Triple
T6959289
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sean Patrick Flanery |
E161327
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Saw 3D |
E295573
|
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: Saw 3D | Statement: [Sean Patrick Flanery, notableWork, Saw 3D]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Saw 3D Context triple: [Sean Patrick Flanery, notableWork, Saw 3D]
-
A.
Saw 3D
chosen
Saw 3D is a 2010 American horror film in the Saw franchise, marketed as the series’ first 3D installment and intended as a concluding chapter to the long-running torture-porn saga.
-
B.
Saw III
Saw III is a 2006 American horror film in the Saw franchise, known for its elaborate traps, graphic violence, and continuation of the Jigsaw killer’s storyline.
-
C.
Saw
Saw is a 2004 horror film that launched a popular franchise known for its psychological terror, elaborate death traps, and twist ending.
-
D.
Saw IV
Saw IV is a 2007 American horror film in the Saw franchise, continuing the series’ elaborate trap-based storyline and psychological terror.
-
E.
Saw VI
Saw VI is a 2009 American horror film in the Saw franchise that continues the story of the Jigsaw Killer’s gruesome moral tests and traps.
- 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_69c68852a9a0819097797e31d492e273 |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6daedbb4c8190b46846fb1265b937 |
completed | March 27, 2026, 7:30 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c75893a4808190b94a70d8823a01d3 |
completed | March 28, 2026, 4:26 a.m. |
Created at: March 27, 2026, 2:29 p.m.