Triple
T24776527
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Davidia involucrata |
E619875
|
entity |
| Predicate | bractFunction |
P64055
|
FINISHED |
| Object | attract pollinators |
—
|
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: attract pollinators | Statement: [Davidia involucrata, bractFunction, attract pollinators]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bractFunction Context triple: [Davidia involucrata, bractFunction, attract pollinators]
-
A.
leafFunction
Indicates that something serves as a terminal or non-decomposable function within a larger functional or computational structure.
-
B.
flowerFunction
chosen
Indicates the biological or practical role that a flower serves, such as reproduction, attraction of pollinators, or ornamental use.
-
C.
functie
Indicates that one entity serves as a function, role, or operational purpose in relation to another entity.
-
D.
artifactFunction
Indicates that an artifact is used for, designed for, or serves a particular function or purpose.
-
E.
claimedFunction
Indicates that one entity asserts or describes a particular role, purpose, or function for another entity, regardless of whether that function is verified or actual.
- 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_69e2fabd04488190a2d13c97be745a2d |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f410d320c88190b6bca2c68cb01194 |
completed | May 1, 2026, 2:32 a.m. |
| PD | Predicate disambiguation | batch_69f40ef612c88190ab2f3f08d4a92018 |
completed | May 1, 2026, 2:24 a.m. |
Created at: April 18, 2026, 4:34 a.m.