Triple
T36059890
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Donnie Darko |
E1043046
|
entity |
| Predicate | mentalDisorder |
P113325
|
FINISHED |
| Object | schizophrenia (implied) |
—
|
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: schizophrenia (implied) | Statement: [Donnie Darko, mentalDisorder, schizophrenia (implied)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mentalDisorder Context triple: [Donnie Darko, mentalDisorder, schizophrenia (implied)]
-
A.
hasPsychologicalCondition
chosen
Indicates that an entity experiences or is diagnosed with a particular psychological or mental health condition.
-
B.
hasPsychiatricComponent
Indicates that something includes, involves, or is associated with a psychiatric aspect, factor, or condition as part of its overall nature or composition.
-
C.
exampleOfDisorder
Indicates that one entity is an instance or specific case of a particular disorder represented by another entity.
-
D.
mentalStateChange
Indicates a change in an entity’s mental or emotional condition from one state to another.
-
E.
causeOfMentalHealthIssues
Indicates that one entity is a contributing factor in producing or worsening another entity’s mental health issues.
- 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_69f76e2f09448190b0486d5ecad5e243 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7b2c771108190adeec151daad5dab |
completed | May 3, 2026, 8:40 p.m. |
| PD | Predicate disambiguation | batch_69f7b1bad2e88190963ab4ee5d4f2038 |
completed | May 3, 2026, 8:36 p.m. |
Created at: May 3, 2026, 4:08 p.m.