Triple
T23407953
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Luge at the 2018 Winter Olympics |
E559985
|
entity |
| Predicate | isPartOfMultiSportEvent |
P129671
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [Luge at the 2018 Winter Olympics, isPartOfMultiSportEvent, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isPartOfMultiSportEvent Context triple: [Luge at the 2018 Winter Olympics, isPartOfMultiSportEvent, true]
-
A.
partOfMultiSportEvent
chosen
Indicates that an event or competition is included as one component within a larger multi-sport event.
-
B.
representsInMultiSportEvent
Indicates that an entity serves as a representative (such as an athlete or team) for another entity (such as a country, club, or organization) in a multi-sport event.
-
C.
plannedMultiSportEvent
Indicates that an event has been organized to include multiple different sports or athletic disciplines as part of a coordinated program.
-
D.
multiSport
Indicates that an entity participates in, is associated with, or is designed for more than one sport.
-
E.
isMultiSportConference
Indicates that a sports conference encompasses multiple sports rather than being dedicated to a single sport.
- 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.