Triple
T32643599
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Isabel (Lower City) |
E834543
|
entity |
| Predicate | hasScreenTimeCharacteristic |
P189735
|
FINISHED |
| Object | appears throughout most of the film |
—
|
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: appears throughout most of the film | Statement: [Isabel (Lower City), hasScreenTimeCharacteristic, appears throughout most of the film]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasScreenTimeCharacteristic Context triple: [Isabel (Lower City), hasScreenTimeCharacteristic, appears throughout most of the film]
-
A.
hasScreenTimeIn
Indicates that an entity appears on screen for a certain duration within a specified audiovisual work or segment.
-
B.
hasScreenTimeType
Indicates the type or category of screen time associated with an entity (e.g., usage mode, content type, or context of screen use).
-
C.
screenTime
Indicates the amount of time an entity spends viewing or interacting with a screen-based device.
-
D.
screenTimeProportion
Indicates the proportion of total time that an entity spends looking at or using a screen relative to a defined overall time period.
-
E.
screenTimeRelation
Indicates a relationship between entities based on the amount, duration, or pattern of time spent using screens or digital devices.
- 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_69f3492e773c81908afc10651e46cad3 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69fbca6c066c8190a1599202f341417f |
completed | May 6, 2026, 11:10 p.m. |
| PD | Predicate disambiguation | batch_69fbc8ec03ac8190a757563f96fab283 |
completed | May 6, 2026, 11:04 p.m. |
| PDg | Predicate description generation | batch_69fbc9d0854c8190aa00093274afebb8 |
completed | May 6, 2026, 11:08 p.m. |
Created at: May 1, 2026, 1:07 a.m.