Triple
T23407848
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Biathlon at the 2018 Winter Olympics |
E559983
|
entity |
| Predicate | mixedEvent |
P122745
|
FINISHED |
| Object | Mixed 2 × 6 km + 2 × 7.5 km relay |
—
|
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: Mixed 2 × 6 km + 2 × 7.5 km relay | Statement: [Biathlon at the 2018 Winter Olympics, mixedEvent, Mixed 2 × 6 km + 2 × 7.5 km relay]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mixedEvent Context triple: [Biathlon at the 2018 Winter Olympics, mixedEvent, Mixed 2 × 6 km + 2 × 7.5 km relay]
-
A.
mainEventFor
Indicates that one event is the primary or central event associated with another entity, such as a context, grouping, or larger occurrence.
-
B.
typicalEvent
Indicates that the associated event is a common, characteristic, or prototypical occurrence for the given entity or situation.
-
C.
alternativeEvent
Indicates that one event serves as an alternative or substitute option to another event within the same context.
-
D.
combineEvent
chosen
Indicates that two or more events are merged into a single, unified event or outcome.
-
E.
significantConcurrentEvent
Indicates that another event occurs at the same time and is of notable or meaningful importance in relation to the referenced event.
- 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_69e2454b3a5881909c64773dc8a5d289 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1a50f3f90819084fb682597fee1e1 |
completed | April 29, 2026, 6:28 a.m. |
| PD | Predicate disambiguation | batch_69f061ed34288190a2e5e8cae03b0095 |
completed | April 28, 2026, 7:29 a.m. |
Created at: April 17, 2026, 5:38 p.m.