Triple
T12900375
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Emacs state |
E308595
|
entity |
| Predicate | differsFrom |
P278
|
FINISHED |
| Object | Evil Insert state |
E59585
|
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: Evil Insert state | Statement: [Emacs state, differsFrom, Evil Insert state]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Evil Insert state Context triple: [Emacs state, differsFrom, Evil Insert state]
-
A.
Evil mode
chosen
Evil mode is a popular Emacs extension that emulates Vim’s modal editing, allowing users to use Vim-style keybindings and workflows within the Emacs environment.
-
B.
Beyond Evil
Beyond Evil is a critically acclaimed South Korean psychological crime thriller drama series centered on two detectives obsessively pursuing a serial killer in a small town.
-
C.
Evil Stuff
Evil Stuff is a themed retail shop in Minion Land offering villain-inspired merchandise and playful, mischievous souvenirs.
-
D.
Evil
"Evil" is a soulful, introspective song by Stevie Wonder from his 1972 album *Music of My Mind*, reflecting on inner conflict and moral struggle.
-
E.
Evil
Evil is a psychological horror television series that follows a skeptical psychologist, a priest-in-training, and a contractor as they investigate alleged supernatural occurrences for the Catholic Church.
- 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_69d7bdf7c1f0819098102569a8d8cbf5 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d97180ee708190b60a3e58c42f764f |
completed | April 10, 2026, 9:54 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6a56189b081909ed838addcb6d265 |
completed | May 3, 2026, 1:31 a.m. |
Created at: April 9, 2026, 5:40 p.m.