Triple
T10443463
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Konstal 105Na |
E246225
|
entity |
| Predicate | manufacturer |
P490
|
FINISHED |
| Object |
Konstal
Konstal is a Polish rolling stock manufacturer best known for producing trams and other urban rail vehicles used widely across Poland and Eastern Europe.
|
E864113
|
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: Konstal | Statement: [Konstal 105Na, manufacturer, Konstal]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Konstal Context triple: [Konstal 105Na, manufacturer, Konstal]
-
A.
Borregaard
Borregaard is a Norwegian biorefinery company that produces advanced and sustainable bio-based chemicals and materials from wood.
-
B.
Höganäs
Höganäs is a coastal town and municipality in Skåne County in southern Sweden, known for its ceramics industry and scenic location by the Öresund Strait.
-
C.
Tengbom
Tengbom is a prominent Swedish architectural firm known for its influential role in shaping modern Scandinavian architecture.
-
D.
Bilröst
Bilröst is an alternate name for Bifröst, the rainbow bridge in Norse mythology that connects the realm of the gods to the world of humans.
-
E.
Kleiser
Kleiser is a surname most notably associated with American film director Randal Kleiser, known for directing the musical romantic comedy "Grease."
- 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: Konstal Triple: [Konstal 105Na, manufacturer, Konstal]
Generated description
Konstal is a Polish rolling stock manufacturer best known for producing trams and other urban rail vehicles used widely across Poland and Eastern Europe.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Konstal Target entity description: Konstal is a Polish rolling stock manufacturer best known for producing trams and other urban rail vehicles used widely across Poland and Eastern Europe.
-
A.
Borregaard
Borregaard is a Norwegian biorefinery company that produces advanced and sustainable bio-based chemicals and materials from wood.
-
B.
Höganäs
Höganäs is a coastal town and municipality in Skåne County in southern Sweden, known for its ceramics industry and scenic location by the Öresund Strait.
-
C.
Tengbom
Tengbom is a prominent Swedish architectural firm known for its influential role in shaping modern Scandinavian architecture.
-
D.
Bilröst
Bilröst is an alternate name for Bifröst, the rainbow bridge in Norse mythology that connects the realm of the gods to the world of humans.
-
E.
Kleiser
Kleiser is a surname most notably associated with American film director Randal Kleiser, known for directing the musical romantic comedy "Grease."
- 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_69d381c04fe08190957c26c526a3b05a |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4fdbd731c819084dfff83b4481ae8 |
completed | April 7, 2026, 12:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d87ee0c2208190ae8d51a2a89a2586 |
completed | April 10, 2026, 4:38 a.m. |
| NEDg | Description generation | batch_69d886c3fdcc8190a67a7f7788b8a2e8 |
completed | April 10, 2026, 5:12 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69d88dc15ab481909011c5de93bbab14 |
completed | April 10, 2026, 5:42 a.m. |
Created at: April 6, 2026, 12:15 p.m.