Triple
T11103158
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chaplet of Saint Michael |
E262560
|
entity |
| Predicate | honors |
P2354
|
FINISHED |
| Object | Seraphim |
E437896
|
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: Seraphim | Statement: [Chaplet of Saint Michael, honors, Seraphim]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Seraphim Context triple: [Chaplet of Saint Michael, honors, Seraphim]
-
A.
Seraphim
chosen
Seraphim are the highest-ranking class of angels in Christian angelology, traditionally associated with fiery devotion and the worship of God.
-
B.
Séraphîta
Séraphîta is a mystical philosophical novel by Honoré de Balzac that blends spiritual speculation, romantic narrative, and Swedenborgian ideas within the larger cycle of La Comédie humaine.
-
C.
Seraph
Seraph is a skilled, enigmatic guardian and martial arts master in the Matrix universe who protects the Oracle and tests those who seek her.
-
D.
Metatron
Metatron is a powerful angelic being often depicted in Jewish and Christian mysticism as a celestial scribe or the voice of God.
-
E.
Adriel
Adriel is the given first name of American former NFL wide receiver A. J. Green.
- 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_69d6aa9a40d88190a373e2c7e48285db |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d79a2c30a481908c45020c37caebe4 |
completed | April 9, 2026, 12:23 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e3e7ff368c8190ab01b7538ad83826 |
completed | April 18, 2026, 8:22 p.m. |
Created at: April 8, 2026, 9:27 p.m.