Triple
T30956679
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Beijing 2008 Olympic Torch Relay |
E788693
|
entity |
| Predicate | openingCeremonyUse |
P48976
|
FINISHED |
| Object | lighting of Olympic cauldron |
—
|
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: lighting of Olympic cauldron | Statement: [Beijing 2008 Olympic Torch Relay, openingCeremonyUse, lighting of Olympic cauldron]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: openingCeremonyUse Context triple: [Beijing 2008 Olympic Torch Relay, openingCeremonyUse, lighting of Olympic cauldron]
-
A.
hasOpeningCeremony
Indicates that an event or entity includes or is associated with a formal opening ceremony.
-
B.
openingCeremonyHeldBefore
Indicates that the opening ceremony of one event or activity occurs earlier in time than the opening ceremony of another.
-
C.
closingCeremonyParticipation
Indicates that an entity takes part in the closing ceremony of an event or activity.
-
D.
openingOccasion
chosen
Indicates the event, circumstance, or occasion during which an opening (such as a launch, inauguration, or start) takes place.
-
E.
openingPerformance
Indicates the performance or event that serves as the first or inaugural showing in a series, season, or run.
- 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_69f224c28c1881908c33b45d689f1724 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f7516d5b4081908588a6feb541f355 |
completed | May 3, 2026, 1:45 p.m. |
| PD | Predicate disambiguation | batch_69f74d40ebb081909daf60623e38f41d |
completed | May 3, 2026, 1:27 p.m. |
Created at: April 29, 2026, 8:54 p.m.