Triple
T21029267
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Θήβα |
E518021
|
entity |
| Predicate | μυθικός_βασιλιάς |
P9987
|
FINISHED |
| Object | Κρέων |
—
|
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: Κρέων | Statement: [Θήβα, μυθικός_βασιλιάς, Κρέων]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Κρέων Context triple: [Θήβα, μυθικός_βασιλιάς, Κρέων]
-
A.
Creon of Corinth
Creon of Corinth is a king in Greek mythology, best known from Euripides’ Medea as the ruler who grants Jason and Medea refuge before later banishing Medea and being killed by her revenge.
-
B.
Orestheus
Orestheus is a minor figure in Greek mythology known primarily as a son of the flood survivor and progenitor of humankind, Deucalion.
-
C.
Creon
chosen
Creon is a mythological king of Thebes in Greek tragedy, best known for his roles in the stories of Oedipus and Antigone.
-
D.
Laius
Laius is a mythological king of Thebes in Greek tragedy, best known for the prophecy that his son would kill him and marry his wife, setting the stage for the story of Oedipus.
-
E.
Ligkiades
Ligkiades is a village in northwestern Greece overlooking Lake Pamvotida, known for its scenic views and tragic World War II history.
- 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_69e6fc7fd3ec81908ac237047f9b0d7a |
completed | April 21, 2026, 4:26 a.m. |
Created at: April 16, 2026, 1:55 p.m.