Triple
T5337358
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Atlantic Water |
E123857
|
entity |
| Predicate | hasMainEntryPathway |
P27773
|
FINISHED |
| Object | Fram Strait branch |
—
|
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: Fram Strait branch | Statement: [Atlantic Water, hasMainEntryPathway, Fram Strait branch]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMainEntryPathway Context triple: [Atlantic Water, hasMainEntryPathway, Fram Strait branch]
-
A.
hasPathway
chosen
Indicates that there exists a route, channel, or sequence of steps through which one entity leads, connects, or gives access to another.
-
B.
hasMultipleEntrances
Indicates that an entity possesses more than one distinct entrance or access point.
-
C.
hasMainOrgan
Indicates that an entity possesses a primary or principal organ that plays a central role in its biological or functional system.
-
D.
isMainTractOf
Indicates that one tract or pathway is the primary or principal route among related tracts within a system or structure.
-
E.
hasMainSource
Indicates that one entity serves as the primary or principal source or origin for 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_69bd464b07f8819095aa76577c9829e4 |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd85c6ec008190ad7a8a54360387d8 |
completed | March 20, 2026, 5:37 p.m. |
| PD | Predicate disambiguation | batch_69bd84583dbc819088a03e3afb30178c |
completed | March 20, 2026, 5:31 p.m. |
Created at: March 20, 2026, 2 p.m.