Triple
T20584929
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Helen Benson |
E505758
|
entity |
| Predicate | filmColorProcessOfWork |
P13343
|
FINISHED |
| Object | black‑and‑white |
—
|
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: black‑and‑white | Statement: [Helen Benson, filmColorProcessOfWork, black‑and‑white]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: filmColorProcessOfWork Context triple: [Helen Benson, filmColorProcessOfWork, black‑and‑white]
-
A.
hasFilmColorType
chosen
Indicates that a film is associated with a particular color process or color classification (e.g., color, black-and-white).
-
B.
workFilmProcess
Indicates that an entity is involved in a specific stage or aspect of the filmmaking process for a work.
-
C.
color work
Indicates that an entity applies or adds color to another entity, typically as part of a creative or finishing process.
-
D.
coloristNote
Indicates that one entity (typically a colorist) has added notes, comments, or annotations related to the coloring or color treatment of another entity.
-
E.
playedInBlackAndWhiteOrColorFilm
Indicates that the subject participated in a film, regardless of whether it was produced in black-and-white or in color.
- 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_69e0b4b9669c8190b8e81fc72817d42c |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6a975f098819083700593a9fa6cd0 |
completed | April 20, 2026, 10:32 p.m. |
| PD | Predicate disambiguation | batch_69e59fffe1748190825e4eaa90340631 |
completed | April 20, 2026, 3:39 a.m. |
Created at: April 16, 2026, 11:40 a.m.