Triple
T811405
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Antarctic Circumpolar Current |
E17552
|
entity |
| Predicate | hasApproximateTransport |
P19879
|
FINISHED |
| Object | 100 to 150 Sverdrups |
—
|
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: 100 to 150 Sverdrups | Statement: [Antarctic Circumpolar Current, hasApproximateTransport, 100 to 150 Sverdrups]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasApproximateTransport Context triple: [Antarctic Circumpolar Current, hasApproximateTransport, 100 to 150 Sverdrups]
-
A.
hasTransportFunction
Indicates that an entity serves to move or carry something (such as people, goods, or signals) from one place or state to another.
-
B.
hasTransportRoute
Indicates that there exists a designated transportation connection or route linking one entity to another.
-
C.
usesTransport
Indicates that an entity employs or relies on a particular mode or means of transportation to move from one place to another.
-
D.
hasApproximateCoordinates
Indicates that an entity is associated with location coordinates that are estimated or imprecise rather than exact.
-
E.
hasTunnelLengthApprox
Indicates that an entity has a tunnel whose length is approximately a specified value.
- F. None of above. chosen
Provenance (4 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_69a4937ae8a08190b5084a03d532b30e |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4ab4c7418819085cb64c6bf5fa70c |
completed | March 1, 2026, 9:10 p.m. |
| PD | Predicate disambiguation | batch_69a4aa73df08819096d0553a4b2509de |
completed | March 1, 2026, 9:07 p.m. |
| PDg | Predicate description generation | batch_69a4ab4781c88190ae36906251347cdc |
completed | March 1, 2026, 9:10 p.m. |
Created at: March 1, 2026, 7:38 p.m.