Triple
T31800815
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wyee, New South Wales |
E811730
|
entity |
| Predicate | waterCatchment |
P1559
|
FINISHED |
| Object | Lake Macquarie catchment |
E20270
|
NE 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: Lake Macquarie catchment | Statement: [Wyee, New South Wales, waterCatchment, Lake Macquarie catchment]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: waterCatchment Context triple: [Wyee, New South Wales, waterCatchment, Lake Macquarie catchment]
-
A.
reservoirCatchment
Indicates that one entity is the catchment area that drains water into a specified reservoir.
-
B.
watershedName
Indicates the name assigned to the watershed with which an entity is associated.
-
C.
feedsWatersThatReach
Indicates that one body of water supplies or contributes flow to other waters that it eventually reaches.
-
D.
watercourseHelpsForm
Indicates that a watercourse contributes to the creation, shaping, or delineation of another geographic feature or boundary.
-
E.
drainageBasin
chosen
Indicates the area of land where all precipitation and surface water flow are collected and drained toward a particular river, lake, or other water body.
- F. None of above.
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_69f348e70d188190b4637c5509f81274 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69fd0b92f42881908cd77e3f058adcc2 |
completed | May 7, 2026, 10 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a2e6596a7108190a242c2cc59ef3bf2 |
completed | June 14, 2026, 8:25 a.m. |
| PD | Predicate disambiguation | batch_69fd0a3d68d4819094d92040f7c48d7c |
completed | May 7, 2026, 9:55 p.m. |
Created at: April 30, 2026, 11:41 p.m.