Triple
T30112297
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thackery Binx (human form) in Hocus Pocus |
E765313
|
entity |
| Predicate | cursedInto |
P141639
|
FINISHED |
| Object | immortal black cat |
—
|
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: immortal black cat | Statement: [Thackery Binx (human form) in Hocus Pocus, cursedInto, immortal black cat]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cursedInto Context triple: [Thackery Binx (human form) in Hocus Pocus, cursedInto, immortal black cat]
-
A.
cursedToDieIn
Indicates that an entity is under a curse that causes them to die in a specified place or context.
-
B.
cursedIdentityOf
chosen
Indicates that one entity is the cursed or negatively transformed identity or form of another entity.
-
C.
curseCondition
Indicates a condition or state in which an entity is affected by a curse or cursed effect.
-
D.
associatedCurse
Indicates that one entity is linked to, affected by, or bears responsibility for a particular curse related to another entity.
-
E.
curseSymbol
Indicates that one entity serves as a symbol, sign, or representation of a curse associated with another entity.
- 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_69f22475ad7c8190be7f9541044a0bbb |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f67dc094a081908f4214b878598e54 |
completed | May 2, 2026, 10:42 p.m. |
| PD | Predicate disambiguation | batch_69f673c664f08190b4d66cdc305e10db |
completed | May 2, 2026, 9:59 p.m. |
Created at: April 29, 2026, 7:10 p.m.