Triple
T3367961
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marcus |
E70882
|
entity |
| Predicate | etymologicalRoot |
P453
|
FINISHED |
| Object | Marius |
E194582
|
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: Marius | Statement: [Marcus, etymologicalRoot, Marius]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marius Context triple: [Marcus, etymologicalRoot, Marius]
-
A.
Marius
Marius is the given name of the Norwegian mathematician Sophus Lie, a pioneer in the theory of continuous transformation groups (Lie groups).
-
B.
Marius
Marius was a short-lived 3rd-century Roman usurper who briefly ruled the breakaway Gallic Empire during the Crisis of the Third Century.
-
C.
Marius
chosen
Marius is the family name (nomen) of the prominent Roman general and statesman Gaius Marius, known for his military reforms and multiple consulships in the late Roman Republic.
-
D.
Marius Pontmercy
Marius Pontmercy is a central character in Victor Hugo’s novel *Les Misérables*, a young idealistic law student and revolutionary who falls in love with Cosette.
-
E.
Lucien
Lucien is a masculine given name of Latin origin, historically associated with figures such as Lucien Bonaparte, the brother of Napoleon Bonaparte.
- 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_69ad85a729d48190afd789cd8417f289 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb2890480819082fe2e3c2874cece |
completed | March 8, 2026, 5:31 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b3343664cc81909793820377b4bdc1 |
completed | March 12, 2026, 9:46 p.m. |
Created at: March 8, 2026, 3:13 p.m.