Triple
T8876186
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Green Line (SEPTA) |
E211290
|
entity |
| Predicate | hasRoute |
P4374
|
FINISHED |
| Object | Route 34 |
E38204
|
NE FINISHED |
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: Route 34 | Statement: [Green Line (SEPTA), hasRoute, Route 34]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Route 34 Context triple: [Green Line (SEPTA), hasRoute, Route 34]
-
A.
Route 34
chosen
Route 34 is a SEPTA subway–surface trolley line in Philadelphia that runs between Center City and West Philadelphia.
-
B.
Route 35
Route 35 is a major New Jersey state highway running along the central Jersey Shore and through several urban and suburban communities.
-
C.
Route 32
Route 32 is a state highway in New York that runs through several communities in the Hudson Valley and central parts of the state.
-
D.
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.
-
E.
Route 36
Route 36 is a SEPTA subway–surface trolley line in Philadelphia that provides light rail service between Center City and Southwest Philadelphia.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca838e78748190934d82db3104f855 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc61472cc081909e51b4a35a20ef43 |
completed | April 1, 2026, 12:05 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfaba6f2f481909a30f71e96bc9079 |
completed | April 3, 2026, 11:59 a.m. |
Created at: March 30, 2026, 6:52 p.m.