Triple
T32074867
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Act III of Swan Lake |
E819114
|
entity |
| Predicate | isFrequentlyExcerpted |
P46711
|
FINISHED |
| Object | Black Swan Pas de Deux in gala performances |
—
|
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 Swan Pas de Deux in gala performances | Statement: [Act III of Swan Lake, isFrequentlyExcerpted, Black Swan Pas de Deux in gala performances]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isFrequentlyExcerpted Context triple: [Act III of Swan Lake, isFrequentlyExcerpted, Black Swan Pas de Deux in gala performances]
-
A.
isFrequentlyAnthologized
Indicates that a work is often selected and included in multiple anthologies or collected editions.
-
B.
isFrequentlyCoveredBy
Indicates that one entity is regularly or repeatedly reported on, discussed, or featured by another entity, such as a media outlet or information source.
-
C.
isFrequentlyIncludedIn
chosen
Indicates that something is regularly or commonly contained or made part of something else.
-
D.
isFrequentlyCovered
Indicates that an entity is regularly or commonly reported on, discussed, or featured, especially in media or informational sources.
-
E.
isFrequentlyCoveredSince
Indicates that one entity has been regularly or repeatedly covered (e.g., in media, reports, or discussions) starting from a specified point in time.
- 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_69f6b52ac6f48190ac3e563e45464d43 |
completed | May 3, 2026, 2:38 a.m. |
| PD | Predicate disambiguation | batch_69f6b3a7bdb481908d16a32f49e38c2c |
completed | May 3, 2026, 2:32 a.m. |
Created at: May 1, 2026, 12:23 a.m.