Triple
T17865261
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arthur Franz |
E446681
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | The Sniper |
—
|
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: The Sniper | Statement: [Arthur Franz, notableWork, The Sniper]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: The Sniper Context triple: [Arthur Franz, notableWork, The Sniper]
-
A.
The Sniper
chosen
The Sniper is a 1952 film noir crime drama about a mentally disturbed sniper terrorizing San Francisco, featuring actress Marie Windsor in a prominent role.
-
B.
The Sniper
The Sniper is a Chinese war drama film best known for featuring actor Zhang Hanyu in a prominent role.
-
C.
I, Sniper
"I, Sniper" is a thriller novel by Stephen Hunter featuring Marine sniper Bob Lee Swagger as he investigates a series of seemingly perfect long-range killings.
-
D.
Sniper
"Sniper" is a track likely characterized by intense, precise, and hard-hitting themes, fitting the style and persona associated with the artist King of the North.
-
E.
Sniper
Sniper is a 1993 action thriller film about an expert Marine sniper and his spotter undertaking a dangerous mission in the Panamanian jungle.
- 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_69d8b9f4c22c819093c2680434472894 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e49793a2588190bb341ac606d767fe |
completed | April 19, 2026, 8:51 a.m. |
Created at: April 10, 2026, 10:17 a.m.