Triple
T1065757
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paralympic Games |
E23205
|
entity |
| Predicate | hasOpeningCeremony |
P24274
|
FINISHED |
| Object | Paralympic opening ceremony |
—
|
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: Paralympic opening ceremony | Statement: [Paralympic Games, hasOpeningCeremony, Paralympic opening ceremony]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOpeningCeremony Context triple: [Paralympic Games, hasOpeningCeremony, Paralympic opening ceremony]
-
A.
openingCeremonyDirector
Indicates the person who is responsible for directing or overseeing the opening ceremony of an event.
-
B.
ceremonyHeld
Indicates that a formal ceremony or ritual event has taken place at a particular time and/or location.
-
C.
ceremonyBroadcastOn
Indicates that a particular ceremony is broadcast or aired on a specified channel, platform, or medium.
-
D.
awardCeremonyBroadcastOn
Indicates that an award ceremony event is broadcast or aired on a particular channel, platform, or medium.
-
E.
celebratedEvent
Indicates that an entity has been honored, commemorated, or festively observed as a special event.
- F. None of above. chosen
Provenance (4 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_69a493ee1f908190992b5f0d1b04459b |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b9e1047481909af1cf8df2a01fff |
completed | March 1, 2026, 10:12 p.m. |
| PD | Predicate disambiguation | batch_69a4b736f1e881909bace735b38c0ade |
completed | March 1, 2026, 10:01 p.m. |
| PDg | Predicate description generation | batch_69a4b9df0a308190a0d87dcd8afe58bc |
completed | March 1, 2026, 10:12 p.m. |
Created at: March 1, 2026, 7:42 p.m.