Triple
T5825732
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 斎藤 実 |
E129217
|
entity |
| Predicate | 朝鮮総督在任開始日 |
P23958
|
FINISHED |
| Object | 1919-08-12 |
—
|
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: 1919-08-12 | Statement: [斎藤 実, 朝鮮総督在任開始日, 1919-08-12]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 朝鮮総督在任開始日 Context triple: [斎藤 実, 朝鮮総督在任開始日, 1919-08-12]
-
A.
startTime as Governor-General of Korea
chosen
Indicates the point in time at which an individual began serving in the role of Governor-General of Korea.
-
B.
JapaneseOccupationStart
Indicates the point in time when a Japanese occupation of a place or population begins.
-
C.
timeInOfficeBeginsIn
Indicates the point in time or date when an entity’s term, tenure, or period in office starts.
-
D.
termStartAsActingGovernor
Indicates that a person’s term in office began while they were serving in the capacity of an acting governor rather than as a fully appointed or elected governor.
-
E.
lastOfficeHolderStartDate
Indicates the date on which the most recent person to hold a particular office or position began their term.
- 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_69c00849d55481908b4f9f5543e0bf6d |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c0400f1af881908d376ea4793f6dea |
completed | March 22, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_69c0333fdd7081908d829265caa2ac11 |
completed | March 22, 2026, 6:21 p.m. |
Created at: March 22, 2026, 3:53 p.m.