Triple
T3170892
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Theme from "No Strings" (revised) |
E66333
|
entity |
| Predicate | originalWorkType |
P35132
|
FINISHED |
| Object | Broadway musical |
—
|
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: Broadway musical | Statement: [Theme from "No Strings" (revised), originalWorkType, Broadway musical]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalWorkType Context triple: [Theme from "No Strings" (revised), originalWorkType, Broadway musical]
-
A.
creativeWorkType
Indicates the specific category or form of a creative work (such as book, movie, painting, or song) that characterizes the relationship.
-
B.
originalPublicationOfWholeWork
Indicates that one entity is the original publication in which an entire work was first made publicly available.
-
C.
originalPublicationForm
chosen
Indicates the format or medium in which a work was first originally published.
-
D.
publicationType
Indicates the specific category or format of a published work that characterizes how it is issued or presented.
-
E.
formatOfWorks
Indicates the specific medium, layout, or structural form in which works are created, presented, or published.
- 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_69ad8585d7988190af37365331093ccd |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada66c043081908eb23a4fe3420a78 |
completed | March 8, 2026, 4:40 p.m. |
| PD | Predicate disambiguation | batch_69ad9e0076b4819094628f1ad10b8f68 |
completed | March 8, 2026, 4:04 p.m. |
Created at: March 8, 2026, 3:06 p.m.