Triple
T25827362
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Charlie Chaplin |
E650568
|
entity |
| Predicate | workedWithCinematographer |
P45033
|
FINISHED |
| Object | Rollie Totheroh |
—
|
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: Rollie Totheroh | Statement: [Charlie Chaplin, workedWithCinematographer, Rollie Totheroh]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: workedWithCinematographer Context triple: [Charlie Chaplin, workedWithCinematographer, Rollie Totheroh]
-
A.
cinematographerOfWork
Indicates that a person served as the cinematographer (director of photography) for a specific creative work.
-
B.
workedWithDirector
Indicates that one entity has collaborated professionally with a director on a project or production.
-
C.
hasWorkedOnFilmBy
Indicates that one entity has worked on a film that was created, directed, or otherwise authored by another entity.
-
D.
coDirectedWith
Indicates that two or more entities jointly directed the same work or project.
-
E.
filmDirectorWorkedWith
chosen
Indicates that a film director has collaborated professionally with another person on one or more film projects.
- 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_69e7ab37438081908f1ccf6284839520 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f61f12b0f08190bc4a16907941864c |
completed | May 2, 2026, 3:58 p.m. |
| PD | Predicate disambiguation | batch_69f61b37a5648190b10d33ae205ccfee |
completed | May 2, 2026, 3:41 p.m. |
Created at: April 22, 2026, 7:36 a.m.