Triple
T16673736
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Half-Breed |
E405165
|
entity |
| Predicate | featuresCostumeTheme |
P58290
|
FINISHED |
| Object | Native American-inspired outfit |
—
|
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: Native American-inspired outfit | Statement: [Half-Breed, featuresCostumeTheme, Native American-inspired outfit]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresCostumeTheme Context triple: [Half-Breed, featuresCostumeTheme, Native American-inspired outfit]
-
A.
costumeInspiration
Indicates that one entity serves as the creative source or model for another entity’s costume design.
-
B.
costumeFeatures
chosen
Indicates that a costume possesses or includes specific features, attributes, or decorative elements.
-
C.
costumeType
Indicates the specific kind or category of costume associated with an entity.
-
D.
costumeDesignEmphasisOn
Indicates that a costume design places particular focus or priority on a specified element, style, feature, or thematic aspect.
-
E.
numberOfCostumes
Indicates the total count of costumes associated with or used by a given 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_69d8838c28748190b3f5967c743940ab |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e37d6904008190a79ab30b6d9ccae9 |
completed | April 18, 2026, 12:47 p.m. |
| PD | Predicate disambiguation | batch_69e319bc73908190a0e38bc926b31f10 |
completed | April 18, 2026, 5:42 a.m. |
Created at: April 10, 2026, 5:19 a.m.