Triple
T23781505
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yalu River Broken Bridge |
E587825
|
entity |
| Predicate | hasViewingSubject |
P127904
|
FINISHED |
| Object | North Korean cityscape |
—
|
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: North Korean cityscape | Statement: [Yalu River Broken Bridge, hasViewingSubject, North Korean cityscape]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasViewingSubject Context triple: [Yalu River Broken Bridge, hasViewingSubject, North Korean cityscape]
-
A.
hasView
Indicates that one entity provides a visual perspective or outlook onto another entity or scene.
-
B.
hasParticularView
Indicates that one entity holds, expresses, or is characterized by a specific opinion, perspective, or standpoint regarding something.
-
C.
hasViewingPointFor
chosen
Indicates that one entity serves as a vantage point or location from which another entity can be viewed or observed.
-
D.
hasViewThrough
Indicates that one entity can be seen or visually perceived through another entity acting as an intermediate medium or opening.
-
E.
hasObservationView
Indicates that an entity provides or is associated with a particular way or perspective from which observations or measurements are made.
- 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_69e2490f4ad48190b690878eec3596c6 |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1c62d7c608190b5fd0cf35f5faf42 |
completed | April 29, 2026, 8:49 a.m. |
| PD | Predicate disambiguation | batch_69f155f79e34819080f9ddb972b34deb |
completed | April 29, 2026, 12:51 a.m. |
Created at: April 17, 2026, 7:16 p.m.