Triple
T26194568
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Banpo Bridge Rainbow Fountain |
E655061
|
entity |
| Predicate | shootsWater |
P2208
|
FINISHED |
| Object | into Han River |
—
|
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: into Han River | Statement: [Banpo Bridge Rainbow Fountain, shootsWater, into Han River]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: shootsWater Context triple: [Banpo Bridge Rainbow Fountain, shootsWater, into Han River]
-
A.
waterSport
Indicates participation in or association with a sport or recreational activity that takes place on or in water.
-
B.
tookOnWater
Indicates that an entity began to fill or absorb water, typically in an unintended or problematic way (e.g., a vessel leaking or flooding).
-
C.
shoots
chosen
Indicates that one entity propels a projectile or discharge toward another entity, typically with the intent to hit or affect it.
-
D.
shootsCatches
Indicates that one entity shoots something that is then caught by another entity.
-
E.
playsShoots
Indicates that an entity participates in a sport or game using a particular shooting style or handedness (e.g., a hockey player who shoots left or right).
- 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_69ee5b48236c81908fe385b6afc4f60b |
completed | April 26, 2026, 6:36 p.m. |
| NER | Named-entity recognition | batch_69f60ca50d0081909d146f3c697227aa |
completed | May 2, 2026, 2:39 p.m. |
| PD | Predicate disambiguation | batch_69f5b007ec1c819092e2c3605933f60b |
completed | May 2, 2026, 8:04 a.m. |
Created at: April 26, 2026, 8:45 p.m.