Triple
T9598673
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mediterranean maquis |
E231795
|
entity |
| Predicate | hasLeafPhenology |
P35423
|
FINISHED |
| Object | evergreen |
—
|
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: evergreen | Statement: [Mediterranean maquis, hasLeafPhenology, evergreen]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLeafPhenology Context triple: [Mediterranean maquis, hasLeafPhenology, evergreen]
-
A.
leafPhenology
chosen
Indicates the timing and pattern of leaf developmental stages (such as budburst, expansion, coloration, and fall) in relation to environmental or seasonal conditions.
-
B.
foliageSeasonalColor
Indicates the characteristic color that a plant’s foliage takes on during a particular season.
-
C.
hasCanopyDensity
Indicates the degree to which a canopy (such as a tree or forest cover) occupies or obscures the area beneath it.
-
D.
typicalLeafCharacteristic
Indicates the usual or defining features of a leaf that characterize it under normal conditions.
-
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_69ca8484838c8190b2049199d22fef70 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9a366d3481908db62e476958eafe |
completed | April 1, 2026, 10:20 p.m. |
| PD | Predicate disambiguation | batch_69ccd5a359788190b24f82399489f7fe |
completed | April 1, 2026, 8:21 a.m. |
Created at: March 30, 2026, 8:07 p.m.