Triple
T16658823
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Taipei New Year fireworks |
E404803
|
entity |
| Predicate | peakCrowdTime |
P69800
|
FINISHED |
| Object | late evening of December 31 |
—
|
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: late evening of December 31 | Statement: [Taipei New Year fireworks, peakCrowdTime, late evening of December 31]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: peakCrowdTime Context triple: [Taipei New Year fireworks, peakCrowdTime, late evening of December 31]
-
A.
deploymentPeakNumber
Indicates the maximum number of deployments (or deployment instances) reached during a specified period or under given conditions.
-
B.
peakActivity
Indicates that an entity is at its highest or most intense level of activity within a given period or context.
-
C.
peakServicePeriod
chosen
Indicates the time interval during which a service experiences its highest or most intensive level of use or operation.
-
D.
hasCrowdLevel
Indicates the degree or intensity of how crowded a place, event, or situation is.
-
E.
approximateAudienceSize
Indicates an estimated number of individuals or entities that are expected to be reached or affected in a given context.
- 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_69d8838b5fbc81908c6575c132b82e80 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e37bfcbb6881909c0419174dd017dc |
completed | April 18, 2026, 12:41 p.m. |
| PD | Predicate disambiguation | batch_69e319b1d7f08190b5ecb4a68c636c15 |
completed | April 18, 2026, 5:42 a.m. |
Created at: April 10, 2026, 5:18 a.m.