Triple
T28368484
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Effie Gray (2014 film) |
E718555
|
entity |
| Predicate | screenplaySubject |
P166217
|
FINISHED |
| Object | marital breakdown |
—
|
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: marital breakdown | Statement: [Effie Gray (2014 film), screenplaySubject, marital breakdown]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: screenplaySubject Context triple: [Effie Gray (2014 film), screenplaySubject, marital breakdown]
-
A.
screenplayType
Indicates the specific category or format of a screenplay associated with a work or production.
-
B.
screenplayInspiration
Indicates that one work or real-world source served as the creative basis or inspiration for the screenplay of another work.
-
C.
screenplayFeature
Indicates that one entity is a screenplay that serves as the primary feature or main written work associated with another entity, such as a film or production.
-
D.
screenplayRecord
Indicates that there exists a record or documentation associated with a particular screenplay, capturing information about its creation, version, or related details.
-
E.
screenplayDevelopment
Indicates a relationship where a screenplay is being created, refined, or otherwise developed, typically through writing, revising, or collaborative work.
- 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_69eff6ed5af48190be4e0adf298223e0 |
completed | April 27, 2026, 11:53 p.m. |
| NER | Named-entity recognition | batch_69f66003a3f48190a2ba6da5aafbb5cb |
completed | May 2, 2026, 8:35 p.m. |
| PD | Predicate disambiguation | batch_69f65c2198208190a3954086c22cfcbf |
completed | May 2, 2026, 8:18 p.m. |
| PDg | Predicate description generation | batch_69f65f75ac608190a62cd6afce14f68e |
completed | May 2, 2026, 8:32 p.m. |
Created at: April 28, 2026, 12:57 a.m.