicate hasBuilding P105 FINISHED
Object New Guy’s House
New Guy’s House is a modern building within the Guy’s Hospital campus in London, used primarily for clinical, educational, and administrative functions.
E694388 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: New Guy’s House | Statement: [Guy’s Hospital, hasBuilding, New Guy’s House]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: New Guy’s House
Context triple: [Guy’s Hospital, hasBuilding, New Guy’s House]
  • A. Robie House
    Robie House is a landmark Prairie School residence in Chicago, celebrated as one of Frank Lloyd Wright’s most important and influential architectural masterpieces.
  • B. Stong Residence
    Stong Residence is a student housing facility located on York University’s Keele Campus in Toronto, Canada.
  • C. Anderson House
    Anderson House is a historic Beaux-Arts mansion in Washington, D.C., that serves as the headquarters and museum of the Society of the Cincinnati.
  • D. Blake House
    Blake House is a historic residence and notable landmark located in the City of Fairfax, Virginia.
  • E. Pat House
    Pat House is a technology executive best known as a co-founder of Siebel Systems, a pioneering customer relationship management (CRM) software company.
  • 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: New Guy’s House
Triple: [Guy’s Hospital, hasBuilding, New Guy’s House]
Generated description
New Guy’s House is a modern building within the Guy’s Hospital campus in London, used primarily for clinical, educational, and administrative functions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: New Guy’s House
Target entity description: New Guy’s House is a modern building within the Guy’s Hospital campus in London, used primarily for clinical, educational, and administrative functions.
  • A. Robie House
    Robie House is a landmark Prairie School residence in Chicago, celebrated as one of Frank Lloyd Wright’s most important and influential architectural masterpieces.
  • B. Stong Residence
    Stong Residence is a student housing facility located on York University’s Keele Campus in Toronto, Canada.
  • C. Anderson House
    Anderson House is a historic Beaux-Arts mansion in Washington, D.C., that serves as the headquarters and museum of the Society of the Cincinnati.
  • D. Blake House
    Blake House is a historic residence and notable landmark located in the City of Fairfax, Virginia.
  • E. Pat House
    Pat House is a technology executive best known as a co-founder of Siebel Systems, a pioneering customer relationship management (CRM) software company.
  • 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_69ca827e50cc8190a92a733577184938 completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69caf63838b88190a085756db9ca25c4 completed March 30, 2026, 10:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69cb14439c8081908331caf450462a0e completed March 31, 2026, 12:24 a.m.
NEDg Description generation batch_69cb1638c9888190be533d55fd0b494f completed March 31, 2026, 12:32 a.m.
NED2 Entity disambiguation (via description) batch_69cb1a49beb4819090532acabb9391b1 completed March 31, 2026, 12:50 a.m.
Created at: March 30, 2026, 4:35 p.m.