Triple
T14575057
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Clan MacMillan |
E342019
|
entity |
| Predicate | tartanFeature |
P64189
|
FINISHED |
| Object | predominantly 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: predominantly green | Statement: [Clan MacMillan, tartanFeature, predominantly green]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tartanFeature Context triple: [Clan MacMillan, tartanFeature, predominantly green]
-
A.
tartan
Indicates that something has a tartan pattern or is characterized by a tartan design.
-
B.
principalTartanOf
Indicates that one entity is the officially recognized primary tartan associated with another entity, such as a clan, organization, or region.
-
C.
textileFeature
chosen
Indicates a characteristic, property, or notable aspect associated with a textile or fabric.
-
D.
clothingFeature
Indicates that one entity has a specific clothing-related attribute, detail, or characteristic associated with it.
-
E.
fashionCharacteristic
Indicates a relationship where one entity possesses or exhibits a particular style, trend, or fashion-related attribute in relation to another.
- 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_69d822dcc6248190bed689984bceb0e2 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb3f49d58819094fcd2a702e146cb |
completed | April 14, 2026, 9:39 p.m. |
| PD | Predicate disambiguation | batch_69de656a953481909a4645b004c40de7 |
completed | April 14, 2026, 4:03 p.m. |
Created at: April 10, 2026, 1:24 a.m.