Triple

T3090354
Position Surface form Disambiguated ID Type / Status
Subject McDowell County E64465 entity
Predicate hasTown P847 FINISHED
Object Keystone
Keystone is a small town located in McDowell County, West Virginia, historically associated with the region’s coal mining industry.
 E325354 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: Keystone | Statement: [McDowell County, hasTown, Keystone]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Keystone
Context triple: [McDowell County, hasTown, Keystone]
  • A. Northstar
    Northstar is a commuter rail service in Minnesota that connects downtown Minneapolis with its northwestern suburbs and exurban communities.
  • B. Heart of America
    Heart of America is a nickname for Kansas City, Missouri, highlighting its central location and cultural significance in the United States.
  • C. Dirigo
    Dirigo is the Latin motto meaning "I lead," famously associated with the state of Maine and the University of Maine.
  • D. Southesk
    Southesk is the traditional war cry associated with Clan Carnegie, a Scottish noble family from Angus.
  • E. Bakken
    Bakken is a surname most notably associated with Earl Bakken, the American engineer and co-founder of the medical device company Medtronic.
  • 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: Keystone
Triple: [McDowell County, hasTown, Keystone]
Generated description
Keystone is a small town located in McDowell County, West Virginia, historically associated with the region’s coal mining industry.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Keystone
Target entity description: Keystone is a small town located in McDowell County, West Virginia, historically associated with the region’s coal mining industry.
  • A. Northstar
    Northstar is a commuter rail service in Minnesota that connects downtown Minneapolis with its northwestern suburbs and exurban communities.
  • B. Heart of America
    Heart of America is a nickname for Kansas City, Missouri, highlighting its central location and cultural significance in the United States.
  • C. Dirigo
    Dirigo is the Latin motto meaning "I lead," famously associated with the state of Maine and the University of Maine.
  • D. Southesk
    Southesk is the traditional war cry associated with Clan Carnegie, a Scottish noble family from Angus.
  • E. Bakken
    Bakken is a surname most notably associated with Earl Bakken, the American engineer and co-founder of the medical device company Medtronic.
  • 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_69ad857c97d88190b26f9b1c90839c77 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada20d8f788190b05b8b6b5042bc1a completed March 8, 2026, 4:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69b1f8a6fe2081909e2bf9ee5629f017 completed March 11, 2026, 11:20 p.m.
NEDg Description generation batch_69b1f94a05608190bc163a6950586ff9 completed March 11, 2026, 11:22 p.m.
NED2 Entity disambiguation (via description) batch_69b1f9ad0b148190b98f93699598dd1e completed March 11, 2026, 11:24 p.m.
Created at: March 8, 2026, 3:03 p.m.