Triple
T21560941
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gussie |
E532023
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Gussie |
—
|
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: Gussie | Statement: [Gussie, name, Gussie]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gussie Context triple: [Gussie, name, Gussie]
-
A.
Gussie
chosen
Gussie is a fictional character best known as the hapless young protagonist in P. G. Wodehouse’s comic story “Extricating Young Gussie.”
-
B.
Gus
Gus is one of the three iconic Hitchhiking Ghosts from Disney's Haunted Mansion attraction, recognizable as the short, bearded prisoner ghost with a ball and chain.
-
C.
Gus
Gus is one of the central child protagonists in the animated film "Wonder Park," known for helping bring a fantastical amusement park to life.
-
D.
Gus
Gus is the given name of the early 20th-century Swedish-American vaudeville comedian and film actor known professionally as El Brendel.
-
E.
Gus
Gus is a supporting character in the crime action film "3000 Miles to Graceland," which centers on a group of criminals executing a heist during an Elvis impersonator convention.
- 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_69e0c460db088190828c64206a450273 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69eed2e3e2348190b5c3b66cdc871e6e |
completed | April 27, 2026, 3:07 a.m. |
Created at: April 16, 2026, 6:29 p.m.