Triple
T12746503
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stellaria |
E304617
|
entity |
| Predicate | petalCharacteristic |
P12542
|
FINISHED |
| Object | deeply notched petals that can appear as 10 |
—
|
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: deeply notched petals that can appear as 10 | Statement: [Stellaria, petalCharacteristic, deeply notched petals that can appear as 10]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: petalCharacteristic Context triple: [Stellaria, petalCharacteristic, deeply notched petals that can appear as 10]
-
A.
petalShape
Indicates the characteristic form or outline of a flower’s petals in relation to the whole blossom.
-
B.
flowerCharacteristic
Indicates that a flower possesses a particular attribute, quality, or feature (such as color, shape, size, or scent).
-
C.
petalTexture
Indicates the type or quality of surface texture exhibited by a flower’s petals.
-
D.
petalMarkings
Indicates the pattern, color, or distinctive markings present on the petals of a flower in relation to the flower they belong to.
-
E.
petalCount
chosen
Indicates the number of petals associated with an entity, typically a flower or floral structure.
- 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_69d7bdf1426c8190a4402e1c4cdec33a |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96d89ea70819098c470344f172167 |
completed | April 10, 2026, 9:37 p.m. |
| PD | Predicate disambiguation | batch_69d96406e97c8190b79081039847115c |
completed | April 10, 2026, 8:56 p.m. |
Created at: April 9, 2026, 5:27 p.m.