Triple
T17348343
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shot |
E421743
|
entity |
| Predicate | hasTrack |
P3284
|
FINISHED |
| Object | Thumper |
—
|
NE ONNED1 |
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: Thumper | Statement: [Shot, hasTrack, Thumper]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Thumper Context triple: [Shot, hasTrack, Thumper]
-
A.
Thumper
chosen
Thumper is the cheerful, talkative rabbit who serves as Bambi’s playful best friend and comic relief in Disney’s classic animated film.
-
B.
Ferdie Fieldmouse
Ferdie Fieldmouse is a classic Disney cartoon character, best known as one of Mickey Mouse’s young nephews who appears in various animated shorts and comic stories.
-
C.
Flopsy
Flopsy is one of the young rabbit characters in Beatrix Potter’s stories, best known as one of Peter Rabbit’s sisters.
-
D.
Frank the Rabbit
Frank the Rabbit is a haunting, time-traveling figure in a grotesque rabbit costume who serves as the eerie, prophetic guide to the troubled protagonist in the cult psychological thriller film "Donnie Darko."
-
E.
Mortimer Mouse
Mortimer Mouse is a classic Disney character best known as Mickey Mouse’s smug, antagonistic rival, often portrayed as a boastful suitor to Minnie.
- 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_69d889d520008190a26917a95bf1c2ea |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e43a2a2ee48190976732e654a40053 |
completed | April 19, 2026, 2:12 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a01955658b88190bce3fb2b5738afc6 |
in_progress | May 11, 2026, 8:37 a.m. |
Created at: April 10, 2026, 5:44 a.m.