Triple
T16071708
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tokyo 2020 Closing Ceremony |
E389877
|
entity |
| Predicate | flagHandoverFrom |
P121768
|
FINISHED |
| Object | Governor of Tokyo |
—
|
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: Governor of Tokyo | Statement: [Tokyo 2020 Closing Ceremony, flagHandoverFrom, Governor of Tokyo]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: flagHandoverFrom Context triple: [Tokyo 2020 Closing Ceremony, flagHandoverFrom, Governor of Tokyo]
-
A.
handsOverTo
Indicates that one entity transfers possession, control, or responsibility of something directly to another entity.
-
B.
flagBearerState
Indicates that a state serves as the flag-bearing entity (e.g., the country whose flag is being represented) in relation to another entity or context.
-
C.
flagBearer
Indicates that one entity serves as the carrier or holder of a flag on behalf of another entity, group, or cause.
-
D.
handedOverOfficeDuring
Indicates that one entity transferred official control, authority, or responsibility of an office or position to another entity during a specified time period.
-
E.
flagStateAfterTransfer
Indicates the resulting status or condition of a flag after a transfer action has been completed.
- 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_69d86daf32ec8190a8c0466c8f49c3c0 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e1ff63edb0819092cbb671967bbdcd |
completed | April 17, 2026, 9:37 a.m. |
| PD | Predicate disambiguation | batch_69e1827ad7c88190b867da511cbfb7fa |
completed | April 17, 2026, 12:44 a.m. |
| PDg | Predicate description generation | batch_69e1ff5cd7e481908a29214139a3de2e |
completed | April 17, 2026, 9:37 a.m. |
Created at: April 10, 2026, 4:57 a.m.