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.