Triple
T22315400
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lee Chang-dong |
E551626
|
entity |
| Predicate | wroteScreenplayFor |
P15305
|
FINISHED |
| Object | Poetry |
—
|
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: Poetry | Statement: [Lee Chang-dong, wroteScreenplayFor, Poetry]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Poetry Context triple: [Lee Chang-dong, wroteScreenplayFor, Poetry]
-
A.
Poetry
Poetry is a Python dependency management and packaging tool that simplifies creating, building, and publishing Python projects.
-
B.
Poetry
chosen
"Poetry" is a 2010 South Korean drama film by Lee Chang-dong that follows an elderly woman who discovers a passion for writing poetry while confronting a harrowing family tragedy.
-
C.
Poems
Poems is a collection of poetry published in 1844, best known as one of Elizabeth Barrett Browning’s early and influential volumes.
-
D.
Poetry Please
Poetry Please is a long-running BBC Radio 4 programme that features listeners’ requests for classic and contemporary poetry, often introduced and read by notable poets and actors.
-
E.
Poetry Review
Poetry Review is a leading British literary magazine dedicated to publishing contemporary poetry, criticism, and essays.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e4776588190abb21e5cea79973f |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1575287688190aa642bb49b24f5a1 |
completed | April 29, 2026, 12:56 a.m. |
Created at: April 16, 2026, 8:42 p.m.