Triple
T14060891
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jingshan |
E338340
|
entity |
| Predicate | viewDirectionHighlights |
P17987
|
FINISHED |
| Object | southward view over the Forbidden City |
—
|
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: southward view over the Forbidden City | Statement: [Jingshan, viewDirectionHighlights, southward view over the Forbidden City]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: viewDirectionHighlights Context triple: [Jingshan, viewDirectionHighlights, southward view over the Forbidden City]
-
A.
highlights
Indicates that one entity draws special attention to, emphasizes, or visually marks another entity as important or noteworthy.
-
B.
viewDirectionAtSunrise
Indicates the direction an entity is oriented or looking toward at the time of sunrise.
-
C.
viewOver
chosen
Indicates that one entity has a visual perspective overlooking or facing another entity, typically providing a vantage point onto it.
-
D.
hasViewingAngles
Indicates that one entity possesses or is characterized by specific viewing angles relative to another entity or reference frame.
-
E.
gazeDirection
Indicates the direction in which an entity is looking or focusing its visual attention.
- 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_69d81c67ba6c819091935650dfb3b895 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de5686f51c81908c33143ecbaae83d |
completed | April 14, 2026, 3 p.m. |
| PD | Predicate disambiguation | batch_69de05adef888190b023ab42ef5076b6 |
completed | April 14, 2026, 9:15 a.m. |
Created at: April 9, 2026, 10:21 p.m.