Triple
T8661664
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kate Dickie |
E205561
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Filth |
E533912
|
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: Filth | Statement: [Kate Dickie, notableWork, Filth]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Filth Context triple: [Kate Dickie, notableWork, Filth]
-
A.
Filth
chosen
Filth is a 2013 dark comedy crime film based on Irvine Welsh's novel, following a corrupt, drug-addicted Scottish police officer whose life spirals out of control.
-
B.
Filthy
"Filthy" is a funk-influenced lead single by Justin Timberlake from his 2018 album "Man of the Woods."
-
C.
Dirty
"Dirty" is a 1992 alternative rock album by Sonic Youth, noted for its noisy guitar sound and association with the grunge era.
-
D.
Stink
Stink is a 1982 EP by American punk rock band The Replacements, known for its raw, hardcore-influenced sound and rebellious energy.
-
E.
Scum
Scum is a gritty 1979 British crime drama film depicting the brutal realities of life inside a borstal (youth detention center), noted for its stark violence and Ray Winstone’s powerful performance.
- 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_69ca8350897c819086cde7596fbe5fe7 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc487147248190b5f1bff836a11e68 |
completed | March 31, 2026, 10:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cef37efbf08190805fbb270a4bce37 |
completed | April 2, 2026, 10:53 p.m. |
Created at: March 30, 2026, 6:30 p.m.