Triple
T29220680
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Liquid Tension Experiment |
E740795
|
entity |
| Predicate | primaryRecordingMethod |
P15057
|
FINISHED |
| Object | live studio improvisation |
—
|
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: live studio improvisation | Statement: [Liquid Tension Experiment, primaryRecordingMethod, live studio improvisation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryRecordingMethod Context triple: [Liquid Tension Experiment, primaryRecordingMethod, live studio improvisation]
-
A.
primaryReceptionMethod
Indicates the main way in which something is received, accessed, or obtained among multiple possible methods.
-
B.
recordingMethod
chosen
Indicates the technique or process used to capture or record something (such as data, audio, or video).
-
C.
recordingType
Indicates the specific kind or category of recording associated with an entity (e.g., audio, video, live, studio, etc.).
-
D.
recordingStyle
Indicates the manner or technique used to capture or document something, such as audio, video, or data.
-
E.
mainlyRecordedBy
Indicates that the primary or most significant recording of something (such as a work, event, or data set) was made by a particular agent or 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_69f07cba2f808190a2746477d4e8345b |
completed | April 28, 2026, 9:24 a.m. |
| NER | Named-entity recognition | batch_6a00ccadb6908190ab810a7c05315fa8 |
completed | May 10, 2026, 6:21 p.m. |
| PD | Predicate disambiguation | batch_6a00cc0f86b88190a0d2c43618558f86 |
completed | May 10, 2026, 6:18 p.m. |
Created at: April 28, 2026, 12:15 p.m.