Triple
T32564916
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | U.S. Route 90 Business |
E832334
|
entity |
| Predicate | namedStructureOnRoute |
P53579
|
FINISHED |
| Object | Crescent City Connection |
—
|
NE NERFINISHED |
How this triple was built (2 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: Crescent City Connection | Statement: [U.S. Route 90 Business, namedStructureOnRoute, Crescent City Connection]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: namedStructureOnRoute Context triple: [U.S. Route 90 Business, namedStructureOnRoute, Crescent City Connection]
-
A.
namedPassAlongRoute
Indicates that an entity is designated by name as a waypoint or intermediate stop along a specified route.
-
B.
routeStructure
Indicates the structural or organizational relationship between a route and its constituent segments, paths, or connections.
-
C.
hasMajorStructureOnRoute
chosen
Indicates that a significant physical structure is located along or directly associated with a particular route.
-
D.
connectedRoute
Indicates that there is a direct or logically continuous path linking two locations or segments within a network.
-
E.
namingStructure
Indicates a relationship where one entity defines, organizes, or constrains the naming or label format used for another entity.
- F. None of above.
Provenance (3 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_69f34927bb308190ad94da1b11cad13c |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f78c61ed4c8190ad84c918fa9af55a |
completed | May 3, 2026, 5:56 p.m. |
| PD | Predicate disambiguation | batch_69f78b8cb3a881909ebaac1b503988c2 |
completed | May 3, 2026, 5:53 p.m. |
Created at: May 1, 2026, 1:03 a.m.