Triple
T2643788
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jaq |
E62937
|
entity |
| Predicate | enemyOf |
P437
|
FINISHED |
| Object | Lady Tremaine |
E62935
|
NE 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: Lady Tremaine | Statement: [Jaq, enemyOf, Lady Tremaine]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lady Tremaine Context triple: [Jaq, enemyOf, Lady Tremaine]
-
A.
Lady Tremaine
chosen
Lady Tremaine is the cruel and calculating stepmother of Cinderella, best known as the primary antagonist in Disney’s 1950 animated film.
-
B.
The Evil Queen
The Evil Queen is the vain and power-hungry royal villain from Disney’s Snow White, infamous for her jealousy and use of dark magic to eliminate her rival.
-
C.
Carabosse
Carabosse is the malevolent fairy or sorceress who curses Princess Aurora in the classic fairy tale and ballet "The Sleeping Beauty."
-
D.
Drizella Tremaine
Drizella Tremaine is one of Cinderella’s vain and spiteful stepsisters in Disney’s Cinderella, known for her jealousy, cruelty, and comic incompetence.
-
E.
Blanche de Mille (stepmother)
Blanche de Mille was the stepmother of American screenwriter and film director William C. deMille, connected to the prominent deMille family of early Hollywood.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ab4c3f2dcc819082df80f5e032f690 |
completed | March 6, 2026, 9:50 p.m. |
| NER | Named-entity recognition | batch_69abd90046dc81908bab3440733f1e98 |
completed | March 7, 2026, 7:51 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69afa050cc408190b2fa81a0f2da06eb |
completed | March 10, 2026, 4:38 a.m. |
Created at: March 6, 2026, 9:53 p.m.