Triple
T4943918
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | war in Latium |
E111000
|
entity |
| Predicate | featuresCharacter |
P626
|
FINISHED |
| Object | Turnus |
E112534
|
NE 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: Turnus | Statement: [war in Latium, featuresCharacter, Turnus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Turnus Context triple: [war in Latium, featuresCharacter, Turnus]
-
A.
Turnus
chosen
Turnus is the hot-headed Rutulian prince and chief antagonist of Aeneas in Virgil’s epic poem the Aeneid.
-
B.
Ascanius
Ascanius is the legendary son of Aeneas in Roman mythology, regarded as an ancestor of the founders of Rome and a symbol of its destined imperial future.
-
C.
Tullus Hostilius
Tullus Hostilius was the legendary third king of Rome, traditionally remembered for his warlike reign and the destruction of Alba Longa.
-
D.
Aeneas
Aeneas is a Trojan hero in Greco-Roman mythology, renowned as the legendary ancestor of the Romans and the pious protagonist of Virgil’s epic poem the Aeneid.
-
E.
Antenor
Antenor is a wise Trojan elder and counselor in Greek mythology, often portrayed as an advocate for peace during the Trojan War.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69bd441721cc819085c7e33fe0876818 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd70a7650c8190b046b65072fd8eae |
completed | March 20, 2026, 4:07 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be81cc862081908b42686f04915238 |
completed | March 21, 2026, 11:32 a.m. |
Created at: March 20, 2026, 1:31 p.m.