Triple
T27907078
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Buk-gu, Ulsan |
E705812
|
entity |
| Predicate | isOneOfDistrictsOf |
P115673
|
FINISHED |
| Object | Ulsan Metropolitan City |
—
|
NE NERFINISHED |
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: Ulsan Metropolitan City | Statement: [Buk-gu, Ulsan, isOneOfDistrictsOf, Ulsan Metropolitan City]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isOneOfDistrictsOf Context triple: [Buk-gu, Ulsan, isOneOfDistrictsOf, Ulsan Metropolitan City]
-
A.
isSingleDistrictFor
Indicates that one district uniquely and exclusively serves or applies to a given entity, with no other districts sharing that role.
-
B.
isInnerDistrictOf
chosen
Indicates that one district is geographically or administratively located within and subordinate to another, larger district.
-
C.
isKeyDistrictOf
Indicates that a district holds strategic, political, or administrative importance within a larger region, organization, or system.
-
D.
occursInDistrict
Indicates that an event or activity takes place within the boundaries of a specific district.
-
E.
isMainDistrictOf
Indicates that a district serves as the primary or central administrative district of a specified larger area or jurisdiction.
- 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_69ef96b5aad08190be36a277c31e7004 |
completed | April 27, 2026, 5:02 p.m. |
| NER | Named-entity recognition | batch_69f674e06c9481909ed0ea736408f0d7 |
completed | May 2, 2026, 10:04 p.m. |
| PD | Predicate disambiguation | batch_69f673c2f81c8190bf369226306eef09 |
completed | May 2, 2026, 9:59 p.m. |
Created at: April 27, 2026, 6:46 p.m.