Triple

T2859743
Position Surface form Disambiguated ID Type / Status
Subject Deerfield Academy E63290 entity
Predicate mascot P52 FINISHED
Object Big Green
Big Green is the nickname and mascot representing the athletic teams and school spirit of Deerfield Academy.
 E306476 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: Big Green | Statement: [Deerfield Academy, mascot, Big Green]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Big Green
Context triple: [Deerfield Academy, mascot, Big Green]
  • A. Big Green
    Big Green is the collective nickname for Dartmouth College’s athletic teams and, more broadly, its campus community identity.
  • B. Greenleaf
    Greenleaf is the middle name of the 19th-century American Quaker poet and abolitionist John Greenleaf Whittier.
  • C. Greenleaf
    Greenleaf is a dramatic television series that explores the secrets, scandals, and power struggles within a wealthy African-American megachurch family.
  • D. The Green One
    The Green One is an epithet of the ancient Egyptian cobra goddess Wadjet, who served as a protective deity and symbol of royal authority, especially associated with Lower Egypt and the pharaoh.
  • E. Little Green
    Little Green is a song by Joni Mitchell from her 1971 album "Blue," known for its poignant lyrics about the daughter she gave up for adoption.
  • 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: Big Green
Triple: [Deerfield Academy, mascot, Big Green]
Generated description
Big Green is the nickname and mascot representing the athletic teams and school spirit of Deerfield Academy.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Big Green
Target entity description: Big Green is the nickname and mascot representing the athletic teams and school spirit of Deerfield Academy.
  • A. Big Green
    Big Green is the collective nickname for Dartmouth College’s athletic teams and, more broadly, its campus community identity.
  • B. Greenleaf
    Greenleaf is the middle name of the 19th-century American Quaker poet and abolitionist John Greenleaf Whittier.
  • C. Greenleaf
    Greenleaf is a dramatic television series that explores the secrets, scandals, and power struggles within a wealthy African-American megachurch family.
  • D. The Green One
    The Green One is an epithet of the ancient Egyptian cobra goddess Wadjet, who served as a protective deity and symbol of royal authority, especially associated with Lower Egypt and the pharaoh.
  • E. Little Green
    Little Green is a song by Joni Mitchell from her 1971 album "Blue," known for its poignant lyrics about the daughter she gave up for adoption.
  • 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_69ab4c41e8c08190a9e8f5249cc12610 completed March 6, 2026, 9:50 p.m.
NER Named-entity recognition batch_69abdf8aec3c8190a4168d8c916b5268 completed March 7, 2026, 8:19 a.m.
NED1 Entity disambiguation (via context triple) batch_69b01d972aa481908f6cb5f27706990c completed March 10, 2026, 1:33 p.m.
NEDg Description generation batch_69b021fbc2808190b415fd8af934cf73 completed March 10, 2026, 1:51 p.m.
NED2 Entity disambiguation (via description) batch_69b02656f8488190ab0d715d1634b6a7 completed March 10, 2026, 2:10 p.m.
Created at: March 6, 2026, 10:02 p.m.