Triple
T498242
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Additional Protocol III |
E10342
|
entity |
| Predicate | protectiveEmblemShape |
P1601
|
FINISHED |
| Object | red frame in the shape of a square on edge on a white ground |
—
|
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: red frame in the shape of a square on edge on a white ground | Statement: [Additional Protocol III, protectiveEmblemShape, red frame in the shape of a square on edge on a white ground]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: protectiveEmblemShape Context triple: [Additional Protocol III, protectiveEmblemShape, red frame in the shape of a square on edge on a white ground]
-
A.
badgeShape
chosen
Indicates the geometric form or outline that a badge takes.
-
B.
emblemFeatures
Indicates that an emblem includes or displays specific visual elements or characteristics.
-
C.
primaryEmblem
Indicates that one emblem is the main or most representative symbol associated with an entity.
-
D.
coatOfArms
Indicates that one entity serves as the heraldic emblem or coat of arms representing another entity.
-
E.
emblemStatus
Indicates the current state or condition of an emblem, such as whether it is active, valid, displayed, or in use.
- 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_69a2e847df8481909239ec08ccf1e376 |
completed | Feb. 28, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69a2f1183e988190bce70932a9678134 |
completed | Feb. 28, 2026, 1:43 p.m. |
| PD | Predicate disambiguation | batch_69a2edfa87cc8190a77c726a5a55b7d9 |
completed | Feb. 28, 2026, 1:30 p.m. |
Created at: Feb. 28, 2026, 1:12 p.m.