Triple
T37721389
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Castle House dance studio, New York City |
E939591
|
entity |
| Predicate | taughtStyle |
P44259
|
FINISHED |
| Object | foxtrot |
—
|
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: foxtrot | Statement: [Castle House dance studio, New York City, taughtStyle, foxtrot]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: taughtStyle Context triple: [Castle House dance studio, New York City, taughtStyle, foxtrot]
-
A.
typeOfTeaching
Indicates the specific method or style of teaching used in an instructional context.
-
B.
courseStyle
chosen
Indicates the manner, format, or pedagogical approach in which a course is delivered or conducted.
-
C.
taughtThrough
Indicates that one entity provided instruction, education, or training to another entity by means of a specified method, medium, or intermediary.
-
D.
taughtThat
Indicates that one entity provided instruction or education to another entity about a specific subject, skill, or concept.
-
E.
taughtAs
Indicates that one entity served as a teacher or instructor for another entity in an educational or training context.
- 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_69f76edc208c8190bc8b9683f75e1024 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fbb9e8108c8190ae1c7940b1677e95 |
completed | May 6, 2026, 10 p.m. |
| PD | Predicate disambiguation | batch_69fbb141605c8190b9c27d70352522db |
completed | May 6, 2026, 9:23 p.m. |
Created at: May 3, 2026, 4:18 p.m.