Triple
T10702713
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Japan Association for the 1970 World Exposition |
E252316
|
entity |
| Predicate | eventYearManaged |
P16171
|
FINISHED |
| Object | 1970 |
—
|
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: 1970 | Statement: [Japan Association for the 1970 World Exposition, eventYearManaged, 1970]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: eventYearManaged Context triple: [Japan Association for the 1970 World Exposition, eventYearManaged, 1970]
-
A.
hostedEventYear
chosen
Indicates the specific year in which an entity hosted a particular event.
-
B.
yearOfEventLed
Indicates the specific year in which a particular event took place or was carried out.
-
C.
organizedInYear
Indicates that an event, activity, or entity was organized or took place in a specific calendar year.
-
D.
yearOfEventSupport
Indicates the specific year in which support for a particular event occurred or was provided.
-
E.
scheduledInYear
Indicates that an event, activity, or item is planned or set to occur within a specific calendar year.
- 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_69d6aa5cbabc8190973e683950d89faf |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d6fddd28d481908abc5c1d4e5a9f3e |
completed | April 9, 2026, 1:16 a.m. |
| PD | Predicate disambiguation | batch_69d6dd8ea6408190a800f9cb57372189 |
completed | April 8, 2026, 10:58 p.m. |
Created at: April 8, 2026, 9:12 p.m.