Triple
T30887987
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Annaberg-Buchholz–Flöha railway |
E786818
|
entity |
| Predicate | hasTerminusTown |
P171096
|
FINISHED |
| Object | Annaberg-Buchholz |
—
|
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: Annaberg-Buchholz | Statement: [Annaberg-Buchholz–Flöha railway, hasTerminusTown, Annaberg-Buchholz]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTerminusTown Context triple: [Annaberg-Buchholz–Flöha railway, hasTerminusTown, Annaberg-Buchholz]
-
A.
hasCapitalTerminus
Indicates that a transportation route or line has its endpoint located in a capital city.
-
B.
hasUrbanTerminus
chosen
Indicates that a route, line, or service ends or terminates within an urban area or city.
-
C.
hasTown
Indicates that one entity possesses, contains, or is associated with a town as part of its structure, jurisdiction, or composition.
-
D.
hasCentralTerminus
Indicates that one entity serves as the primary or central terminus (end point or hub) for another entity.
-
E.
hasSuburbanTerminus
Indicates that a transportation route or service ends at a terminus located in a suburban area.
- 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_69f224bbfa7c81908448e0c261c523e3 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69fce7671f108190bf3ebf54339068b5 |
completed | May 7, 2026, 7:26 p.m. |
| PD | Predicate disambiguation | batch_69fce5b5a84c81908ac1b5b9f08d48d0 |
completed | May 7, 2026, 7:19 p.m. |
Created at: April 29, 2026, 8:49 p.m.