Triple
T20090267
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | fragments of Sophocles |
E496248
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Cercyon |
—
|
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: Cercyon | Statement: [fragments of Sophocles, hasPart, Cercyon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cercyon Context triple: [fragments of Sophocles, hasPart, Cercyon]
-
A.
Cercyon
chosen
Cercyon is a figure from Greek mythology, a violent bandit and wrestler slain by the hero Theseus during his journey to Athens.
-
B.
Dictys
Dictys is a fisherman and brother of King Polydectes in Greek mythology who discovers and shelters Perseus and his mother Danaë after they wash ashore.
-
C.
Ancaeus
Ancaeus is a figure in Greek mythology, often depicted as a bold but ill-fated hero and Argonaut who met his death during the legendary Calydonian Boar Hunt.
-
D.
Aleus
Aleus is a figure in Greek mythology, a king of Tegea in Arcadia and a descendant of the god Arcas.
-
E.
Gryphus
Gryphus is a fictional character known primarily as the father of Rosa Gryphus.
- 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_69da626eee3881909f3454986d4a6511 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e6655e1ef0819095f40a1ce2eb17b7 |
completed | April 20, 2026, 5:41 p.m. |
Created at: April 11, 2026, 11:20 p.m.