Triple
T33730873
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MTRX |
E864269
|
entity |
| Predicate | operatesWithinRailSystem |
P522
|
FINISHED |
| Object | Swedish railway system |
—
|
LITERAL 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: Swedish railway system | Statement: [MTRX, operatesWithinRailSystem, Swedish railway system]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: operatesWithinRailSystem Context triple: [MTRX, operatesWithinRailSystem, Swedish railway system]
-
A.
operatedUndergroundRailway
Indicates that an entity managed or ran an underground railway system as an operator or controlling organization.
-
B.
isOnRailway
Indicates that one entity is positioned on, aligned with, or traveling along a railway track or railway system in relation to another entity.
-
C.
hasRailMode
Indicates that an entity is associated with or supports transportation via rail-based modes (such as trains, trams, or subways).
-
D.
hasRailSystem
chosen
Indicates that an entity possesses or is served by a rail-based transportation system.
-
E.
isPassengerRail
Indicates that something functions as or is classified as a passenger rail service or system, primarily used to transport people rather than freight.
- 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_69f3498a64cc8190b4b414c67b280d93 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a008ac37dc081908d360574912f40ec |
completed | May 10, 2026, 1:40 p.m. |
| PD | Predicate disambiguation | batch_6a008a67d73881909855ab4cfca3c399 |
completed | May 10, 2026, 1:38 p.m. |
Created at: May 1, 2026, 1:44 a.m.