Triple
T15763433
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Luigi's Mansion: Dark Moon |
E382154
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object | Luigi |
E11428
|
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: Luigi | Statement: [Luigi's Mansion: Dark Moon, mainCharacter, Luigi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Luigi Context triple: [Luigi's Mansion: Dark Moon, mainCharacter, Luigi]
-
A.
Luigi
chosen
Luigi is a timid yet heroic green-clad plumber from Nintendo’s Mario franchise, known as Mario’s younger brother and frequent co-adventurer.
-
B.
Luigi
Luigi is the birth name of Hall of Fame basketball coach Geno Auriemma, renowned for leading the University of Connecticut women's team to multiple national championships.
-
C.
Luigi
Luigi is a small, enthusiastic Italian Fiat 500 who runs a tire shop and provides comic relief in Pixar's Cars franchise.
-
D.
Luigi
Luigi is a character in Robert Browning's verse drama "Pippa Passes," depicted as an Italian patriot involved in a plot against Austrian rule.
-
E.
Luigi
Luigi is the given first name of the Italian actor and comedian Gigi Proietti.
- 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_69d86da09a10819082fe9797b23e4664 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e050b6c9fc8190a1bcf763c4b04b12 |
completed | April 16, 2026, 3 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff8776c2488190ad27fd79e2ce4e14 |
completed | May 9, 2026, 7:13 p.m. |
Created at: April 10, 2026, 4:47 a.m.