Triple
T20217781
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mario Kart 7 |
E495172
|
entity |
| Predicate | includesCharacter |
P5716
|
FINISHED |
| Object | Lakitu |
—
|
NE NERFINISHED |
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: Lakitu | Statement: [Mario Kart 7, includesCharacter, Lakitu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lakitu Context triple: [Mario Kart 7, includesCharacter, Lakitu]
-
A.
Lakitu
chosen
Lakitu is a recurring cloud-riding Koopa in the Super Mario series known for hovering above the player and attacking by throwing Spiny eggs.
-
B.
Lakalai
Lakalai is an Oceanic language spoken by an indigenous community in Papua New Guinea.
-
C.
Luti
Luti is an Italian surname most notably associated with Margherita Luti, traditionally identified as the model for Raphael’s famous painting "La Fornarina."
-
D.
Lahmu
Lahmu is a protective Mesopotamian deity or mythological figure, often depicted as a bearded man with a red sash and associated with primordial waters and temple guardianship.
-
E.
Niulakita
Niulakita is the southernmost island of Tuvalu, known as a small, remote coral atoll with a tiny population and traditional significance for Tuvaluan people.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69da626cff80819097b530718a7c98b6 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e66edaeeb08190bb74bd4a10aceca2 |
completed | April 20, 2026, 6:22 p.m. |
Created at: April 11, 2026, 11:39 p.m.