Triple

T8556937
Position Surface form Disambiguated ID Type / Status
Subject David Farquharson E202593 entity
Predicate designed P184 FINISHED
Object South Hall
South Hall is a building designed by Scottish architect David Farquharson, noted for his work in the late 19th and early 20th centuries.
 E743256 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: South Hall | Statement: [David Farquharson, designed, South Hall]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: South Hall
Context triple: [David Farquharson, designed, South Hall]
  • A. South Hall
    South Hall is one of the main academic buildings on the University of California, Berkeley campus, housing classrooms, offices, and university departments.
  • B. South Hall
    South Hall is a section of the Mausoleum of Mao Zedong in Beijing, forming part of the memorial complex dedicated to China's former leader.
  • C. South Hall
    South Hall is a major exhibition hall within the Los Angeles Convention Center complex, commonly used for large trade shows, conventions, and public events.
  • D. Loomis Hall
    Loomis Hall is a building on the Yale University campus that houses the university’s Department of Mathematics.
  • E. Devlin Hall
    Devlin Hall is a historic academic building on Boston College’s Chestnut Hill campus, known for housing classrooms and faculty offices.
  • 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: South Hall
Triple: [David Farquharson, designed, South Hall]
Generated description
South Hall is a building designed by Scottish architect David Farquharson, noted for his work in the late 19th and early 20th centuries.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: South Hall
Target entity description: South Hall is a building designed by Scottish architect David Farquharson, noted for his work in the late 19th and early 20th centuries.
  • A. South Hall
    South Hall is one of the main academic buildings on the University of California, Berkeley campus, housing classrooms, offices, and university departments.
  • B. South Hall
    South Hall is a section of the Mausoleum of Mao Zedong in Beijing, forming part of the memorial complex dedicated to China's former leader.
  • C. South Hall
    South Hall is a major exhibition hall within the Los Angeles Convention Center complex, commonly used for large trade shows, conventions, and public events.
  • D. Loomis Hall
    Loomis Hall is a building on the Yale University campus that houses the university’s Department of Mathematics.
  • E. Devlin Hall
    Devlin Hall is a historic academic building on Boston College’s Chestnut Hill campus, known for housing classrooms and faculty offices.
  • 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.