Triple

T5196356
Position Surface form Disambiguated ID Type / Status
Subject Connecticut Route 58 E117280 entity
Predicate hasJunctionWith P1018 FINISHED
Object Route 302
Route 302 is a state highway in Connecticut that serves as a regional connector route in the southwestern part of the state.
E500848 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: Route 302 | Statement: [Connecticut Route 58, hasJunctionWith, Route 302]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Route 302
Context triple: [Connecticut Route 58, hasJunctionWith, Route 302]
  • A. Route 3
    Route 3 is a major east–west highway in northern New Jersey that connects the New Jersey Turnpike area to the Lincoln Tunnel approach into New York City.
  • B. Route 3A
    Route 3A is a state highway in Massachusetts that generally parallels Route 3, connecting various coastal and suburban communities south and north of Boston.
  • C. Route 30
    Route 30 is a major east–west highway in Massachusetts that serves as a key commercial and commuter corridor through communities such as Framingham.
  • D. Route 34
    Route 34 is a SEPTA subway–surface trolley line in Philadelphia that runs between Center City and West Philadelphia.
  • E. Route 5
    Route 5 is a major Chilean highway forming the backbone of the country’s north–south road network as part of the Pan-American Highway.
  • 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: Route 302
Triple: [Connecticut Route 58, hasJunctionWith, Route 302]
Generated description
Route 302 is a state highway in Connecticut that serves as a regional connector route in the southwestern part of the state.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Route 302
Target entity description: Route 302 is a state highway in Connecticut that serves as a regional connector route in the southwestern part of the state.
  • A. Route 3
    Route 3 is a major east–west highway in northern New Jersey that connects the New Jersey Turnpike area to the Lincoln Tunnel approach into New York City.
  • B. Route 3A
    Route 3A is a state highway in Massachusetts that generally parallels Route 3, connecting various coastal and suburban communities south and north of Boston.
  • C. Route 30
    Route 30 is a major east–west highway in Massachusetts that serves as a key commercial and commuter corridor through communities such as Framingham.
  • D. Route 34
    Route 34 is a SEPTA subway–surface trolley line in Philadelphia that runs between Center City and West Philadelphia.
  • E. Route 5
    Route 5 is a major Chilean highway forming the backbone of the country’s north–south road network as part of the Pan-American Highway.
  • 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_69bd4462ed04819084fcb01eb9d2fa74 completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd7a1c2184819083f4b1d8830bebae completed March 20, 2026, 4:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69bee09d84f08190b8270394fc35e195 completed March 21, 2026, 6:17 p.m.
NEDg Description generation batch_69bee5b5c6688190ab4dcdcf50424436 completed March 21, 2026, 6:38 p.m.
NED2 Entity disambiguation (via description) batch_69bee67364588190b5d8f31af7adf1f4 completed March 21, 2026, 6:41 p.m.
Created at: March 20, 2026, 1:46 p.m.