Triple
T15915345
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Skanstull metro station |
E385953
|
entity |
| Predicate | locatedOn |
P40
|
FINISHED |
| Object | Green Line 18 |
E1134381
|
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: Green Line 18 | Statement: [Skanstull metro station, locatedOn, Green Line 18]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Green Line 18 Context triple: [Skanstull metro station, locatedOn, Green Line 18]
-
A.
Green Line 17
Green Line 17 is a branch of Stockholm's metro Green Line that serves several southern and central districts of the city.
-
B.
Green line 18
chosen
Green line 18 is a route on Stockholm's metro system that serves the southern suburbs and terminates at Farsta strand station.
-
C.
Green Line
The Green Line is one of Chicago's elevated rapid transit routes, running primarily along the city's West and South Sides as part of the Chicago "L" system.
-
D.
Green Line
The Green Line is one of the main corridors of the Hyderabad Metro rapid transit system, serving key areas of the city along its north–south axis.
-
E.
Green Line
The Green Line is one of the color-coded rapid transit routes in the Washington Metro system, serving key neighborhoods in Washington, D.C. and parts of Maryland.
- 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_69d86da686e4819097cbf3b1fc2d881d |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e1566216d481908dd6e3acaa26fd45 |
completed | April 16, 2026, 9:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffc3bb7d608190babbea74a9ca9f4c |
completed | May 9, 2026, 11:31 p.m. |
Created at: April 10, 2026, 4:52 a.m.