Triple
T24424601
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Coat of arms of Mauritius |
E615820
|
entity |
| Predicate | shieldQuarter3 |
P47929
|
FINISHED |
| Object | key and star on a blue field |
—
|
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: key and star on a blue field | Statement: [Coat of arms of Mauritius, shieldQuarter3, key and star on a blue field]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: shieldQuarter3 Context triple: [Coat of arms of Mauritius, shieldQuarter3, key and star on a blue field]
-
A.
shieldQuarter
chosen
Indicates that one entity is depicted as a quarter (one-fourth) section of a shield in relation to another entity.
-
B.
shieldMaterial
Indicates the material from which a shield is made or constructed.
-
C.
shieldType
Indicates the specific kind or category of shield associated with an entity or interaction.
-
D.
shieldDivision
Indicates a defensive relationship where one entity protects or buffers another entity or group from harm, impact, or external influence.
-
E.
shieldPosition
Indicates the relative location or orientation of a shield with respect to the entity or context it is protecting.
- 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_69e2d7eadb248190a867130fe45f0388 |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f296a62644819089d01ec90e8bee3c |
completed | April 29, 2026, 11:39 p.m. |
| PD | Predicate disambiguation | batch_69f287cc4fd4819081e93cc638d9512d |
completed | April 29, 2026, 10:35 p.m. |
Created at: April 18, 2026, 2:14 a.m.