Triple
T29300087
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Madras Talkies |
E742933
|
entity |
| Predicate | frequentCinematographerCollaborator |
P167957
|
FINISHED |
| Object | P. C. Sreeram |
—
|
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: P. C. Sreeram | Statement: [Madras Talkies, frequentCinematographerCollaborator, P. C. Sreeram]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: frequentCinematographerCollaborator Context triple: [Madras Talkies, frequentCinematographerCollaborator, P. C. Sreeram]
-
A.
cinematographerOfWork
chosen
Indicates that a person served as the cinematographer (director of photography) for a specific creative work.
-
B.
frequentDirector
Indicates that a director has collaborated with a particular entity (such as an actor, writer, or production) many times, more often than typical.
-
C.
coDirectedWith
Indicates that two or more entities jointly directed the same work or project.
-
D.
notableCinematographer
Indicates that the subject is a cinematographer who is particularly distinguished or well-known for their work.
-
E.
associatedWithComposerOfFilm
Indicates a relationship where an entity is connected to the composer who created the musical score for a specific film.
- F. None of above.
Provenance (4 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_69f09123ed9881909f351f7541933f5e |
completed | April 28, 2026, 10:51 a.m. |
| NER | Named-entity recognition | batch_69f66e5f7e30819094530abceabd5f43 |
completed | May 2, 2026, 9:36 p.m. |
| PD | Predicate disambiguation | batch_69f66abfdaf08190a55f14c70be6fd4d |
completed | May 2, 2026, 9:21 p.m. |
| PDg | Predicate description generation | batch_69f66d75a8788190aa9ca2c977429045 |
completed | May 2, 2026, 9:32 p.m. |
Created at: April 28, 2026, 1:09 p.m.