Triple
T22722872
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | exorcism of Asmodeus |
E561911
|
entity |
| Predicate | performedBy |
P1363
|
FINISHED |
| Object | Tobiah |
—
|
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: Tobiah | Statement: [exorcism of Asmodeus, performedBy, Tobiah]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tobiah Context triple: [exorcism of Asmodeus, performedBy, Tobiah]
-
A.
Tobiah
chosen
Tobiah is a central figure in the biblical Book of Tobit, known for his divinely guided journey during which he overcomes the demon Asmodeus and marries Sarah.
-
B.
Tobiah the Ammonite
Tobiah the Ammonite is a biblical figure known as one of the chief opponents of Nehemiah’s efforts to rebuild Jerusalem’s walls after the Babylonian exile.
-
C.
Tobit Raphael
Tobit Raphael is an actor best known for his role as Yo-Yo Santos in the comedy film "The Internship."
-
D.
Eleazar
Eleazar is a masculine given name of Hebrew origin, traditionally associated with religious and historical figures.
-
E.
Eleazar
Eleazar is a biblical priest, son of Aaron, who succeeded his father as high priest of Israel.
- 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_69e2454fc984819088213b58ee87a002 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f17926ae0c8190af8493cab6b15261 |
completed | April 29, 2026, 3:21 a.m. |
Created at: April 17, 2026, 3:20 p.m.