Triple
T10224282
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Patrick Kenzie – Casey Affleck |
E242660
|
entity |
| Predicate | cameraFocus |
P31
|
FINISHED |
| Object | character-driven narrative |
—
|
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: character-driven narrative | Statement: [Patrick Kenzie – Casey Affleck, cameraFocus, character-driven narrative]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cameraFocus Context triple: [Patrick Kenzie – Casey Affleck, cameraFocus, character-driven narrative]
-
A.
autofocusPoints
Indicates the relationship between a camera (or imaging device) and the specific focus points it can automatically select or use for focusing.
-
B.
focusOf
Indicates that one entity is the primary subject, target, or center of attention, activity, or interest for another entity.
-
C.
typicalBackFocus
Indicates a relationship where attention, emphasis, or focus is characteristically directed toward the back or rear part of something.
-
D.
focusesOn
chosen
Indicates that one entity directs its attention, effort, or primary activity toward another entity or specific subject.
-
E.
telescopeFocus
Indicates that one entity adjusts or sets the focal point of a telescope relative to another entity or target.
- 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_69d381ae26c48190985abd0e25ee5d04 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d3aa84a9ac819093d551005a1c8f3d |
completed | April 6, 2026, 12:43 p.m. |
| PD | Predicate disambiguation | batch_69d3955f61f88190b8d37ff645cd44d3 |
completed | April 6, 2026, 11:13 a.m. |
Created at: April 6, 2026, 11:11 a.m.