Triple
T8900605
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Serenade to Music |
E211919
|
entity |
| Predicate | textExcerpt |
P9883
|
FINISHED |
| Object | How sweet the moonlight sleeps upon this bank |
—
|
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: How sweet the moonlight sleeps upon this bank | Statement: [Serenade to Music, textExcerpt, How sweet the moonlight sleeps upon this bank]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: textExcerpt Context triple: [Serenade to Music, textExcerpt, How sweet the moonlight sleeps upon this bank]
-
A.
textContent
Indicates that one entity is the textual content or written material contained within another entity.
-
B.
textFragment
chosen
Indicates that one piece of text is a constituent part or segment of a larger text.
-
C.
textTitle
Indicates that one text entity serves as the title or heading for another text or resource.
-
D.
hasExcerpt
Indicates that one entity contains or is associated with a selected portion or extract taken from another entity.
-
E.
textBy
Indicates that a given text or written content was authored or produced by a particular 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_69ca83918d3081909b326fa3750cb8c8 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc6428ffc48190814f6b865961dbd1 |
completed | April 1, 2026, 12:17 a.m. |
| PD | Predicate disambiguation | batch_69cc5c2bfb38819083d5eb1af8ccf4d6 |
completed | March 31, 2026, 11:43 p.m. |
Created at: March 30, 2026, 6:54 p.m.