Triple
T34371802
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paul Kersey |
E882175
|
entity |
| Predicate | portrayedInRemake |
P189533
|
FINISHED |
| Object | Death Wish (2018 film) |
—
|
NE NERFINISHED |
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: Death Wish (2018 film) | Statement: [Paul Kersey, portrayedInRemake, Death Wish (2018 film)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: portrayedInRemake Context triple: [Paul Kersey, portrayedInRemake, Death Wish (2018 film)]
-
A.
remakePortrayedBy
chosen
Indicates that in a remake of a work, a given role or character is portrayed by a specified performer.
-
B.
appearsInRemakeAs
Indicates that an entity reappears in a remake version of a work, typically in a similar or related role as in the original.
-
C.
remakeOfFilmStarring
Indicates that one film is a remake of another film in which a specified actor or set of actors starred.
-
D.
appearsInRemakeOf
Indicates that an entity appears in a work that is a remake of another original work.
-
E.
remakeAppearsIn
Indicates that a remake of a work is featured, shown, or included within a particular context, such as a collection, series, or medium.
- 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_69f349bf5d7481908dd5da4cbdf74047 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69ff0e9c75208190a4423261f00b79b3 |
completed | May 9, 2026, 10:38 a.m. |
| PD | Predicate disambiguation | batch_69ff0e07f08481909c4ae322632a6bf0 |
completed | May 9, 2026, 10:35 a.m. |
Created at: May 1, 2026, 1:59 a.m.