Triple
T1655940
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Namba Yasaka Shrine |
E35798
|
entity |
| Predicate | photographySpot |
P17748
|
FINISHED |
| Object | lion-head stage |
—
|
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: lion-head stage | Statement: [Namba Yasaka Shrine, photographySpot, lion-head stage]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: photographySpot Context triple: [Namba Yasaka Shrine, photographySpot, lion-head stage]
-
A.
oftenPhotographedAt
chosen
Indicates that an entity is frequently the subject of photographs taken at a particular location or during a specific event.
-
B.
photographedByTourists
Indicates that the subject has been photographed by people visiting as tourists.
-
C.
touristAttractionIn
Indicates that a place functions as a tourist attraction located within a specified geographic area or entity.
-
D.
cityPanorama
Indicates a wide, comprehensive visual view or representation of a cityscape, typically encompassing many of its features in a single scene.
-
E.
hasPhotographicSignificance
Indicates that something holds notable importance or relevance in the context of photography, such as for documentation, artistic value, or visual record.
- 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_69a88606aa808190aa0b421b4271f220 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69aaf3359ce48190803b322db8ad6027 |
completed | March 6, 2026, 3:31 p.m. |
| PD | Predicate disambiguation | batch_69a907cff53c8190b424f088478d3e2c |
completed | March 5, 2026, 4:34 a.m. |
Created at: March 4, 2026, 7:29 p.m.