Triple
T36831593
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shakhter Stadium |
E910153
|
entity |
| Predicate | hasCompetitionHosted |
P59860
|
FINISHED |
| Object | Kazakh Premier League matches |
—
|
LITERAL 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: Kazakh Premier League matches | Statement: [Shakhter Stadium, hasCompetitionHosted, Kazakh Premier League matches]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCompetitionHosted Context triple: [Shakhter Stadium, hasCompetitionHosted, Kazakh Premier League matches]
-
A.
hasHostedSport
chosen
Indicates that a place or organization has served as the venue or organizer for one or more sporting events.
-
B.
hasCompetition
Indicates that one entity is in a state of rivalry or contest with another entity, typically competing for the same goal, resource, or advantage.
-
C.
primaryCompetitionHosted
Indicates that an entity serves as the main host or organizer of a particular competition or contest.
-
D.
hasBeenHostOf
Indicates that an entity has previously served in the role of host for another entity, such as an event, show, or program.
-
E.
hasHostedTour
Indicates that an entity has organized and conducted a tour for another entity or group.
- F. None of above.
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_69f76e7e9d60819092442fba73290a46 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a037c8e2c648190a65fc9c7872861af |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a0e039481908a4a2666f76c5363 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:13 p.m.