Triple
T26898887
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Argyroxiphium sandwicense |
E677969
|
entity |
| Predicate | primaryGrowthForm |
P571
|
FINISHED |
| Object | stemless rosette |
—
|
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: stemless rosette | Statement: [Argyroxiphium sandwicense, primaryGrowthForm, stemless rosette]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryGrowthForm Context triple: [Argyroxiphium sandwicense, primaryGrowthForm, stemless rosette]
-
A.
hasGrowthHabit
Indicates the characteristic way in which an organism typically grows or develops in form or structure.
-
B.
treeHabit
Indicates the growth form or structural habit characteristic of a tree, such as its typical shape, branching pattern, or overall stature.
-
C.
growthForm
chosen
Indicates the physical structure or habit in which something develops or grows (such as its overall shape, form, or growth pattern).
-
D.
leafGrowthPattern
Indicates the characteristic way in which a plant’s leaves develop, arrange, and expand over time.
-
E.
isGrowingPartOf
Indicates that one entity is an expanding or developing component within the larger whole represented by 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_69eee9befee48190a26f214faa867be7 |
completed | April 27, 2026, 4:44 a.m. |
| NER | Named-entity recognition | batch_69fec5c503808190bde0b1829ea43071 |
completed | May 9, 2026, 5:27 a.m. |
| PD | Predicate disambiguation | batch_69fec535dd6c8190a6ab85201f5a04a9 |
completed | May 9, 2026, 5:25 a.m. |
Created at: April 27, 2026, 5:49 a.m.