Triple
T23349115
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kubo and the Two Strings |
E591956
|
entity |
| Predicate | featuresCharacter |
P626
|
FINISHED |
| Object | Beetle |
—
|
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: Beetle | Statement: [Kubo and the Two Strings, featuresCharacter, Beetle]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Beetle Context triple: [Kubo and the Two Strings, featuresCharacter, Beetle]
-
A.
Beetle
Beetle is a Kirby copy ability that lets Kirby grab, throw, and impale enemies using a powerful horn-based moveset.
-
B.
Beetle
chosen
Beetle is a Marvel Comics supervillain known for his high-tech armored suit and frequent clashes with Spider-Man.
-
C.
Bettles
Bettles is a small, remote community in northern Alaska that serves as a key access point and logistical hub for visitors to Gates of the Arctic National Park and Preserve.
-
D.
Maria Beetle
Maria Beetle is a Japanese crime novel by Kōtarō Isaka that follows multiple assassins whose intersecting missions unfold aboard a high-speed train.
-
E.
Buzzy Beetle
Buzzy Beetle is a hard-shelled, fireproof enemy from the Super Mario series that typically walks along surfaces and retreats into its shell when jumped on.
- 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_69e25d20e3d08190bcede87673cafb25 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f199cb2a3c8190a5c0c8d8735256c7 |
completed | April 29, 2026, 5:40 a.m. |
Created at: April 17, 2026, 5:19 p.m.