Triple
T7862710
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ma Ying-jeou |
E182537
|
entity |
| Predicate | endTime (Mayor of Taipei) |
P79426
|
FINISHED |
| Object | 2006-12-25 |
—
|
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: 2006-12-25 | Statement: [Ma Ying-jeou, endTime (Mayor of Taipei), 2006-12-25]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: endTime (Mayor of Taipei) Context triple: [Ma Ying-jeou, endTime (Mayor of Taipei), 2006-12-25]
-
A.
endTime (mayor of North York)
Indicates the point in time at which a person’s tenure as mayor of North York concludes.
-
B.
endTime (as Mayor of Detroit)
Indicates the date and time at which a person’s tenure as Mayor of Detroit concludes.
-
C.
endTime (National Commission on Fiscal Responsibility and Reform)
Indicates the point in time at which the activities, mandate, or existence of the National Commission on Fiscal Responsibility and Reform conclude.
-
D.
endTime (Rector of Masaryk University)
Indicates the point in time at which a person’s tenure as Rector of Masaryk University concludes.
-
E.
endTime (NSA directorship)
Indicates the point in time at which an individual's tenure in the NSA directorship role 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_69ca82887fd48190975896bf38c4596b |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb36be5f408190b82a097b0825c57a |
completed | March 31, 2026, 2:51 a.m. |
| PD | Predicate disambiguation | batch_69cae925ca388190ae4a01fa76e957e8 |
completed | March 30, 2026, 9:20 p.m. |
| PDg | Predicate description generation | batch_69caf786ec748190b6347b0c94335550 |
completed | March 30, 2026, 10:21 p.m. |
Created at: March 30, 2026, 4:53 p.m.