Triple
T13672434
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ne-Yo |
E327782
|
entity |
| Predicate | wroteSongFor |
P15505
|
FINISHED |
| Object | Mario |
E95100
|
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: Mario | Statement: [Ne-Yo, wroteSongFor, Mario]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mario Context triple: [Ne-Yo, wroteSongFor, Mario]
-
A.
Mario
chosen
Mario is an American R&B singer, songwriter, and occasional actor best known for his early-2000s hits like "Let Me Love You."
-
B.
Mario
Mario is a fictional Italian plumber and the iconic protagonist of Nintendo's long-running Super Mario video game franchise.
-
C.
Mário
Mário is a masculine given name of Latin origin, widely used in Portuguese- and Italian-speaking countries.
-
D.
Hotel Mario
Hotel Mario is a 1994 Philips CD-i puzzle-platform video game based on the Mario franchise, infamous for its poor quality and awkward full-motion video cutscenes.
-
E.
Mario vs. Donkey Kong series
The Mario vs. Donkey Kong series is a puzzle-platform video game franchise in which Mario navigates intricate, toy-themed levels to outwit Donkey Kong and solve object-based challenges.
- 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_69d8076f1fa8819094664a59b55010df |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbc65aab348190a6611f5765f8392d |
completed | April 12, 2026, 4:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f78b1222648190a70f50e6e5c34593 |
completed | May 3, 2026, 5:51 p.m. |
Created at: April 9, 2026, 9:53 p.m.