Triple
T18351031
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Haruki Murakami |
E439666
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | After Dark |
—
|
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: After Dark | Statement: [Haruki Murakami, notableWork, After Dark]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: After Dark Context triple: [Haruki Murakami, notableWork, After Dark]
-
A.
After Dark
chosen
After Dark is a surreal, nocturnal novel by Haruki Murakami that intertwines the lives of several Tokyo residents over the course of a single night.
-
B.
After Dark
After Dark is a 1980 pop/disco studio album by singer Andy Gibb, featuring hit singles and collaborations with members of the Bee Gees.
-
C.
After Dark
After Dark is a collection of short stories by Victorian author Wilkie Collins, framed by a narrative about an artist whose wife records his tales as he loses his eyesight.
-
D.
After Dark
"After Dark" is a live album by the Washington, D.C. post-punk band The Make-Up, showcasing their gospel-infused, garage rock sound and charismatic performance style.
-
E.
After Dark, My Sweet
After Dark, My Sweet is a 1990 neo-noir crime drama film adapted from a Jim Thompson novel, noted for its moody atmosphere and psychologically driven story.
- 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_69d8b918221c8190a9f7b563d64ac677 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e514f83b648190b473cf611851c666 |
completed | April 19, 2026, 5:46 p.m. |
Created at: April 10, 2026, 10:37 a.m.