Triple
T20661707
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cell (2016 film) |
E507773
|
entity |
| Predicate | basedOn |
P98
|
FINISHED |
| Object | Cell |
—
|
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: Cell | Statement: [Cell (2016 film), basedOn, Cell]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cell Context triple: [Cell (2016 film), basedOn, Cell]
-
A.
Cell
Cell is a leading peer-reviewed scientific journal that publishes high-impact research across the life sciences, particularly in molecular and cellular biology.
-
B.
Cell
chosen
"Cell" is a horror novel by Stephen King that follows a group of survivors navigating a post-apocalyptic world after a mysterious signal transmitted through cell phones turns people into violent killers.
-
C.
Cell
Cell is a major bio-engineered villain in Dragon Ball Z who possesses the abilities of multiple characters and seeks perfection through absorbing others.
-
D.
Cells
Cells is a series of large-scale sculptural installations by Louise Bourgeois that explore themes of memory, trauma, and the body through enclosed, room-like structures filled with symbolic objects.
-
E.
Cell 211
Cell 211 is a critically acclaimed Spanish prison thriller film centered on a deadly riot and the moral dilemmas it creates.
- 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_69e0b4c059bc81908ea762cd73ea4424 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6b2f2ee4081908df9ba897c9dfc98 |
completed | April 20, 2026, 11:12 p.m. |
Created at: April 16, 2026, 11:44 a.m.