Triple
T29114678
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Calceolariaceae |
E737009
|
entity |
| Predicate | floralNectar |
P137227
|
FINISHED |
| Object | nectar produced in lower lip pouch |
—
|
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: nectar produced in lower lip pouch | Statement: [Calceolariaceae, floralNectar, nectar produced in lower lip pouch]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: floralNectar Context triple: [Calceolariaceae, floralNectar, nectar produced in lower lip pouch]
-
A.
hasNectar
chosen
Indicates that one entity contains or produces nectar that is available to or associated with another entity.
-
B.
hasNectarSpur
Indicates that one entity possesses a nectar spur, typically a tubular or elongated floral structure that contains or produces nectar.
-
C.
flowerUse
Indicates how a flower is used or purposed in a particular context (e.g., decorative, medicinal, culinary, or symbolic use).
-
D.
honeyYield
Indicates the amount of honey produced or obtained from a given source, such as a hive, colony, or beekeeping operation.
-
E.
flowerFunction
Indicates the biological or practical role that a flower serves, such as reproduction, attraction of pollinators, or ornamental use.
- 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_69f077ed54e08190bb02a744e8121a66 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69f661ef9e2481908788797adbd5c937 |
completed | May 2, 2026, 8:43 p.m. |
| PD | Predicate disambiguation | batch_69f65c2376a08190be5215171e908e69 |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 28, 2026, 11:21 a.m.