Triple
T20887813
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Apsyrtus |
E514330
|
entity |
| Predicate | killedBy |
P4646
|
FINISHED |
| Object | Medea |
—
|
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: Medea | Statement: [Apsyrtus, killedBy, Medea]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Medea Context triple: [Apsyrtus, killedBy, Medea]
-
A.
Medea
chosen
Medea is a mythological figure from Greek tragedy, best known as a powerful sorceress who kills her own children to avenge her husband Jason’s betrayal.
-
B.
L’Egisto
L’Egisto is a 17th-century Italian opera by Francesco Cavalli, known for its expressive early Baroque style and mythological subject matter.
-
C.
The Women of Trachis
The Women of Trachis is an ancient Greek tragedy by Sophocles that dramatizes the tragic fate of Heracles and his wife Deianeira, exploring themes of love, jealousy, and unintended destruction.
-
D.
Electra (Euripides)
Electra (Euripides) is a Greek tragedy by Euripides that retells the myth of Electra and Orestes avenging their father Agamemnon’s murder.
-
E.
Phoenician Women
Phoenician Women is an ancient Greek tragedy by Euripides that dramatizes the conflict between the sons of Oedipus during the war of the Seven against Thebes.
- 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_69e0b4f7ebe48190952a85547a0f31a1 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6d05acf848190a2bbbf33377f23d3 |
completed | April 21, 2026, 1:18 a.m. |
Created at: April 16, 2026, 12:46 p.m.