Triple
T24213213
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | sinking of SF Hydro |
E600611
|
entity |
| Predicate | operatorOfTargetVessel |
P109038
|
FINISHED |
| Object | Norsk Hydro |
—
|
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: Norsk Hydro | Statement: [sinking of SF Hydro, operatorOfTargetVessel, Norsk Hydro]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: operatorOfTargetVessel Context triple: [sinking of SF Hydro, operatorOfTargetVessel, Norsk Hydro]
-
A.
operatesVessel
Indicates that an agent is responsible for controlling, managing, or running the operation of a vessel.
-
B.
usesVesselsOperatedBy
Indicates that one entity makes use of vessels that are operated or controlled by another entity.
-
C.
shipOperator
chosen
Indicates the entity that is responsible for operating, managing, or running a ship.
-
D.
vesselService
Indicates a service relationship in which one entity provides, operates, or maintains a vessel (such as a ship or boat) for another entity.
-
E.
vesselFunction
Indicates that one entity serves as the functional role, purpose, or operational use of a vessel in relation to another entity.
- 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_69e2953344c48190875730c7d52112a0 |
completed | April 17, 2026, 8:16 p.m. |
| NER | Named-entity recognition | batch_69f28204e288819081e8a6121e229df6 |
completed | April 29, 2026, 10:11 p.m. |
| PD | Predicate disambiguation | batch_69f1c43e55688190b55fc20274ed471c |
completed | April 29, 2026, 8:41 a.m. |
Created at: April 17, 2026, 11:56 p.m.