Triple
T6080490
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fred Schepisi |
E135509
|
entity |
| Predicate | directed |
P7373
|
FINISHED |
| Object | Words and Pictures |
E566010
|
NE 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: Words and Pictures | Statement: [Fred Schepisi, directed, Words and Pictures]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Words and Pictures Context triple: [Fred Schepisi, directed, Words and Pictures]
-
A.
Words and Pictures
chosen
Words and Pictures is a 2013 romantic drama film about the rivalry and relationship between an art teacher and an English teacher at a prep school, directed by Fred Schepisi.
-
B.
Stories and Pictures
Stories and Pictures is a celebrated collection of Yiddish short stories by I. L. Peretz that helped define modern Jewish literature.
-
C.
The Book with No Pictures
The Book with No Pictures is a bestselling children's picture book by comedian and writer B. J. Novak that uses only text and playful typography to create a humorous, read-aloud experience without any illustrations.
-
D.
The Ink Factory
The Ink Factory is a British production company best known for adapting John le Carré’s works for film and television.
-
E.
Of Words
"Of Words" is a chapter in Book III that examines the nature, use, and significance of language and terminology.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69c0087ad31c8190ab936e0ff28614b6 |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c057735b6081908b82757505fa7d5d |
completed | March 22, 2026, 8:56 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c1252a178c81909a3d689ad748fb5e |
completed | March 23, 2026, 11:34 a.m. |
Created at: March 22, 2026, 4:11 p.m.