Triple
T38527306
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Indonesian Throughflow |
E923262
|
entity |
| Predicate | typicalVolumeTransport |
P191174
|
FINISHED |
| Object | approximately 15 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: approximately 15 Sverdrups | Statement: [Indonesian Throughflow, typicalVolumeTransport, approximately 15 Sverdrups]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalVolumeTransport Context triple: [Indonesian Throughflow, typicalVolumeTransport, approximately 15 Sverdrups]
-
A.
volumeTransportRange
chosen
Indicates the range of volume or quantity that can be transported or carried within a specified context or system.
-
B.
typicalTransportObject
Indicates that one entity is a typical or commonly used object for transporting or carrying the other entity.
-
C.
typicalNetTransport
Indicates the usual or most common means by which something is transported or carried from one place to another.
-
D.
volumeOf
Indicates the quantitative three-dimensional space occupied by an entity or contained within an object.
-
E.
isTransportNeutral
Indicates that the relationship or action does not depend on, favor, or change with the specific mode or means of transport used.
- 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_69f76ea8f6348190a5c03fb6292bbee3 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a037c903be48190a2fafa53d7d50d42 |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a1e32108190897356d6a7fed879 |
completed | May 12, 2026, 7:06 p.m. |
Created at: May 3, 2026, 4:32 p.m.