Triple
T19630747
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gallantry and Criminal Conversation |
E471261
|
entity |
| Predicate | costumePattern |
P65728
|
FINISHED |
| Object | African-inspired Dutch wax prints |
—
|
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: African-inspired Dutch wax prints | Statement: [Gallantry and Criminal Conversation, costumePattern, African-inspired Dutch wax prints]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: costumePattern Context triple: [Gallantry and Criminal Conversation, costumePattern, African-inspired Dutch wax prints]
-
A.
typicalCostumePattern
chosen
Indicates that one entity is the characteristic or commonly used costume pattern associated with another entity.
-
B.
costumeDesignEmphasisOn
Indicates that a costume design places particular focus or priority on a specified element, style, feature, or thematic aspect.
-
C.
costume
Indicates that one entity is wearing, dressed in, or outfitted with the other entity as a costume.
-
D.
costumeContext
Indicates the situational or narrative context in which a costume is used, such as the event, setting, or role it is associated with.
-
E.
costumeType
Indicates the specific kind or category of costume associated with an entity.
- 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_69d8e511f28481909f4bc3ea9191e54a |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e641025d708190aa44bb24671b9455 |
completed | April 20, 2026, 3:06 p.m. |
| PD | Predicate disambiguation | batch_69e514e5cb108190ae260e466c447314 |
completed | April 19, 2026, 5:46 p.m. |
Created at: April 10, 2026, 1:44 p.m.