Triple
T10666236
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | FC Kairat |
E251363
|
entity |
| Predicate | hasRival |
P1375
|
FINISHED |
| Object | FC Astana |
E242095
|
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: FC Astana | Statement: [FC Kairat, hasRival, FC Astana]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: FC Astana Context triple: [FC Kairat, hasRival, FC Astana]
-
A.
FC Astana
chosen
FC Astana is a professional football club from Kazakhstan that competes in the country’s top division and regularly features in European competitions.
-
B.
FC Kairat
FC Kairat is a professional football club from Almaty, Kazakhstan, known as one of the country’s most historic and successful teams.
-
C.
Barys Astana
Barys Astana is a professional ice hockey team from Astana, Kazakhstan that competes in the Kontinental Hockey League (KHL).
-
D.
Shakhter Karagandy football club
Shakhter Karagandy football club is a professional Kazakhstani football team known for competing in the country’s top division and achieving domestic league success.
-
E.
FC Aktobe
FC Aktobe is a professional football club from Aktobe, Kazakhstan, known for competing in the Kazakhstan Premier League and winning multiple national titles.
- 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_69d6aa5b0d2881909584b20efc5877f0 |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d6f31f87748190bb44db8afa901763 |
completed | April 9, 2026, 12:30 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d97a9566e08190a92b49ce73963078 |
completed | April 10, 2026, 10:32 p.m. |
Created at: April 8, 2026, 9:08 p.m.