Triple
T12057561
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 孫基禎 |
E287080
|
entity |
| Predicate | yearOfWorldRecord |
P102987
|
FINISHED |
| Object | 1935 |
—
|
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: 1935 | Statement: [孫基禎, yearOfWorldRecord, 1935]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: yearOfWorldRecord Context triple: [孫基禎, yearOfWorldRecord, 1935]
-
A.
wasWorldRecordFor
Indicates that something held the status of being the best performance or highest achievement ever recorded for a particular event, category, or metric at a given time.
-
B.
worldRecordSet
Indicates that an entity has achieved and established the best performance ever recorded in the world for a particular activity, event, or measurable criterion.
-
C.
worldRecordEndDate
Indicates the date on which a particular world record ceased to be valid or was superseded.
-
D.
heldWorldRecordTime
Indicates that an entity achieved and maintained the fastest known performance time in a specific event or activity, recognized as the official world record for a period.
-
E.
worldRecordCount
Indicates the number of world records associated with a given entity.
- 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_69d6ab4780948190bdb9f7620c2ac27e |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d9100b4ca8819084845ca4c13e34ce |
completed | April 10, 2026, 2:58 p.m. |
| PD | Predicate disambiguation | batch_69d902bda47c8190b94860b31df4a98c |
completed | April 10, 2026, 2:01 p.m. |
| PDg | Predicate description generation | batch_69d91006e14081909838412df082f794 |
completed | April 10, 2026, 2:58 p.m. |
Created at: April 8, 2026, 9:47 p.m.