Triple
T35660898
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United States polar icebreaking fleet |
E1030430
|
entity |
| Predicate | componentVesselClass |
P11978
|
FINISHED |
| Object | Polar-class icebreaker |
—
|
NE NERFINISHED |
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: Polar-class icebreaker | Statement: [United States polar icebreaking fleet, componentVesselClass, Polar-class icebreaker]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: componentVesselClass Context triple: [United States polar icebreaking fleet, componentVesselClass, Polar-class icebreaker]
-
A.
hasVesselType
chosen
Indicates that an entity is associated with or classified by a specific type of vessel (e.g., ship, boat, or container).
-
B.
isVesselFor
Indicates that one entity functions as a container or medium specifically used to hold, carry, or convey another entity.
-
C.
usesVesselType
Indicates that an entity performs an activity or operation by employing a specific type or category of vessel.
-
D.
shipClassVariant
Indicates that one ship class is a variant or modified version derived from another ship class.
-
E.
vesselDesignation
Indicates that a specific identifying designation (such as a name, number, or code) is assigned to a vessel.
- 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_69f76e09f87881909c954aaac176c34f |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fdb31800508190beec15adb9bbd292 |
completed | May 8, 2026, 9:55 a.m. |
| PD | Predicate disambiguation | batch_69fdb19c381c8190bafb2f565da097f1 |
completed | May 8, 2026, 9:49 a.m. |
Created at: May 3, 2026, 4:05 p.m.