Triple
T21028730
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Phrixus |
E518007
|
entity |
| Predicate | honoredBy |
P500
|
FINISHED |
| Object | King Aeëtes |
—
|
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: King Aeëtes | Statement: [Phrixus, honoredBy, King Aeëtes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: King Aeëtes Context triple: [Phrixus, honoredBy, King Aeëtes]
-
A.
Aeëtes
chosen
Aeëtes is a king in Greek mythology, best known as the ruler of Colchis and keeper of the Golden Fleece.
-
B.
Eurystheus
Eurystheus is the mythological king of Tiryns and Mycenae in Greek mythology who imposed the Twelve Labors upon Heracles.
-
C.
Pelias
Pelias is a figure in Greek mythology, best known as the usurping king of Iolcus who sent Jason on the quest for the Golden Fleece.
-
D.
King Augeas
King Augeas is a figure from Greek mythology, a king of Elis best known for his immense cattle herds and the filthy stables that Heracles was tasked with cleaning as one of his Twelve Labors.
-
E.
Polydectes
Polydectes is a king in Greek mythology best known for sending Perseus on the quest to slay Medusa in an attempt to get rid of him.
- 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_69e0b503275c8190afd9a163f997c709 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6fc7efda081909a4de1c389166bf2 |
completed | April 21, 2026, 4:26 a.m. |
Created at: April 16, 2026, 1:55 p.m.