Triple
T15983416
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tokyo 2020 Opening Ceremony |
E387630
|
entity |
| Predicate | COVID19MeasuresIncluded |
P58395
|
FINISHED |
| Object | mask wearing |
—
|
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: mask wearing | Statement: [Tokyo 2020 Opening Ceremony, COVID19MeasuresIncluded, mask wearing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: COVID19MeasuresIncluded Context triple: [Tokyo 2020 Opening Ceremony, COVID19MeasuresIncluded, mask wearing]
-
A.
stanceOnCOVID-19Measures
Indicates a subject’s position, attitude, or level of support or opposition toward policies and actions taken in response to COVID-19 (such as restrictions, mandates, or public health measures).
-
B.
epidemicControlActivities
chosen
Indicates actions or measures undertaken to prevent, contain, or mitigate the spread and impact of an epidemic.
-
C.
hasQuarantine
Indicates that an entity is subject to, or associated with, a quarantine condition or period.
-
D.
isEmergencyMeasure
Indicates that an action, policy, or measure is taken specifically in response to an urgent or crisis situation, typically as a temporary or exceptional intervention.
-
E.
hasHealthCode
Indicates that an entity is associated with a specific health-related classification or status code.
- 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_69d86da94ccc819083d187f5dc6a123e |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e17d4d08f481909f38b75e3f42d9ab |
completed | April 17, 2026, 12:22 a.m. |
| PD | Predicate disambiguation | batch_69e142d9d8e881909b559a3e3ca21d24 |
completed | April 16, 2026, 8:13 p.m. |
Created at: April 10, 2026, 4:54 a.m.