Triple
T13226065
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Korean Intellectual Property Office |
E314882
|
entity |
| Predicate | typeOfIPOffice |
P5164
|
FINISHED |
| Object | national IP office |
—
|
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: national IP office | Statement: [Korean Intellectual Property Office, typeOfIPOffice, national IP office]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfIPOffice Context triple: [Korean Intellectual Property Office, typeOfIPOffice, national IP office]
-
A.
hasOfficeType
chosen
Indicates that an entity’s office is classified as a specific type or category of office.
-
B.
governsOfficeType
Indicates that an entity has authoritative control or regulatory oversight over a particular type or category of office.
-
C.
specifiesOffice
Indicates that an entity is assigned to or associated with a particular office or official position.
-
D.
ipoType
Indicates the type or category of an entity’s initial public offering (IPO) event.
-
E.
establishedOffice
Indicates that an entity created or set up an official office or place of operation.
- 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_69d806affc688190a25b6ccc588e9c72 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98d3128348190836158467e9cfbe2 |
completed | April 10, 2026, 11:52 p.m. |
| PD | Predicate disambiguation | batch_69d98bcb21648190aef241de1e7887e2 |
completed | April 10, 2026, 11:46 p.m. |
Created at: April 9, 2026, 9:19 p.m.