Triple
T21650320
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yongsan Presidential Office |
E534318
|
entity |
| Predicate | hasOfficialUseStart |
P32466
|
FINISHED |
| Object | 2022 |
—
|
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: 2022 | Statement: [Yongsan Presidential Office, hasOfficialUseStart, 2022]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOfficialUseStart Context triple: [Yongsan Presidential Office, hasOfficialUseStart, 2022]
-
A.
hasOfficialUse
Indicates that something is used in an authorized or formally recognized capacity, typically by an official body or for official purposes.
-
B.
hasOfficial
Indicates that an entity is formally associated with, represented by, or served by a designated official or office-holder.
-
C.
firstOfficialUse
chosen
Indicates the earliest point in time when something was formally or officially put into use.
-
D.
endDateOfficialUse
Indicates the date on which the official use or validity of something (such as a document, status, or authorization) comes to an end.
-
E.
usedAsOfficialTime
Indicates that something is employed as the recognized standard or authoritative reference for measuring time in an official context.
- 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_69e0c466aec88190ba39c7543dbc8ba2 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef5913cd9c81908a6ce9bc741416bf |
completed | April 27, 2026, 12:39 p.m. |
| PD | Predicate disambiguation | batch_69e696826c3c81909270791e79760937 |
completed | April 20, 2026, 9:11 p.m. |
Created at: April 16, 2026, 6:35 p.m.