Triple
T7622948
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ʻāhinahina (Haleakalā silversword) |
E172544
|
entity |
| Predicate | leafFunction |
P78171
|
FINISHED |
| Object | insulating the plant from cold |
—
|
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: insulating the plant from cold | Statement: [ʻāhinahina (Haleakalā silversword), leafFunction, insulating the plant from cold]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: leafFunction Context triple: [ʻāhinahina (Haleakalā silversword), leafFunction, insulating the plant from cold]
-
A.
flowerFunction
Indicates the biological or practical role that a flower serves, such as reproduction, attraction of pollinators, or ornamental use.
-
B.
linkFunctionFamily
Indicates a relationship where one function is associated with or belongs to a particular family of related functions.
-
C.
formFunction
Indicates that one entity’s physical form, structure, or configuration determines or enables the function or role performed by another (or by itself).
-
D.
roofFunction
Indicates the functional role or purpose that a roof serves in relation to the structure it covers.
-
E.
laterFunction
Indicates that one function or event occurs after another in time.
- F. None of above. chosen
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_69c699506b308190826894dab1d9ea86 |
completed | March 27, 2026, 2:50 p.m. |
| NER | Named-entity recognition | batch_69c6fe73ff7c8190ab1218d97b37416d |
completed | March 27, 2026, 10:02 p.m. |
| PD | Predicate disambiguation | batch_69c6f4e725a88190b1f05dd224f7f4f2 |
completed | March 27, 2026, 9:21 p.m. |
| PDg | Predicate description generation | batch_69c6fe7323b0819081664662d2f26937 |
completed | March 27, 2026, 10:02 p.m. |
Created at: March 27, 2026, 3:56 p.m.