Triple
T22703556
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chen Yi |
E561384
|
entity |
| Predicate | officeEndForGovernorOfTaiwanProvince |
P149384
|
FINISHED |
| Object | 1947-05-16 |
—
|
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: 1947-05-16 | Statement: [Chen Yi, officeEndForGovernorOfTaiwanProvince, 1947-05-16]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: officeEndForGovernorOfTaiwanProvince Context triple: [Chen Yi, officeEndForGovernorOfTaiwanProvince, 1947-05-16]
-
A.
officeEndTime (President of the Republic of China)
Indicates the time at which a President of the Republic of China’s term in office concludes.
-
B.
officeEnd (Chairman of State Council)
Indicates the date or point in time when an entity’s tenure as Chairman of the State Council comes to an end.
-
C.
officeStartTime (President of the Republic of China)
Indicates the date and time at which a person begins their term in office as President of the Republic of China.
-
D.
officeEndTime (Chairperson of the Democratic Progressive Party)
Indicates the time at which the chairperson’s term in office as leader of the Democratic Progressive Party ends.
-
E.
endTime (Mayor of Taipei)
Indicates the point in time at which a person’s tenure as Mayor of Taipei concludes.
- 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_69e2454e615481909c177440be559d2c |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f178cca1e48190bbe7910f13692803 |
completed | April 29, 2026, 3:19 a.m. |
| PD | Predicate disambiguation | batch_69ee62bd657c81909f7b01245b080a5f |
completed | April 26, 2026, 7:08 p.m. |
| PDg | Predicate description generation | batch_69ee8843d3308190b6e22bb98ae5c3d8 |
completed | April 26, 2026, 9:48 p.m. |
Created at: April 17, 2026, 3:16 p.m.