Triple
T24181317
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Water Runs Dry |
E599431
|
entity |
| Predicate | hasVocalGroupType |
P135747
|
FINISHED |
| Object | male vocal quartet |
—
|
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: male vocal quartet | Statement: [Water Runs Dry, hasVocalGroupType, male vocal quartet]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasVocalGroupType Context triple: [Water Runs Dry, hasVocalGroupType, male vocal quartet]
-
A.
hasMusicalVocalType
chosen
Indicates that an entity is associated with a specific type or classification of singing voice.
-
B.
hasNotableVocalType
Indicates that an entity is associated with a specific, noteworthy type or quality of vocalization or voice.
-
C.
vocalHarmonyType
Indicates the specific kind or style of vocal harmony relationship that exists between the involved vocal parts or voices.
-
D.
vocalGroupOnNotableRecording
Indicates that a vocal group performed on or contributed vocals to a notable audio recording.
-
E.
hasVocals
Indicates that the subject includes or features vocal elements, such as singing or spoken voice, rather than being purely instrumental or non-vocal.
- 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_69e288cca05481908faeb1563711114a |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f27c9ddfcc819096697a844b300cce |
completed | April 29, 2026, 9:48 p.m. |
| PD | Predicate disambiguation | batch_69f1c42f942c8190b103ff29a60fef34 |
completed | April 29, 2026, 8:41 a.m. |
Created at: April 17, 2026, 11:34 p.m.