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.