Triple
T16925970
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fiji Water |
E410574
|
entity |
| Predicate | labelDesignFeature |
P14764
|
FINISHED |
| Object | tropical flowers |
—
|
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: tropical flowers | Statement: [Fiji Water, labelDesignFeature, tropical flowers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: labelDesignFeature Context triple: [Fiji Water, labelDesignFeature, tropical flowers]
-
A.
featureDesignation
Indicates the specific label or name assigned to a feature to distinguish it from other features.
-
B.
cardDesignFeature
Indicates that a card possesses or incorporates a particular design feature or visual element.
-
C.
ribbonDesignFeature
Indicates a design-related characteristic or attribute that is specifically associated with a ribbon.
-
D.
brandingFeature
chosen
Indicates that one entity serves as a branding-related characteristic, element, or attribute that helps define or distinguish another entity’s brand identity.
-
E.
designedFeature
Indicates that one entity is a feature or component intentionally planned, created, or specified by another entity as part of a design.
- 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_69d886c7b1e481908c3766dfa8c13458 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3cdf1ebdc8190b39a9469636de01e |
completed | April 18, 2026, 6:31 p.m. |
| PD | Predicate disambiguation | batch_69e32b982f548190b08414d55810de19 |
completed | April 18, 2026, 6:58 a.m. |
Created at: April 10, 2026, 5:30 a.m.