Triple
T16036244
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lavinia |
E388975
|
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: [Lavinia, featuresCharacter, Turnus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Turnus Context triple: [Lavinia, 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.
Montillus
Montillus is a masculine given name, most notably borne by Montillus Murray Beatty.
-
D.
Caeneus
Caeneus is a figure from Greek mythology who was originally a woman named Caenis, transformed into an invulnerable male warrior and famed member of the Lapiths.
-
E.
Tullus Hostilius
Tullus Hostilius was the legendary third king of Rome, traditionally remembered for his warlike reign and the destruction of Alba Longa.
- 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_69d86dada3808190825d5f80d72fbe88 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e1833ca66881909475fac23e6fbf86 |
completed | April 17, 2026, 12:47 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffdbd3a1248190ad055892cebde5f0 |
completed | May 10, 2026, 1:13 a.m. |
Created at: April 10, 2026, 4:56 a.m.