Triple
T1049556
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Deutsche Bahn |
E22662
|
entity |
| Predicate | brand |
P1500
|
FINISHED |
| Object | InterCity |
E20070
|
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: InterCity | Statement: [Deutsche Bahn, brand, InterCity]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: InterCity Context triple: [Deutsche Bahn, brand, InterCity]
-
A.
InterCity
chosen
InterCity is a category of long-distance passenger trains in several European countries, notably providing fast, regular intercity rail services.
-
B.
InterCityExpress
InterCityExpress is Germany’s high-speed train service operated by Deutsche Bahn, known for fast long-distance connections between major cities and neighboring countries.
-
C.
RegioExpress
RegioExpress is a category of Swiss regional express trains that provide relatively fast, limited-stop connections between major and medium-sized towns.
-
D.
Tren Ligero
Tren Ligero is a light rail transit system in Mexico City that complements the metro and bus networks by serving southern areas of the city.
-
E.
Auto Train
Auto Train is a long-distance Amtrak service that carries both passengers and their vehicles nonstop between the Washington, D.C. area and central Florida.
- 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_69a493da02e081908c13ff5e02a0fe7a |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b8b2c6208190b6fdf3e93b1b1d04 |
completed | March 1, 2026, 10:07 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ac429cc3c481909c55459790d6857f |
completed | March 7, 2026, 3:22 p.m. |
Created at: March 1, 2026, 7:42 p.m.