Triple
T9719747
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Black Swan Pas de deux |
E235432
|
entity |
| Predicate | characterTypeOfOdile |
P60013
|
FINISHED |
| Object | black swan |
—
|
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 | Statement: [Black Swan Pas de deux, characterTypeOfOdile, black swan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: characterTypeOfOdile Context triple: [Black Swan Pas de deux, characterTypeOfOdile, black swan]
-
A.
typeOfCharacter
chosen
Indicates that one entity is a specific kind or category of character in relation to another entity.
-
B.
danceRole
Indicates that one entity has a specific role or function within a dance performed with or in relation to another entity.
-
C.
genreOfCharacter
Indicates that a character belongs to or is associated with a particular genre (such as fantasy, horror, or comedy).
-
D.
musicalCharacter
Indicates that one entity is a character or role that appears within the other entity, which is a musical work or production.
-
E.
characterTypeOfEdward
Indicates that the specified attribute or classification is the character type assigned to Edward.
- 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_69ca84d0123c819096f9dc3b6abb0881 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cd9e4022c4819097455f14dd9b1a77 |
completed | April 1, 2026, 10:37 p.m. |
| PD | Predicate disambiguation | batch_69cd03bfeca08190924fca43aaa9c10f |
completed | April 1, 2026, 11:38 a.m. |
Created at: March 30, 2026, 8:20 p.m.