Triple
T19710570
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eastleigh Works |
E473333
|
entity |
| Predicate | ownedBy |
P347
|
FINISHED |
| Object |
Knorr-Bremse
Knorr-Bremse is a leading global manufacturer of braking systems and other safety-critical systems for rail and commercial vehicles.
|
E1390871
|
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: Knorr-Bremse | Statement: [Eastleigh Works, ownedBy, Knorr-Bremse]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Knorr-Bremse Context triple: [Eastleigh Works, ownedBy, Knorr-Bremse]
-
A.
WABCO
WABCO is a global supplier of braking, stability, suspension, and transmission automation systems for commercial vehicles and trailers.
-
B.
Vossloh
Vossloh is a German company specializing in rail technology and infrastructure, known for manufacturing locomotives, light rail vehicles, and railway components.
-
C.
Siemens–Duewag
Siemens–Duewag was a German rolling stock manufacturer known for producing light rail vehicles and trams used in many cities worldwide.
-
D.
Pierer Mobility AG
Pierer Mobility AG is an Austrian automotive group best known as the owner of motorcycle brands such as KTM, Husqvarna, and GasGas.
-
E.
Brugg AG
Brugg AG is a municipality in the canton of Aargau in northern Switzerland, known as a regional transport hub and local economic center.
- 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: Knorr-Bremse Triple: [Eastleigh Works, ownedBy, Knorr-Bremse]
Generated description
Knorr-Bremse is a leading global manufacturer of braking systems and other safety-critical systems for rail and commercial vehicles.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Knorr-Bremse Target entity description: Knorr-Bremse is a leading global manufacturer of braking systems and other safety-critical systems for rail and commercial vehicles.
-
A.
WABCO
WABCO is a global supplier of braking, stability, suspension, and transmission automation systems for commercial vehicles and trailers.
-
B.
Vossloh
Vossloh is a German company specializing in rail technology and infrastructure, known for manufacturing locomotives, light rail vehicles, and railway components.
-
C.
Siemens–Duewag
Siemens–Duewag was a German rolling stock manufacturer known for producing light rail vehicles and trams used in many cities worldwide.
-
D.
Pierer Mobility AG
Pierer Mobility AG is an Austrian automotive group best known as the owner of motorcycle brands such as KTM, Husqvarna, and GasGas.
-
E.
Brugg AG
Brugg AG is a municipality in the canton of Aargau in northern Switzerland, known as a regional transport hub and local economic center.
- 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_69d8e516dd048190a0b6c93ea3e71f58 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e64407ed208190944ae43b5e44bbdc |
completed | April 20, 2026, 3:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a07ab9ea0708190ba465450a31e5aef |
completed | May 15, 2026, 11:26 p.m. |
| NEDg | Description generation | batch_6a07ac97c68c819094b8013f6134ba8a |
completed | May 15, 2026, 11:30 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a07ae88e76481908b9a6fda698eec12 |
completed | May 15, 2026, 11:38 p.m. |
Created at: April 10, 2026, 1:46 p.m.