Triple
T22915059
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 11th hole (White Dogwood) |
E568712
|
entity |
| Predicate | hasGreenComplex |
P31120
|
FINISHED |
| Object | elevated green |
—
|
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: elevated green | Statement: [11th hole (White Dogwood), hasGreenComplex, elevated green]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasGreenComplex Context triple: [11th hole (White Dogwood), hasGreenComplex, elevated green]
-
A.
hasGreenType
Indicates that an entity possesses or is associated with a type classified as green.
-
B.
hasComplex
chosen
Indicates that one entity possesses, is associated with, or is part of a larger composite structure or complex formed with another entity.
-
C.
hasGreenRuns
Indicates that an entity possesses or includes ski runs that are classified as green (i.e., beginner-level).
-
D.
hasChlorophyll
Indicates that one entity possesses or contains chlorophyll, typically as a component or characteristic of its biological makeup.
-
E.
hasGreenCorridorFunction
Indicates that something serves as a green corridor, enabling ecological connectivity or movement of species between natural or semi-natural areas.
- 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_69e2458d90c88190a58cead4e781ca6a |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18078077881908b8124cc22110c6e |
completed | April 29, 2026, 3:52 a.m. |
| PD | Predicate disambiguation | batch_69ef3b7c5fc081909ac50c5c8569cc19 |
completed | April 27, 2026, 10:33 a.m. |
Created at: April 17, 2026, 3:42 p.m.