Triple
T27645951
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Air Force Outstanding Unit Award |
E696712
|
entity |
| Predicate | ribbonColorScheme |
P21498
|
FINISHED |
| Object | predominantly red with blue and gold stripes |
—
|
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 red with blue and gold stripes | Statement: [Air Force Outstanding Unit Award, ribbonColorScheme, predominantly red with blue and gold stripes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ribbonColorScheme Context triple: [Air Force Outstanding Unit Award, ribbonColorScheme, predominantly red with blue and gold stripes]
-
A.
ribbonColours
chosen
Indicates that there is an association between an entity and one or more colours of ribbons related to it.
-
B.
ribbonStripeColor
Indicates the color of a stripe on a ribbon in the relationship or depiction being described.
-
C.
ringColor
Indicates that an entity has a ring whose color is specified by the related value or entity.
-
D.
bandColor
Indicates the color associated with a band, such as a stripe, ring, or marking on an object.
-
E.
beltColor
Indicates the color attribute associated with a belt.
- 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_69ef590abd3c8190834d0193bde12007 |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_69f63195d7808190a4d4bde80e99d31d |
completed | May 2, 2026, 5:17 p.m. |
| PD | Predicate disambiguation | batch_69f62c1921008190a62675a31f66a875 |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 27, 2026, 2:29 p.m.