Triple
T20359898
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cats (franchise) |
E496748
|
entity |
| Predicate | hasCharacter |
P2308
|
FINISHED |
| Object | Jellylorum |
—
|
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: Jellylorum | Statement: [Cats (franchise), hasCharacter, Jellylorum]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jellylorum Context triple: [Cats (franchise), hasCharacter, Jellylorum]
-
A.
Jellylorum
chosen
Jellylorum is a nurturing, older Jellicle cat from the musical "Cats," often portrayed as a caretaker figure who looks after the kittens and supports Gus the Theatre Cat.
-
B.
Jelly
Jelly is a now-defunct Q&A and search app that let users get answers by sending questions, often with images, to a network of people.
-
C.
Jellies
Jellies is a popular Monterey Bay Aquarium exhibit showcasing diverse jellyfish species in immersive, artful displays.
-
D.
Jelbi
Jelbi is a mobility app by Berlin’s public transport operator that integrates various transport options like buses, trains, bikes, and scooters into a single platform for planning and booking trips.
-
E.
Jelly Fresh
Jelly Fresh is a shop in the Splatoon series’ Inkopolis hub, known for selling fashionable gear to players.
- 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.