Triple

T2098463
Position Surface form Disambiguated ID Type / Status
Subject Virginia State Route 28 E37037 entity
Predicate abbreviation P43 FINISHED
Object SR 28
SR 28 is a primary state highway in Virginia that serves as a major north–south transportation corridor in the northern part of the state.
 E236859 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: SR 28 | Statement: [Virginia State Route 28, abbreviation, SR 28]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SR 28
Context triple: [Virginia State Route 28, abbreviation, SR 28]
  • A. SR 27
    SR 27 is a state highway in Maine that runs north–south, connecting coastal communities with inland towns and recreational areas.
  • B. SR 21
    SR 21 is a primary state highway in Alabama that runs north–south across the state, connecting several major towns and highways.
  • C. SR 286
    SR 286 is a major north–south arterial highway in Fairfax County, Virginia, commonly known as the Fairfax County Parkway.
  • D. SR 18
    SR 18 is a state highway in Georgia that runs east–west across the central part of the state, connecting several small towns and regional routes.
  • E. SR 143
    SR 143 is a short Arizona state highway in the Phoenix metropolitan area that primarily serves as a connector between Interstate 10 and Phoenix Sky Harbor International Airport.
  • 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: SR 28
Triple: [Virginia State Route 28, abbreviation, SR 28]
Generated description
SR 28 is a primary state highway in Virginia that serves as a major north–south transportation corridor in the northern part of the state.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SR 28
Target entity description: SR 28 is a primary state highway in Virginia that serves as a major north–south transportation corridor in the northern part of the state.
  • A. SR 27
    SR 27 is a state highway in Maine that runs north–south, connecting coastal communities with inland towns and recreational areas.
  • B. SR 21
    SR 21 is a primary state highway in Alabama that runs north–south across the state, connecting several major towns and highways.
  • C. SR 286
    SR 286 is a major north–south arterial highway in Fairfax County, Virginia, commonly known as the Fairfax County Parkway.
  • D. SR 18
    SR 18 is a state highway in Georgia that runs east–west across the central part of the state, connecting several small towns and regional routes.
  • E. SR 143
    SR 143 is a short Arizona state highway in the Phoenix metropolitan area that primarily serves as a connector between Interstate 10 and Phoenix Sky Harbor International Airport.
  • 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_69a8861828948190924aa30c08806b3a completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69abba9de75c81909770409b5ae62c24 completed March 7, 2026, 5:41 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae518d29d4819090aa2a1c6fc7304d completed March 9, 2026, 4:50 a.m.
NEDg Description generation batch_69ae522f0394819087a7e7d9c6ca354c completed March 9, 2026, 4:53 a.m.
NED2 Entity disambiguation (via description) batch_69ae5316acf881908dde9d83c36c8fd0 completed March 9, 2026, 4:56 a.m.
Created at: March 4, 2026, 7:43 p.m.