Triple
T4315875
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dubai Water Canal |
E96388
|
entity |
| Predicate | allowsVesselDraft |
P29240
|
FINISHED |
| Object | up to 4 metres |
—
|
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: up to 4 metres | Statement: [Dubai Water Canal, allowsVesselDraft, up to 4 metres]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: allowsVesselDraft Context triple: [Dubai Water Canal, allowsVesselDraft, up to 4 metres]
-
A.
maximumVesselDraft
chosen
Indicates the greatest depth a vessel can safely extend below the waterline, typically limiting where it can navigate or dock.
-
B.
maximumVesselAirDraft
Indicates the greatest vertical distance from the waterline to the highest point of a vessel that is allowed or applicable in a given context.
-
C.
hasBerthDepth
Indicates the depth of water available at a specific berth where a vessel can be moored.
-
D.
shipDraft
Indicates the depth of a ship’s hull below the waterline, typically representing how deeply the vessel sits in the water.
-
E.
maxVesselTonnage
Indicates the maximum tonnage capacity that a vessel is allowed or designed to carry.
- 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_69b345422aac81909ddbadae437d122e |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b350f60dfc819098202b7eb3bbf402 |
completed | March 12, 2026, 11:49 p.m. |
| PD | Predicate disambiguation | batch_69b34f4a07b08190a06ada0d9cbb14fb |
completed | March 12, 2026, 11:42 p.m. |
Created at: March 12, 2026, 11:12 p.m.