Triple
T13146248
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | David Zellner |
E312341
|
entity |
| Predicate | appearsIn |
P795
|
FINISHED |
| Object | Kid-Thing |
E1024368
|
NE FINISHED |
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: Kid-Thing | Statement: [David Zellner, appearsIn, Kid-Thing]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kid-Thing Context triple: [David Zellner, appearsIn, Kid-Thing]
-
A.
Kid-Thing
chosen
Kid-Thing is an independent, surreal drama film directed by David Zellner that follows a lonely young girl who discovers a mysterious voice calling for help from a well.
-
B.
Flint Marko
Flint Marko, also known as the Sandman, is a Marvel Comics supervillain who can transform his body into sand and is a prominent adversary of Spider-Man.
-
C.
Tigerman
Tigerman is the surname of Stanley Tigerman, a notable American architect associated with postmodern design.
-
D.
X-23
X-23 is a Marvel Comics character, a female clone and successor to Wolverine known for her adamantium claws, healing factor, and complex struggle with her assassin origins.
-
E.
Amadeus Cho
Amadeus Cho is a Marvel Comics super-genius and superhero who has taken on roles such as the Hulk and a key member of various Avengers teams.
- 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_69d806aabde48190899e13e41659cae5 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98bcf6d0c819081d078f33e4bdedc |
completed | April 10, 2026, 11:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f70a2894848190b5853127ef04932c |
completed | May 3, 2026, 8:41 a.m. |
Created at: April 9, 2026, 9:10 p.m.