Triple
T22617870
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | coat of arms of Ghana |
E558195
|
entity |
| Predicate | hasShieldDivision |
P98443
|
FINISHED |
| Object | quartered by a St George’s Cross |
—
|
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: quartered by a St George’s Cross | Statement: [coat of arms of Ghana, hasShieldDivision, quartered by a St George’s Cross]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasShieldDivision Context triple: [coat of arms of Ghana, hasShieldDivision, quartered by a St George’s Cross]
-
A.
shieldDivision
Indicates a defensive relationship where one entity protects or buffers another entity or group from harm, impact, or external influence.
-
B.
shieldDivisions
chosen
Indicates that one entity provides protective separation or buffering between different parts, groups, or segments of another entity.
-
C.
hasShieldBearer
Indicates that one entity serves as the shield-bearing protector or defensive attendant for another entity.
-
D.
hasMilitaryDivision
Indicates that an entity possesses, includes, or is organizationally associated with a specific military division.
-
E.
ShieldsSide
Indicates that one entity is positioned or aligned on a particular side of another entity’s shield.
- 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_69e24545a8e08190bfa7482a2c725ff1 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f167ef7a148190870334af9c8b79a4 |
completed | April 29, 2026, 2:07 a.m. |
| PD | Predicate disambiguation | batch_69ee62855558819080da946c7b35a160 |
completed | April 26, 2026, 7:07 p.m. |
Created at: April 17, 2026, 2:59 p.m.