Triple
T30925285
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marlborough Sounds |
E787839
|
entity |
| Predicate | hasMajorInlet |
P15759
|
FINISHED |
| Object | Queen Charlotte Sound / Tōtaranui |
—
|
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: Queen Charlotte Sound / Tōtaranui | Statement: [Marlborough Sounds, hasMajorInlet, Queen Charlotte Sound / Tōtaranui]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMajorInlet Context triple: [Marlborough Sounds, hasMajorInlet, Queen Charlotte Sound / Tōtaranui]
-
A.
hasInlet
Indicates that one entity serves as an inlet or entry point through which another entity receives a flow of material, energy, or fluid.
-
B.
hasPrimaryInflow
Indicates that one entity serves as the main source of inflowing material, energy, or influence into another entity.
-
C.
hasMajorPort
Indicates that a location possesses a primary, significant seaport used for major commercial or transportation activities.
-
D.
inletType
Indicates the specific kind or category of inlet through which something (such as a fluid, signal, or material) enters a system or component.
-
E.
hasMajorComponent
chosen
Indicates that one entity includes another entity as a primary or most significant component or part.
- 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_69f224bfaca88190b9d0dfcc86297fe9 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69ffe6e2eb688190a45fd2c6415cd86a |
completed | May 10, 2026, 2:01 a.m. |
| PD | Predicate disambiguation | batch_69ffe65939488190a35b9c2e9c7ad868 |
completed | May 10, 2026, 1:58 a.m. |
Created at: April 29, 2026, 8:51 p.m.