Triple
T25619545
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nymphaea |
E642253
|
entity |
| Predicate | rooting |
P31465
|
FINISHED |
| Object | rooted in sediment |
—
|
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: rooted in sediment | Statement: [Nymphaea, rooting, rooted in sediment]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rooting Context triple: [Nymphaea, rooting, rooted in sediment]
-
A.
rootUse
Indicates that one entity serves as the primary or foundational use, function, or purpose of another entity.
-
B.
rootSystem
chosen
Indicates that one entity is the primary or foundational source from which another entity originates, grows, or is structurally anchored.
-
C.
rootSystemCharacteristic
Indicates a relationship where a specified characteristic or property is attributed to the root system of an organism or plant.
-
D.
relatedRoot
Indicates that one entity is connected to another through a shared or common root, origin, or foundational source.
-
E.
isRootOf
Indicates that one entity is the root or origin point from which another entity directly or indirectly descends or is derived.
- 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_69e77e7a96748190b10f2699041e4e43 |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f5fa1f5710819086f3ba4b42b6478b |
completed | May 2, 2026, 1:20 p.m. |
| PD | Predicate disambiguation | batch_69f4807f8680819098a524158d049c63 |
completed | May 1, 2026, 10:29 a.m. |
Created at: April 21, 2026, 5:02 p.m.