Triple
T20164133
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wanda |
E491785
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Cosmo |
—
|
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: Cosmo | Statement: [Wanda, spouse, Cosmo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cosmo Context triple: [Wanda, spouse, Cosmo]
-
A.
Cosmo
chosen
Cosmo is a fairy godparent character from the animated series "The Fairly OddParents," known for his goofy, dim-witted personality and magical mishaps.
-
B.
Cosmo
Cosmo is the costumed cougar mascot of Brigham Young University, known for energetic performances at athletic events.
-
C.
Cosmo
Cosmo is a given name most notably borne by Cosmo Gordon Lang, a 20th-century Archbishop of Canterbury.
-
D.
Cosm
Cosm is a hard science fiction novel by Gregory Benford that explores the discovery of an artificial universe and its scientific and philosophical implications.
-
E.
COSMO
COSMO is a German public radio station focused on multicultural, international, and contemporary music and culture, produced by Westdeutscher Rundfunk and partner broadcasters.
- 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.