Triple

T21388506
Position Surface form Disambiguated ID Type / Status
Subject Frank Ricard E527574 entity
Predicate hasNickname P39 FINISHED
Object Frank the Tank
Frank the Tank is the hard-partying alter ego of Frank Ricard, a character from the comedy film "Old School" portrayed by Will Ferrell.
 E1480690 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: Frank the Tank | Statement: [Frank Ricard, hasNickname, Frank the Tank]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Frank the Tank
Context triple: [Frank Ricard, hasNickname, Frank the Tank]
  • A. Tank Abbott
    Tank Abbott is an American mixed martial artist and professional wrestler known as one of the early brawling heavyweights in the Ultimate Fighting Championship (UFC).
  • B. Porter the Growler
    Porter the Growler is the costumed team mascot of the Kalamazoo Growlers baseball club, entertaining fans at games and community events.
  • C. Toofer
    Toofer is a pretentious, Harvard-educated writer on the fictional sketch show within the TV series "30 Rock."
  • D. Big Lug
    Big Lug is the costumed mascot character for the Lansing Lugnuts minor league baseball team, known for entertaining fans at games and community events.
  • E. Keeble
    Keeble is a fictional aristocratic surname most notably associated with Lady Constance Keeble in P. G. Wodehouse’s Blandings Castle stories.
  • 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: Frank the Tank
Triple: [Frank Ricard, hasNickname, Frank the Tank]
Generated description
Frank the Tank is the hard-partying alter ego of Frank Ricard, a character from the comedy film "Old School" portrayed by Will Ferrell.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Frank the Tank
Target entity description: Frank the Tank is the hard-partying alter ego of Frank Ricard, a character from the comedy film "Old School" portrayed by Will Ferrell.
  • A. Tank Abbott
    Tank Abbott is an American mixed martial artist and professional wrestler known as one of the early brawling heavyweights in the Ultimate Fighting Championship (UFC).
  • B. Porter the Growler
    Porter the Growler is the costumed team mascot of the Kalamazoo Growlers baseball club, entertaining fans at games and community events.
  • C. Toofer
    Toofer is a pretentious, Harvard-educated writer on the fictional sketch show within the TV series "30 Rock."
  • D. Big Lug
    Big Lug is the costumed mascot character for the Lansing Lugnuts minor league baseball team, known for entertaining fans at games and community events.
  • E. Keeble
    Keeble is a fictional aristocratic surname most notably associated with Lady Constance Keeble in P. G. Wodehouse’s Blandings Castle stories.
  • 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_69e0b51ff3748190935c0a513c62a12b completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e8b0f6ce4c81909da915139610a2a7 completed April 22, 2026, 11:28 a.m.
NED1 Entity disambiguation (via context triple) batch_6a09b42a4fa88190a167206cedb206ab completed May 17, 2026, 12:27 p.m.
NEDg Description generation batch_6a09b4bd826c8190968bc43f22a5a290 completed May 17, 2026, 12:29 p.m.
NED2 Entity disambiguation (via description) batch_6a09b543ce9881909073c30b7749757b completed May 17, 2026, 12:32 p.m.
Created at: April 16, 2026, 5:12 p.m.