Triple
T20164518
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marty the Zebra |
E491793
|
entity |
| Predicate | friend |
P8712
|
FINISHED |
| Object | Skipper |
—
|
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: Skipper | Statement: [Marty the Zebra, friend, Skipper]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Skipper Context triple: [Marty the Zebra, friend, Skipper]
-
A.
Skipper
Skipper is a central comic character from the early 20th-century newspaper strip "Toonerville Folks," known as the energetic and often hapless captain of the Toonerville Trolley.
-
B.
Skipper
Skipper is the gruff but good-hearted captain of the shipwrecked crew on the classic American TV sitcom "Gilligan's Island."
-
C.
Skipper the Penguin
chosen
Skipper the Penguin is the tough, militaristic leader of the penguin commando team from the Madagascar animated franchise.
-
D.
Skipper Worse
Skipper Worse is a 19th-century Norwegian novel by Alexander Kielland that portrays the lives, moral conflicts, and social changes in a coastal fishing community.
-
E.
Zissou
Zissou is a family name most notably associated with characters in Wes Anderson’s film "The Life Aquatic with Steve Zissou."
- 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_69da6266c6888190bc1a3ecf24814d34 |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e6684376408190a68890ab48fa5424 |
completed | April 20, 2026, 5:54 p.m. |
Created at: April 11, 2026, 11:35 p.m.