Triple
T9727871
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HMS Vigilant |
E235660
|
entity |
| Predicate | topSpeedSubmerged |
P71676
|
FINISHED |
| Object | over 25 knots |
—
|
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: over 25 knots | Statement: [HMS Vigilant, topSpeedSubmerged, over 25 knots]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: topSpeedSubmerged Context triple: [HMS Vigilant, topSpeedSubmerged, over 25 knots]
-
A.
speedSubmerged
chosen
Indicates the speed at which an entity moves while it is submerged in a fluid, typically underwater.
-
B.
diveSpeed
Indicates the speed at which an entity moves downward or descends, typically through a fluid such as air or water.
-
C.
maximumWaterSpeed_kmh
Indicates the highest speed, measured in kilometers per hour, at which an entity can move through water.
-
D.
submergedBy
Indicates that one entity is covered or overwhelmed by liquid, typically water, to the point of being beneath its surface due to the action or presence of another entity.
-
E.
submerged
Indicates that one entity is located beneath the surface of a liquid or other surrounding medium, typically fully covered by it.
- 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_69ca84d0fad481909cdd45aa77416c48 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cd9e7af544819090a8a1adec41943c |
completed | April 1, 2026, 10:38 p.m. |
| PD | Predicate disambiguation | batch_69cd03c6ffc88190a5e9569e19122ad5 |
completed | April 1, 2026, 11:38 a.m. |
Created at: March 30, 2026, 8:21 p.m.