Triple
T32543768
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sam Rockwell as Bob Fosse |
E831784
|
entity |
| Predicate | portraysHealthIssues |
P109068
|
FINISHED |
| Object | substance abuse |
—
|
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: substance abuse | Statement: [Sam Rockwell as Bob Fosse, portraysHealthIssues, substance abuse]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: portraysHealthIssues Context triple: [Sam Rockwell as Bob Fosse, portraysHealthIssues, substance abuse]
-
A.
depictsMedicalCondition
Indicates that one entity visually represents or illustrates a particular medical condition affecting another entity or subject.
-
B.
portraysSocialIssue
chosen
Indicates that an entity depicts, represents, or brings attention to a social problem or concern within its content or context.
-
C.
diseaseDepicted
Indicates that a visual representation (such as an image or illustration) shows or portrays a particular disease.
-
D.
patientPortrayedBy
Indicates that a patient is represented or depicted by a particular actor, model, or illustrative figure.
-
E.
challengesPortrayalOf
Indicates that one entity questions, disputes, or undermines the way another entity is represented or depicted.
- 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_69f34925fd08819084cfe4ec566cb704 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fe6739d4dc8190ae7505c089bbac29 |
completed | May 8, 2026, 10:44 p.m. |
| PD | Predicate disambiguation | batch_69fe6541dffc81909c66a61ba69f38fc |
completed | May 8, 2026, 10:35 p.m. |
Created at: May 1, 2026, 1:02 a.m.