Triple
T20164098
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cosmo |
E491784
|
entity |
| Predicate | residence |
P75
|
FINISHED |
| Object | Fairy World |
—
|
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: Fairy World | Statement: [Cosmo, residence, Fairy World]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fairy World Context triple: [Cosmo, residence, Fairy World]
-
A.
Fairy World
chosen
Fairy World is a whimsical magical realm in the Sesame Street universe where the fairy-in-training Abby Cadabby comes from and other fairies live and learn magic.
-
B.
Faerie Land
Faerie Land is the richly allegorical, fantastical realm that serves as the primary setting of Edmund Spenser’s epic poem *The Faerie Queene*.
-
C.
The Fairy
"The Fairy" is one of the classic short tales included in Charles Perrault’s influential fairy-tale collection *Tales of Mother Goose*.
-
D.
Fairy May
Fairy May is a whimsical, childlike patient in the play "The Curious Savage," known for her fanciful stories and poignant blend of humor and vulnerability.
-
E.
All the Way to Fairyland
All the Way to Fairyland is a late-19th-century collection of original fairy tales for children by British author Evelyn Sharp.
- 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.