Triple
T3898148
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Langwasser Süd |
E90421
|
entity |
| Predicate | servedByLine |
P1293
|
FINISHED |
| Object | U1 |
E90418
|
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: U1 | Statement: [Langwasser Süd, servedByLine, U1]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: U1 Context triple: [Langwasser Süd, servedByLine, U1]
-
A.
U1
chosen
U1 is a major line of the Nuremberg U-Bahn rapid transit system, connecting key districts across the Nuremberg metropolitan area.
-
B.
U5
U5 is one of the lines of the Frankfurt U-Bahn rapid transit system in Frankfurt, Germany.
-
C.
U6
U6 is the IATA airline designator assigned to Ural Airlines, a Russian commercial air carrier.
-
D.
U6
U6 is a major north–south line of the Berlin U-Bahn rapid transit system, connecting several key districts across the city.
-
E.
U21
U21 is a global network of leading research-intensive universities that collaborate to enhance higher education and research through international partnerships and initiatives.
- 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_69aed95d315881908cbf1bf4a7215fbf |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aeecd48b208190afaa62975805d087 |
completed | March 9, 2026, 3:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b51ca0f72c819084726f631a947f8c |
completed | March 14, 2026, 8:30 a.m. |
Created at: March 9, 2026, 3:21 p.m.