Triple
T8170264
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dutch Water Line |
E190797
|
entity |
| Predicate | floodDepth |
P42760
|
FINISHED |
| Object | approximately 30 to 60 centimeters |
—
|
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 30 to 60 centimeters | Statement: [Dutch Water Line, floodDepth, approximately 30 to 60 centimeters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: floodDepth Context triple: [Dutch Water Line, floodDepth, approximately 30 to 60 centimeters]
-
A.
riverbedDepth
Indicates the depth or vertical distance from the water surface to the bottom of a river at a given location or time.
-
B.
maximumWaterDepth
chosen
Indicates the greatest depth of water present or allowed in a given context, such as a location, container, or body of water.
-
C.
floodGauge
Indicates that a device or measurement point is used to monitor and record the level or intensity of flooding at a specific location.
-
D.
hasWaterDepthCategory
Indicates the classification of something based on the range or category of its water depth.
-
E.
designedFloodLevel
Indicates the flood level that a structure or system is specifically engineered to withstand or accommodate.
- 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_69ca82c1c0a08190bf8692b4d91a03ca |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb4803de688190960438aa059d163b |
completed | March 31, 2026, 4:05 a.m. |
| PD | Predicate disambiguation | batch_69cb36a4c40c81909f60aef0e1624c13 |
completed | March 31, 2026, 2:51 a.m. |
Created at: March 30, 2026, 5:39 p.m.