Triple
T17072237
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | San Francisco Maru |
E414250
|
entity |
| Predicate | sternDepth |
P125750
|
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, sternDepth, approximately 64 meters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sternDepth Context triple: [San Francisco Maru, sternDepth, approximately 64 meters]
-
A.
designedTargetDepthInKilometers
Indicates the intended or planned depth, measured in kilometers, that something is designed to reach or operate at.
-
B.
searchDepth
Indicates the extent or level to which a search process explores through layers, steps, or hierarchy within a structure or space.
-
C.
summitDepth
Indicates the vertical distance from a summit’s highest point down to a specified reference level, such as a base or surrounding terrain.
-
D.
deepestStationDepthMeters
Indicates the maximum depth, in meters, reached by any station associated with the subject.
-
E.
gorgeDepth
Indicates the measured vertical distance from a gorge’s rim down to its lowest point.
- F. None of above. chosen
Provenance (4 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. |
| PDg | Predicate description generation | batch_69e3753f93c88190808fec5692f66699 |
completed | April 18, 2026, 12:12 p.m. |
Created at: April 10, 2026, 5:34 a.m.