Triple
T23510337
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Schwerin Hauptbahnhof |
E572401
|
entity |
| Predicate | connectsTo |
P845
|
FINISHED |
| Object | Parchim |
—
|
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: Parchim | Statement: [Schwerin Hauptbahnhof, connectsTo, Parchim]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Parchim Context triple: [Schwerin Hauptbahnhof, connectsTo, Parchim]
-
A.
Parchim
chosen
Parchim is a small historic town in the state of Mecklenburg-Vorpommern in northern Germany.
-
B.
Parkstein
Parkstein is a market town in Bavaria, Germany, known for its prominent basalt cone and historic castle ruins.
-
C.
Pucté
Pucté is a locality within the municipality of Othón P. Blanco in the Mexican state of Quintana Roo, known for its rural character in the southern Yucatán Peninsula region.
-
D.
Damrak
Damrak is a central street and canal in Amsterdam that runs from Amsterdam Centraal Station toward Dam Square, forming one of the city’s main tourist and commercial arteries.
-
E.
Pamiers
Pamiers is a historic commune in southwestern France, known as the largest town in the Ariège department and noted for its medieval architecture and role as a local economic center.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e245b5e4208190bac8a6509867e394 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1a90455f0819092b37c69d7e73c43 |
completed | April 29, 2026, 6:45 a.m. |
Created at: April 17, 2026, 6:07 p.m.