Triple
T7644419
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Do You Want to Build a Snowman? |
E173084
|
entity |
| Predicate | adultVersionOfSinger |
P65617
|
FINISHED |
| Object | adult Anna |
—
|
LITERAL 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: adult Anna | Statement: [Do You Want to Build a Snowman?, adultVersionOfSinger, adult Anna]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: adultVersionOfSinger Context triple: [Do You Want to Build a Snowman?, adultVersionOfSinger, adult Anna]
-
A.
vocalistIn
Indicates that a person serves as a vocalist (singer) in a particular musical group, band, or ensemble.
-
B.
coveredArtist
Indicates that one artist has performed or recorded a cover version of another artist’s original work.
-
C.
appearsAsAdultIn
chosen
Indicates that an entity is depicted or presented in its adult form within a specified context, such as a work, scene, or time period.
-
D.
performedAsSingerIn
Indicates that an entity took part in a performance specifically in the role of a singer within a particular event, production, or context.
-
E.
singsAbout
Indicates that one entity performs a song whose subject or theme is another entity.
- F. None of above.
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_69c6995360188190968ee57b72a1627f |
completed | March 27, 2026, 2:50 p.m. |
| NER | Named-entity recognition | batch_69c6faf13858819095262664e1e04eb7 |
completed | March 27, 2026, 9:47 p.m. |
| PD | Predicate disambiguation | batch_69c6f4e8cadc8190b7977fcd213954dd |
completed | March 27, 2026, 9:21 p.m. |
Created at: March 27, 2026, 3:58 p.m.