Triple
T8276528
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stuttgart Hauptbahnhof |
E193559
|
entity |
| Predicate | plannedConfiguration |
P80800
|
FINISHED |
| Object | underground through station |
—
|
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: underground through station | Statement: [Stuttgart Hauptbahnhof, plannedConfiguration, underground through station]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: plannedConfiguration Context triple: [Stuttgart Hauptbahnhof, plannedConfiguration, underground through station]
-
A.
plannedComponent
Indicates that one entity is intended or scheduled to serve as a component or part of another entity in a planned or future configuration.
-
B.
plannedStructure
chosen
Indicates that one entity is a structure that is intended or designed to be built or established in the future, rather than already existing.
-
C.
plannedUpgrade
Indicates that an entity has a scheduled or intended improvement or enhancement to be carried out in the future.
-
D.
planned
Indicates that an entity has intentionally arranged or scheduled another entity or event to occur in the future.
-
E.
plannedWith
Indicates that an entity created or arranged a plan in collaboration or coordination with 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_69ca82e14ae481908ffdb822cd2192bc |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb798d69508190b581ad8a38730175 |
completed | March 31, 2026, 7:36 a.m. |
| PD | Predicate disambiguation | batch_69cb70a4525481909399d313a6247ace |
completed | March 31, 2026, 6:58 a.m. |
Created at: March 30, 2026, 5:51 p.m.