Triple

T9212300
Position Surface form Disambiguated ID Type / Status
Subject Brian Frosh E221152 entity
Predicate familyName P18 FINISHED
Object Frosh
Frosh is a surname most notably associated with Brian Frosh, an American lawyer and former Attorney General of Maryland.
 E785410 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: Frosh | Statement: [Brian Frosh, familyName, Frosh]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Frosh
Context triple: [Brian Frosh, familyName, Frosh]
  • A. College Green
    College Green is a historic open space in Westminster, London, commonly used as a backdrop for political interviews and media broadcasts near the UK Parliament.
  • B. College Green
    College Green is a historic public square in central Dublin, Ireland, known as a civic and commercial hub surrounded by landmark buildings including Trinity College Dublin.
  • C. Junger
    Junger is the surname of Sebastian Junger, an American author, journalist, and documentary filmmaker known for works like "The Perfect Storm" and "Restrepo."
  • D. Junior
    Junior is a 1994 comedy film in which Arnold Schwarzenegger plays a scientist who becomes pregnant as part of an experimental fertility project.
  • E. Junior
    Junior is the protagonist of the novel "Love" by Toni Morrison, around whom the story’s complex relationships and themes of desire, memory, and power revolve.
  • 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: Frosh
Triple: [Brian Frosh, familyName, Frosh]
Generated description
Frosh is a surname most notably associated with Brian Frosh, an American lawyer and former Attorney General of Maryland.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Frosh
Target entity description: Frosh is a surname most notably associated with Brian Frosh, an American lawyer and former Attorney General of Maryland.
  • A. College Green
    College Green is a historic open space in Westminster, London, commonly used as a backdrop for political interviews and media broadcasts near the UK Parliament.
  • B. College Green
    College Green is a historic public square in central Dublin, Ireland, known as a civic and commercial hub surrounded by landmark buildings including Trinity College Dublin.
  • C. Junger
    Junger is the surname of Sebastian Junger, an American author, journalist, and documentary filmmaker known for works like "The Perfect Storm" and "Restrepo."
  • D. Junior
    Junior is a 1994 comedy film in which Arnold Schwarzenegger plays a scientist who becomes pregnant as part of an experimental fertility project.
  • E. Junior
    Junior is the protagonist of the novel "Love" by Toni Morrison, around whom the story’s complex relationships and themes of desire, memory, and power revolve.
  • 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_69ca83e9d0e081908bdb71097201a06c completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69ccd9b69838819088f33ca995fce222 completed April 1, 2026, 8:39 a.m.
NED1 Entity disambiguation (via context triple) batch_69d0660839f88190afdfb8bc2d710fc3 completed April 4, 2026, 1:14 a.m.
NEDg Description generation batch_69d06770ccf08190b00bf35c16a80071 completed April 4, 2026, 1:20 a.m.
NED2 Entity disambiguation (via description) batch_69d06864b8c48190b8e08ab9c1c85c9a completed April 4, 2026, 1:24 a.m.
Created at: March 30, 2026, 7:27 p.m.