Triple
T17072234
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | San Francisco Maru |
E414250
|
entity |
| Predicate | wreckDepthMax |
P38776
|
FINISHED |
| Object | approximately 64 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 64 meters | Statement: [San Francisco Maru, wreckDepthMax, approximately 64 meters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wreckDepthMax Context triple: [San Francisco Maru, wreckDepthMax, approximately 64 meters]
-
A.
wreckDepth
chosen
Indicates the depth at which a wreck is located below the water surface.
-
B.
maximumVesselDraft
Indicates the greatest depth a vessel can safely extend below the waterline, typically limiting where it can navigate or dock.
-
C.
maximumDiveDepth
Indicates the greatest depth below the surface that an entity is capable of or allowed to dive.
-
D.
maximumWaterDepth
Indicates the greatest depth of water present or allowed in a given context, such as a location, container, or body of water.
-
E.
hasBerthDepth
Indicates the depth of water available at a specific berth where a vessel can be moored.
- 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_69d886cef44c8190ba56c44b4e863e64 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3dbc1b7d48190979a848b4188cb22 |
completed | April 18, 2026, 7:30 p.m. |
| PD | Predicate disambiguation | batch_69e35d642f74819098c014135e249b27 |
completed | April 18, 2026, 10:31 a.m. |
Created at: April 10, 2026, 5:34 a.m.