Triple
T20359912
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cats (franchise) |
E496748
|
entity |
| Predicate | hasCharacter |
P2308
|
FINISHED |
| Object | Tumblebrutus |
—
|
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: Tumblebrutus | Statement: [Cats (franchise), hasCharacter, Tumblebrutus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tumblebrutus Context triple: [Cats (franchise), hasCharacter, Tumblebrutus]
-
A.
Tumblebrutus
chosen
Tumblebrutus is a playful, acrobatic tomcat character from the musical "Cats," known for his energetic dancing and youthful exuberance.
-
B.
Busta Gallorum
Busta Gallorum is the historic battlefield in Italy where the Ostrogothic king Totila was killed during the Gothic War against the Byzantine Empire.
-
C.
Vulfpeck
Vulfpeck is an American funk band known for its tight, minimalist grooves, virtuosic musicianship, and innovative, DIY approach to recording and releasing music.
-
D.
Becmen
Becmen is a village in the Surčin municipality of Belgrade, Serbia.
-
E.
Brutinel
Brutinel is a French surname most notably associated with Raymond Brutinel, a pioneering military officer and early advocate of mechanized warfare.
- 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_69e0b4a3f7f48190b37f354574028ca6 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e678584294819093788ccf2fb8e588 |
completed | April 20, 2026, 7:02 p.m. |
Created at: April 16, 2026, 11:25 a.m.