Triple
T9001486
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Blue Exorcist |
E215047
|
entity |
| Predicate | setting |
P1957
|
FINISHED |
| Object | Gehenna |
E68979
|
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: Gehenna | Statement: [Blue Exorcist, setting, Gehenna]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gehenna Context triple: [Blue Exorcist, setting, Gehenna]
-
A.
Sheol
Sheol is the ancient Hebrew concept of the shadowy underworld or abode of the dead, where all souls go after death.
-
B.
Hell
chosen
Hell is a supernatural underworld realm commonly depicted in religion and fiction as a place of torment, demons, and the damned.
-
C.
Naraka
Naraka is the concept of an underworld or hell in several Indian religions, where souls undergo punishment or purification after death.
-
D.
Tartarus
Tartarus is the deep, gloomy abyss in Greek mythology used as a dungeon of torment and imprisonment for the Titans and other divine enemies.
-
E.
Averno
Averno is a 2006 poetry collection by Nobel Prize–winning American poet Louise Glück that meditates on themes of death, the underworld, and female identity through reimagined myth.
- 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_69ca83a12d648190b1e4fe11e8a31890 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc6956a6e08190bd3853a7c1c130eb |
completed | April 1, 2026, 12:39 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfd0ddb1648190a50f8877218d9883 |
completed | April 3, 2026, 2:38 p.m. |
Created at: March 30, 2026, 7:05 p.m.