Triple
T28902628
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Louise Sawyer |
E732987
|
entity |
| Predicate | screenTimeRelativeToOthers |
P168639
|
FINISHED |
| Object | one of two characters with the most screen time in Thelma & Louise |
—
|
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: one of two characters with the most screen time in Thelma & Louise | Statement: [Louise Sawyer, screenTimeRelativeToOthers, one of two characters with the most screen time in Thelma & Louise]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: screenTimeRelativeToOthers Context triple: [Louise Sawyer, screenTimeRelativeToOthers, one of two characters with the most screen time in Thelma & Louise]
-
A.
screenTimeRelation
Indicates a relationship between entities based on the amount, duration, or pattern of time spent using screens or digital devices.
-
B.
screenTimeProportion
Indicates the proportion of total time that an entity spends looking at or using a screen relative to a defined overall time period.
-
C.
screenTime
Indicates the amount of time an entity spends viewing or interacting with a screen-based device.
-
D.
screenTimeRelativeImportance
Indicates how important or significant an entity’s screen time is relative to that of other entities.
-
E.
screenTimeEra
Indicates the period or era during which a particular screen-based technology, medium, or usage pattern is prevalent or characteristic.
- 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_69f05b08c2008190ac426a035a2ed66d |
completed | April 28, 2026, 7 a.m. |
| NER | Named-entity recognition | batch_69f67595fa7c8190b6e9f7a8c700dd97 |
completed | May 2, 2026, 10:07 p.m. |
| PD | Predicate disambiguation | batch_69f673c4abec8190bc2379e66f4af0a9 |
completed | May 2, 2026, 9:59 p.m. |
| PDg | Predicate description generation | batch_69f674df80b08190adb7f7531083bbb1 |
completed | May 2, 2026, 10:04 p.m. |
Created at: April 28, 2026, 8:04 a.m.