Triple
T17988107
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lake Rotokakahi |
E430292
|
entity |
| Predicate | waterColourCause |
P23298
|
FINISHED |
| Object | shallow depth and sandy bottom |
—
|
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: shallow depth and sandy bottom | Statement: [Lake Rotokakahi, waterColourCause, shallow depth and sandy bottom]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: waterColourCause Context triple: [Lake Rotokakahi, waterColourCause, shallow depth and sandy bottom]
-
A.
waterColor
Indicates that one entity is the color or hue characteristic of water associated with another entity.
-
B.
colorOfLagoonsCausedBy
Indicates that the color observed in lagoons is caused or determined by the specified factor or agent.
-
C.
hasWaterColor
Indicates that an entity possesses or is characterized by a particular color of water.
-
D.
waterAppearance
Indicates how the water involved in the situation looks or visually appears (e.g., its color, clarity, or surface condition).
-
E.
colorationCause
chosen
Indicates that one entity is the cause or source of the coloration observed in 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_69d8b90364248190a37381adea932f42 |
completed | April 10, 2026, 8:46 a.m. |
| NER | Named-entity recognition | batch_69e4b29d3ad4819096c2600aa2a99f21 |
completed | April 19, 2026, 10:46 a.m. |
| PD | Predicate disambiguation | batch_69e3f90039e4819080527f860dca042e |
completed | April 18, 2026, 9:34 p.m. |
Created at: April 10, 2026, 10:23 a.m.