Triple
T23169015
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Terra Nova FPSO |
E578791
|
entity |
| Predicate | offloadingType |
P68985
|
FINISHED |
| Object | tandem offloading to shuttle tankers |
—
|
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: tandem offloading to shuttle tankers | Statement: [Terra Nova FPSO, offloadingType, tandem offloading to shuttle tankers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: offloadingType Context triple: [Terra Nova FPSO, offloadingType, tandem offloading to shuttle tankers]
-
A.
offloadingMethod
chosen
Indicates the method or process by which something is transferred or offloaded from one entity, system, or location to another.
-
B.
offloadsFrom
Indicates that a task, responsibility, or load is transferred or shifted away from one entity to another.
-
C.
transmissionType
Indicates the method or medium through which something is transmitted or conveyed from one entity to another.
-
D.
offeringType
Indicates the category or nature of what is being offered in a transaction or interaction (e.g., product, service, or other type of offering).
-
E.
implementationType
Indicates the specific manner or approach by which something is implemented or realized in practice.
- 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_69e245fc75348190a0288401044c8af8 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18f2e5e208190839ec37de4b974af |
completed | April 29, 2026, 4:55 a.m. |
| PD | Predicate disambiguation | batch_69ef89ff76808190808ee4ad9dea776b |
completed | April 27, 2026, 4:08 p.m. |
Created at: April 17, 2026, 4:03 p.m.