Triple

T8267664
Position Surface form Disambiguated ID Type / Status
Subject Mark Harmon E193341 entity
Predicate givenName P17 FINISHED
Object Thomas
Thomas is the first name of American actor Mark Harmon, best known for his long-running role as Leroy Jethro Gibbs on the television series "NCIS."
 E726903 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: [Mark Harmon, givenName, Thomas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Thomas
Context triple: [Mark Harmon, givenName, Thomas]
  • A. Thomas
    Thomas is the given name of Tommy Lasorda, the Hall of Fame former manager of the Los Angeles Dodgers.
  • B. Thomas
    Thomas is the given name of Thomas Osborne, 1st Duke of Leeds, a prominent 17th-century English statesman and politician.
  • C. Thomas
    Thomas is the given name of Old Tom Morris, the 19th-century Scottish golfer regarded as a pioneer and four-time Open Championship winner.
  • D. Thomas
    Thomas is the given name of Thomas Pelham-Holles, 1st Duke of Newcastle, a prominent 18th-century British Whig statesman and prime minister.
  • E. Thomas
    Thomas is the given name of Sir Thomas Frankland, a titled member of the British Frankland family.
  • 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: [Mark Harmon, givenName, Thomas]
Generated description
Thomas is the first name of American actor Mark Harmon, best known for his long-running role as Leroy Jethro Gibbs on the television series "NCIS."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Thomas
Target entity description: Thomas is the first name of American actor Mark Harmon, best known for his long-running role as Leroy Jethro Gibbs on the television series "NCIS."
  • A. Thomas
    Thomas is the given first name of English actor Tom Hiddleston, known for his role as Loki in the Marvel Cinematic Universe.
  • B. Thomas
    Thomas is the first name of American actor and comedian Chris Parnell, known for his work on "Saturday Night Live" and "30 Rock."
  • C. 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.
  • D. Thomas
    Thomas is the given name of American actor Tom Bosley, best known for playing Howard Cunningham on the television series "Happy Days."
  • E. Thomas
    Thomas is the birth name of American actor and producer Tom Cruise, one of Hollywood’s most famous and highest-grossing movie stars.
  • 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_69ca82e081d48190986beaa51f498ab9 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb794fc4208190b268bc69ff2b28a9 completed March 31, 2026, 7:35 a.m.
NED1 Entity disambiguation (via context triple) batch_69cd94ec40a8819081655fee94614525 completed April 1, 2026, 9:58 p.m.
NEDg Description generation batch_69cdb20cc18081908269516e49ce0fd3 completed April 2, 2026, 12:02 a.m.
NED2 Entity disambiguation (via description) batch_69cdb44ff9a88190bbcb4a56f9b44dc1 completed April 2, 2026, 12:12 a.m.
Created at: March 30, 2026, 5:50 p.m.