Triple
T3738564
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saab Kockums |
E79643
|
entity |
| Predicate | historicalOrigin |
P1823
|
FINISHED |
| Object |
Kockums Mekaniska Verkstad
Kockums Mekaniska Verkstad was a historic Swedish industrial and shipbuilding company based in Malmö, known for constructing naval vessels and submarines.
|
E384119
|
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: Kockums Mekaniska Verkstad | Statement: [Saab Kockums, historicalOrigin, Kockums Mekaniska Verkstad]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kockums Mekaniska Verkstad Context triple: [Saab Kockums, historicalOrigin, Kockums Mekaniska Verkstad]
-
A.
Erla Maschinenwerk
Erla Maschinenwerk was a German aircraft manufacturing company best known for producing Messerschmitt fighter planes under license during World War II.
-
B.
Marcussen & Søn
Marcussen & Søn is a renowned Danish firm celebrated for crafting high-quality pipe organs for churches and concert halls worldwide.
-
C.
Neoplan
Neoplan is a German bus and coach manufacturer renowned for its innovative, high-end touring and city buses.
-
D.
Scania
Scania is a historical province in southern Sweden known for its fertile farmland, coastal landscapes, and former status as part of Denmark.
-
E.
Scania
Scania is a Swedish manufacturer renowned for its heavy trucks, buses, and industrial and marine engines.
- 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: Kockums Mekaniska Verkstad Triple: [Saab Kockums, historicalOrigin, Kockums Mekaniska Verkstad]
Generated description
Kockums Mekaniska Verkstad was a historic Swedish industrial and shipbuilding company based in Malmö, known for constructing naval vessels and submarines.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Kockums Mekaniska Verkstad Target entity description: Kockums Mekaniska Verkstad was a historic Swedish industrial and shipbuilding company based in Malmö, known for constructing naval vessels and submarines.
-
A.
Erla Maschinenwerk
Erla Maschinenwerk was a German aircraft manufacturing company best known for producing Messerschmitt fighter planes under license during World War II.
-
B.
Marcussen & Søn
Marcussen & Søn is a renowned Danish firm celebrated for crafting high-quality pipe organs for churches and concert halls worldwide.
-
C.
Neoplan
Neoplan is a German bus and coach manufacturer renowned for its innovative, high-end touring and city buses.
-
D.
Scania
Scania is a Swedish manufacturer renowned for its heavy trucks, buses, and industrial and marine engines.
-
E.
Scania
Scania is a historical province in southern Sweden known for its fertile farmland, coastal landscapes, and former status as part of Denmark.
- 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_69ad8b115610819095b02007da5ca3cb |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69adcb3e9248819098d481fe29e1c628 |
completed | March 8, 2026, 7:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b4db20bdfc81909cd27278ff5d9716 |
completed | March 14, 2026, 3:50 a.m. |
| NEDg | Description generation | batch_69b4dbeb2a2881908bfa05613fafc53c |
completed | March 14, 2026, 3:54 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b4dc65c88c8190b1215fed2451d45f |
completed | March 14, 2026, 3:56 a.m. |
Created at: March 8, 2026, 3:34 p.m.