Triple

T9010674
Position Surface form Disambiguated ID Type / Status
Subject Havre, Montana E215461 entity
Predicate locatedOn P40 FINISHED
Object Hi-Line
The Hi-Line is a sparsely populated region of northern Montana centered along the BNSF Railway and U.S. Highway 2, known for its small towns, prairie landscapes, and agricultural economy.
E772679 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: Hi-Line | Statement: [Havre, Montana, locatedOn, Hi-Line]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hi-Line
Context triple: [Havre, Montana, locatedOn, Hi-Line]
  • A. Haise
    Haise is the surname of Fred Haise, the American astronaut and Apollo 13 lunar module pilot.
  • B. Deering
    Deering is a small Inupiat community and city located on the Seward Peninsula in northwestern Alaska.
  • C. Dairyland
    Dairyland was the former name of the city now known as La Palma in Orange County, California, reflecting its origins as a dairy-farming community.
  • D. Harline
    Harline is a surname most notably associated with Leigh Harline, an American film composer known for his work with Walt Disney Studios.
  • E. U Line
    U Line is a light metro line in the Seoul metropolitan area that serves the city of Uijeongbu with driverless trains on an elevated and mostly automated system.
  • 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: Hi-Line
Triple: [Havre, Montana, locatedOn, Hi-Line]
Generated description
The Hi-Line is a sparsely populated region of northern Montana centered along the BNSF Railway and U.S. Highway 2, known for its small towns, prairie landscapes, and agricultural economy.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Hi-Line
Target entity description: The Hi-Line is a sparsely populated region of northern Montana centered along the BNSF Railway and U.S. Highway 2, known for its small towns, prairie landscapes, and agricultural economy.
  • A. Haise
    Haise is the surname of Fred Haise, the American astronaut and Apollo 13 lunar module pilot.
  • B. Deering
    Deering is a small Inupiat community and city located on the Seward Peninsula in northwestern Alaska.
  • C. Dairyland
    Dairyland was the former name of the city now known as La Palma in Orange County, California, reflecting its origins as a dairy-farming community.
  • D. Harline
    Harline is a surname most notably associated with Leigh Harline, an American film composer known for his work with Walt Disney Studios.
  • E. U Line
    U Line is a light metro line in the Seoul metropolitan area that serves the city of Uijeongbu with driverless trains on an elevated and mostly automated system.
  • 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_69ca83a2bf088190986ee7a8eb90407d completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc69c1571881908d0b144786b5ee1f completed April 1, 2026, 12:41 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfdb9dca848190952427bb5712081f completed April 3, 2026, 3:24 p.m.
NEDg Description generation batch_69cfdc5b230881908057cc868e44ea44 completed April 3, 2026, 3:27 p.m.
NED2 Entity disambiguation (via description) batch_69cfdcfc28288190b849b3f0216a7e9a completed April 3, 2026, 3:30 p.m.
Created at: March 30, 2026, 7:06 p.m.