Triple
T1324948
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Spartak Moscow |
E28304
|
entity |
| Predicate | rival |
P437
|
FINISHED |
| Object | CSKA Moscow |
E28149
|
NE FINISHED |
How this triple was built (2 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: CSKA Moscow | Statement: [Spartak Moscow, rival, CSKA Moscow]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: CSKA Moscow Context triple: [Spartak Moscow, rival, CSKA Moscow]
-
A.
CSKA Moscow
chosen
CSKA Moscow is a major Russian sports club best known for its successful football and basketball teams and intense rivalries with other Moscow clubs.
-
B.
Dynamo Moscow
Dynamo Moscow is a prominent Russian professional ice hockey club based in Moscow, historically known for developing elite players such as Alex Ovechkin.
-
C.
Lokomotiv Moscow
Lokomotiv Moscow is a major Russian professional football club from Moscow, known for competing in the Russian Premier League and being one of the city’s traditional powerhouses.
-
D.
Spartak Moscow
Spartak Moscow is one of Russia’s most successful and popular football clubs, historically known as the “people’s team” and a major force in the Soviet and Russian leagues.
-
E.
Dinamo Riga
Dinamo Riga is a professional ice hockey club based in Riga, Latvia, known for competing in top European and international leagues.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69a498540a2481909e807a762280d3ba |
completed | March 1, 2026, 7:49 p.m. |
| NER | Named-entity recognition | batch_69a4c19e81c0819092f85201ae34422a |
completed | March 1, 2026, 10:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69adeab9dd008190a07b22ba3bd5bc22 |
completed | March 8, 2026, 9:31 p.m. |
Created at: March 1, 2026, 7:55 p.m.