Triple
T15476422
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 龍山寺 |
E376790
|
entity |
| Predicate | 所在城市地標地位 |
P43158
|
FINISHED |
| Object | 臺北市著名地標 |
—
|
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: 臺北市著名地標 | Statement: [龍山寺, 所在城市地標地位, 臺北市著名地標]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 所在城市地標地位 Context triple: [龍山寺, 所在城市地標地位, 臺北市著名地標]
-
A.
相关城市地标
Indicates a relationship where a city landmark is associated with, connected to, or relevant to a given entity or context.
-
B.
emblematicBuildingLocation
Indicates that a building serves as a symbolic or representative landmark for a particular location or area.
-
C.
partOfSkylineOf
Indicates that one entity is a visible component or feature contributing to the overall skyline profile of another entity, typically a city or urban area.
-
D.
cityRegisteredLandmark
Indicates that a city has officially registered a particular landmark within its jurisdiction.
-
E.
isLandmarkFor
chosen
Indicates that one entity serves as a notable or significant reference point or attraction for another entity, such as a place, route, or area.
- 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_69d85cd21dcc81908646251b1c26ea00 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e03f88a5dc8190a2d7830748e29180 |
completed | April 16, 2026, 1:46 a.m. |
| PD | Predicate disambiguation | batch_69ded2874b788190999158e0f043be21 |
completed | April 14, 2026, 11:49 p.m. |
Created at: April 10, 2026, 3:34 a.m.