Triple
T25088961
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Emblem of the Maldives |
E628399
|
entity |
| Predicate | orientationOfFlags |
P41721
|
FINISHED |
| Object | crossed |
—
|
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: crossed | Statement: [Emblem of the Maldives, orientationOfFlags, crossed]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: orientationOfFlags Context triple: [Emblem of the Maldives, orientationOfFlags, crossed]
-
A.
orientationInFlag
chosen
Indicates the spatial orientation or alignment of an entity as it appears within a flag.
-
B.
nationalFlag
Indicates that one entity is the official national flag representing the other entity (a country or nation).
-
C.
alignmentWithNationalFlag
Indicates how closely something corresponds to, matches, or is consistent with the design, symbolism, or standards of a specified national flag.
-
D.
officialFlagOf
Indicates that one entity is the formally recognized flag that represents another entity (such as a country, organization, or region).
-
E.
isOnFlagOf
Indicates that something (typically a symbol, image, or design element) appears on or is depicted on a flag.
- 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_69e2ff2f58e881908340527bc5d34f07 |
completed | April 18, 2026, 3:49 a.m. |
| NER | Named-entity recognition | batch_69f461e7fe048190adfaf71724f707e3 |
completed | May 1, 2026, 8:18 a.m. |
| PD | Predicate disambiguation | batch_69f44d8043b081908bbffd7f044b4f26 |
completed | May 1, 2026, 6:51 a.m. |
Created at: April 18, 2026, 6:24 a.m.