Triple
T13836284
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Στερόπη |
E332535
|
entity |
| Predicate | είναι_γνωστή_ως |
P85915
|
FINISHED |
| Object | μία από τις επτά θυγατέρες του Άτλαντα και της Πλειόνης |
—
|
LITERAL 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: μία από τις επτά θυγατέρες του Άτλαντα και της Πλειόνης | Statement: [Στερόπη, είναι_γνωστή_ως, μία από τις επτά θυγατέρες του Άτλαντα και της Πλειόνης]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: είναι_γνωστή_ως Context triple: [Στερόπη, είναι_γνωστή_ως, μία από τις επτά θυγατέρες του Άτλαντα και της Πλειόνης]
-
A.
известенКак
chosen
Indicates that one entity is known or recognized by a particular name, title, or role.
-
B.
knownAsOneOf
Indicates that an entity is recognized or referred to as one member of a specified set of alternative names, labels, or identities.
-
C.
knownAsBy
Indicates that one entity is referred to or recognized by another entity using a particular name or designation.
-
D.
известенС
Indicates that one entity is known or recognized by another entity.
-
E.
oftenUsedAsNameFor
Indicates that something frequently serves as a name or designation for another entity.
- F. None of above.
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_69d81c5ae7c88190b0dd41bdafeb5999 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de029b352081909605baaedc336213 |
completed | April 14, 2026, 9:02 a.m. |
| PD | Predicate disambiguation | batch_69dbc86668e08190ba9135d1c3f38d35 |
completed | April 12, 2026, 4:29 p.m. |
Created at: April 9, 2026, 10:13 p.m.