Triple

T15563
Position Surface form Disambiguated ID Type / Status
Subject Harvard Yard E310 entity
Predicate contains P35 FINISHED
Object Grays Hall
Grays Hall is a historic freshman dormitory in Harvard Yard at Harvard University, known for housing first-year students in the heart of the campus.
 E8300 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: Grays Hall | Statement: [Harvard Yard, contains, Grays Hall]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Grays Hall
Context triple: [Harvard Yard, contains, Grays Hall]
  • A. Mower Hall
    Mower Hall is a freshman dormitory building located within Harvard University's historic Harvard Yard.
  • B. Sever Hall
    Sever Hall is a historic red-brick academic building at Harvard University, known for its distinctive Romanesque architecture and use as a classroom facility.
  • C. Griswold Hall
    Griswold Hall is an academic and administrative building at Harvard Law School that houses faculty offices, classrooms, and legal research facilities.
  • D. White Hall
    White Hall is a grand ceremonial room within the Livadia Palace, historically used for important receptions and diplomatic events.
  • E. Clarendon
    Clarendon is a vibrant urban neighborhood in Arlington, Virginia, known for its lively dining, shopping, and nightlife scene.
  • 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: Grays Hall
Triple: [Harvard Yard, contains, Grays Hall]
Generated description
Grays Hall is a historic freshman dormitory in Harvard Yard at Harvard University, known for housing first-year students in the heart of the campus.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Grays Hall
Target entity description: Grays Hall is a historic freshman dormitory in Harvard Yard at Harvard University, known for housing first-year students in the heart of the campus.
  • A. Mower Hall chosen
    Mower Hall is a freshman dormitory building located within Harvard University's historic Harvard Yard.
  • B. Sever Hall
    Sever Hall is a historic red-brick academic building at Harvard University, known for its distinctive Romanesque architecture and use as a classroom facility.
  • C. Griswold Hall
    Griswold Hall is an academic and administrative building at Harvard Law School that houses faculty offices, classrooms, and legal research facilities.
  • D. White Hall
    White Hall is a grand ceremonial room within the Livadia Palace, historically used for important receptions and diplomatic events.
  • E. Clarendon
    Clarendon is a vibrant urban neighborhood in Arlington, Virginia, known for its lively dining, shopping, and nightlife scene.
  • 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_69a23d7ad88c8190bffe8ab091d86642 completed Feb. 28, 2026, 12:57 a.m.
NER Named-entity recognition batch_69a2400257208190b3cd87ad2a06c18f completed Feb. 28, 2026, 1:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69a266e1e9408190989c703bfc694682 completed Feb. 28, 2026, 3:54 a.m.
NEDg Description generation batch_69a267c8dd688190bef495cc98c4966f completed Feb. 28, 2026, 3:58 a.m.
NED2 Entity disambiguation (via description) batch_69a268227ecc8190bb4b4149a7e15923 completed Feb. 28, 2026, 3:59 a.m.
Created at: Feb. 28, 2026, 1:02 a.m.