Triple
T13227752
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | smart fortwo |
E314925
|
entity |
| Predicate | manufacturer |
P490
|
FINISHED |
| Object |
Smart GmbH
Smart GmbH is a German automotive company best known for producing compact city cars under the Smart brand.
|
E1028052
|
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: Smart GmbH | Statement: [smart fortwo, manufacturer, Smart GmbH]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Smart GmbH Context triple: [smart fortwo, manufacturer, Smart GmbH]
-
A.
Innotek GmbH
Innotek GmbH was a German software company best known for creating the VirtualBox virtualization platform before its acquisition by Sun Microsystems.
-
B.
Sogeti
Sogeti is a professional services and technology consulting company specializing in IT and engineering solutions, operating as a subsidiary of Capgemini.
-
C.
Intevation GmbH
Intevation GmbH is a German company specializing in free and open-source software solutions, particularly in the areas of security, geospatial systems, and IT consulting.
-
D.
SIGA Technologies
SIGA Technologies is a pharmaceutical company specializing in the development of antiviral treatments, particularly for smallpox and other orthopoxvirus infections.
-
E.
Calliope gGmbH
Calliope gGmbH is a German company focused on developing educational hardware and digital tools to teach children programming and computational thinking.
- 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: Smart GmbH Triple: [smart fortwo, manufacturer, Smart GmbH]
Generated description
Smart GmbH is a German automotive company best known for producing compact city cars under the Smart brand.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Smart GmbH Target entity description: Smart GmbH is a German automotive company best known for producing compact city cars under the Smart brand.
-
A.
Innotek GmbH
Innotek GmbH was a German software company best known for creating the VirtualBox virtualization platform before its acquisition by Sun Microsystems.
-
B.
Sogeti
Sogeti is a professional services and technology consulting company specializing in IT and engineering solutions, operating as a subsidiary of Capgemini.
-
C.
Intevation GmbH
Intevation GmbH is a German company specializing in free and open-source software solutions, particularly in the areas of security, geospatial systems, and IT consulting.
-
D.
SIGA Technologies
SIGA Technologies is a pharmaceutical company specializing in the development of antiviral treatments, particularly for smallpox and other orthopoxvirus infections.
-
E.
Calliope gGmbH
Calliope gGmbH is a German company focused on developing educational hardware and digital tools to teach children programming and computational thinking.
- 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_69d806affc688190a25b6ccc588e9c72 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98d3232d48190a3c792b025c596a6 |
completed | April 10, 2026, 11:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6ff2a4b0c8190a853a1f6f4d1cbaf |
completed | May 3, 2026, 7:54 a.m. |
| NEDg | Description generation | batch_69f70099f98081909877392c9ec49766 |
completed | May 3, 2026, 8 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69f702620bc881909d4348fd2c709232 |
completed | May 3, 2026, 8:08 a.m. |
Created at: April 9, 2026, 9:21 p.m.