Triple
T21242230
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sinking of ROKS Cheonan |
E523502
|
entity |
| Predicate | seaDepthAtSite |
P36028
|
FINISHED |
| Object | approximately 25 meters |
—
|
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: approximately 25 meters | Statement: [Sinking of ROKS Cheonan, seaDepthAtSite, approximately 25 meters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: seaDepthAtSite Context triple: [Sinking of ROKS Cheonan, seaDepthAtSite, approximately 25 meters]
-
A.
seaDepth
chosen
Indicates the measured vertical distance from the sea surface down to the seafloor at a given location.
-
B.
seaDepthRange
Indicates the minimum and maximum water depth values associated with a given sea or marine location.
-
C.
deepestStationDepthMeters
Indicates the maximum depth, in meters, reached by any station associated with the subject.
-
D.
depthRelativeToSeabed
Indicates the vertical distance of something measured relative to the seabed, typically how far above or below the seabed it is located.
-
E.
maximumDepthBelowSeaLevel
Indicates the greatest vertical distance an entity extends or reaches below sea level.
- 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_69e0b513b89c81908b27147e91368db2 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e7352453f88190b38de7b0108c683a |
completed | April 21, 2026, 8:28 a.m. |
| PD | Predicate disambiguation | batch_69e5f61239708190ab7b3c83ae848a0d |
completed | April 20, 2026, 9:46 a.m. |
Created at: April 16, 2026, 3:47 p.m.