Triple
T36129970
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Quercus glauca |
E1044987
|
entity |
| Predicate | leafDescription |
P17481
|
FINISHED |
| Object | glossy dark-green leaves |
—
|
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: glossy dark-green leaves | Statement: [Quercus glauca, leafDescription, glossy dark-green leaves]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: leafDescription Context triple: [Quercus glauca, leafDescription, glossy dark-green leaves]
-
A.
leafType
Indicates the specific kind or classification of leaf associated with an entity.
-
B.
leafTip
Indicates that one entity is the tip or terminal end of a leaf associated with another entity.
-
C.
typicalLeafCharacteristic
chosen
Indicates the usual or defining features of a leaf that characterize it under normal conditions.
-
D.
leafProperty
Indicates that the subject has a property that is terminal (i.e., not further decomposed into sub-properties) within a property hierarchy or structure.
-
E.
leafShape
Indicates the characteristic form or outline of a leaf that an entity possesses or exhibits.
- 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_69f76e356c908190abc6ca1e6a05b011 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7b3e2f3c08190be4fd1ae4fa1266d |
completed | May 3, 2026, 8:45 p.m. |
| PD | Predicate disambiguation | batch_69f7b1bcc47081909fe7d592ac69006c |
completed | May 3, 2026, 8:36 p.m. |
Created at: May 3, 2026, 4:08 p.m.