Triple
T13942970
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marcus Junius Silanus |
E335302
|
entity |
| Predicate | relativeByMarriage |
P7844
|
FINISHED |
| Object | Caligula |
E10757
|
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: Caligula | Statement: [Marcus Junius Silanus, relativeByMarriage, Caligula]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Caligula Context triple: [Marcus Junius Silanus, relativeByMarriage, Caligula]
-
A.
Caligula
chosen
Caligula was a first-century Roman emperor infamous for his autocratic rule, extravagance, and accounts of cruelty and madness.
-
B.
Nero
Nero is the vengeful Romulan miner who serves as the primary antagonist in the 2009 Star Trek film reboot.
-
C.
Nero
Nero was a 1st-century Roman emperor best known for his tyrannical rule, persecution of Christians, and association with the Great Fire of Rome.
-
D.
Nero
Nero is one of Madame Medusa’s pet alligators and henchmen in Disney’s animated film “The Rescuers.”
-
E.
Nero Julius Caesar
Nero Julius Caesar was the eldest son of the Roman emperor Vespasian and an early heir of the Flavian dynasty who died before he could claim the throne.
- 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_69d81c6081b88190b53e317c3370c8fe |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2e0f6f3c8190a64058b732b0ac52 |
completed | April 14, 2026, 12:07 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcdef3f31c8190a2fc3eed316756d6 |
completed | May 7, 2026, 6:50 p.m. |
Created at: April 9, 2026, 10:17 p.m.