Triple
T35289680
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Wormwood |
E1019185
|
entity |
| Predicate | treatmentOfMatilda |
P183000
|
FINISHED |
| Object | unkind |
—
|
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: unkind | Statement: [Michael Wormwood, treatmentOfMatilda, unkind]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: treatmentOfMatilda Context triple: [Michael Wormwood, treatmentOfMatilda, unkind]
-
A.
outcomeForMatilda
Indicates the result, consequence, or effect that an event, action, or situation has specifically for Matilda.
-
B.
formerGovernessOf
Indicates that one person previously served as the governess of another person.
-
C.
treatmentOfCinderella
Indicates how one party behaves toward or deals with Cinderella.
-
D.
treatmentOf
Indicates a relationship where one entity administers, provides, or is responsible for a therapeutic intervention directed toward another entity (typically a patient or condition).
-
E.
godmother
Indicates that one entity serves as a godmother to another, typically holding a special, often ceremonial or mentoring, parental-like role in their life.
- F. None of above. chosen
Provenance (4 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_69f76de6d39c8190bb11342e4b91ff2b |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f795b5228c8190adb5bf86e581f70c |
completed | May 3, 2026, 6:36 p.m. |
| PD | Predicate disambiguation | batch_69f79104f5b48190a496cdffde8472da |
completed | May 3, 2026, 6:16 p.m. |
| PDg | Predicate description generation | batch_69f79527c7bc8190a69d87bec01f65c8 |
completed | May 3, 2026, 6:34 p.m. |
Created at: May 3, 2026, 4:03 p.m.