Triple
T3900187
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Opernhaus |
E90468
|
entity |
| Predicate | servesLine |
P839
|
FINISHED |
| Object | U3 line |
E300311
|
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: U3 line | Statement: [Opernhaus, servesLine, U3 line]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: U3 line Context triple: [Opernhaus, servesLine, U3 line]
-
A.
U3 line
chosen
The U3 line is a route of the Frankfurt U-Bahn rapid transit system that connects central Frankfurt with its northwestern suburbs.
-
B.
U1 line
The U1 line is a route of the Frankfurt U-Bahn rapid transit system that connects central Frankfurt with several northern suburbs.
-
C.
U4 line
The U4 line is one of Berlin's U-Bahn subway lines, running a short route in the inner city and connecting key stations including Nollendorfplatz.
-
D.
U6 line
The U6 line is a route of the Frankfurt U-Bahn rapid transit system that connects various districts across the city, including central hubs such as Hauptwache.
-
E.
U7 line
The U7 line is a route of the Frankfurt U-Bahn rapid transit system that runs across the city and serves major central stations including Hauptwache.
- 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_69aeecf17ef4819083db0a22e24d5b89 |
completed | March 9, 2026, 3:53 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5285093208190a2ba00afcbd8a261 |
completed | March 14, 2026, 9:20 a.m. |
Created at: March 9, 2026, 3:21 p.m.