Triple
T11648374
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | coat of arms of Equatorial Guinea |
E276836
|
entity |
| Predicate | hasShieldShape |
P41231
|
FINISHED |
| Object | heraldic shield |
—
|
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: heraldic shield | Statement: [coat of arms of Equatorial Guinea, hasShieldShape, heraldic shield]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasShieldShape Context triple: [coat of arms of Equatorial Guinea, hasShieldShape, heraldic shield]
-
A.
hasHeraldicShieldShape
chosen
Indicates that an entity’s heraldic shield is characterized by a specific geometric or stylistic shape.
-
B.
shieldType
Indicates the specific kind or category of shield associated with an entity or interaction.
-
C.
hasLanternShape
Indicates that one entity has the form, outline, or configuration characteristic of a lantern.
-
D.
traditionalShield
Indicates that an entity functions as or possesses a shield that is made or used according to traditional or culturally established practices.
-
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_69d6aafbb3c081908a9cdb4ecb8d981d |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a2cd9bb0819093d107204bed2fe0 |
completed | April 10, 2026, 7:12 a.m. |
| PD | Predicate disambiguation | batch_69d85dd94bdc819091fa2ed33eb31624 |
completed | April 10, 2026, 2:18 a.m. |
Created at: April 8, 2026, 9:39 p.m.