Triple
T20898040
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Worst Witch |
E514593
|
entity |
| Predicate | notableCharacter |
P1481
|
FINISHED |
| Object |
Miss Cackle
Miss Cackle is the kindly but firm headmistress of Miss Cackle’s Academy for Witches in Jill Murphy’s The Worst Witch series.
|
E1457185
|
NE FINISHED |
How this triple was built (4 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: Miss Cackle | Statement: [The Worst Witch, notableCharacter, Miss Cackle]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Miss Cackle Context triple: [The Worst Witch, notableCharacter, Miss Cackle]
-
A.
Miss Crawly
Miss Crawly is an elderly, one-eyed iguana and Buster Moon’s loyal assistant in the animated film series "Sing."
-
B.
Mavis Grind
Mavis Grind is a narrow isthmus in Northmavine, Shetland, known for nearly connecting the Atlantic Ocean and the North Sea at one of their closest points.
-
C.
Miss Sylvester
Miss Sylvester was an educator significant enough in her community or field that a school was named in her honor.
-
D.
Madam Mim
Madam Mim is a comically wicked, shape-shifting witch and the main antagonist from Disney’s animated film "The Sword in the Stone."
-
E.
Miss Granny
Miss Granny is a popular South Korean comedy-drama film about an elderly woman who mysteriously regains her youthful appearance, leading to humorous and heartfelt consequences.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Miss Cackle Triple: [The Worst Witch, notableCharacter, Miss Cackle]
Generated description
Miss Cackle is the kindly but firm headmistress of Miss Cackle’s Academy for Witches in Jill Murphy’s The Worst Witch series.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Miss Cackle Target entity description: Miss Cackle is the kindly but firm headmistress of Miss Cackle’s Academy for Witches in Jill Murphy’s The Worst Witch series.
-
A.
Miss Crawly
Miss Crawly is an elderly, one-eyed iguana and Buster Moon’s loyal assistant in the animated film series "Sing."
-
B.
Mavis Grind
Mavis Grind is a narrow isthmus in Northmavine, Shetland, known for nearly connecting the Atlantic Ocean and the North Sea at one of their closest points.
-
C.
Miss Sylvester
Miss Sylvester was an educator significant enough in her community or field that a school was named in her honor.
-
D.
Madam Mim
Madam Mim is a comically wicked, shape-shifting witch and the main antagonist from Disney’s animated film "The Sword in the Stone."
-
E.
Miss Granny
Miss Granny is a popular South Korean comedy-drama film about an elderly woman who mysteriously regains her youthful appearance, leading to humorous and heartfelt consequences.
- F. None of above. chosen
Provenance (5 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_69e0b4f7ebe48190952a85547a0f31a1 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6e8f826788190b11008cc94b2a4e4 |
completed | April 21, 2026, 3:03 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0918cefa2081909768f9923a96f209 |
completed | May 17, 2026, 1:24 a.m. |
| NEDg | Description generation | batch_6a091ca90e788190bb74c161c9233634 |
completed | May 17, 2026, 1:40 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a091d9402448190bb223e0950450e4e |
completed | May 17, 2026, 1:44 a.m. |
Created at: April 16, 2026, 12:47 p.m.