Triple
T19134741
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ulysses |
E468406
|
entity |
| Predicate | encountersCreature |
P84701
|
FINISHED |
| Object | Charybdis |
—
|
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: Charybdis | Statement: [Ulysses, encountersCreature, Charybdis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Charybdis Context triple: [Ulysses, encountersCreature, Charybdis]
-
A.
Charybdis
chosen
Charybdis is a monstrous sea creature from Greek mythology, often depicted as a deadly whirlpool that threatens sailors alongside the monster Scylla.
-
B.
Scylla
Scylla is a fearsome sea monster from Greek mythology, often depicted with multiple heads and dwelling in a narrow strait opposite the whirlpool Charybdis.
-
C.
Scylla and Charybdis
Scylla and Charybdis are a pair of deadly sea monsters from Greek mythology that embody the perilous choice between two dangers, famously encountered by Odysseus.
-
D.
Ceto
Ceto is a primordial sea goddess in Greek mythology associated with the dangers and monstrous creatures of the ocean.
-
E.
Diomedea
Diomedea is a genus of large albatrosses, renowned oceanic seabirds known for their impressive wingspans and long-distance soaring over open seas.
- 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_69d8dd0796a48190b34ce4cd9d3f3be5 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e3ec4c848190af450bf5bf8db5e7 |
completed | April 20, 2026, 8:29 a.m. |
Created at: April 10, 2026, 12:05 p.m.