Triple

T2214207
Position Surface form Disambiguated ID Type / Status
Subject Durant Motors E50985 entity
Predicate brand P1500 FINISHED
Object Mason
Mason was an early 20th-century American automobile marque produced under the Durant Motors company, known for manufacturing mid-priced cars during the 1920s.
 E248231 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: Mason | Statement: [Durant Motors, brand, Mason]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mason
Context triple: [Durant Motors, brand, Mason]
  • A. Mason
    Mason is the given first name of Red Cashion, the famed American NFL referee known for his exuberant "First down!" calls.
  • B. Mason
    Mason is a common English surname of occupational origin, historically referring to a stoneworker or builder.
  • C. Hayden
    Hayden is a surname most notably associated with American actor and author Sterling Hayden, known for his roles in classic mid-20th-century films.
  • D. Myles
    Myles is a masculine given name of English origin, historically associated with figures such as Mayflower military leader Myles Standish.
  • E. Hayes
    Hayes is a suburban district in southeast London, England, known for its residential character and green spaces within the London Borough of Bromley.
  • 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: Mason
Triple: [Durant Motors, brand, Mason]
Generated description
Mason was an early 20th-century American automobile marque produced under the Durant Motors company, known for manufacturing mid-priced cars during the 1920s.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mason
Target entity description: Mason was an early 20th-century American automobile marque produced under the Durant Motors company, known for manufacturing mid-priced cars during the 1920s.
  • A. Mason
    Mason is the given first name of Red Cashion, the famed American NFL referee known for his exuberant "First down!" calls.
  • B. Mason
    Mason is a common English surname of occupational origin, historically referring to a stoneworker or builder.
  • C. Hayden
    Hayden is a surname most notably associated with American actor and author Sterling Hayden, known for his roles in classic mid-20th-century films.
  • D. Myles
    Myles is a masculine given name of English origin, historically associated with figures such as Mayflower military leader Myles Standish.
  • E. Hayes
    Hayes is a suburban district in southeast London, England, known for its residential character and green spaces within the London Borough of Bromley.
  • 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_69a88b06709c8190978fb2418470d1b6 completed March 4, 2026, 7:41 p.m.
NER Named-entity recognition batch_69abbfef875c8190b642736b4cc11d4c completed March 7, 2026, 6:04 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae6afa4f4481908cd1559624805559 completed March 9, 2026, 6:38 a.m.
NEDg Description generation batch_69ae6bbba3908190b24b6e29175cc449 completed March 9, 2026, 6:42 a.m.
NED2 Entity disambiguation (via description) batch_69ae6c5f6364819085aed383ab0ff8c5 completed March 9, 2026, 6:44 a.m.
Created at: March 4, 2026, 7:46 p.m.