Triple
T22445619
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fuchsia |
E554855
|
entity |
| Predicate | shell |
P7380
|
FINISHED |
| Object | Ermine (experimental) |
—
|
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: Ermine (experimental) | Statement: [Fuchsia, shell, Ermine (experimental)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: shell Context triple: [Fuchsia, shell, Ermine (experimental)]
-
A.
terminal
Indicates that one entity is the final or end point in a process, sequence, or structure, beyond which no further continuation occurs.
-
B.
shellFeature
Indicates that one entity functions as a characteristic or structural feature of another entity’s shell.
-
C.
shellType
chosen
Indicates the type or classification of a shell associated with an entity (e.g., its form, structure, or category).
-
D.
commands
Indicates that one entity holds authority over another and issues directives or orders that the other is expected to follow.
-
E.
typicalShells
Indicates that the associated shells are characteristic or commonly found for the given entity or category.
- 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_69e11e5113208190ab58c6b595f9d1d0 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15b46e8ac8190bfa8c611ffcba822 |
completed | April 29, 2026, 1:13 a.m. |
| PD | Predicate disambiguation | batch_69e898ad961c819098fd1e46129bddcc |
completed | April 22, 2026, 9:45 a.m. |
Created at: April 16, 2026, 8:47 p.m.