Triple
T30613605
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tommy Lascelles (The Crown) |
E779252
|
entity |
| Predicate | screenTimeConcentratedIn |
P173421
|
FINISHED |
| Object | early seasons of The Crown |
—
|
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: early seasons of The Crown | Statement: [Tommy Lascelles (The Crown), screenTimeConcentratedIn, early seasons of The Crown]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: screenTimeConcentratedIn Context triple: [Tommy Lascelles (The Crown), screenTimeConcentratedIn, early seasons of The Crown]
-
A.
screenTimeProportion
Indicates the proportion of total time that an entity spends looking at or using a screen relative to a defined overall time period.
-
B.
screenTime
Indicates the amount of time an entity spends viewing or interacting with a screen-based device.
-
C.
screenTimeFocus
Indicates the amount or proportion of time an entity’s attention or activity is concentrated on a particular screen or digital display.
-
D.
screenTimeRelation
Indicates a relationship between entities based on the amount, duration, or pattern of time spent using screens or digital devices.
-
E.
screenTimeFunction
Indicates a functional relationship that maps an entity (such as a user, device, or app) to the amount of time its screen is active or in use.
- 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_69f224a3307081909a6dca8ca75dbf48 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f6b56ed31481908c3e5d749e46bad9 |
completed | May 3, 2026, 2:39 a.m. |
| PD | Predicate disambiguation | batch_69f6b3a7bdb481908d16a32f49e38c2c |
completed | May 3, 2026, 2:32 a.m. |
| PDg | Predicate description generation | batch_69f6b49339048190b617a6749f648825 |
completed | May 3, 2026, 2:36 a.m. |
Created at: April 29, 2026, 8:26 p.m.