Triple
T33873279
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Colin Farrell as Tommy Sweet |
E868281
|
entity |
| Predicate | screenTimeRelativeToLead |
P101227
|
FINISHED |
| Object | supporting role |
—
|
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: supporting role | Statement: [Colin Farrell as Tommy Sweet, screenTimeRelativeToLead, supporting role]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: screenTimeRelativeToLead Context triple: [Colin Farrell as Tommy Sweet, screenTimeRelativeToLead, supporting role]
-
A.
screenTimeRelativeToProtagonist
Indicates the amount of time a character appears on screen compared to the story’s main protagonist.
-
B.
screenTimeRelativeToOthers
Indicates how an entity’s amount of screen time compares to that of other entities.
-
C.
startTimeRelativeToGame
Indicates the time at which an event or action occurs, expressed relative to the start time of the game rather than as an absolute timestamp.
-
D.
screenTimeRole
chosen
Indicates the role or capacity in which an entity appears on screen, such as main, supporting, cameo, or other participation type.
-
E.
positionInTimeScale
Indicates the specific point or interval an event or state occupies within a defined temporal scale or timeline.
- 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_69f34995029081909ede0f7df73d1a5e |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f760a35b988190904e6267553ad2fe |
completed | May 3, 2026, 2:50 p.m. |
| PD | Predicate disambiguation | batch_69f75eb3d6f081908c933474eb359e3d |
completed | May 3, 2026, 2:41 p.m. |
Created at: May 1, 2026, 1:47 a.m.