Triple
T29028388
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ballades, Op. 10 |
E737657
|
entity |
| Predicate | firstBalladeTitle |
P202386
|
FINISHED |
| Object |
Ballade in D minor
"Ballade in D minor" is the first of Johannes Brahms's Four Ballades, Op. 10, a Romantic-era piano piece noted for its dark, narrative character and lyrical intensity.
|
E737657
|
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: Ballade in D minor | Statement: [Ballades, Op. 10, firstBalladeTitle, Ballade in D minor]
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: Ballade in D minor Triple: [Ballades, Op. 10, firstBalladeTitle, Ballade in D minor]
Generated description
"Ballade in D minor" is the first of Johannes Brahms's Four Ballades, Op. 10, a Romantic-era piano piece noted for its dark, narrative character and lyrical intensity.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstBalladeTitle Context triple: [Ballades, Op. 10, firstBalladeTitle, Ballade in D minor]
-
A.
firstBalladeComposed
Indicates that the subject is the entity for which the object is the first ballade that they composed.
-
B.
secondBalladeTitle
Indicates the title assigned to an entity’s second ballade.
-
C.
firstMovementTitle
Indicates the title or name given to the first movement of a multi-movement work.
-
D.
firstSong
Indicates that one song is the earliest or initial song in a specified sequence, collection, or context.
-
E.
lastBalladeComposed
Indicates that one entity is the most recent ballade composed by another entity.
- F. None of above. chosen
Provenance (7 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_69f077ef00fc81909325f084ad37c035 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_6a007899cadc8190a04edd503eaf6514 |
completed | May 10, 2026, 12:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a2505d58bf48190823f8b06939e92c3 |
completed | June 7, 2026, 5:47 a.m. |
| NEDg | Description generation | batch_6a250a085b9481909bfbe976439f91e9 |
completed | June 7, 2026, 6:04 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a250e1ce7348190b10cbfb40269ce0d |
completed | June 7, 2026, 6:22 a.m. |
| PD | Predicate disambiguation | batch_6a0078493e088190b0c5047cbe75d304 |
completed | May 10, 2026, 12:21 p.m. |
| PDg | Predicate description generation | batch_6a00789927708190b031d3a9d5f4f68e |
completed | May 10, 2026, 12:22 p.m. |
Created at: April 28, 2026, 9:54 a.m.