Triple
T29519878
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Central Stadium Cherkasy |
E748900
|
entity |
| Predicate | isSecondaryUse |
P78228
|
FINISHED |
| Object | athletics |
—
|
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: athletics | Statement: [Central Stadium Cherkasy, isSecondaryUse, athletics]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isSecondaryUse Context triple: [Central Stadium Cherkasy, isSecondaryUse, athletics]
-
A.
hasSecondaryUsage
chosen
Indicates that an entity is associated with an additional, non-primary function or purpose beyond its main intended use.
-
B.
hasSecondary
Indicates that an entity is associated with an additional or subordinate counterpart beyond its primary one.
-
C.
isPrimarilyUsedAs
Indicates that one entity serves mainly or most commonly in the role, function, or purpose specified by the other entity.
-
D.
hasSecondaryUser
Indicates that an entity is associated with an additional, non-primary user who also has access to or control over it.
-
E.
hasSecondarySee
Indicates that an entity has an additional, secondary “see also” reference or cross-link to another related entity.
- 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_69f0bd461c208190bec20bbf24e02cc5 |
completed | April 28, 2026, 1:59 p.m. |
| NER | Named-entity recognition | batch_69f66c97ee788190a4ef192d3141fa57 |
completed | May 2, 2026, 9:28 p.m. |
| PD | Predicate disambiguation | batch_69f6659b62fc8190b21555d0ba54db2d |
completed | May 2, 2026, 8:59 p.m. |
Created at: April 28, 2026, 4:40 p.m.