Triple
T3897345
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Polish defense industry |
E90401
|
entity |
| Predicate | hasKeyActor |
P30416
|
FINISHED |
| Object |
Telesystem-Mesko
Telesystem-Mesko is a Polish defense company known for developing advanced guided missile and precision weapon systems.
|
E398119
|
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: Telesystem-Mesko | Statement: [Polish defense industry, hasKeyActor, Telesystem-Mesko]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Telesystem-Mesko Context triple: [Polish defense industry, hasKeyActor, Telesystem-Mesko]
-
A.
Telefunken
Telefunken is a historic German electronics and television brand known for its radios, audio equipment, and consumer electronics.
-
B.
Metricom
Metricom was a pioneering wireless data communications company best known for its Ricochet wireless internet service in the 1990s.
-
C.
Fitel
Fitel was a financial technology startup where Jeff Bezos worked early in his career, before joining D. E. Shaw and later founding Amazon.
-
D.
Boxtel
Boxtel is a town and municipality in the southern Netherlands known for its historic center and location between the cities of Eindhoven and ’s-Hertogenbosch.
-
E.
Teldec
Teldec was a prominent German classical music record label known for its high-quality recordings and influential catalog of orchestral and early music.
- 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: Telesystem-Mesko Triple: [Polish defense industry, hasKeyActor, Telesystem-Mesko]
Generated description
Telesystem-Mesko is a Polish defense company known for developing advanced guided missile and precision weapon systems.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Telesystem-Mesko Target entity description: Telesystem-Mesko is a Polish defense company known for developing advanced guided missile and precision weapon systems.
-
A.
Telefunken
Telefunken is a historic German electronics and television brand known for its radios, audio equipment, and consumer electronics.
-
B.
Metricom
Metricom was a pioneering wireless data communications company best known for its Ricochet wireless internet service in the 1990s.
-
C.
Fitel
Fitel was a financial technology startup where Jeff Bezos worked early in his career, before joining D. E. Shaw and later founding Amazon.
-
D.
Boxtel
Boxtel is a town and municipality in the southern Netherlands known for its historic center and location between the cities of Eindhoven and ’s-Hertogenbosch.
-
E.
Teldec
Teldec was a prominent German classical music record label known for its high-quality recordings and influential catalog of orchestral and early music.
- 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_69aed95d315881908cbf1bf4a7215fbf |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aeecd48b208190afaa62975805d087 |
completed | March 9, 2026, 3:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b51ca0f72c819084726f631a947f8c |
completed | March 14, 2026, 8:30 a.m. |
| NEDg | Description generation | batch_69b5207c0cfc8190aae16e8a88348679 |
completed | March 14, 2026, 8:46 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b52163bf888190b38f87d22ecd200e |
completed | March 14, 2026, 8:50 a.m. |
Created at: March 9, 2026, 3:21 p.m.