Triple
T30083162
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Down Ampney |
E764526
|
entity |
| Predicate | associatedHymnText |
P60491
|
FINISHED |
| Object |
Come Down, O Love Divine
"Come Down, O Love Divine" is a well-known Christian hymn text, translated by Richard Frederick Littledale from a 14th-century Italian poem by Bianco da Siena, often sung to Ralph Vaughan Williams’s tune "Down Ampney."
|
E1898550
|
NE FINISHED |
How this triple was built (3 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: Come Down, O Love Divine | Statement: [Down Ampney, associatedHymnText, Come Down, O Love Divine]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Come Down, O Love Divine Triple: [Down Ampney, associatedHymnText, Come Down, O Love Divine]
Generated description
"Come Down, O Love Divine" is a well-known Christian hymn text, translated by Richard Frederick Littledale from a 14th-century Italian poem by Bianco da Siena, often sung to Ralph Vaughan Williams’s tune "Down Ampney."
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedHymnText Context triple: [Down Ampney, associatedHymnText, Come Down, O Love Divine]
-
A.
associatedWithHymns
chosen
Indicates that something has a connection or relationship to hymns, such as being used in, derived from, or thematically linked to them.
-
B.
relatedChantOrSong
Indicates that one chant or song is associated with, derived from, or otherwise connected to another chant or song.
-
C.
hymnsDedicatedTo
Indicates that certain hymns are specifically devoted or addressed to a particular entity as their subject or object of veneration.
-
D.
hymnTuneName
Indicates the specific musical tune or melody name associated with a hymn.
-
E.
languageOfHymnsUsed
Indicates the language in which the hymns are performed, recited, or used.
- F. None of above.
Provenance (6 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_69f22473c0fc8190a926a8051b3b378b |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_6a037c876524819098545e6037d3107d |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a27432285f48190a43cb4233283f1b2 |
completed | June 8, 2026, 10:33 p.m. |
| NEDg | Description generation | batch_6a2743e893708190a11e3888456906bb |
completed | June 8, 2026, 10:36 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a274507fa3c819098819c5b1c2c4133 |
completed | June 8, 2026, 10:41 p.m. |
| PD | Predicate disambiguation | batch_6a0379e0f3d88190a4ee7b0673f1ef90 |
completed | May 12, 2026, 7:05 p.m. |
Created at: April 29, 2026, 7:03 p.m.