Triple
T1424063
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cap of Maintenance |
E30288
|
entity |
| Predicate | trimmedWith |
P26148
|
FINISHED |
| Object | ermine |
—
|
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 | Statement: [Cap of Maintenance, trimmedWith, ermine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: trimmedWith Context triple: [Cap of Maintenance, trimmedWith, ermine]
-
A.
notableTrim
Indicates that an entity has a particularly significant or distinguished trim level or decorative variant compared to standard versions.
-
B.
trimLevel
Indicates the specific configuration or package level of features or options applied to an item, typically distinguishing variants within the same base model.
-
C.
cutFormat
chosen
Indicates that one entity trims or shapes another entity into a specified format or pattern.
-
D.
rinkType
Indicates the specific kind or category of rink associated with an entity (e.g., ice rink, roller rink, practice rink).
-
E.
abridgedIn
Indicates that one entity is a shortened or condensed version of the content found within another entity.
- 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_69a498fb823c8190a67ce4c4837e641a |
completed | March 1, 2026, 7:52 p.m. |
| NER | Named-entity recognition | batch_69a4c52e4ed881908d85e0cb9fe851ac |
completed | March 1, 2026, 11:01 p.m. |
| PD | Predicate disambiguation | batch_69a4c4752abc8190a33b634c4d6fad28 |
completed | March 1, 2026, 10:57 p.m. |
Created at: March 1, 2026, 8 p.m.