Triple
T502641
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HMS Ivanhoe |
E10431
|
entity |
| Predicate | displacementDeepLoad |
P6546
|
FINISHED |
| Object | approximately 1888 long tons |
—
|
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 1888 long tons | Statement: [HMS Ivanhoe, displacementDeepLoad, approximately 1888 long tons]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: displacementDeepLoad Context triple: [HMS Ivanhoe, displacementDeepLoad, approximately 1888 long tons]
-
A.
displacement
Indicates a change in an entity’s position from one location to another, typically specifying both direction and magnitude of that movement.
-
B.
displacementFullLoad
chosen
Indicates the total volume of water displaced by a vessel when it is fully loaded to its maximum operational capacity.
-
C.
maxDepthLocation
Indicates the location at which the maximum depth of something (e.g., an object, structure, or feature) is reached or measured.
-
D.
maximumDepth
Indicates the greatest extent or deepest level reached by something within a given context or structure.
-
E.
DSTRelation
Indicates a temporal relationship where one event, state, or timestamp is adjusted or interpreted according to Daylight Saving Time rules.
- 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_69a2e848adf881908e5e04f7af030093 |
completed | Feb. 28, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69a2f1339748819089f89691a1698dd9 |
completed | Feb. 28, 2026, 1:44 p.m. |
| PD | Predicate disambiguation | batch_69a2edfbb7e0819092cf29c2c68fe8fb |
completed | Feb. 28, 2026, 1:30 p.m. |
Created at: Feb. 28, 2026, 1:12 p.m.