Triple
T330745
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | I Will Always Love You |
E6619
|
entity |
| Predicate | WhitneyHoustonVersionType |
P11504
|
FINISHED |
| Object | power ballad |
—
|
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: power ballad | Statement: [I Will Always Love You, WhitneyHoustonVersionType, power ballad]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: WhitneyHoustonVersionType Context triple: [I Will Always Love You, WhitneyHoustonVersionType, power ballad]
-
A.
hasAudiobookVersion
Indicates that an entity has a corresponding version available in audiobook format.
-
B.
hasPartInDiscography
Indicates that an entity (such as a song, album, or track) is included as a component within another entity’s discography.
-
C.
hasVocalDuet
Indicates that two entities perform or participate together in a vocal duet.
-
D.
hasSpecialSong
Indicates that one entity possesses or is associated with a particular song that is unique, distinctive, or specially designated for it.
-
E.
hasLyricalStyle
Indicates that one entity possesses or is characterized by a particular lyrical style in relation to another entity or context.
- F. None of above. chosen
Provenance (4 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_69a2e79434908190a9d5afe415153ad9 |
completed | Feb. 28, 2026, 1:03 p.m. |
| NER | Named-entity recognition | batch_69a2eaafd1a48190a6d001af3c2a5318 |
completed | Feb. 28, 2026, 1:16 p.m. |
| PD | Predicate disambiguation | batch_69a2e94c6d8881908239d3788c018adf |
completed | Feb. 28, 2026, 1:10 p.m. |
| PDg | Predicate description generation | batch_69a2ea09a5e881908b313cb37409a4f9 |
completed | Feb. 28, 2026, 1:13 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.