Triple
T2326642
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rodgers and Hammerstein musicals |
E48301
|
entity |
| Predicate | hasWorkWithTopic |
P24066
|
FINISHED |
| Object | racism and prejudice |
—
|
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: racism and prejudice | Statement: [Rodgers and Hammerstein musicals, hasWorkWithTopic, racism and prejudice]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasWorkWithTopic Context triple: [Rodgers and Hammerstein musicals, hasWorkWithTopic, racism and prejudice]
-
A.
hasWorkSubject
Indicates that a work (such as a document, artwork, or project) is about or concerns a particular subject or topic.
-
B.
hasWorkAsSubject
Indicates that an entity serves as the subject (creator or originator) of a particular work or creative output.
-
C.
hasWorkBy
Indicates that one entity (such as a collection, exhibition, or publication) includes or contains creative works produced by another entity (such as an artist, author, or creator).
-
D.
includesTopics
chosen
Indicates that one entity contains, covers, or addresses the specified topics as part of its content or scope.
-
E.
usesResearchSubject
Indicates that one entity employs or utilizes another entity as a research subject in a study or investigation.
- 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_69a88aa308a88190b0b86c011fda7fce |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abcc30c5e881908c5d526d7e7491d0 |
completed | March 7, 2026, 6:56 a.m. |
| PD | Predicate disambiguation | batch_69abc5926d048190a535e3f23d41de2a |
completed | March 7, 2026, 6:28 a.m. |
Created at: March 4, 2026, 7:50 p.m.