Triple
T21619604
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saw film series |
E533540
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Jigsaw (2017 film) |
—
|
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: Jigsaw (2017 film) | Statement: [Saw film series, hasPart, Jigsaw (2017 film)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jigsaw (2017 film) Context triple: [Saw film series, hasPart, Jigsaw (2017 film)]
-
A.
Jigsaw Falling into Place
"Jigsaw Falling into Place" is a song by the English rock band Radiohead, known for its dynamic build, intricate rhythms, and vivid lyrical portrayal of a chaotic night out.
-
B.
Jigsaw
Jigsaw was a British pop rock band best known for their 1975 hit single "Sky High."
-
C.
Jigsaw
chosen
Jigsaw is a 2017 American horror film in the Saw franchise that revives the series’ signature deadly games and moral tests years after the apparent death of the Jigsaw Killer.
-
D.
Saw
Saw is a 2004 horror film that launched a popular franchise known for its psychological terror, elaborate death traps, and twist ending.
-
E.
Saw X
Saw X is a 2023 American horror film in the Saw franchise that follows John Kramer as he seeks brutal revenge on scammers through elaborate and deadly traps.
- 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_69e0c464fba881908d0ff2ac80511ce1 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef3bad094c8190879d4aef7988254a |
completed | April 27, 2026, 10:34 a.m. |
Created at: April 16, 2026, 6:34 p.m.