Triple
T6022181
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Malus floribunda |
E134089
|
entity |
| Predicate | deciduousOrEvergreen |
P24488
|
FINISHED |
| Object | deciduous |
—
|
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: deciduous | Statement: [Malus floribunda, deciduousOrEvergreen, deciduous]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: deciduousOrEvergreen Context triple: [Malus floribunda, deciduousOrEvergreen, deciduous]
-
A.
isDeciduous
chosen
Indicates that an entity (typically a plant or tree) seasonally sheds its leaves, distinguishing it from evergreen entities.
-
B.
evergreenHabit
Indicates that a plant maintains its foliage year-round rather than shedding leaves seasonally.
-
C.
evergreen
Indicates that something remains persistently relevant, active, or unchanged over time, without becoming outdated or obsolete.
-
D.
isConifer
Indicates that the subject is a coniferous plant, typically bearing cones and having needle-like or scale-like evergreen leaves.
-
E.
containsDeciduousTaxa
Indicates that the subject group or area includes one or more taxa that are deciduous (shedding leaves seasonally).
- 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_69c008742a5c8190b9cb9c2787a3d8b3 |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c04fbbf03c8190baf449a5d393af5c |
completed | March 22, 2026, 8:23 p.m. |
| PD | Predicate disambiguation | batch_69c049e75b3881908be106fbcf8c68d4 |
completed | March 22, 2026, 7:58 p.m. |
Created at: March 22, 2026, 4:07 p.m.