Triple
T38363521
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jessica Lange as Leigh Bowden |
E892360
|
entity |
| Predicate | workEditor |
P107303
|
FINISHED |
| Object | Thelma Schoonmaker |
—
|
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: Thelma Schoonmaker | Statement: [Jessica Lange as Leigh Bowden, workEditor, Thelma Schoonmaker]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: workEditor Context triple: [Jessica Lange as Leigh Bowden, workEditor, Thelma Schoonmaker]
-
A.
editorOfWork
chosen
Indicates that one entity serves as the editor responsible for preparing, revising, or overseeing the content of a particular work.
-
B.
coEditor
Indicates that two or more entities share responsibility for editing the same work or publication.
-
C.
editingOfWorkBy
Indicates that one entity performs editorial modifications or revisions on a work created by another entity.
-
D.
editorCommunity
Indicates a relationship where an editor is associated with, participates in, or belongs to a particular community.
-
E.
editorActivity
Indicates the actions or interactions performed by an editor in the context of creating, modifying, or managing content.
- 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_69f76e47cb4c8190bdd92cd1db59c0c5 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fcd1499e2c81909bafd84dc4810f45 |
completed | May 7, 2026, 5:52 p.m. |
| PD | Predicate disambiguation | batch_69fcccf024ec819086383ffbb6cfc036 |
completed | May 7, 2026, 5:33 p.m. |
Created at: May 3, 2026, 4:31 p.m.