Triple
T32364887
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ICY GRL |
E826962
|
entity |
| Predicate | hasChorusCatchphrase |
P195404
|
FINISHED |
| Object | icy girl |
—
|
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: icy girl | Statement: [ICY GRL, hasChorusCatchphrase, icy girl]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasChorusCatchphrase Context triple: [ICY GRL, hasChorusCatchphrase, icy girl]
-
A.
hasChorus
Indicates that something (typically a song or musical piece) includes a chorus section as part of its structure.
-
B.
hasChorusIn
Indicates that a musical work includes a chorus section within the specified part or segment.
-
C.
hasChorusBy
Indicates that something (typically a musical work or song) includes a chorus section that is performed, written, or provided by a specified entity.
-
D.
hasChorusMentioning
Indicates that a work’s chorus explicitly mentions or refers to a specified entity or concept.
-
E.
containsChorusOf
Indicates that one entity (typically a musical work or section) includes within it a chorus performed by another entity (such as a group of singers or ensemble).
- F. None of above. chosen
Provenance (4 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_69f349166d548190887b412fe908e2f4 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fdd07a34c08190982b8c61c2775cf6 |
completed | May 8, 2026, noon |
| PD | Predicate disambiguation | batch_69fdbd25c7908190b72fca8de7ce503f |
completed | May 8, 2026, 10:38 a.m. |
| PDg | Predicate description generation | batch_69fdd07724f88190a33ec602642d2ea3 |
completed | May 8, 2026, noon |
Created at: May 1, 2026, 12:50 a.m.