Triple

T23028372
Position Surface form Disambiguated ID Type / Status
Subject Tarkio College E573387 entity
Predicate city P40 FINISHED
Object Tarkio
Tarkio is a small city in northwest Missouri known historically as the home of Tarkio College.
 E1565897 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: Tarkio | Statement: [Tarkio College, city, Tarkio]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tarkio
Context triple: [Tarkio College, city, Tarkio]
  • A. Trulaske
    Trulaske is the commonly used name for the Robert J. Trulaske, Sr. College of Business at the University of Missouri, a business school offering undergraduate and graduate programs in fields such as accounting, finance, and management.
  • B. Purdi
    Purdi is a small settlement located in Järva County in central Estonia.
  • C. Shorsey
    Shorsey is a Canadian comedy television series, created by and starring Jared Keeso, that follows the foul-mouthed hockey player Shorsey as he joins a struggling senior AAA team in Sudbury, Ontario.
  • D. Twachtman
    Twachtman is the surname of American Impressionist painter John Henry Twachtman, known for his atmospheric landscapes and innovative use of color and composition.
  • E. Yost
    Yost is a surname most notably associated with Fielding H. Yost, the pioneering early 20th-century American college football coach.
  • 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: Tarkio
Triple: [Tarkio College, city, Tarkio]
Generated description
Tarkio is a small city in northwest Missouri known historically as the home of Tarkio College.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tarkio
Target entity description: Tarkio is a small city in northwest Missouri known historically as the home of Tarkio College.
  • A. Trulaske
    Trulaske is the commonly used name for the Robert J. Trulaske, Sr. College of Business at the University of Missouri, a business school offering undergraduate and graduate programs in fields such as accounting, finance, and management.
  • B. Purdi
    Purdi is a small settlement located in Järva County in central Estonia.
  • C. Shorsey
    Shorsey is a Canadian comedy television series, created by and starring Jared Keeso, that follows the foul-mouthed hockey player Shorsey as he joins a struggling senior AAA team in Sudbury, Ontario.
  • D. Twachtman
    Twachtman is the surname of American Impressionist painter John Henry Twachtman, known for his atmospheric landscapes and innovative use of color and composition.
  • E. Yost
    Yost is a surname most notably associated with Fielding H. Yost, the pioneering early 20th-century American college football coach.
  • 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_69e245b821008190b0e09cb02092aae1 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1847f453881909a8f2affb48c64f1 completed April 29, 2026, 4:09 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0bf2b3ac308190bc241acfd02903d8 completed May 19, 2026, 5:18 a.m.
NEDg Description generation batch_6a0bf70818608190b6d7c5ee633bb4ce completed May 19, 2026, 5:37 a.m.
NED2 Entity disambiguation (via description) batch_6a0bf76284988190ac4b8f08859aecc6 completed May 19, 2026, 5:38 a.m.
Created at: April 17, 2026, 3:52 p.m.