Triple
T13685205
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Justin Kurzel |
E328103
|
entity |
| Predicate | directed |
P7373
|
FINISHED |
| Object | Snowtown |
E960484
|
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: Snowtown | Statement: [Justin Kurzel, directed, Snowtown]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Snowtown Context triple: [Justin Kurzel, directed, Snowtown]
-
A.
Snowtown
chosen
Snowtown is a 2011 Australian true-crime horror film depicting the infamous "Snowtown murders," noted for its bleak realism and disturbing subject matter.
-
B.
The Snowtown Murders
The Snowtown Murders is a 2011 Australian crime drama film that chillingly dramatizes the real-life Snowtown serial killings in South Australia.
-
C.
Stone City
Stone City is an ancient walled city and historic fortification area that forms part of the old core of Nanjing, China.
-
D.
Stone City
Stone City is the nickname of Tenino, Washington, reflecting its historic sandstone quarrying and stone-carving heritage.
-
E.
L-Town
L-Town is a colloquial nickname for Lansing, the capital city of the U.S. state of Michigan.
- 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_69d8076f1fa8819094664a59b55010df |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbc66f8acc8190b2a82b722930b995 |
completed | April 12, 2026, 4:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f79d4a4a50819098bd4348eba19ee7 |
completed | May 3, 2026, 7:08 p.m. |
Created at: April 9, 2026, 9:53 p.m.