Triple
T4646951
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Beretta |
E102193
|
entity |
| Predicate | subsidiary |
P258
|
FINISHED |
| Object |
Sako
Sako is a Finnish firearms manufacturer renowned for its high-quality rifles and precision engineering, operating as a subsidiary of Beretta.
|
E457056
|
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: Sako | Statement: [Beretta, subsidiary, Sako]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sako Context triple: [Beretta, subsidiary, Sako]
-
A.
Hewrami
Hewrami is a dialect of the Gorani branch of Northwestern Iranian languages, traditionally spoken by Kurdish communities in the Hawraman region of western Iran and northeastern Iraq.
-
B.
Guni
Guni is a biblical figure mentioned in the Hebrew Bible as a descendant within the tribe of Naphtali.
-
C.
Mopin
Mopin is a major agrarian festival of the Galo (Adi) people in Arunachal Pradesh, celebrated with traditional dances, rituals, and feasting to invoke prosperity and ward off evil.
-
D.
Orpo
Orpo was the uniformed regular police force of Nazi Germany, responsible for maintaining public order and involved in numerous wartime atrocities and repressive activities.
-
E.
Sakaar
Sakaar is a chaotic, trash-covered planet ruled by the Grandmaster in the Marvel Cinematic Universe, known for its gladiatorial contests and bizarre cosmic detritus.
- 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: Sako Triple: [Beretta, subsidiary, Sako]
Generated description
Sako is a Finnish firearms manufacturer renowned for its high-quality rifles and precision engineering, operating as a subsidiary of Beretta.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Sako Target entity description: Sako is a Finnish firearms manufacturer renowned for its high-quality rifles and precision engineering, operating as a subsidiary of Beretta.
-
A.
Hewrami
Hewrami is a dialect of the Gorani branch of Northwestern Iranian languages, traditionally spoken by Kurdish communities in the Hawraman region of western Iran and northeastern Iraq.
-
B.
Guni
Guni is a biblical figure mentioned in the Hebrew Bible as a descendant within the tribe of Naphtali.
-
C.
Mopin
Mopin is a major agrarian festival of the Galo (Adi) people in Arunachal Pradesh, celebrated with traditional dances, rituals, and feasting to invoke prosperity and ward off evil.
-
D.
Orpo
Orpo was the uniformed regular police force of Nazi Germany, responsible for maintaining public order and involved in numerous wartime atrocities and repressive activities.
-
E.
Sakaar
Sakaar is a chaotic, trash-covered planet ruled by the Grandmaster in the Marvel Cinematic Universe, known for its gladiatorial contests and bizarre cosmic detritus.
- 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_69bd43d71a308190afea7280841b0de8 |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd62fcb8508190a17c4437b3d226b2 |
completed | March 20, 2026, 3:08 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bdfadfe8b4819088a5fb1565bbe94a |
completed | March 21, 2026, 1:56 a.m. |
| NEDg | Description generation | batch_69bdfb9422e48190819d5d99e72e8854 |
completed | March 21, 2026, 1:59 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69bdfc6ac91c819090776365d3dc05d4 |
completed | March 21, 2026, 2:03 a.m. |
Created at: March 20, 2026, 1:14 p.m.