Triple
T18992865
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Expo 2020 Dubai organizers |
E464732
|
entity |
| Predicate | originalScheduledPeriod |
P60078
|
FINISHED |
| Object | 2020–2021 |
—
|
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: 2020–2021 | Statement: [Expo 2020 Dubai organizers, originalScheduledPeriod, 2020–2021]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalScheduledPeriod Context triple: [Expo 2020 Dubai organizers, originalScheduledPeriod, 2020–2021]
-
A.
originalScheduleStartDate
Indicates the date on which a schedule was initially planned or set to begin, before any later changes or adjustments.
-
B.
nextScheduledCycle
Indicates that one event, process, or state is the immediately upcoming occurrence in a recurring sequence relative to a given reference point.
-
C.
scheduledDuring
chosen
Indicates that one event or activity is planned to occur within the time interval defined by another event or period.
-
D.
periodizedAs
Indicates that something has been divided or organized into distinct time periods according to a particular periodization scheme.
-
E.
originalBroadcastPeriod
Indicates the time span during which a work was first broadcast or aired in its original 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_69d8dd01a56c81909694a128c66b21d7 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d67eedc88190bfb7b327b47db76d |
completed | April 20, 2026, 7:32 a.m. |
| PD | Predicate disambiguation | batch_69e4a2f88e0c81908cb20f08bf24cd32 |
completed | April 19, 2026, 9:40 a.m. |
Created at: April 10, 2026, 12:01 p.m.