Triple
T9968627
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Atomic Monster Productions |
E195745
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | M3GAN |
E606099
|
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: M3GAN | Statement: [Atomic Monster Productions, notableWork, M3GAN]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: M3GAN Context triple: [Atomic Monster Productions, notableWork, M3GAN]
-
A.
M3GAN
chosen
M3GAN is a 2022 sci-fi horror film about an artificially intelligent doll that becomes dangerously overprotective of the child it is designed to befriend.
-
B.
Prevenge
Prevenge is a 2016 British black comedy slasher film written, directed by, and starring Alice Lowe, about a pregnant woman who believes her unborn child is compelling her to commit murders.
-
C.
Mandy
Mandy is a given name, typically a diminutive of names like Amanda or Armand, used for both females and males.
-
D.
Golem
Golem is a classic 1915 science fiction novel by Polish writer Gustav Meyrink that reimagines the Jewish legend of a mystical clay creature brought to life in the Prague ghetto.
-
E.
Tronzilla
Tronzilla is a music producer best known for crafting hard-hitting, high-energy tracks in the electronic and hip-hop scenes.
- 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_69ca82ebd1288190912f9e4482d1fa35 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdb7b683ac8190ac97bd775a860d29 |
completed | April 2, 2026, 12:26 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d23dc117f48190ad66dd62f9833a10 |
completed | April 5, 2026, 10:47 a.m. |
Created at: March 30, 2026, 8:47 p.m.