Triple
T10770671
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Corpus Hermeticum |
E254065
|
entity |
| Predicate | relatedWork |
P37
|
FINISHED |
| Object | Asclepius |
E28749
|
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: Asclepius | Statement: [Corpus Hermeticum, relatedWork, Asclepius]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Asclepius Context triple: [Corpus Hermeticum, relatedWork, Asclepius]
-
A.
Asclepius
chosen
Asclepius is the ancient Greek god of medicine and healing, revered for his ability to cure illness and restore health.
-
B.
Medeius
Medeius is a figure from Greek mythology known as a descendant of the hero Jason’s family line.
-
C.
Calchas
Calchas is a prophetic Trojan priest who defects to the Greeks in medieval and classical tales of the Trojan War, including Chaucer’s "Troilus and Criseyde."
-
D.
Ascalaphe
Ascalaphe is a minor figure in Greek mythology, known as the informer who revealed Persephone’s eating of pomegranate seeds and was punished by being transformed into an owl.
-
E.
Dorotheus
Dorotheus was a 6th-century Byzantine jurist who helped systematize and codify Roman law under Emperor Justinian I.
- 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_69d6aa5f54f4819082d0bbcb6f8797e6 |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d732314bcc8190980c6f698f64ccf5 |
completed | April 9, 2026, 4:59 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69de23798af48190874d7e12c5155913 |
completed | April 14, 2026, 11:22 a.m. |
Created at: April 8, 2026, 9:16 p.m.