Triple
T32074848
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Act III of Swan Lake |
E819114
|
entity |
| Predicate | oftenFeaturesCostume |
P58290
|
FINISHED |
| Object | black tutu for Odile |
—
|
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: black tutu for Odile | Statement: [Act III of Swan Lake, oftenFeaturesCostume, black tutu for Odile]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: oftenFeaturesCostume Context triple: [Act III of Swan Lake, oftenFeaturesCostume, black tutu for Odile]
-
A.
costumeFeatures
chosen
Indicates that a costume possesses or includes specific features, attributes, or decorative elements.
-
B.
costume
Indicates that one entity is wearing, dressed in, or outfitted with the other entity as a costume.
-
C.
costumeType
Indicates the specific kind or category of costume associated with an entity.
-
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.
costumeElement
Indicates that one item functions as a component or part of another item's costume.
- 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_69f348ff8ef88190931c08ba530a36bc |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fbaebc8f2c8190b94f1b4a3ec92e8c |
completed | May 6, 2026, 9:12 p.m. |
| PD | Predicate disambiguation | batch_69fbadf1e6008190a71bbd196ba06844 |
completed | May 6, 2026, 9:09 p.m. |
Created at: May 1, 2026, 12:23 a.m.