Triple

T800174
Position Surface form Disambiguated ID Type / Status
Subject Super Bowl XXXVII E17111 entity
Predicate MVP P2630 FINISHED
Object Dexter Jackson
Dexter Jackson is a former NFL safety best known for his standout performance with the Tampa Bay Buccaneers, including earning Super Bowl XXXVII Most Valuable Player honors.
E95428 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: Dexter Jackson | Statement: [Super Bowl XXXVII, MVP, Dexter Jackson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dexter Jackson
Context triple: [Super Bowl XXXVII, MVP, Dexter Jackson]
  • A. Derek
    Derek is a masculine given name of English origin commonly used in the United States and other English-speaking countries.
  • B. Darryl
    Darryl is a masculine given name most notably associated with influential American film producer and studio executive Darryl F. Zanuck.
  • C. Dustin
    Dustin is a masculine given name commonly used in English-speaking countries.
  • D. Cedric Maxwell
    Cedric Maxwell is a former NBA forward best known for his key role in the Boston Celtics’ 1981 and 1984 championship teams and for earning the 1981 NBA Finals MVP award.
  • E. Darnell Donerson
    Darnell Donerson was the mother of singer and actress Jennifer Hudson, tragically known for her murder in 2008.
  • 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: Dexter Jackson
Triple: [Super Bowl XXXVII, MVP, Dexter Jackson]
Generated description
Dexter Jackson is a former NFL safety best known for his standout performance with the Tampa Bay Buccaneers, including earning Super Bowl XXXVII Most Valuable Player honors.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Dexter Jackson
Target entity description: Dexter Jackson is a former NFL safety best known for his standout performance with the Tampa Bay Buccaneers, including earning Super Bowl XXXVII Most Valuable Player honors.
  • A. Derek
    Derek is a masculine given name of English origin commonly used in the United States and other English-speaking countries.
  • B. Darryl
    Darryl is a masculine given name most notably associated with influential American film producer and studio executive Darryl F. Zanuck.
  • C. Dustin
    Dustin is a masculine given name commonly used in English-speaking countries.
  • D. Cedric Maxwell
    Cedric Maxwell is a former NBA forward best known for his key role in the Boston Celtics’ 1981 and 1984 championship teams and for earning the 1981 NBA Finals MVP award.
  • E. Darnell Donerson
    Darnell Donerson was the mother of singer and actress Jennifer Hudson, tragically known for her murder in 2008.
  • 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_69a49378b9c48190adbf5f62e5b7aca1 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a7cb26dc8190bdd3a278b8695873 completed March 1, 2026, 8:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69a68924e1048190ba60034c8b8b3b9e completed March 3, 2026, 7:09 a.m.
NEDg Description generation batch_69a68a0f581c8190bdb2a9bda9bce1fa completed March 3, 2026, 7:13 a.m.
NED2 Entity disambiguation (via description) batch_69a6d6042aac8190ba0b092c4b3df66e completed March 3, 2026, 12:37 p.m.
Created at: March 1, 2026, 7:38 p.m.