Triple
T17893896
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MVD Spetsnaz |
E447384
|
entity |
| Predicate | notableUnit |
P304
|
FINISHED |
| Object |
Rus
Rus is a prominent Russian MVD special forces unit known for high-risk counter-terrorism and hostage-rescue operations.
|
E1294979
|
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: Rus | Statement: [MVD Spetsnaz, notableUnit, Rus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rus Context triple: [MVD Spetsnaz, notableUnit, Rus]
-
A.
Rus
Rus was a medieval East Slavic cultural and political realm that laid the foundations for the modern nations of Russia, Ukraine, and Belarus.
-
B.
Russan
Russan is a commune in southern France situated along the Gardon River.
-
C.
Russo
Russo is an Italian surname commonly used as a variant of Rossi, often associated with people of Italian heritage.
-
D.
Russian
Russian is an East Slavic language that serves as the official language of Russia and a major lingua franca across much of Eastern Europe and Central Asia.
-
E.
RUS
RUS is the National Rail station code assigned to Russell Square station in London.
- 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: Rus Triple: [MVD Spetsnaz, notableUnit, Rus]
Generated description
Rus is a prominent Russian MVD special forces unit known for high-risk counter-terrorism and hostage-rescue operations.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Rus Target entity description: Rus is a prominent Russian MVD special forces unit known for high-risk counter-terrorism and hostage-rescue operations.
-
A.
Rus
Rus was a medieval East Slavic cultural and political realm that laid the foundations for the modern nations of Russia, Ukraine, and Belarus.
-
B.
Russan
Russan is a commune in southern France situated along the Gardon River.
-
C.
Russo
Russo is an Italian surname commonly used as a variant of Rossi, often associated with people of Italian heritage.
-
D.
Russian
Russian is an East Slavic language that serves as the official language of Russia and a major lingua franca across much of Eastern Europe and Central Asia.
-
E.
RUS
RUS is the National Rail station code assigned to Russell Square station in London.
- 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_69d8b9f59bd48190a6fc925a855b8bac |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e49d7ccf808190b4c1fd477043bcc8 |
completed | April 19, 2026, 9:16 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a031b22e4bc8190b9b9632870d10334 |
completed | May 12, 2026, 12:20 p.m. |
| NEDg | Description generation | batch_6a031c438a448190aabbd2057b47a88b |
completed | May 12, 2026, 12:25 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a031cc67f7881908933c14a5386fb25 |
completed | May 12, 2026, 12:27 p.m. |
Created at: April 10, 2026, 10:19 a.m.