Triple
T8053833
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Geumjeong Fortress |
E187742
|
entity |
| Predicate | topView |
P17987
|
FINISHED |
| Object | panoramic views of Busan |
—
|
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: panoramic views of Busan | Statement: [Geumjeong Fortress, topView, panoramic views of Busan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: topView Context triple: [Geumjeong Fortress, topView, panoramic views of Busan]
-
A.
topLocation
Indicates that one location is the primary, highest-level, or most prominent place associated with another entity or set of locations.
-
B.
viewOver
chosen
Indicates that one entity has a visual perspective overlooking or facing another entity, typically providing a vantage point onto it.
-
C.
primaryView
Indicates that one view or representation is designated as the main or default perspective among multiple possible views of the same entity or content.
-
D.
viewType
Indicates the specific manner or format in which something is displayed, presented, or visually arranged.
-
E.
targetVertical
Indicates that one entity is directed toward, aligned with, or intended for a specific vertical market, domain, or industry segment.
- 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_69ca82b15e948190a62fd7af5218426a |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3f9fb8dc8190bacc1f66ddfd1cbf |
completed | March 31, 2026, 3:29 a.m. |
| PD | Predicate disambiguation | batch_69cb049a1b9c8190811c396421ebf9c9 |
completed | March 30, 2026, 11:17 p.m. |
Created at: March 30, 2026, 5:25 p.m.