Triple
T25333560
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hoolock |
E635215
|
entity |
| Predicate | usesCanopyLayer |
P61871
|
FINISHED |
| Object | upper canopy |
—
|
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: upper canopy | Statement: [Hoolock, usesCanopyLayer, upper canopy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesCanopyLayer Context triple: [Hoolock, usesCanopyLayer, upper canopy]
-
A.
hasCanopy
Indicates that one entity possesses or is characterized by a canopy associated with it.
-
B.
hasCanopyDensity
Indicates the degree to which a canopy (such as a tree or forest cover) occupies or obscures the area beneath it.
-
C.
hasVegetationLayer
Indicates that an entity possesses a distinct layer or cover of vegetation as part of its structure or surface.
-
D.
canopyType
Indicates the type or structure of a canopy associated with an entity, such as its form, coverage, or configuration.
-
E.
canopyPosition
chosen
Indicates the relative location or layer an entity occupies within a canopy structure (e.g., upper, middle, or lower canopy).
- 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_69e75a99bd6481909476115b35b9a8e4 |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f62d89b89c8190afb372a8172111e7 |
completed | May 2, 2026, 4:59 p.m. |
| PD | Predicate disambiguation | batch_69f62c1379f08190836c3e02b0c892df |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 21, 2026, 1:31 p.m.