Triple
T23042810
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kochstraße U-Bahn station |
E573784
|
entity |
| Predicate | hasStationCode |
P1289
|
FINISHED |
| Object |
KOS
KOS is the station code used to identify the Berlin U-Bahn stop Kochstraße, located near Checkpoint Charlie in the city center.
|
E1569011
|
NE FINISHED |
How this triple was built (4 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: KOS | Statement: [Kochstraße U-Bahn station, hasStationCode, KOS]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: KOS Context triple: [Kochstraße U-Bahn station, hasStationCode, KOS]
-
A.
KOS
KOS is the vehicle registration code assigned to the town of Oświęcim in southern Poland.
-
B.
KOS
KOS is the three-letter International Olympic Committee country code representing Kosovo in Olympic competitions.
-
C.
KCOS
KCOS is the ICAO airport code for Colorado Springs Airport, a public civil-military airport serving Colorado Springs, Colorado.
-
D.
KOST
KOST is a Los Angeles-based adult contemporary radio station known for its mainstream pop and soft rock programming.
-
E.
KOSB
KOSB is the commonly used abbreviation for the King's Own Scottish Borderers, a historic line infantry regiment of the British Army with strong ties to Scotland's border region.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: KOS Triple: [Kochstraße U-Bahn station, hasStationCode, KOS]
Generated description
KOS is the station code used to identify the Berlin U-Bahn stop Kochstraße, located near Checkpoint Charlie in the city center.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: KOS Target entity description: KOS is the station code used to identify the Berlin U-Bahn stop Kochstraße, located near Checkpoint Charlie in the city center.
-
A.
KOS
KOS is the vehicle registration code assigned to the town of Oświęcim in southern Poland.
-
B.
KOS
KOS is the three-letter International Olympic Committee country code representing Kosovo in Olympic competitions.
-
C.
KCOS
KCOS is the ICAO airport code for Colorado Springs Airport, a public civil-military airport serving Colorado Springs, Colorado.
-
D.
KOST
KOST is a Los Angeles-based adult contemporary radio station known for its mainstream pop and soft rock programming.
-
E.
KOSB
KOSB is the commonly used abbreviation for the King's Own Scottish Borderers, a historic line infantry regiment of the British Army with strong ties to Scotland's border region.
- F. None of above. chosen
Provenance (5 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_69e245b9c11481909d06c872214d21af |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18516417081908bf747b20de23a75 |
completed | April 29, 2026, 4:12 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0c0ad85abc8190ab6328224aa3320f |
completed | May 19, 2026, 7:01 a.m. |
| NEDg | Description generation | batch_6a0c0f873d588190be23c0040c50024c |
completed | May 19, 2026, 7:21 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0c0fe69cf0819091fe545b9fdfeaca |
completed | May 19, 2026, 7:23 a.m. |
Created at: April 17, 2026, 3:54 p.m.