Triple

T4781024
Position Surface form Disambiguated ID Type / Status
Subject Tom Bosley E106164 entity
Predicate givenName P17 FINISHED
Object Thomas
Thomas is the given name of American actor Tom Bosley, best known for playing Howard Cunningham on the television series "Happy Days."
E472995 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: Thomas | Statement: [Tom Bosley, givenName, Thomas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Thomas
Context triple: [Tom Bosley, givenName, Thomas]
  • A. Thomas
    Thomas is the middle name of Edward Thomas Wailes, an American diplomat.
  • B. Thomas
    Thomas is the given first name of the renowned American playwright Tennessee Williams, known for works such as "A Streetcar Named Desire" and "Cat on a Hot Tin Roof."
  • C. Thomas
    Thomas is the middle name of William T. Sampson, a notable U.S. Navy admiral from the Spanish–American War era.
  • D. Thomas
    Thomas is the given first name of American astronaut Ken Mattingly, known for his role in the Apollo and Space Shuttle programs.
  • E. Thomas
    Thomas is the given name of Sir Thomas Blamey, an Australian field marshal and senior military commander during World War II.
  • 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: Thomas
Triple: [Tom Bosley, givenName, Thomas]
Generated description
Thomas is the given name of American actor Tom Bosley, best known for playing Howard Cunningham on the television series "Happy Days."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Thomas
Target entity description: Thomas is the given name of American actor Tom Bosley, best known for playing Howard Cunningham on the television series "Happy Days."
  • A. Thomas
    Thomas is the given first name of the renowned American playwright Tennessee Williams, known for works such as "A Streetcar Named Desire" and "Cat on a Hot Tin Roof."
  • B. Thomas
    Thomas is the full given name of Tom Brady, the legendary NFL quarterback widely regarded as one of the greatest players in American football history.
  • C. Thomas
    Thomas is the given name of Tommy Lasorda, the Hall of Fame former manager of the Los Angeles Dodgers.
  • D. Thomas
    Thomas is the given name of English actor Tom Courtenay, a prominent figure in British cinema and theatre since the 1960s.
  • E. Thomas
    Thomas is the given name of Tom Savini, the renowned American special effects makeup artist, actor, and director known for his groundbreaking work in horror films.
  • 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_69bd43f3074c8190937e7b0a457fe9f1 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd65aa577c81909ec1b94e47810169 completed March 20, 2026, 3:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69be4d8e724c8190bfca713d5d022be6 completed March 21, 2026, 7:49 a.m.
NEDg Description generation batch_69be516836ec8190b5ee3829945ffc06 completed March 21, 2026, 8:06 a.m.
NED2 Entity disambiguation (via description) batch_69be52cd7aa481908963eb1ec2683a76 completed March 21, 2026, 8:11 a.m.
Created at: March 20, 2026, 1:21 p.m.