Triple
T34836150
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Belfast shipyards |
E1004203
|
entity |
| Predicate | constructedVesselType |
P92486
|
FINISHED |
| Object | ocean liners |
—
|
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: ocean liners | Statement: [Belfast shipyards, constructedVesselType, ocean liners]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: constructedVesselType Context triple: [Belfast shipyards, constructedVesselType, ocean liners]
-
A.
vesselBuilder
chosen
Indicates that one entity is the builder, manufacturer, or constructor of a vessel associated with another entity.
-
B.
hasVesselType
Indicates that an entity is associated with or classified by a specific type of vessel (e.g., ship, boat, or container).
-
C.
usesVesselType
Indicates that an entity performs an activity or operation by employing a specific type or category of vessel.
-
D.
hasVessel
Indicates that one entity possesses, uses, or is associated with a particular vessel (such as a container, ship, or transport medium) in the context of the described relationship or action.
-
E.
vesselTypeServedOn
Indicates the type of vessel on which an entity has served or performed duty.
- 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_69f76db97714819099b5bed36fd64e9d |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fd4f39b5008190b83b3227ce22c509 |
completed | May 8, 2026, 2:49 a.m. |
| PD | Predicate disambiguation | batch_69fd4df17c548190a4e2a6fea70f7e10 |
completed | May 8, 2026, 2:44 a.m. |
Created at: May 3, 2026, 4 p.m.