Triple
T23340962
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Berlioz’s Les Troyens à Carthage |
E591732
|
entity |
| Predicate | basedOn |
P98
|
FINISHED |
| Object | Aeneid |
—
|
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: Aeneid | Statement: [Berlioz’s Les Troyens à Carthage, basedOn, Aeneid]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Aeneid Context triple: [Berlioz’s Les Troyens à Carthage, basedOn, Aeneid]
-
A.
Virgil's Aeneid
chosen
Virgil's Aeneid is a Latin epic poem that narrates the legendary journey of Aeneas from the ruins of Troy to Italy, laying a mythic foundation for the origins of Rome.
-
B.
Les Troyens
Les Troyens is a grand five-act French opera by Hector Berlioz, inspired by Virgil’s Aeneid and renowned for its epic scale and rich orchestration.
-
C.
Enneüs
Enneüs is a Dutch given name most notably borne by politician Enneüs Heerma.
-
D.
Eneida
Eneida is a landmark Ukrainian mock-heroic poem by Ivan Kotliarevsky that adapts Virgil’s Aeneid into a satirical portrayal of Ukrainian Cossack life and culture.
-
E.
Troy and the Trojans
"Troy and the Trojans" is an influential archaeological and historical study of ancient Troy and its inhabitants, authored by American archaeologist Carl Blegen.
- 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_69e25d20e3d08190bcede87673cafb25 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f198329d9c8190992627afa9b54bed |
completed | April 29, 2026, 5:33 a.m. |
Created at: April 17, 2026, 5:18 p.m.